System for detecting failure signs of sliding mechanism protection member, method for detecting failure signs of sliding mechanism protection member, and program for detecting failure signs of sliding mechanism protection member

Abstract

To provide a system for detecting a failure sign of a protective member used in a slide mechanism.SOLUTION: A failure sign detection system 10 includes: a seal material 5 which is placed on a slider 3 of an LM guide 1 to cover the gap between the slider 3 and a rail 2; a microphone 11 which is located along a path in which the slider 3 moves and acquires an acoustic signal generated by the LM guide 1 when it is in operation; and a PC 16 which extracts feature quantity that is characteristic frequency component level appeared in a frequency component of the acquired acoustic signal. Based on the extracted feature quantity, a sign that the sealing material 5 may fail is detected.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a system, a method, and a computer program for detecting a sign of failure of a protection member used in a sliding mechanism.

Background Art

[0002] When wear or damage due to aging occurs in equipment used in production facilities, there is a risk that the equipment may stop abnormally or malfunction, resulting in a decrease in productivity. For example, a linear guide device such as an LM guide (registered trademark) linearly moves a slider along a rail by interposing balls between a rail, which is a fixed part, and the slider, which is a movable part. In such a device, if foreign matter enters the gap between the rail and the slider from the outside, the mechanism parts such as the rail and the balls will wear, resulting in a reduced lifespan. Therefore, conventionally, techniques for detecting wear in the mechanism parts and techniques for predicting the lifespan after wear has occurred have been proposed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In addition, in the above linear guide device, in order to prevent foreign matter from entering the gap between the rail and the slider, some are provided with a sealing material arranged to block the gap. Since this sealing member is fixed to the slider side, it is inevitable that the sealing member itself will also experience wear and damage due to the sliding of the slider. However, no technique has been proposed so far for detecting such wear and damage occurring in the sealing member itself.

[0005] The present invention has been made in view of the above circumstances, and an object thereof is to provide a system, a method, and a computer program for detecting a sign of failure of a protection member used in a sliding mechanism. **Means for Solving the Problems**

[0006] According to the failure sign detection system for a sliding mechanism protection member according to claim 1, the sliding mechanism protection member is disposed on a moving part of a moving device so as to cover a gap between the moving part and a fixed part. The acoustic signal acquisition unit is disposed along a path along which the moving part moves, and acquires an acoustic signal generated when the moving device operates. The feature amount extraction unit extracts a feature amount that is a level of a characteristic frequency component appearing in the frequency components of the acquired acoustic signal. Then, based on the extracted feature amount, a sign of failure of the sliding mechanism protection member is detected.

[0007] That is, when the moving device operates, since the sliding mechanism protection member moves together with the moving part, a sound is generated at a portion in contact with the fixed part. The frequency components of the sound change as the shape of the sliding mechanism protection member changes over time. Therefore, by extracting a feature amount for the frequency components of the acquired acoustic signal, it is possible to determine that the shape of the sliding mechanism protection member has changed and deteriorated to a certain extent even in an environment with a lot of noise during operation of the moving device. Thereby, it is possible to detect a sign that the protection member is about to reach a failure state.

[0008] Furthermore, according to the failure sign detection system for a sliding mechanism protection member according to claim 1, when the conditions and values of parameters that affect the waveform of the acoustic signal change, correction or adjustment is performed on the intensity, frequency, noise intensity, frequency, or determination threshold value of the sound required for anomaly detection. Also, according to the failure sign detection system for a sliding mechanism protection member according to claim 2, a difference in the material of the sliding mechanism protection member or foreign matter mixed in the gap is detected from the feature amount. Also, according to the failure sign detection system for a sliding mechanism protection member according to claim 3, based on the feature amount extracted when the moving part is moved forward and backward along the fixed part, a sign of failure of the sliding mechanism protection member is detected.

Brief Explanation of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

Figure 23

Figure 24

Figure 25

Figure 26

Figure 27

Figure 28

Mode for Carrying Out the Invention

[0010] (First Embodiment) Hereinafter, the first embodiment will be described. As shown in FIGS. 9 and 10, an LM guide 1, which is an example of a moving device or a linear guiding device, moves a slider 3, which is a moving part, along a linear rail 2 while sliding it via a bearing or the like, which is a sliding mechanism not shown, in the left-right direction in the drawing. The length of the rail 2 is 1000 mm, the width is 53 mm, and the height is 43 mm. The length of the slider 3 is 193 mm.

[0011] As shown in Fig. 3, sealing materials 5 attached to the holding member 4 are arranged on both the left and right end faces of the slider 3. As shown in Fig. 11, the cross-sectional shape of the rail 2 has a narrow central part, and the sealing material 5, which is a protective member, has a shape along the outer contour of its cross-sectional shape. The material of the sealing material 5 is, for example, nitrile rubber, and its thickness dimension is, for example, about 5 mm. The dimensions of the holding member 4 are 71 mm in length and 100 mm in width, and it is arranged on the upper side from the 9 mm high part of the rail 2. The holding member 4 is fixed to both end faces of the slider 3 by screwing. This sealing material 5 prevents foreign substances from entering bearings and the like between the rail 2 and the slider 3.

[0012] As shown in Fig. 3, a microphone 11 is arranged in the vicinity along the movement path of the slider 3 in the LM guide 1. As the slider 3 moves when the LM guide 1 operates, an acoustic signal generated by the sliding of the sealing material 5 on the rail 2 is acquired. By observing the characteristic amount of the frequency components of the acoustic signal, the deterioration state of the sealing material 5 is determined. The characteristic amount is the level of the characteristic frequency components appearing in the frequency components of the acoustic signal. The microphone 11 is an example of an acoustic signal acquisition unit.

[0013] As shown by an example in Fig. 4, two sliders 3 are used, and a cutter 7 attached via a support member 6 is moved in the left-right direction in the figure. Note that the left direction in the figure is "front". As shown in Fig. 5, after the slider 3 is rapidly accelerated and advanced from the initial position and then rapidly decelerated, it is moved at a constant speed. Then, when the slider 3 is decelerated and stopped, after being rapidly accelerated and reversed, and then rapidly decelerated, it is reversed at a constant speed faster than when moving forward and stopped when returning to the initial position.

[0014] In the fault prediction detection system 10 shown in FIG. 1, the acoustic signal acquired by the microphone 11 is input to the data logger 13 via the audio interface 12 (FIG. 2; S1 to S3). Therefore, after the acoustic signal is A / D converted, it is output to a CSV (Comma Separated Value) file. The CSV file is stored in the NAS (Network Attached Storage) 15 via the HUB 14 for LAN communication.

[0015] Here, as the acoustic signal acquisition unit, by using the audio interface 12 in addition to the microphone 11, the gain adjustment and frequency adjustment of the amplifier built in the interface 12 can be performed, and the load of the subsequent processing can be reduced. Also, when the sound pressure of the acoustic signal is low, the necessary sound pressure can be ensured by adjusting the gain of the amplifier. Further, if the sound pressure of the acoustic signal is at a sufficient level, the microphone 11 and the relay device may be directly connected. Note that the function of the above relay device is to perform A / D conversion if the acoustic signal is an analog signal or to relay with the state detection unit.

[0016] Also, by using the NAS 15 as the data recording medium, the risk of data leakage outside the company can be minimized. Also, if a cloud service is used instead of the NAS 15, data can be accessed from anywhere without worrying about the storage capacity and the like. Note that it can also be performed by edge processing without using a data storage medium. Note that the illustrations related to these are shown in the fourth embodiment described later.

[0017] The personal computer; PC 16 accesses the NAS 15 via the HUB 14, and when reading the data of the acoustic signal; microphone data stored in the CSV file, it calculates the feature amount of the frequency components included in the microphone data by performing frequency analysis by FFT, statistical processing, or machine learning, etc. The PC 16 is an example of a feature amount extraction unit.

[0018] As shown in Fig. 6, when the sealing material 5 is in a new state, there are no prominent features in the spectrogram showing the result of frequency analysis. In contrast, as shown in Fig. 7, when the sealing material 5 is worn to a certain extent, it can be seen that the sound pressure of the components around approximately 500 Hz to 6000 Hz increases. As the deterioration of the sealing material 5 progresses, if powders or the like of the sealing material 5 get mixed between the rail 2 and the slider 3, the LM guide 1 will be in a failed state. The failed state refers to a state where the portion where the rail 2 and the slider 3 contact is rubbed by the mixed powders or the like and scratches occur, and the dynamic and static accuracy of the LM guide 1 deteriorates. In this case, as shown in Fig. 8, the sound pressure of the frequency components is lower than that in the case shown in Fig. 7, but it shows similar characteristics.

[0019] The PC 16 causes the display 17 to display a trend regarding the above processing result, and also determines the deterioration state of the sealing material 5 based on the feature amount (S4), and displays the determination result. Further, the PC 16 stores the processing result and the like in the NAS 15. If the determination result indicates the deterioration of the sealing material 5, it is regarded as a sign of failure and an abnormality determination is made, an alarm is displayed on the display 17, and a display prompting the operator to perform maintenance and the like is made (S5). Note that "the sealing material 5 fails" refers to a state where its wear progresses to cause the LM guide 1 to fail as shown in Fig. 8.

[0020] Here, by using the display 17 of the PC 16 as a notification unit or medium for notifying the operator, various information such as the content processed by the PC 6 and the trend graph can be immediately compared and confirmed. Also, if a lantern is used as an example of the lighting display unit, people far away can also be informed, so there is no need to place a person near the display 17. Furthermore, if a terminal connected to the Internet is prepared using email, chat, etc., the determination result can be known anywhere. Note that the illustrations related to these are shown in the fifth embodiment described later.

[0021] As described above, according to the present embodiment, in the failure prediction detection system 10, the sealing material 5 is disposed on the slider 3 of the LM guide 1 so as to cover the gap between the slider 3 and the rail 2. The microphone 11 is disposed along the path along which the slider 3 moves, and acquires an acoustic signal generated when the LM guide 1 operates. The PC 16 extracts a feature amount that is the level of a characteristic frequency component appearing in the frequency components of the acquired acoustic signal. Specifically, the frequency components of the acoustic signal are analyzed, and the feature amount appearing in the frequency components is extracted. Then, based on the extracted feature amount, a sign of failure of the sealing material 5 is detected.

[0022] That is, when the LM guide 1 operates, the frequency components of the sound generated at the portion where the sealing material 5 is in contact with the rail 2 change as the shape of the sealing material 5 changes over time. Therefore, by extracting the feature amount for the frequency components of the acquired acoustic signal, even in an environment with a lot of noise during the operation of the LM guide 1, it can be determined that the shape of the sealing material 5 has changed and deteriorated to a certain extent. Thereby, a sign of the sealing material 5 reaching a failure state can be detected. Needless to say, the system 10 can also detect the case where the sealing material 5 has already failed.

[0023] Here, if the microphone 11 is installed outside the slider 3 and at a position where it does not contact the rail 2, it can be installed without stopping the equipment. Also, if it is installed on the rail 2 outside the slider 3 and without interfering with the operation of the slider 3, the signal-to-noise ratio can be improved by approaching the sound source. Further, if it is installed inside the slider 3 or above including those that move together such as the holding member 4, the distance between the sealing material 5 and the microphone 11 can be made constant regardless of the operation of the slider 3, and the absolute value of the sound pressure of the acoustic signal can be compared.

[0024] In addition, as a countermeasure after the omen is detected, by supplying oil to Rail 2, it is possible to prevent the promotion of wear and deterioration of the sealing material 5. Further, if only the sealing material 5 is replaced with a new one, it is possible to prevent a large amount of foreign matter from entering the inside of the slider 3 and accelerating the deterioration of the bearing. Furthermore, when the characteristic amount changes due to an abnormality in the mounting state of the sealing material 5 when only the sealing material 5 is replaced, it is also possible to detect the mounting state. Incidentally, the illustrations related to these will be shown in the sixth embodiment described later.

[0025] (Second Embodiment) Hereinafter, the same parts as those in the first embodiment will be denoted by the same reference numerals and the description thereof will be omitted, and the different parts will be described. The second embodiment shows an example in which the determination is made by statistical processing in the PC 16. In the horizontal axis of the spectrograms shown in FIGS. 6 to 8, 0 s to 6 s is the forward movement period of the slider 3, and 6 s to 10 s is the backward movement period thereof. During the period when the slider 3 moves backward, for the frequency band of 1000 Hz to 6000 Hz, the total value and the average value of the intensity of the frequency components are obtained.

[0026] As shown in FIG. 12, the total value when the sealing material 5 is new is "8.88" and the average value is "0.00056", whereas the total value when the sealing material 5 is worn and deteriorated is "23.75" and the average value is "0.0015", and both values are increasing. By monitoring this trend of increase in the numerical value and applying a threshold value, an omen leading to a failure state is detected.

[0027] (Third Embodiment) The third embodiment shows an example in which the determination is made by machine learning in the PC 16. The outline of the processing is shown below. (1) When the sealing material 5 is new, that is, a plurality of waveforms of acoustic signals in a normal state are prepared. (2) Each waveform is divided by a time window and the frequency is analyzed (see FIGS. 13 and 14). (3) The frequency distribution is divided into a certain interval, and the maximum value and the average value of the signal level are obtained for each interval. (4) By repeating (2) and (3), the characteristic amount for each waveform is extracted (see FIG. 15). (5) For example, a model is created from the feature quantities in the normal state using a method for detecting outliers in unsupervised learning, namely, the so-called Isolation Forest. (6) The data in the normal state and the worn state are compared, and the degree of change from the normal state is quantified for determination.

[0028] As shown in FIG. 16, assume that a histogram of the evaluation values of the Isolation Forest appears. The number of data for new products is 49, and the number of data for worn products is 55. In this case, if the threshold value of the evaluation value is set to about 0.64, for example, as shown in FIG. 17, in actual operation, it is possible to determine deterioration by monitoring the trend of the average value of the evaluation values.

[0029] (Fourth Embodiment) The fourth embodiment illustrates a variation of the configuration of the system 10 shown in FIG. 1 described above. FIG. 18 is a somewhat higher-level conceptualization of the functional block diagram shown in FIG. 1. In the system 21, the facility 22 includes an LM guide 1 and the like, and includes a sliding mechanism 23, a sliding mechanism protection member 24, and an acoustic signal acquisition unit 25.

[0030] The acoustic signal acquired by the acoustic signal acquisition unit 25 is input to the state detection unit 27 via the relay 26. The state detection unit 27 corresponds to a storage that stores acoustic data like the data logger 13, or a device having functions of frequency analysis and statistical processing of the PC 16. The processing result by the state detection unit 27 is displayed on a display device 28 corresponding to, for example, the display 17 and presented to the operator 29.

[0031] FIGS. 19 to 21 show variations of the embodiment based on the configuration shown in FIG. 18. The system 21A shown in FIG. 19 shows a configuration realized on-premises, and the parts corresponding to the relay 26 and the state detection unit 27 are realized by a PC or the like 30 and a NAS server 31.

[0032] The system 21B shown in FIG. 20 shows a configuration realized by replacing the NAS server 31 shown in FIG. 19 with a cloud service 32. Further, the system 21C shown in FIG. 21 shows a configuration realized by edge computing by deleting the NAS server 31 shown in FIG. 20. In the system 21C, processing such as frequency analysis is processed in real time without using storage such as the NAS server 31.

[0033] (Fifth Embodiment) The fifth embodiment illustrates a variation of the form of notifying the above-described worker 29 of the processing result. FIG. 22 shows a case where a lantern 33 is provided on the facility 22 in the factory, and by performing a lighting display with the lantern 33, it is possible to notify also a worker 29 located far from the facility 22. Further, notification is also performed on the display of the PC 31 arranged in the vicinity of the facility 22.

[0034] Further, FIG. 23 shows a case where a PC 31, a tablet 34, a smartphone 35, etc., which are communication terminals connected via a communication network such as the Internet, are arranged at a base different from the factory, and messages, icons, etc. are transmitted to them by mail, chat, etc. and displayed on the display for notification.

[0035] (Sixth Embodiment) The sixth embodiment illustrates a variation of the mode of arranging the above-described microphone 11. The star-shaped symbol shown in FIG. 24 indicates the microphone 11, and it is arranged in the vicinity of moving objects such as, for example, the indicating member 6 and the cutter 7 mounted on the rail 2, the slider 3, and the slider 3.

[0036] (Seventh Embodiment) The seventh embodiment illustrates an example of a response when a sign of the above-described failure is detected. Note that the "rolling element" shown in the figure is a bearing or the like constituting a sliding mechanism. FIG. 25 shows a state where the sealing material 5 is in a sound state, and FIG. 26 shows a state where the sealing material 5 is worn. FIG. 27 shows a case where the progress of deterioration is suppressed by injecting a lubricant 36 such as oil into the sliding mechanism portion. FIG. 28 shows a state where the sealing material 5 is replaced with a new one.

[0037] (Other Embodiments) It is not always necessary to use the PC 16 or the like, and the operator may make a determination by visually observing the spectrogram displayed on the display 17. The features appearing in the frequency components vary depending on the size and shape of the LM guide 1, the size, shape and material of the sealing material 5, the operation pattern of the slider 3, and the like. The linear guide device is not limited to the LM guide 1. The data logger 13 to the PC 16 may be configured by a single device, and the processing may be executed by a single program executed by the computer constituting the device.

[0038] Incidentally, examples of the parameters that affect the waveform of the acoustic signal include the following. <Rail> · Width, length, height, cross-sectional shape, material. <Slider> · Width, length, height, cross-sectional shape, material. <Side Sealing Material> · Rail contact circumferential shape or rail cross-sectional shape, rail contact circumferential length, rail contact width, material. <LM Guide Control Unit> · Moving speed, speed pattern. <Sensor> · Arrangement, distance to the sealing material, type of sensor, sensor specifications. <Moving Object> · Weight, center of gravity position. <Environment> · Amount of foreign matter, foreign matter size, foreign matter material, blow cycle, temperature, humidity, amount of oil supply, type of oil, oil supply cycle.

[0039] Even when the conditions and values of these parameters change, appropriate correction and adjustment can be made for the sound intensity and frequency required for anomaly detection, the noise intensity and frequency, and the determination threshold by using classical statistical methods or sensor signal processing using machine learning during pre-evaluation or operation. In addition, the material of the protective member also varies depending on the mounting environment conditions such as temperature and water absorption rate, and is affected by, for example, changes in hardness and the like. Those environmental conditions are acquired by sensors and judged comprehensively. The characteristic amount of the acoustic signal changes not only depending on the configuration of the linear guide device and other moving devices, but also depending on the shape of the foreign object, for example, spherical, elliptical, uneven shape, and the material physical properties, for example, hardness, viscosity. It is also possible to detect the characteristics due to the difference in the foreign object.

[0040] Although the present disclosure has been described based on the embodiments, it is understood that the present disclosure is not limited to the embodiments and structures. The present disclosure also includes various modifications and modifications within the equivalent range. In addition, various combinations and forms, and further other combinations and forms including only one element, more than one, or less than one of them are also within the scope and spirit of the present disclosure.

[0041] The means and / or functions provided by each device and the like can be provided by software recorded in a physical memory device and a computer that executes it, software only, hardware only, or a combination thereof. For example, when the control device is provided by an electronic circuit that is hardware, it can be provided by a digital circuit including a number of logic circuits or an analog circuit.

[0042] The control unit and its method described in the present disclosure may be implemented by a dedicated computer provided by configuring a processor and a memory programmed to execute one or more functions embodied by a computer program. Alternatively, the control unit and its method described in the present disclosure may be implemented by a dedicated computer provided by configuring a processor with one or more dedicated hardware logic circuits. Or, the control unit and its method described in the present disclosure may be implemented by one or more dedicated computers configured by a combination of a processor and a memory programmed to execute one or more functions and a processor configured by one or more hardware logic circuits. Also, the computer program may be stored in a computer-readable non-transitory tangible recording medium as instructions to be executed by a computer.

Explanation of Signs

[0043] In the drawings, 1 indicates an LM guide, 2 indicates a rail, 3 indicates a slider, 5 indicates a sealing material, 10 indicates a fault prediction detection system, 11 indicates a microphone, and 16 indicates a personal computer.

Claims

1. In a moving device comprising a fixed part (2) and a moving part (3) that moves along the fixed part via a sliding mechanism, it is for detecting a sign of failure of a sliding mechanism protection member (5) arranged so as to cover a gap between the moving part and the fixed part, an acoustic signal acquisition unit (11) arranged along a path along which the moving part moves via the sliding mechanism and acquiring an acoustic signal generated when the moving device operates, and a feature quantity extraction unit (16) extracting a feature quantity that is a level of a characteristic frequency component appearing in the frequency components of the acquired acoustic signal, detecting a sign of failure of the sliding mechanism protection member based on the extracted feature quantity, A failure sign detection system for a sliding mechanism protection member that corrects or adjusts the sound intensity, frequency, noise intensity, frequency, or determination threshold value necessary for anomaly detection when conditions and values of parameters affecting the waveform of the acoustic signal change.

2. In a moving device comprising a fixed part (2) and a moving part (3) that moves along the fixed part via a sliding mechanism, it is for detecting a sign of failure of a sliding mechanism protection member (5) arranged so as to cover a gap between the moving part and the fixed part, an acoustic signal acquisition unit (11) arranged along a path along which the moving part moves via the sliding mechanism and acquiring an acoustic signal generated when the moving device operates, and a feature quantity extraction unit (16) extracting a feature quantity that is a level of a characteristic frequency component appearing in the frequency components of the acquired acoustic signal, detecting a sign of failure of the sliding mechanism protection member based on the extracted feature quantity, A failure sign detection system for a sliding mechanism protection member that detects a difference in the material of the sliding mechanism protection member or foreign matter mixed in the gap from the feature quantity.

3. In a moving device comprising a fixed part (2) and a moving part (3) that moves along the fixed part via a sliding mechanism, it is for detecting a sign of failure of a sliding mechanism protection member (5) arranged so as to cover a gap between the moving part and the fixed part, an acoustic signal acquisition unit (11) arranged along a path along which the moving part moves via the sliding mechanism and acquiring an acoustic signal generated when the moving device operates, and a feature quantity extraction unit (16) extracting a feature quantity that is a level of a characteristic frequency component appearing in the frequency components of the acquired acoustic signal, A failure prediction detection system for a sliding mechanism protection member that detects a sign of failure of the sliding mechanism protection member based on feature amounts extracted when the moving part moves forward and backward along the fixed part.

4. In a moving device including a fixed part and a moving part that is disposed via a sliding mechanism on the fixed part and moves along the fixed part, a method for detecting a sign of failure of a sliding mechanism protection member that is disposed on the moving part so as to cover a gap between the moving part and the fixed part, comprising: acquiring an acoustic signal generated when the moving device operates, the acoustic signal being disposed along a path along which the moving part moves; extracting a feature amount that is a level of a characteristic frequency component that appears in a frequency component of the acquired acoustic signal; detecting a sign of failure of the sliding mechanism protection member based on the extracted feature amount; A method for detecting a sign of failure of a sliding mechanism protection member, wherein when conditions or values of parameters that affect the waveform of the acoustic signal change, correction or adjustment is performed on the sound intensity, frequency, noise intensity, frequency, or determination threshold value required for abnormality detection.

5. In a moving device including a fixed part and a moving part that is disposed via a sliding mechanism on the fixed part and moves along the fixed part, a method for detecting a sign of failure of a sliding mechanism protection member that is disposed on the moving part so as to cover a gap between the moving part and the fixed part, comprising: acquiring an acoustic signal generated when the moving device operates, the acoustic signal being disposed along a path along which the moving part moves; extracting a feature amount that is a level of a characteristic frequency component that appears in a frequency component of the acquired acoustic signal; detecting a sign of failure of the sliding mechanism protection member based on the extracted feature amount; A method for detecting a sign of failure of a sliding mechanism protection member, wherein a difference in the material of the sliding mechanism protection member or foreign matter mixed in the gap is detected from the feature amount.

6. In a moving device including a fixed part and a moving part that is disposed via a sliding mechanism on the fixed part and moves along the fixed part, a method for detecting a sign of failure of a sliding mechanism protection member that is disposed on the moving part so as to cover a gap between the moving part and the fixed part, comprising: acquiring an acoustic signal generated when the moving device operates, the acoustic signal being disposed along a path along which the moving part moves; extracting a feature amount that is a level of a characteristic frequency component that appears in a frequency component of the acquired acoustic signal; A method for detecting a sign of failure of a sliding mechanism protection member, which detects a sign of failure of the sliding mechanism protection member based on a feature amount extracted when the moving part is moved forward and backward along the fixed part.

7. In a moving device including a fixed part and a moving part that is arranged via a sliding mechanism on the fixed part and moves along the fixed part, a computer including a device that detects a sign of failure of a sliding mechanism protection member arranged so as to cover a gap between the moving part and the fixed part is configured to execute: acquire an acoustic signal generated when the moving device operates, the acoustic signal being arranged along a path along which the moving part moves; extract a feature amount that is a level of a characteristic frequency component appearing in a frequency component of the acquired acoustic signal; detect a sign of failure of the sliding mechanism protection member based on the extracted feature amount; A failure prediction detection program for a sliding mechanism protection member that corrects or adjusts the intensity of sound, frequency, noise intensity, frequency, or determination threshold value required for abnormality detection when conditions and values of parameters affecting the waveform of the acoustic signal change.

8. In a moving device including a fixed part and a moving part that is arranged via a sliding mechanism on the fixed part and moves along the fixed part, a computer including a device that detects a sign of failure of a sliding mechanism protection member arranged so as to cover a gap between the moving part and the fixed part is configured to execute: acquire an acoustic signal generated when the moving device operates, the acoustic signal being arranged along a path along which the moving part moves; extract a feature amount that is a level of a characteristic frequency component appearing in a frequency component of the acquired acoustic signal; detect a sign of failure of the sliding mechanism protection member based on the extracted feature amount; A failure prediction detection program for a sliding mechanism protection member that detects a difference in the material of the sliding mechanism protection member or foreign matter mixed in the gap from the feature amount.

9. In a moving device including a fixed part and a moving part that is arranged via a sliding mechanism on the fixed part and moves along the fixed part, a computer including a device that detects a sign of failure of a sliding mechanism protection member arranged so as to cover a gap between the moving part and the fixed part is configured to execute: acquire an acoustic signal generated when the moving device operates, the acoustic signal being arranged along a path along which the moving part moves; Extract a feature amount, which is the level of a characteristic frequency component that appears in the frequency components of the acquired acoustic signal, A failure prediction detection program for a sliding mechanism protection member that causes the moving part to detect a sign of failure of the sliding mechanism protection member based on the feature amount extracted when the moving part moves forward and backward along the fixed part.

Images