WO2020170409A1 - 異常検知システム、及び異常検知方法 - Google Patents
異常検知システム、及び異常検知方法 Download PDFInfo
- Publication number
- WO2020170409A1 WO2020170409A1 PCT/JP2019/006703 JP2019006703W WO2020170409A1 WO 2020170409 A1 WO2020170409 A1 WO 2020170409A1 JP 2019006703 W JP2019006703 W JP 2019006703W WO 2020170409 A1 WO2020170409 A1 WO 2020170409A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- abnormality
- speed reducer
- sensor
- detection system
- statistical analysis
- Prior art date
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 42
- 238000007619 statistical method Methods 0.000 claims abstract description 43
- 230000005856 abnormality Effects 0.000 claims description 136
- 239000003638 chemical reducing agent Substances 0.000 claims description 104
- 238000001228 spectrum Methods 0.000 claims description 35
- 230000001133 acceleration Effects 0.000 claims description 27
- 238000009826 distribution Methods 0.000 claims description 17
- 230000002159 abnormal effect Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 description 18
- 238000007781 pre-processing Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000000034 method Methods 0.000 description 6
- 230000007547 defect Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16H—GEARING
- F16H61/00—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing
- F16H61/12—Detecting malfunction or potential malfunction, e.g. fail safe; Circumventing or fixing failures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/028—Acoustic or vibration analysis
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16H—GEARING
- F16H1/00—Toothed gearings for conveying rotary motion
- F16H1/02—Toothed gearings for conveying rotary motion without gears having orbital motion
- F16H1/04—Toothed gearings for conveying rotary motion without gears having orbital motion involving only two intermeshing members
- F16H1/06—Toothed gearings for conveying rotary motion without gears having orbital motion involving only two intermeshing members with parallel axes
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16H—GEARING
- F16H57/00—General details of gearing
- F16H57/01—Monitoring wear or stress of gearing elements, e.g. for triggering maintenance
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16H—GEARING
- F16H57/00—General details of gearing
- F16H57/01—Monitoring wear or stress of gearing elements, e.g. for triggering maintenance
- F16H2057/018—Detection of mechanical transmission failures
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16H—GEARING
- F16H61/00—Control functions within control units of change-speed- or reversing-gearings for conveying rotary motion ; Control of exclusively fluid gearing, friction gearing, gearings with endless flexible members or other particular types of gearing
- F16H61/12—Detecting malfunction or potential malfunction, e.g. fail safe; Circumventing or fixing failures
- F16H2061/1208—Detecting malfunction or potential malfunction, e.g. fail safe; Circumventing or fixing failures with diagnostic check cycles; Monitoring of failures
Definitions
- the present invention relates to an anomaly detection system and an anomaly detection method, and more particularly to an anomaly detection system and an anomaly detection method for detecting an anomaly in a speed reducer used in an industrial machine.
- Extruders are widely used as industrial machines for manufacturing plastic products.
- extruders there is a twin-screw extruder that kneads a plastic raw material using a twin-screw (see Patent Document 1).
- An extruder which is one of the industrial machines, uses a reducer that transmits the power generated by the motor to each of the twin-screw screws.
- the speed reducer converts the power generated by the motor into a predetermined torque and transmits it to the biaxial screw.
- Various parts such as shafts, bearings, and gears are built in the speed reducer.
- Various parts are built in the speed reducer in this way, and if a defect (such as a scratch) occurs in a part of each part, the defect in the part may lead to failure of the entire speed reducer. Therefore, there is a need for an abnormality detection system capable of accurately detecting an abnormality in the speed reducer (component).
- an object of the present invention is to provide an abnormality detection system and an abnormality detection method capable of accurately detecting an abnormality in a speed reducer.
- An abnormality detection system is an abnormality detection system for detecting an abnormality in a speed reducer, which is attached to a housing of the speed reducer and detects vibration on a surface of the speed reducer housing.
- Sensor for, a statistical analysis unit that performs a statistical analysis of the vibration detected by the sensor, a frequency analysis unit that performs a frequency analysis of the vibration detected by the sensor, the result of the statistical analysis and the result of the frequency analysis
- an abnormality determination unit that determines an abnormality of the speed reducer based on the above.
- An abnormality detection method is an abnormality detection method for detecting an abnormality of a speed reducer, wherein a sensor attached to a housing of the speed reducer is used to detect a surface of a housing of the speed reducer.
- an abnormality detection system and an abnormality detection method capable of accurately detecting an abnormality in a speed reducer.
- FIG. 1 is a block diagram for explaining the abnormality detection system according to the embodiment.
- the abnormality detection system 1 according to the present embodiment is an abnormality detection system for detecting an abnormality of a speed reducer typically used in an industrial machine such as an extruder (a twin screw extruder).
- the abnormality detection system 1 according to the present embodiment includes sensors 11_1 to 11_3, a statistical analysis unit 12, a preprocessing unit 13, a frequency analysis unit 14, a peak processing unit 15, an abnormality determination unit 17, and
- the display unit 18 is provided.
- the number of sensors can be arbitrarily determined as long as it is one or more. Further, in the present specification, the sensors 11_1 to 11_3 may be collectively referred to as the sensor 11.
- the sensor 11 is attached to the housing of the speed reducer 10 and detects vibration on the surface of the housing of the speed reducer 10.
- 2 and 3 are perspective views for explaining the mounting position of the sensor 11, and show an example of the mounting position of the sensor 11 on the speed reducer 10. 2 and 3, the sensor 11 is shown as A1 to A5, H1 to H3, and V1 to V3, and A, H, and V indicate the directions of vibration detected by the sensor.
- the sensor A1 is a sensor that detects vibration in the A (Axis) direction
- the sensor H1 is a sensor that detects vibration in the H (Horizontal: horizontal) direction
- the sensor V1 is the V (Vertical: vertical) direction. Is a sensor that detects the vibration of the.
- the housing (case) of the speed reducer 10 has a substantially box shape.
- the input shaft 21 and the bearing 22 are arranged on the input-side surface 31 of the speed reducer 10, that is, the surface 31 on the side where power is input from a motor (not shown).
- output shafts 25 and 26 are arranged on the output-side surface 35 of the speed reducer 10, that is, the surface 35 on which the power is output to the biaxial screw (not shown).
- Various parts such as shafts and gears are provided inside the speed reducer 10.
- the speed reducer 10 converts the power transmitted from the motor (not shown) to the input shaft 21 into a predetermined torque, and transmits the power of the predetermined torque to the biaxial screw (not shown) via the output shafts 25 and 26. ..
- each sensor is attached to each of the three surfaces forming the corner portion in the vicinity of the corner portion of the casing of the speed reducer 10. Therefore, each sensor can be used to measure the acceleration in the three-axis directions near the corner of the housing.
- the sensors A1, H1, and V1 are provided near the corner 41 of the casing of the speed reducer 10, respectively. That is, the sensors A1, H1, and V1 are attached to the three surfaces 31, 34 (see FIG. 3) and 33, which form the corner portion 41, respectively. In the vicinity of the corner 41, the sensor A1 detects vibration in the A-axis direction, the sensor H1 detects vibration in the H-axis direction, and the sensor V1 detects vibration in the V-axis direction.
- the sensors A2, H2, and V2 are provided near the corners 42 of the casing of the speed reducer 10, respectively. That is, the sensors A2, H2, and V2 are attached to the three surfaces 31, 32, and 33 forming the corner portion 42, respectively. In the vicinity of the corner 42, the sensor A2 detects vibration in the A-axis direction, the sensor H2 detects vibration in the H-axis direction, and the sensor V2 detects vibration in the V-axis direction.
- the sensors A3, H3, and V3 are provided near the corners 43 of the casing of the speed reducer 10, respectively. That is, the sensors A3, H3, and V3 are attached to the three surfaces 35, 34, and 33 forming the corner 43, respectively. In the vicinity of the corner 43, the sensor A3 detects vibration in the A-axis direction, the sensor H3 detects vibration in the H-axis direction, and the sensor V3 detects vibration in the V-axis direction.
- a sensor A4 (see FIG. 2) is provided near the bearing 22 of the speed reducer 10. Therefore, the vibration in the vicinity of the bearing 22 can be detected using the sensor A4. Further, the sensor A5 (see FIG. 2) and the sensor H4 (see FIG. 3) are provided below the speed reducer 10. By using the sensors A5 and H4, the vibration of the lower part of the speed reducer 10 can be detected. Therefore, the difference between the vibration in the upper part and the vibration in the lower part of the speed reducer 10 can be obtained. Further, by providing the sensors A5 and H4 on the lower portion of the speed reducer 10, it is possible to measure the vibration of another machine set near the speed reducer 10 that is the measurement target. Thereby, the vibration data of the other machine can be subtracted from the vibration data of the speed reducer 10.
- each sensor is attached to the upper side of the surface 31 of the speed reducer 10 on the input shaft 21 side and the upper side of the surface 35 of the speed reducer 10 on the output shafts 25 and 26 side.
- many sensors are attached to the upper corners 41, 42, 43 of the casing of the speed reducer 10. Since the upper side of the housing of the speed reducer 10 vibrates more than the lower side, a large number of sensors can be attached to the upper side of the housing of the speed reducer 10 to obtain large vibration data.
- the arrangement of the sensors described above is an example, and the arrangement of the sensors can be appropriately changed according to the shape of the reduction gear 10 and the arrangement of parts.
- a modal analysis is performed on the speed reducer 10 and an analysis for predicting the natural frequency and vibration shape of the speed reducer 10 is performed.
- a hammering test is performed on the speed reducer 10 to experimentally determine the natural frequency and the vibration shape to verify the accuracy of the modal analysis.
- Such modal analysis and hammering test can be repeated to determine the placement of the sensor.
- the vibration analysis simulating the operating state of the speed reducer 10 may be performed to identify the vibration location or resonance location of the speed reducer 10 to determine the placement of the sensor.
- the statistical analysis unit 12 shown in FIG. 1 performs statistical analysis of vibrations detected by the sensors 11_1 to 11_3. Specifically, the statistical analysis unit 12 performs statistical analysis using the acceleration of vibration detected by the sensors 11_1 to 11_3.
- the statistical analysis is a method of performing statistical analysis using vibration acceleration data, for example, a method of obtaining a frequency distribution of vibration acceleration magnitudes detected by the sensors 11_1 to 11_3. The details of the statistical analysis will be described later.
- statistical analysis may be performed using velocity or displacement other than the acceleration of vibration. The same applies to the frequency analysis described below.
- the pre-processing unit 13 performs pre-processing on the vibration data detected by the sensors 11_1 to 11_3. For example, as pre-processing, processing for removing noise included in the vibration data detected by the sensors 11_1 to 11_3 may be performed. The noise can be removed by using a filter such as a low-pass filter. Further, for example, as preprocessing, envelope processing may be performed on the vibration data detected by the sensors 11_1 to 11_3.
- the frequency analysis unit 14 analyzes the frequency of the vibration detected by the sensors 11_1 to 11_3. Specifically, the frequency analysis unit 14 performs frequency analysis on the vibration data from which noise has been removed by the preprocessing unit 13. For example, the frequency analysis unit 14 generates a power spectrum showing the magnitude of acceleration of the vibration detected by the sensors 11_1 to 11_3 with respect to the frequency.
- FFT Fast Fourier transform
- the peak processing unit 15 performs processing that makes the power spectrum generated by the frequency analysis unit 14 clear, that is, processing that emphasizes the peak.
- the peak processing unit 15 can emphasize the peak by adding the frequency-analyzed data (power spectrum) a predetermined number of times and then performing a process of dividing by a predetermined value (averaging process).
- the abnormality determination unit 17 determines the abnormality of the speed reducer 10 based on the analysis result of the statistical analysis unit 12 and the analysis result of the frequency analysis unit 14 (output of the peak processing unit 15). Specifically, the abnormality determination unit 17 determines whether there is an abnormality in the speed reducer 10 based on the result of the statistical analysis by the statistical analysis unit 12. For example, the abnormality determination unit 17 can determine whether or not there is an abnormality in the speed reducer 10 based on the frequency distribution of the magnitudes of the vibration accelerations detected by the sensors 11_1 to 11_3.
- the abnormality determination unit 17 can specify the type of abnormality of the speed reducer 10 based on the power spectrum generated by the frequency analysis unit 14.
- the type of abnormality of the speed reducer 10 is a defect of each component, for example, scratches, cracks, wear, corrosion, etc. on the shaft, the bearing, the gear, and the like. It may also be an oil abnormality.
- the abnormality determination unit 17 may previously store abnormality determination data in which a power spectrum indicating an abnormality and a type of abnormality of the speed reducer 10 are associated with each other.
- the abnormality determination unit 17 can identify the type of abnormality of the speed reducer 10 by collating the power spectrum generated by the frequency analysis unit 14 with the abnormality determination data stored in advance.
- the abnormality determination unit 17 includes a power spectrum corresponding to the type of abnormality of the speed reducer 10 (type of abnormality of parts), such as a power spectrum when the bearing is scratched or a power spectrum when the gear is scratched.
- the database is created in advance. Then, by comparing the power spectrum generated by the frequency analysis unit 14 with this database, it is possible to specify the type of abnormality of the speed reducer 10.
- the sensors 11_1 to 11_3 are attached to the housing surface of the speed reducer 10 at a plurality of locations (see FIGS. 2 and 3).
- the abnormality determination unit 17 may identify the abnormal portion of the speed reducer 10 based on the statistical analysis result and the frequency analysis result of the plurality of sensors 11_1 to 11_3. For example, when the vibration detected by the sensor 11_3 is larger than the reference value, it can be determined that there is an abnormal portion near the sensor 11_3.
- the display unit 18 shown in FIG. 1 displays the determination result of the abnormality determination unit 17.
- the display unit 18 can be configured by using a liquid crystal display or the like.
- the user can grasp the state of the speed reducer 10, that is, the presence/absence of an abnormality, the type of abnormality, and the abnormal location.
- an inspection recommendation message may be displayed on the display unit 18.
- a screen for requesting maintenance may be displayed on the display unit 18.
- the user can easily request the manufacturer for maintenance by pressing the maintenance request button displayed on the display unit 18 (touch panel).
- a screen for ordering defective parts may be displayed on the display unit 18.
- the user can order the defective component from the manufacturer by pressing the order button displayed on the display unit 18 (touch panel).
- step S1 the speed reducer 10 is normally operated (step S1).
- step S2 using the sensors 11_1 to 11_3 attached to the speed reducer 10, vibration data on the surface of the casing of the speed reducer 10 in steady operation is acquired (step S2).
- FIG. 5 is a graph showing vibration waveforms detected by the sensors 11_1 to 11_3.
- the sensors 11_1 to 11_3 are also referred to as sensors A to C.
- the vibration data shown in FIG. 5 shows a change over time in the acceleration of vibration on the housing surface of the speed reducer 10.
- the vibration data shown in FIG. 5 indicates that the larger the acceleration, the larger the amplitude of the vibration on the surface of the housing.
- the acceleration of the vibration data in the sensor C is the largest, which indicates that the vibration amplitude is large at the position where the sensor C is attached.
- FIG. 6 is a graph for explaining an example in which statistical processing is performed using the acceleration of vibration detected by the sensors A to C.
- the graph shown in FIG. 6 shows an example in which the frequency distribution of the magnitude of the acceleration of vibration detected by the sensors A to C is obtained.
- the graph shown in FIG. 6 is a histogram, where the horizontal axis represents the acceleration section (class) and the vertical axis represents the frequency in each section (class).
- the width of each section of acceleration is 0.1. Since the acceleration of the vibration data of the sensors A and B shown in FIG. 5 is in the range of ⁇ 1, the shape of the frequency distribution is sharp in the graph of the sensors A and B shown in FIG. On the other hand, since the acceleration of the vibration data of the sensor C shown in FIG. 5 is in the range of ⁇ 2, the shape of the frequency distribution is broad in the graph of the sensor C shown in FIG. From the results shown in FIG. 6, the statistical analysis unit 12 obtains a variance value as a statistical analysis result of the vibration data of each of the sensors A to C. In the example shown in FIG. 6, the graph of the sensors A and B has a sharp frequency distribution, so the variance value is small. On the other hand, since the shape of the frequency distribution of the graph of the sensor C is broad, the variance value is high.
- the preprocessing unit 13 also performs preprocessing on the vibration data detected by the sensors A to C (step S4). For example, a process of removing noise included in the vibration data detected by the sensors A to C using a low pass filter is performed.
- the frequency analysis unit 14 performs frequency analysis on the vibration data from which noise has been removed by the preprocessing unit 13 (step S5). Specifically, the frequency analysis unit 14 generates a power spectrum indicating the magnitude of acceleration of the vibration detected by the sensors A to C with respect to frequency.
- FFT Fast Fourier transform
- the peak processing unit 15 performs peak processing for clarifying the power spectrum generated by the frequency analysis unit 14 (step S6).
- FIG. 7 is a graph for explaining an example of frequency analysis of vibration detected by the sensor.
- the upper diagram of FIG. 7 shows the power spectrum generated by the frequency analysis unit 14, and the lower diagram of FIG. 7 shows the power spectrum after the peak processing is performed by the peak processing unit 15.
- the power spectrum of the sensor C is shown as a typical example.
- the frequency analysis unit 14 performs a fast Fourier transform (FFT) process on the pre-processed (noise-removed) vibration data to indicate the magnitude of acceleration with respect to the frequency as shown in the upper diagram of FIG. 7. Generating a power spectrum.
- the peak processing unit 15 performs processing (averaging processing) of adding the data (power spectrum) after frequency analysis a predetermined number of times and then dividing by a predetermined value. As a result, the peak can be emphasized as shown in the lower diagram of FIG. 7.
- the abnormality determination unit 17 determines the abnormality of the speed reducer 10 based on the result of the statistical analysis (step S3) and the result of the frequency analysis (steps S4 to S6) (step S7). Specifically, the abnormality determination unit 17 determines whether there is an abnormality in the speed reducer 10 based on the frequency distribution of the vibration data of the sensors A to C (see FIG. 6).
- FIG. 8 is a graph for explaining abnormality determination.
- the horizontal axis of FIG. 8 indicates the degree of abnormality, and the vertical axis indicates the monitoring (judgment) value.
- the monitoring (judgment) value corresponds to the variance value obtained from the frequency distribution shown in FIG. That is, in FIG. 8, the higher the variance value, the higher the degree of abnormality. More specifically, in FIG. 6, the graph of the sensors A and B has a sharp frequency distribution shape, and thus the variance value is a small value. Therefore, in the graph shown in FIG. 8, since the variance values of the sensors A and B are small, the vibration data of the sensors A and B are determined to be normal. On the other hand, in FIG. 6, since the graph of the sensor C has a broad frequency distribution, the variance value is high. Therefore, in the graph shown in FIG. 8, the variance value of the sensor C becomes large, and the vibration data of the sensor C is determined to be abnormal (abnormal level 4).
- abnormal levels 1 to 4 are set by using the variance value of the frequency distribution as a monitoring (judgment) value.
- the graph shown in FIG. 8 indicates that the higher the abnormality level, the greater the degree of abnormality.
- the speed reducer 10 is configured by using each part having a degree of damage of “small”, a degree of damage of “medium”, and a degree of damage of “large”. Then, the vibration data of each of the speed reducers 10 thus configured is acquired, and the variance value of the frequency distribution of the acceleration of each speed reducer 10 is obtained.
- the degree of abnormality on the horizontal axis shown in FIG. 8 corresponds to the degree of scratches (small, medium, large) on the parts that have been scratched in advance, and the higher the degree of abnormality, the greater the degree of scratches. Therefore, in the graph shown in FIG. 8, the higher the abnormality degree, the higher the variance value (monitoring (judgment) value) of the acceleration frequency distribution.
- the abnormality determination unit 17 can accurately determine whether or not there is an abnormality in the speed reducer 10 by creating a graph (determination criterion) as shown in FIG. 8 in advance.
- the abnormality determination unit 17 can specify the type of abnormality of the speed reducer 10 based on the power spectrum that is the result of the frequency analysis (steps S4 to S6).
- the type of abnormality of the speed reducer 10 is a defect of each component, for example, scratches, cracks, wear, corrosion, etc. on the shaft, the bearing, the gear, and the like. It may also be an oil abnormality.
- FIG. 9 is a graph for explaining an example of a power spectrum obtained by frequency analysis, showing a power spectrum in a normal case (upper figure in FIG. 9) and a power spectrum in an abnormal case (lower figure in FIG. 9). ing.
- the power spectrum in the abnormal case (lower figure in FIG. 9) has a higher power value than the power spectrum in the normal case (upper figure in FIG. 9).
- the power value at a specific frequency is high.
- the power value near 30 Hz is particularly high.
- the abnormality determination unit 17 can specify the type of abnormality of the speed reducer 10 (may be an abnormal portion; the same applies below) by using a specific frequency with a high power value.
- the abnormality determination unit 17 stores in advance abnormality determination data in which a power spectrum indicating an abnormality and a type of abnormality of the reduction gear 10 (may be an abnormal location) are associated with each other.
- the abnormality determination unit 17 includes the power spectrum corresponding to the type of abnormality of the speed reducer 10 (type of abnormality of parts), such as the power spectrum when the bearing is scratched and the power spectrum when the gear is scratched.
- the database is created in advance.
- the abnormality determination unit 17 may store a table in which the type of abnormality of the speed reducer 10 and the frequency at which the power value increases in the case of the abnormality are associated with each other.
- the abnormality determination unit 17 can identify the type of abnormality of the speed reducer 10 by comparing the power spectrum generated by the frequency analysis unit 14 with the abnormality determination data stored in advance. Specifically, by collating the specific frequency with the high power value with the abnormality determination data, the type of abnormality corresponding to the specific frequency can be specified.
- step S8: No when the abnormality determination unit 17 determines that there is no abnormality (step S8: No), the operations of steps S2 to S8 are repeated. On the other hand, when the abnormality determination unit 17 determines that there is an abnormality (step S8: Yes), a message indicating that the speed reducer 10 is abnormal is displayed on the display unit 18.
- step S3 and frequency analysis may be either first or may be performed simultaneously.
- the sensor attached to the housing of the speed reducer is used to detect the vibration on the surface of the speed reducer housing. Then, a statistical analysis and a frequency analysis of the vibration detected by the sensor are performed, and the speed reducer abnormality determination is performed based on the analysis results. Therefore, it is possible to provide the abnormality detection system and the abnormality detection method capable of accurately detecting the abnormality of the speed reducer.
- the abnormality detection system it is possible to determine whether there is an abnormality in the speed reducer 10 based on the statistical analysis result of the statistical analysis unit 12.
- the type of abnormality of the speed reducer 10 can be specified based on the power spectrum generated by the frequency analysis unit 14. Further, it is possible to specify the abnormal portion of the speed reducer 10 based on the statistical analysis result and the frequency analysis result of the plurality of sensors 11.
- the speed reducer abnormality determination is performed using the statistical analysis result and the frequency analysis result. Therefore, the speed reducer abnormality (absence of abnormality, type of abnormality, abnormality Location) can be accurately detected.
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Gear Transmission (AREA)
Abstract
Description
図1は、実施の形態にかかる異常検知システムを説明するためのブロック図である。本実施の形態にかかる異常検知システム1は、典型的には押出機(二軸スクリュ押出機)等の産業機械に用いられる減速機の異常を検知するための異常検知システムである。図1に示すように、本実施の形態にかかる異常検知システム1は、センサ11_1~11_3、統計解析部12、前処理部13、周波数解析部14、ピーク処理部15、異常判定部17、及び表示部18を備える。なお、図1では、一例として3つのセンサ11_1~11_3を備える場合を示しているが、センサの数は1つ以上であれば任意に決定することができる。また、本明細書ではセンサ11_1~11_3を総称してセンサ11と記載する場合もある。
10 減速機
11_1、11_2、11_3 センサ
12 統計解析部
13 前処理部
14 周波数解析部
15 ピーク処理部
17 異常判定部
18 表示部
21 入力軸
22 軸受
25、26 出力軸
Claims (9)
- 減速機の異常を検知するための異常検知システムであって、
前記減速機の筐体に取り付けられ、前記減速機の筐体表面における振動を検出するためのセンサと、
前記センサで検出された振動の統計解析を行う統計解析部と、
前記センサで検出された振動の周波数解析を行う周波数解析部と、
前記統計解析の結果と前記周波数解析の結果とに基づいて、前記減速機の異常判定を行う異常判定部と、を備える、
異常検知システム。 - 前記統計解析部は、前記センサで検出された振動の加速度を用いて統計解析を行い、
前記異常判定部は、前記統計解析の結果に基づいて前記減速機の異常の有無を判定する、
請求項1に記載の異常検知システム。 - 前記統計解析部は、前記センサで検出された振動の加速度の大きさの度数分布を求め、
前記異常判定部は、前記求めた度数分布の分散に基づいて前記減速機の異常の有無を判定する、
請求項1または2に記載の異常検知システム。 - 前記周波数解析部は、前記センサで検出された振動の周波数に対する加速度の大きさを示すパワースペクトルを生成し、
前記異常判定部は、前記パワースペクトルに基づいて前記減速機の異常の種類を特定する、
請求項1~3のいずれか一項に記載の異常検知システム。 - 前記異常判定部には、異常を示すパワースペクトルと前記減速機の異常の種類とを対応づけた異常判定用データが予め保存されており、
前記異常判定部は、前記周波数解析部で生成された前記パワースペクトルを前記予め保存されている異常判定用データと照合することで、前記減速機の異常の種類を特定する、
請求項1~4のいずれか一項に記載の異常検知システム。 - 前記センサは、前記減速機の筐体表面の複数箇所に取り付けられており、
前記異常判定部は、前記複数のセンサの前記統計解析の結果及び前記周波数解析の結果に基づいて、前記減速機の異常箇所を特定する、
請求項1~5のいずれか一項に記載の異常検知システム。 - 前記減速機の筐体は略箱型であり、
前記センサは、前記筐体の角部近傍において、当該角部を構成する3つの面に各々取り付けられており、
前記各々のセンサを用いて前記筐体の前記角部近傍における3軸方向の加速度を測定する、
請求項1~6のいずれか一項に記載の異常検知システム。 - 前記各々のセンサは、前記減速機の入力軸側の面の上側および前記減速機の出力軸側の面の上側の少なくとも一方に取り付けられている、請求項7に記載の異常検知システム。
- 減速機の異常を検知するための異常検知方法であって、
前記減速機の筐体に取り付けられたセンサを用いて、前記減速機の筐体表面における振動の統計解析を行う工程と、
前記センサで検出された振動の周波数解析を行う工程と、
前記統計解析の結果と前記周波数解析の結果とに基づいて、前記減速機の異常判定を行う工程と、を備える、
異常検知方法。
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP19915675.3A EP3929460B1 (en) | 2019-02-22 | 2019-02-22 | Anomaly detection system and anomaly detection method |
PCT/JP2019/006703 WO2020170409A1 (ja) | 2019-02-22 | 2019-02-22 | 異常検知システム、及び異常検知方法 |
US17/425,891 US20220276126A1 (en) | 2019-02-22 | 2019-02-22 | Anomaly detection system and anomaly detection method |
JP2021501243A JP7199793B2 (ja) | 2019-02-22 | 2019-02-22 | 異常検知システム、及び異常検知方法 |
KR1020217026750A KR102697388B1 (ko) | 2019-02-22 | 2019-02-22 | 이상 검지 시스템, 및 이상 검지 방법 |
CN201980092690.9A CN113454363B (zh) | 2019-02-22 | 2019-02-22 | 异常探测系统及异常探测方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2019/006703 WO2020170409A1 (ja) | 2019-02-22 | 2019-02-22 | 異常検知システム、及び異常検知方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020170409A1 true WO2020170409A1 (ja) | 2020-08-27 |
Family
ID=72144854
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2019/006703 WO2020170409A1 (ja) | 2019-02-22 | 2019-02-22 | 異常検知システム、及び異常検知方法 |
Country Status (6)
Country | Link |
---|---|
US (1) | US20220276126A1 (ja) |
EP (1) | EP3929460B1 (ja) |
JP (1) | JP7199793B2 (ja) |
KR (1) | KR102697388B1 (ja) |
CN (1) | CN113454363B (ja) |
WO (1) | WO2020170409A1 (ja) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102415347B1 (ko) * | 2021-11-29 | 2022-06-30 | (주)페스코 | 트랜스퍼케이스의 이상 진단장치 및 진단방법 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011027452A (ja) * | 2009-07-22 | 2011-02-10 | Jfe Mechanical Co Ltd | データ収集装置及び該データ収集装置を備えた設備機器の診断装置 |
JP2012008030A (ja) * | 2010-06-25 | 2012-01-12 | Toshiba Plant Systems & Services Corp | 回転機軸受診断装置 |
JP2014008677A (ja) | 2012-06-29 | 2014-01-20 | Japan Steel Works Ltd:The | 二軸スクリュ押出機 |
JP2018091638A (ja) * | 2016-11-30 | 2018-06-14 | 株式会社デンソー | 回転体の検査装置 |
JP2019027788A (ja) * | 2017-07-25 | 2019-02-21 | 日本電気株式会社 | 回転機構の異常検知感度設定装置および異常検知感度設定方法 |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS61114134A (ja) * | 1984-11-09 | 1986-05-31 | Sumitomo Metal Ind Ltd | 回転機械の診断方法 |
JPH0288938A (ja) * | 1988-09-27 | 1990-03-29 | Kobe Steel Ltd | 減速機歯車の故障診断方法 |
SE460315B (sv) * | 1988-10-13 | 1989-09-25 | Ludwik Jan Liszka | Saett att fortloepande oevervaka drifttillstaandet hos en maskin |
JP3393908B2 (ja) * | 1993-12-24 | 2003-04-07 | 株式会社東芝 | 回転機械の音響・振動診断装置及び方法 |
JP3781204B2 (ja) * | 1995-08-09 | 2006-05-31 | 株式会社フジタ | 掘進機の診断装置 |
US6392584B1 (en) * | 2000-01-04 | 2002-05-21 | Richard Eklund | System and method for detecting and warning of potential failure of rotating and vibrating machines |
US6560552B2 (en) * | 2001-03-20 | 2003-05-06 | Johnson Controls Technology Company | Dynamically configurable process for diagnosing faults in rotating machines |
JP6297822B2 (ja) * | 2013-11-19 | 2018-03-20 | ルネサスエレクトロニクス株式会社 | 検知装置、検知システム及び検知方法 |
CN105730450B (zh) * | 2016-01-29 | 2018-01-02 | 北京荣之联科技股份有限公司 | 基于车载数据的驾驶行为分析方法及评价系统 |
KR101764540B1 (ko) * | 2016-06-21 | 2017-08-02 | 두산중공업 주식회사 | 풍력발전기 진동 상태감시 및 진단 시스템 |
CN107576488A (zh) * | 2017-08-30 | 2018-01-12 | 沃德传动(天津)股份有限公司 | 一种采用振动算法对设备运行状态进行监测诊断的方法 |
CN108663988B (zh) * | 2018-05-31 | 2020-03-10 | 哈尔滨莫迪科技有限责任公司 | 基于物联网的数控机床智能监控系统 |
US20210041327A1 (en) * | 2019-08-07 | 2021-02-11 | Caterpillar Inc. | System and method for acquiring vibration-related information associated with operation of a rotary machine |
US11513031B2 (en) * | 2019-10-28 | 2022-11-29 | Aktiebolaget Skf | Conformance test apparatus, sensor system, and processes |
-
2019
- 2019-02-22 CN CN201980092690.9A patent/CN113454363B/zh active Active
- 2019-02-22 EP EP19915675.3A patent/EP3929460B1/en active Active
- 2019-02-22 KR KR1020217026750A patent/KR102697388B1/ko active IP Right Grant
- 2019-02-22 JP JP2021501243A patent/JP7199793B2/ja active Active
- 2019-02-22 WO PCT/JP2019/006703 patent/WO2020170409A1/ja unknown
- 2019-02-22 US US17/425,891 patent/US20220276126A1/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011027452A (ja) * | 2009-07-22 | 2011-02-10 | Jfe Mechanical Co Ltd | データ収集装置及び該データ収集装置を備えた設備機器の診断装置 |
JP2012008030A (ja) * | 2010-06-25 | 2012-01-12 | Toshiba Plant Systems & Services Corp | 回転機軸受診断装置 |
JP2014008677A (ja) | 2012-06-29 | 2014-01-20 | Japan Steel Works Ltd:The | 二軸スクリュ押出機 |
JP2018091638A (ja) * | 2016-11-30 | 2018-06-14 | 株式会社デンソー | 回転体の検査装置 |
JP2019027788A (ja) * | 2017-07-25 | 2019-02-21 | 日本電気株式会社 | 回転機構の異常検知感度設定装置および異常検知感度設定方法 |
Non-Patent Citations (1)
Title |
---|
See also references of EP3929460A4 |
Also Published As
Publication number | Publication date |
---|---|
JPWO2020170409A1 (ja) | 2021-12-16 |
US20220276126A1 (en) | 2022-09-01 |
EP3929460B1 (en) | 2024-05-01 |
KR20210126617A (ko) | 2021-10-20 |
EP3929460A1 (en) | 2021-12-29 |
JP7199793B2 (ja) | 2023-01-06 |
CN113454363B (zh) | 2024-07-26 |
KR102697388B1 (ko) | 2024-08-22 |
CN113454363A (zh) | 2021-09-28 |
EP3929460A4 (en) | 2022-10-26 |
EP3929460C0 (en) | 2024-05-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Fakhfakh et al. | Numerical and experimental analysis of a gear system with teeth defects | |
JP2001304954A (ja) | 故障診断方法及びその装置 | |
JP6150379B2 (ja) | 計量装置 | |
WO2019167180A1 (ja) | 異常種別判定装置及び異常種別判定方法 | |
TWI490465B (zh) | 具有振動測試功能之電子裝置及用以建立振動測試演算法之方法 | |
JP2000171291A (ja) | 故障診断方法および故障診断器 | |
WO2020170409A1 (ja) | 異常検知システム、及び異常検知方法 | |
JP5958932B2 (ja) | 動的設備の状態監視システムとその方法とそのプログラム | |
JPH07324974A (ja) | 回転機振動診断装置 | |
JP2020134479A (ja) | 異常検出方法および異常検出装置 | |
CN114117655A (zh) | 用于估计轴承的剩余使用寿命的系统、装置和方法 | |
JP2005091103A (ja) | 歯車診断方法及び歯車診断装置 | |
US7032453B2 (en) | Method and apparatus for the diagnosis of natural vibrations in a mechatronic system | |
JP2020003363A (ja) | 転がり軸受の異常診断方法及び異常診断装置、異常診断プログラム | |
WO2019220542A1 (ja) | 圧延設備の診断装置及び診断方法 | |
KR100436573B1 (ko) | 진동 및 소음품질 자동검사장치 | |
EP2130021A1 (en) | Pitch line run-out detection apparatus | |
CN118837102A (en) | Abnormality detection system and abnormality detection method | |
GB2593573A (en) | Vibro-electric condition monitoring | |
JP6812529B2 (ja) | 予知保全判定装置、予知保全判定方法及びプログラム | |
JP4303072B2 (ja) | エンジン評価装置 | |
JP7077426B2 (ja) | 診断装置及びこれを備えた設備並びに診断方法 | |
EP4012209A1 (en) | System, apparatus and method for estimating remaining useful life of at least one bearing | |
US20230288290A1 (en) | Method and System for Automatically Loading Parameters, and Client-End Server Thereof | |
JPWO2017006792A1 (ja) | 検査方法および検査装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19915675 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2021501243 Country of ref document: JP Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 20217026750 Country of ref document: KR Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2019915675 Country of ref document: EP Effective date: 20210922 |