Abnormality diagnosis device and abnormality diagnosis method

The abnormality diagnosis device and method effectively identify equipment abnormalities by analyzing sensor signals from multiple sensors, overcoming limitations of existing techniques by correlating signal deviations with specific abnormalities, ensuring accurate detection and timely maintenance.

WO2024242159A1PCT designated stage expired Publication Date: 2024-11-28JFE STEEL CORP
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
PCT/JP2024/018941
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-24
Filing Date
2024-05-23
Publication Date
2024-11-28

AI Technical Summary

Technical Problem

Existing abnormality diagnosis techniques for equipment are limited by the type and degree of abnormality, as they often rely on independent use of sensors like acoustic, vibration, and AE sensors, which may not effectively detect all types of abnormalities, such as wear and play, and can be ineffective for identifying abnormalities like cracks in bearings or minute flaws.

Method used

An abnormality diagnosis device and method that collect and analyze sensor signals from multiple types of sensors, including acoustic, vibration, and AE sensors, to identify abnormal parts by calculating signal deviations across different frequency bands and operating conditions, using a database to correlate deviation patterns with specific abnormalities.

Benefits of technology

This approach allows for accurate identification of abnormal parts in equipment by evaluating variations in multiple sensor signals, enabling timely maintenance and reducing product defects and improving yield.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2024018941_28112024_PF_FP_ABST
    Figure JP2024018941_28112024_PF_FP_ABST
Patent Text Reader

Abstract

An abnormality diagnosis device according to the present invention comprises: an operation signal collection unit that collects a plurality of sensor signals; an operation section operation signal cutout unit that cuts out a sensor signal per each among predetermined operation sections of equipment from the plurality of sensor signals collected by the operation signal collection unit; a signal level acquisition unit that acquires signal levels, per each among frequency bands that are predetermined per each operation section, of the sensor signals per each operation section cut out by the operation section operation signal cutout unit; a deviation degree calculation unit that calculates degrees of deviation from signal levels during normal operation of the same equipment, operation section, and frequency band for the signal levels per each operation section and per each frequency band acquired by the signal level acquisition unit; and an abnormal portion identification unit that identifies an abnormal portion of the equipment on the basis of the deviation degrees calculated by the deviation degree calculation unit.
Need to check novelty before this filing date? Find Prior Art

Description

Abnormality diagnosis device and abnormality diagnosis method

[0001] The present invention relates to an abnormality diagnosis device and an abnormality diagnosis method for identifying an abnormal portion of equipment using a plurality of different types of sensor signals during operation of the equipment.

[0002] Patent Document 1 describes a diagnostic device that diagnoses an object to be diagnosed by comparing an observed waveform observed from the object to be diagnosed with a reference waveform. Patent Document 2 describes a state estimation device that estimates a change in the state of equipment based on waveforms and frequency information detected by multiple sensors installed in the equipment. Patent Document 3 describes a diagnostic device that detects chattering of rolling mill rolls using the frequency of an acoustic signal detected by an acoustic sensor installed in a rolling mill.

[0003] JP 2008-164490 A International Publication No. 2019 / 017345 International Publication No. 2020 / 157818

[0004] The techniques described in Patent Documents 1 to 3 involve independently performing anomaly diagnosis using sound, anomaly detection using electrical signals, and anomaly detection using a vibration sensor. However, when detecting anomalies in equipment, the sensors that can detect anomalies may be limited depending on the type and severity of the anomaly, such as when an AE sensor is effective for detecting early-stage anomalies such as cracks or minute flaws in bearings, and when a vibration sensor is effective for detecting anomalies such as wear or rattle.

[0005] The present invention has been made to solve the above-mentioned problems, and an object of the present invention is to provide an abnormality diagnosis device and an abnormality diagnosis method that can accurately identify an abnormal portion of equipment.

[0006] The abnormality diagnosis device of the present invention is an abnormality diagnosis device that identifies abnormal parts of equipment using multiple sensor signals detected during operation of the equipment using multiple different types of sensors, and includes an operation signal collection unit that collects the multiple sensor signals, an operation interval operation signal extraction unit that extracts sensor signals for each predetermined operation interval of the equipment from the multiple sensor signals collected by the operation signal collection unit, a signal level acquisition unit that acquires signal levels for each frequency band predetermined for each operation interval for the sensor signals extracted for each operation interval by the operation interval operation signal extraction unit, a deviation calculation unit that calculates the degree of deviation from the signal level during normal operation of the same equipment, operation interval, and frequency band for the signal levels acquired by the signal level acquisition unit for each operation interval and for each frequency band, and an abnormal part identification unit that identifies abnormal parts of the equipment based on the deviation calculated by the deviation calculation unit.

[0007] The signal level acquisition unit classifies each sensor signal based on predetermined operating conditions of the equipment to acquire the signal level, and the deviation calculation unit calculates the degree of deviation from the signal level during normal operation of the same equipment, operating section, frequency band, and operating conditions, for the signal level acquired by the signal level acquisition unit for each operating section, frequency band, and operating condition.

[0008] The abnormal part identifying unit may identify an abnormal part of the equipment based on a pattern of deviation degrees that is determined for each of the operation sections and that has as elements the deviation degrees in each frequency band.

[0009] The equipment may include a database unit that stores conditions for extracting the plurality of sensor signals of the equipment and data necessary for identifying abnormal parts of the equipment, and the abnormal part identification unit may identify the abnormal part of the equipment by referring to a table that contains information that indicates the relationship between the patterns of the operation intervals and deviation degrees stored in the database unit and the abnormal parts of the equipment.

[0010] The table includes information indicating the relationship between the operating section, the deviation pattern, and the operating conditions of the equipment and the abnormal part of the equipment, and the abnormal part identification unit may refer to the table and identify the abnormal part of the equipment by taking into consideration the operating section, the deviation pattern, and the operating conditions of the equipment.

[0011] It is preferable to provide a normal state signal level acquisition unit that acquires signal levels for each frequency band predetermined for each operating section for the sensor signal for each operating section extracted by the operating section operating signal extraction unit, and a normal distribution determination and recording unit that classifies the signal levels acquired by the normal state signal level acquisition unit for each equipment, each operating section, and each frequency band, and records them as signal levels during normal operation of the equipment.

[0012] The normal distribution determination and recording unit may record, for each piece of equipment, a table containing information indicating the relationship between a pattern of deviations of signal levels from the signal level during normal operation in each frequency band determined for each operating section and abnormal parts of the equipment.

[0013] The normal distribution determination and recording unit may record a table including information indicating the operation interval, the pattern of the deviation, and the relationship between the operating conditions of the equipment and the abnormal portion of the equipment.

[0014] The operation section may be determined in association with an operation time of the facility or an operation position of a component device of the facility.

[0015] The operating section may be determined based on the specification of an assumed number of categories based on knowledge about the equipment operation for a sensor signal installed in the equipment that can identify a change point in the operation of the equipment, and the determination of the category position by extracting change points by a machine learning technique using data from the sensor signal or by extracting change points by data classification using clustering technology.

[0016] The abnormality diagnosis method according to the present invention is an abnormality diagnosis method for identifying an abnormal part of equipment using a plurality of sensor signals detected during operation of the equipment using a plurality of different types of sensors, and includes: an operation signal collection step for collecting the plurality of sensor signals; an operation interval operation signal extraction step for extracting sensor signals for each predetermined operation interval of the equipment from the plurality of sensor signals collected in the operation signal collection step; a signal level acquisition step for acquiring signal levels for each frequency band predetermined for each operation interval for the sensor signals extracted in the operation interval operation signal extraction step; a deviation calculation step for calculating a deviation from the signal level during normal operation of the same equipment, operation interval, and frequency band for the signal levels acquired in the signal level acquisition step for each operation interval and for each frequency band; and an abnormal part identification step for identifying an abnormal part of the equipment based on the deviation calculated in the deviation calculation step.

[0017] It is preferable that the method includes a normal state signal level acquisition step of acquiring a signal level for each frequency band predetermined for each operating section for the sensor signal extracted in the operating section operating signal extraction step, and a normal distribution determination and recording step of classifying the signal levels acquired in the normal state signal level acquisition step for each equipment, each operating section, and each frequency band, and recording them as signal levels during normal operation of the equipment.

[0018] The plurality of different types of sensors may include acoustic sensors, vibration sensors, and AE sensors.

[0019] The abnormality diagnosis device and acoustic diagnosis method according to the present invention evaluate the variations in signals from multiple different types of sensors and identify abnormal parts of equipment based on the abnormality levels for each operating section and each frequency band of the equipment, thereby enabling the abnormal parts of equipment to be identified with high accuracy.

[0020] FIG. 1 is a block diagram showing the configuration of an abnormality diagnosis device according to one embodiment of the present invention. FIG. 2 is a flowchart showing the flow of data recording processing according to one embodiment of the present invention. FIG. 3 is a diagram for explaining data recording processing according to one embodiment of the present invention. FIG. 4 is a diagram for explaining a method of extracting a sound pressure signal when the extraction condition for the sound pressure signal is specified using the crank angle. FIG. 5 is a diagram showing an example of change in sound pressure level of operation sound in one frequency band with respect to the crank angle. FIG. 6 is a diagram showing an example of classification of the operation sound shown in FIG. 5. FIG. 7 is a flowchart showing the flow of abnormal portion identification processing according to one embodiment of the present invention. FIG. 8 is a diagram for explaining a specific example of abnormal portion identification processing according to one embodiment of the present invention. FIG. 9 is a diagram showing frequency distributions of sound pressure levels when the operating conditions of the press equipment are limited and when they are not limited. FIG. 10 is a diagram showing the frequency distribution of AE waves. FIG. 11 is a diagram for explaining the abnormal portion identification processing of the example.

[0021] An abnormality diagnosis device and an abnormality diagnosis method according to an embodiment of the present invention will be described below with reference to the drawings.

[0022] [Configuration] Fig. 1 is a block diagram showing the configuration of an abnormality diagnosis device according to one embodiment of the present invention. As shown in Fig. 1, the abnormality diagnosis device 1 according to one embodiment of the present invention is a device that identifies an abnormal portion of one or more predetermined pieces of equipment to be diagnosed (hereinafter abbreviated as equipment) A using sensor signals during operation of the equipment A, and is configured by an information processing device such as a computer. Here, the equipment A is equipment that is composed of a plurality of parts, and examples of such equipment include steelmaking equipment such as press equipment and rolling equipment.

[0023] The abnormality diagnosis device 1 includes an operation signal collection unit 11, an operation section operation signal extraction unit 12, a normal state signal level acquisition unit 13, a normal distribution determination and recording unit 14, a signal level acquisition unit 15, a deviation degree calculation unit 16, an abnormality part identification unit 17, and a database unit 18. The operation signal collection unit 11, the operation section operation signal extraction unit 12, the normal state signal level acquisition unit 13, the normal distribution determination and recording unit 14, the signal level acquisition unit 15, the deviation degree calculation unit 16, and the abnormality part identification unit 17 are functional blocks realized by an arithmetic processing unit such as a CPU inside the information processing device executing a computer program. The functions of each unit will be described later.

[0024] The database unit 18 is configured by a storage device such as an HDD that constitutes an information processing device, and includes an extraction condition database 18a, a frequency band database 18b, a normal distribution database 18c, an operating condition database 18d, and a deviation pattern database 18e. Details of each database will be described later. The database unit 18 may be located outside the abnormality diagnosis device 1, and the abnormality diagnosis device 1 may acquire data from the database unit 18 via an electric communication line.

[0025] The fault diagnosis device 1 having such a configuration executes the data recording process and the faulty part identification process described below to identify the faulty part of the equipment A. The operation of the fault diagnosis device 1 when executing the data recording process and the faulty part identification process will be described below.

[0026] [Data Recording Process] Fig. 2 is a flowchart showing the flow of the data recording process according to one embodiment of the present invention. The flowchart shown in Fig. 2 starts when an execution command for the data recording process is input to the abnormality diagnosis device 1, and the data recording process proceeds to step S1.

[0027] In the process of step S1, the operation signal collector 11 uses a plurality of different types of sensors 20 installed near the facility A to collect a plurality of sensor signals (operation signals) of the facility A at predetermined time intervals during a predetermined period of normal operation, including k types (k≧1) of operation sections of the facility A that have been classified in advance. Examples of the plurality of different types of sensors 20 include acoustic sensors, vibration sensors, and AE (Acoustic Emission) sensors. This completes the process of step S1, and the data recording process proceeds to the process of step S2.

[0028] In the processing of step S2, the movement interval operation signal extraction unit 12 extracts sensor signals for each of k types of movement intervals from the multiple sensor signals collected in the processing of step S1. Specifically, the movement interval operation signal extraction unit 12 reads extraction conditions (extraction start time, extraction end time, etc.) for the sensor signals for each of k types of movement intervals from the extraction condition database 18a. For example, in the example shown in FIG. 3( a), the movement interval operation signal extraction unit 12 reads, as extraction conditions, information on the start and end times of movement interval 1, in which the load rises and returns to a predetermined value, and the start and end times of movement interval 2, in which the load maintains the predetermined value. Then, the movement interval operation signal extraction unit 12 extracts sensor signals that satisfy the extraction conditions from the sensor signals collected in the processing of step S1, thereby extracting sensor signals for each of k types of movement intervals. For example, in the example shown in Figure 3(b), the movement section movement signal extraction unit 12 extracts sound pressure signals that satisfy extraction conditions from the sound pressure signals collected using the acoustic sensor in the processing of step S1, thereby extracting sound pressure signals for each of k types of movement sections.

[0029] The extraction conditions for the sensor signal are not limited to the method of specifying the start and end times of the operation interval, but may also be specified based on the operating position of the target equipment. For example, in the case of press equipment that processes a workpiece by pressing a die against the workpiece using a crank mechanism, the operation interval of the press equipment can be specified by the magnitude of the crank angle at which the workpiece contacts the die. Specifically, if the crank angle when the workpiece first contacts the die is α and the crank angle when the workpiece releases from the die is β, the press operation interval can be specified by the crank angles α and β. Furthermore, if there is processing after the press operation (e.g., operation of a conveyor), the operation interval for the post-press processing can be specified by using a crank angle greater than the crank angle β. Therefore, in this case, the extraction conditions for the sensor signal can be specified using the crank angle. When the extraction conditions for the sensor signal are specified based on the operating position of the target equipment, information relating the extraction conditions to the operating position of the equipment can be recorded and stored in the extraction condition database 18a.

[0030] FIG. 4 is a diagram illustrating a method for extracting a sound pressure signal when specifying extraction conditions for the sound pressure signal of an acoustic sensor as a sensor signal using a crank angle. The crank angle α at which the workpiece first contacts the die can be derived from the geometric relationship between the workpiece and the crank mechanism. In the example shown in FIG. 4 , the press operation section in which the press load is applied to the workpiece is divided into multiple sections (subdivision sections 1 to 3), and a sound pressure signal is extracted from each subdivision section. When extracting the sound pressure signal, since the crank angle uniquely corresponds to the start time and end time of each subdivision section, it is sufficient to extract the sound pressure signal within that crank angle range.

[0031] As described above, the time and operating positions for specifying an operating section can be determined by taking into account the relationship between the manufacturing process of each product and the operation of the equipment. However, it is not easy to specify a section that can effectively extract a characteristic sound based on the time and operating positions. In such cases, operating sections can be specified using information about change points in sensor signals indicating changes in equipment operation. For example, in the case of the press equipment described above, the start timing of press operation can be detected by changes in the press load. Therefore, subdivision sections can be specified using the load cell signal that detects the press load. Specifically, in the example shown in FIG. 4 , the load signal indicates changes in the load cell signal. Subdivision sections can be specified by not only the rising and falling points of the load signal, but also the section where the load signal is maximum. In this way, the position of each operating section can be specified by correlating time and operating positions such as the crank angle with change points in sensor signals such as the load cell that indicate changes in equipment operation.

[0032] Additionally, operation sections can be specified using classification techniques based on a combination of knowledge about equipment operation and data on the location of occurrence of physical changes (e.g., operation sounds acquired by acoustic sensors) observed in sensor signals associated with the equipment operation. A single equipment operation may generate multiple operation sounds. Even in such cases, diagnostic accuracy can be improved by categorizing the occurrence patterns of operation sounds associated with the equipment operation. For example, in the case of press equipment, the operation from pressing a workpiece with a die to returning it is considered a single equipment operation. Operation sounds can be classified by subdividing the location of occurrence of operation sounds during this process, such as by crank angle. Specifically, operation sections can be specified as follows based on prior knowledge of press operation:

[0033] (1) Section where the workpiece is transported: Operating noise is generated by the transport machine. (2) Section where the workpiece and die come into contact: Operating noise is generated by friction and collision vibration when the workpiece and die come into contact. Operating noise is the sound of the workpiece and die coming into contact. (3) Section where the workpiece and die separate: Operating noise is generated by the movement and vibration of the crank mechanism when it moves. Operating noise corresponds to the vibration and friction noise when the crank mechanism and die move.

[0034] Although the frequency of the operation noise may differ between the above sections, the period during which the workpiece is pressed results in significant differences in the sound pressure level of the operation noise. Therefore, it is advisable to divide the operation sections based on the sound pressure level. Figure 5 is a diagram showing an example of the change in the sound pressure level of the operation noise in one frequency band versus the crank angle. Figure 5 shows the change in sound pressure level during three press operations. As shown in Figure 5, peaks in the sound pressure level can be observed near crank angles of 50°, 150°, and 250°. Therefore, since the peaks and valleys between the peaks represent the change points of the operation noise, in the example shown in Figure 5, the operation noise is divided into three operation noise categories. The change points of the operation noise can be determined from the data, and machine learning techniques can be used to detect the change points. Furthermore, the K-means algorithm, for example, can be used to classify the operation noise. The K-means algorithm is a technique for classifying data into multiple predetermined clusters. In the example shown in Figure 5, there are three change points in the operation noise, so Figures 6(a) to 6(c) show examples of the operation noise classified into three categories.

[0035] In this way, when classifying operation sounds, the number of divisions for the equipment operation is assumed based on prior knowledge and taking into account the equipment mechanism, and the change points of the sound pressure data are calculated based on the assumed number of divisions using machine learning techniques or clustering techniques, and the division positions are determined based on the calculated change points. Note that, when determining the division positions, data that can express operation characteristics or change point information, such as load data (the above-mentioned load cell data), other than sound pressure data, may also be used. Furthermore, in the above description, the accurate division of the operation section is determined by focusing on the sound pressure level of a specific frequency band. However, the final operation section may also be determined by selecting several candidate frequency bands of interest and performing similar processing on each of them. Furthermore, in the above example, an example was shown in which the sound pressure level signal of an acoustic sensor was used as the sensor signal, but similar processing can also be performed with signals from an AE sensor or a vibration sensor.

[0036] As described above, it is possible to accurately distinguish between operation sections with different characteristics based on sensor signals from sensors installed at or near the target equipment that can identify points of change in the equipment's operation (for press equipment, sensor signals such as press load signals and sound pressure levels of acoustic signals). The operation sections thus determined can be distinguished by time periods from the equipment start time or by the equipment's operating position (for example, the crank angle of the press equipment), and these conditions can be registered in advance in the extraction condition database 18a as extraction conditions. This completes the processing of step S2, and the data recording processing proceeds to step S3.

[0037] In the process of step S3, first, the normal-state signal level acquisition unit 13 converts the sensor signal for each operating interval extracted in the process of step S2 into a signal level relative to frequency using a Fourier transform, an octave band filter, or the like. Next, the normal-state signal level acquisition unit 13 reads information (e.g., minimum and maximum frequency values) regarding l (l≧1) frequency bands used for abnormality detection predetermined for each operating interval from the frequency band database 18b. Then, the normal-state signal level acquisition unit 13 acquires the signal level for each l frequency band (signal level of normal-state operation signal) from the converted signal level data using a band-pass filter or the like. For example, in the example shown in FIG. 3(c), the normal-state signal level acquisition unit 13 acquires the sound pressure level of the normal-state operation sound for each of predetermined frequency bands 1 to 3. This completes the process of step S3, and the data recording process proceeds to the process of step S4.

[0038] In the process of step S4, the normal distribution determination and recording unit 14 classifies the signal levels of the normal operation signals acquired in the process of step S3 by operating section and by frequency band, and records data on the signal level distribution of the normal operation signals and their feature quantities (average value, standard deviation, etc.) in the normal distribution database 18c. Furthermore, the normal distribution determination and recording unit 14 may further classify the signal levels of the normal operation signals by operating condition, taking into account multiple operating conditions (e.g., m types of operating conditions). This completes the process of step S4, and the series of data recording processes ends.

[0039] In the data recording process, in addition to recording data such as operating sounds during normal operation, a data table that organizes the relationship between deviation patterns from normal operation and abnormal parts (to be described later) is stored in advance in the deviation pattern database 18e. The deviation degree of deviation patterns and their registered contents will be defined in the "Abnormal Part Identification Process" below, and an explanation will be provided afterwards.

[0040] 7 is a flowchart showing the flow of the abnormal part identification process according to one embodiment of the present invention. The flowchart shown in FIG. 7 starts when an execution command for the abnormal part identification process is input to the abnormality diagnosis device 1, and the abnormal part identification process proceeds to step S11.

[0041] In the process of step S11, the operation signal collector 11 uses a plurality of different types of sensors 20 installed near the facility A to collect a plurality of sensor signals (operation signals) of the facility A at predetermined time intervals during a predetermined period including k types (k≧1) of operation sections of the pre-classified facility A. This completes the process of step S11, and the abnormal part identification process proceeds to the process of step S12.

[0042] In the process of step S12, the operation section operation signal extractor 12 extracts sensor signals for each of k types of operation sections from the multiple sensor signals collected in the process of step S11. The process flow of this step S12 is the same as the process flow of step S2 described above, so a detailed description thereof will be omitted. This completes the process of step S12, and the abnormal part identification process proceeds to the process of step S13.

[0043] In the processing of step S13, the signal level acquisition unit 15 acquires signal levels for each of k types of operating intervals and l types of frequency bands from the sensor signal extracted in the processing of step S12. The processing flow of this step S13 is the same as the processing flow of step S3 described above, so a detailed description thereof will be omitted. Note that the signal level acquisition unit 15 may read information on m types of operating conditions that affect the operation of the equipment A from the operating condition database 18d, and acquire signal levels for each of k types of operating intervals, l types of frequency bands, and m types of operating conditions. This completes the processing of step S13, and the abnormal part identification processing proceeds to the processing of step S14.

[0044] In the processing of step S14, the deviation calculation unit 16 reads information on the signal level distribution during normal operation and its feature quantities from the normal distribution database 18c for each of k types of operation intervals of equipment A and for each of l types of frequency bands. Next, using the read information, the deviation calculation unit 16 calculates two or more deviations of the signal levels acquired in the processing of step S13 relative to the signal levels during normal operation for each of k types of operation intervals and l types of frequency bands. Then, using the calculated deviations, the deviation calculation unit 16 determines whether equipment A is normal (0) or abnormal (1) for each deviation, and generates, as a deviation pattern, an array pattern vector of the determination results (0, 1) for each of l types of frequency bands in each operation interval.

[0045] The deviation can be calculated, for example, by the following formula (1). Furthermore, the measurement values ​​of the sensor signal level in the target operating section and target frequency band may be statistical values ​​such as the average value of the measurement values ​​within the operating section. After calculating the deviation, if the deviation exceeds a predetermined threshold, it is determined to be abnormal (1), and otherwise it is determined to be normal (0). The threshold may be set, for example, based on 3σ, which is about three times the standard deviation σ, but is not limited to this and may be adjusted and determined while observing the characteristics of the operational data.

[0046]

[0047] In the processing of step S13, when m types of operating conditions are taken into consideration, the deviation degree calculation unit 16 calculates the deviation degree by referring to a data table such as that shown in Table 1 below. The data table shown in Table 1 below shows information on the sound pressure level distribution and its feature quantities during normal operation for each of k types of operating sections, l types of frequency bands, and m types of operating conditions. The data table shown in Table 1 below corresponds to the contents of the extraction condition database 18a, frequency band database 18b, normal distribution database 18c, and operating condition database 18d. The data table shown in Table 1 is for the case where the sensor signal is a sound pressure signal collected using an acoustic sensor, and a similar data table is prepared for each type of sensor. This completes the processing of step S14, and the abnormal part identification processing proceeds to step S15.

[0048]

[0049] In the process of step S15, the abnormal part identifying unit 17 identifies an abnormal part of the equipment A based on the deviation pattern y' generated in the process of step S14. Specifically, as shown in FIGS. 8(a) and 8(b), the abnormal part identifying unit 17 identifies an abnormal part of the equipment A based on the operation section and deviation pattern y' registered in advance in the deviation pattern database 18e. k and the abnormal part of equipment A, a deviation pattern y similar to deviation pattern y' is found. k The data table shown in FIG. 8(b) records deviation patterns obtained when an abnormality occurs in the equipment and organizes them in association with the abnormal part. This data table is created in advance and stored in the deviation pattern database 18e by the normal distribution determination and recording unit 14. The data table can also be configured to identify the abnormal part based on deviation patterns that take into account m types of operating conditions in addition to classification into k types of operating sections and l types of frequency bands. Therefore, the abnormal part identification unit 17 may identify the abnormal part of equipment A by taking into account m types of operating conditions.

[0050] The abnormal part specifying unit 17 uses the Euclidean distance to determine the deviation pattern y kCalculate the similarity of the deviation pattern y′ to the deviation pattern y′, and find the similar deviation pattern y based on the calculated similarity. k The similarity shown in formula (2) is calculated by searching for the deviation pattern y′. k The more similar the deviation pattern y is to , the closer the value is to 1. k For example, in the example shown in FIGS. 8(a) and 8(b), deviation pattern y′ and deviation pattern y generated in the process of step S14 are read out. 2 Since these patterns match, the abnormal part specifying unit 17 determines that the deviation pattern y 2 The part B corresponding to the part B is identified as the abnormal part of the equipment A. This completes the process of step S15, and the series of abnormal part identification processes ends.

[0051]

[0052] As is clear from the above description, the abnormality diagnosis device 1 according to one embodiment of the present invention includes an operation signal collection unit 11 that collects a plurality of sensor signals of equipment A, an operation interval operation signal extraction unit 12 that extracts a sensor signal for each predetermined operation interval of equipment A from the plurality of sensor signals collected by the operation signal collection unit 11, a signal level acquisition unit 15 that acquires a signal level for each predetermined frequency band for each operation interval for the sensor signal extracted by the operation interval operation signal extraction unit 12, a deviation calculation unit 16 that calculates a deviation from a signal level during normal operation of the same equipment, operation interval, and frequency band for the signal level acquired by the signal level acquisition unit 15, and an abnormality part identification unit 17 that identifies an abnormal part of the equipment based on the deviation calculated by the deviation calculation unit 16. With this configuration, variations in a plurality of different types of sensor signals are evaluated and an abnormal part of equipment A is identified based on the signal level for each operation interval and each frequency band of equipment A, thereby enabling accurate identification of the abnormal part of equipment A. This also enables the malfunctioning part to be quickly adjusted, repaired or replaced, thereby preventing deterioration of the quality of manufactured products and reducing defective quality, and also contributes to improving product yield.

[0053] Moreover, the abnormality diagnosis device 1 according to one embodiment of the present invention further includes a normal-state signal level acquisition unit 13 that acquires signal levels for each predetermined frequency band for each operation interval for the sensor signal during normal operation of the equipment A extracted by the operation interval operation signal extraction unit 12, and a normal distribution determination and recording unit 14 that classifies the signal levels acquired by the normal-state signal level acquisition unit 13 for each equipment, each operation interval, and each frequency band, records them as signal levels during normal operation of the equipment A, and records a table in which deviation patterns obtained when an abnormality occurs in the equipment A for each frequency band are associated with abnormal parts for each operation interval. With this configuration, variations in multiple different types of sensor signals are evaluated, and a table in which signal levels for each equipment, each operation interval, and each frequency band for the sensor signal levels during normal operation of the equipment A are associated with deviation patterns obtained when an abnormality occurs and abnormal parts is recorded. As a result, even if there is a change in the signal level of the sensor signal during normal times, a new recording process is performed on the normal signal level, and the abnormal part of equipment A is identified based on the signal level for each operating section and each frequency band using the new normal signal level data as a reference, so that the abnormal part of equipment A can be identified with high accuracy.

[0054] Furthermore, the abnormality diagnosis device 1 according to one embodiment of the present invention identifies an abnormal portion of equipment A while taking into account the operating conditions of equipment A, thereby enabling accurate identification of the abnormal portion of equipment A. Generally, in steelmaking equipment such as press equipment and rolling equipment, even during normal operation, operating conditions such as the amount of rolling and materials change, resulting in corresponding variations in the magnitude and frequency of the sensor signal. As a result, the normal range of the magnitude and frequency of the sensor signal becomes wider, and the magnitude and frequency of the sensor signal become buried within the normal range. As a result, it may not be possible to accurately detect an abnormality in the equipment based solely on the magnitude and frequency of the sensor signal. In contrast, the abnormality diagnosis device 1 according to one embodiment of the present invention identifies an abnormal portion of equipment A while taking into account the operating conditions of equipment A, thereby enabling accurate identification of the abnormal portion of equipment A.

[0055] In this example, an abnormal portion of the press equipment was identified. By installing acoustic sensors around the press equipment, the spectrum of the impact sound can be obtained the moment a press load is applied, and the operating sound of the conveyor can be obtained while it is in operation after pressing is completed. In this example, the operating conditions of the press equipment were taken into account to narrow the range of the frequency distribution of sound pressure levels during normal operation of the press equipment, thereby identifying the abnormal portion of the press equipment. Figure 9(a) shows the frequency distribution of sound pressure levels when the operating conditions of the press equipment are limited (average value 87.6 dB, standard deviation σ 2.19), and Figure 9(b) shows the frequency distribution of sound pressure levels when the operating conditions of the press equipment are not limited (average value 85.7 dB, standard deviation σ 1.6).

[0056] Next, assuming a die abnormality, the degree of deviation of the press equipment when the sound pressure level is 91 dB was calculated. The following formula (3) was used to calculate the degree of deviation of the press equipment. As a result, when the operating conditions were not limited, the degree of deviation of the press equipment when the sound pressure level was 91 dB was calculated to be 1.5, and when the operating conditions were limited, the degree of deviation of the press equipment when the sound pressure level was 91 dB was calculated to be 3.3. Therefore, if the deviation threshold for determining that an abnormality has occurred in the press equipment is set to 3, it is possible to accurately determine an abnormality in the press equipment.

[0057]

[0058] In addition, an AE sensor was installed on the bearing of the press equipment, and the operating range was limited to measure the frequency distribution of the AE waves obtained from the bearing. The measurement results are shown in Figure 10. Assuming that there were minute defects in the bearing, AE waves capable of detecting minute defects in the bearing were monitored in a high-frequency band of 100 kHz or more. When the deviation degree when the assumed abnormality was 60 dB was calculated using the above formula (3), the deviation degree was 8, confirming the presence of minute defects in the bearing. Furthermore, as shown in Figure 11, by searching for deviation patterns similar to the deviation pattern calculated from deviation patterns registered in advance, it was possible to accurately determine that the abnormal part of the equipment was the bearing.

[0059] Although the present invention has been described above as an embodiment, the present invention is not limited to the descriptions and drawings that form part of the disclosure of the present invention. In other words, other embodiments, examples, and operational techniques that can be made by those skilled in the art based on the present invention are all included in the scope of the present invention.

[0060] According to the present invention, it is possible to provide an abnormality diagnosis device and an abnormality diagnosis method that can accurately identify an abnormal portion of equipment.

[0061] REFERENCE SIGNS LIST 1 Abnormality diagnosis device 11 Operation signal collection unit 12 Operation section operation signal extraction unit 13 Normal state signal level acquisition unit 14 Normal distribution determination and recording unit 15 Signal level acquisition unit 16 Deviation degree calculation unit 17 Abnormal part identification unit 18 Database unit 18a Extraction condition database 18b Frequency band database 18c Normal distribution database 18d Operation condition database 18e Deviation pattern database 20 Sensor A Equipment to be diagnosed

Claims

1. An abnormality diagnosis device that identifies abnormal parts of equipment using multiple sensor signals detected using multiple different types of sensors during operation of the equipment, comprising: an operation signal collection unit that collects the multiple sensor signals; an operation section operation signal extraction unit that extracts sensor signals for each predetermined operation section of the equipment from the multiple sensor signals collected by the operation signal collection unit; a signal level acquisition unit that acquires signal levels for each frequency band predetermined for each operation section for the sensor signals for each operation section extracted by the operation section operation signal extraction unit; a deviation calculation unit that calculates a deviation from the signal level during normal operation of the same equipment, operation section, and frequency band for the signal levels for each operation section and for each frequency band acquired by the signal level acquisition unit; and an abnormality part identification unit that identifies abnormal parts of the equipment based on the deviation calculated by the deviation calculation unit.

2. The abnormality diagnosis device according to claim 1, wherein the signal level acquisition unit classifies each sensor signal based on predetermined operating conditions of the equipment and acquires a signal level, and the deviation calculation unit calculates a deviation from a signal level during normal operation of the same equipment, operating section, frequency band, and operating conditions, for the signal level acquired by the signal level acquisition unit for each operating section, frequency band, and operating condition.

3. An abnormality diagnosis device as described in claim 1 or 2, wherein the abnormality part identification unit identifies an abnormal part of the equipment based on a pattern of deviation degrees that have as elements the deviation degrees in each frequency band obtained for each operating section.

4. An abnormality diagnosis device as described in claim 3, further comprising a database unit for storing conditions for extracting the multiple sensor signals of the equipment and data necessary for identifying abnormal parts of the equipment, wherein the abnormal part identification unit identifies the abnormal part of the equipment by referring to a table containing information indicating the relationship between the patterns of the operating sections and deviation degrees stored in the database unit and the abnormal parts of the equipment.

5. The abnormality diagnosis device described in claim 4, wherein the table includes information indicating the relationship between the operating section, the deviation pattern, and the operating conditions of the equipment and the abnormal part of the equipment, and the abnormal part identification unit refers to the table and identifies the abnormal part of the equipment by taking into consideration the operating section, the deviation pattern, and the operating conditions of the equipment.

6. An abnormality diagnosis device as claimed in any one of claims 1 to 5, comprising: a normal state signal level acquisition unit that acquires a signal level for each predetermined frequency band for each operating section for the sensor signal for each operating section extracted by the operating section operating signal extraction unit; and a normal distribution determination and recording unit that classifies the signal levels acquired by the normal state signal level acquisition unit for each equipment, each operating section, and each frequency band, and records them as signal levels during normal operation of the equipment.

7. The abnormality diagnosis device according to claim 6, wherein the normal distribution determination and recording unit records, for each piece of equipment, a table including information showing the relationship between a pattern of deviations, the pattern being determined by the degree of deviation of the signal level from the signal level during normal operation in each frequency band determined for each operating section, and abnormal parts of the equipment.

8. The abnormality diagnosis device according to claim 7, wherein the normal distribution determination and recording unit records a table including information indicating the operating interval, the pattern of the deviation, and the relationship between the operating conditions of the equipment and the abnormal parts of the equipment.

9. An abnormality diagnosis device according to any one of claims 1 to 8, wherein the operation section is determined in correspondence with the operation time of the equipment or the operation position of a component device of the equipment.

10. An abnormality diagnosis device as claimed in any one of claims 1 to 8, wherein the operating section is determined based on designation of an assumed number of categories based on knowledge of equipment operation for a sensor signal installed in the equipment that can identify a change point in the operation of the equipment, and determination of the category position by extracting change points using a machine learning technique using data from the sensor signal or by extracting change points by data classification using clustering technology.

11. The abnormality diagnosis device according to any one of claims 1 to 10, wherein the plurality of different types of sensors include an acoustic sensor, a vibration sensor, and an AE sensor.

12. An abnormality diagnosis method for identifying an abnormal part of equipment using a plurality of sensor signals detected using a plurality of different types of sensors during operation of the equipment, the abnormality diagnosis method comprising: an operation signal collecting step of collecting the plurality of sensor signals; an operation section operation signal extracting step of extracting a sensor signal for each predetermined operation section of the equipment from the plurality of sensor signals collected in the operation signal collecting step; a signal level acquiring step of acquiring a signal level for each frequency band predetermined for each operation section for the sensor signal for each operation section extracted in the operation section operation signal extracting step; a deviation calculation step of calculating a degree of deviation from a signal level during normal operation of the same equipment, operation section and frequency band for the signal level for each operation section and for each frequency band acquired in the signal level acquiring step; and an abnormality part identifying step of identifying an abnormal part of the equipment based on the degree of deviation calculated in the deviation calculation step.

13. The abnormality diagnosis method according to claim 12, comprising: a normal state signal level acquisition step of acquiring a signal level for each predetermined frequency band for each operating section for the sensor signal for each operating section extracted in the operating section operating signal extraction step; and a normal distribution determination and recording step of classifying the signal levels acquired in the normal state signal level acquisition step for each equipment, each operating section, and each frequency band, and recording them as signal levels during normal operation of the equipment.

14. The abnormality diagnosis method according to claim 12 or 13, wherein the plurality of different types of sensors include an acoustic sensor, a vibration sensor, and an AE sensor.

Citation Information

Patent Citations

  • Diagnostic apparatus

    JP2008164490A

  • State estimation device, method, and program

    WO2019017345A1

  • Diagnostic device, equipment comprising same, and diagnostic method

    WO2020157818A1

  • Vibration monitoring system suitable for power equipment

    CN115200699A

  • Device for diagnosing abnormal operation noise of equipment

    JP2013019741A