Acoustic diagnostic device and acoustic diagnosis method

Abstract

An acoustic diagnostic device according to the present invention is configured to: collect operation sounds of a facility and operation monitoring sensor signals for detecting operation information of the facility including operational abnormalities; extract the operation sounds and the operation monitoring sensor signals for each predetermined operation segment of the facility from the collected operation sounds and operation monitoring sensor signals; acquire, for the extracted operation sounds of each operation segment, a sound pressure level for each predetermined frequency band associated with the operation segment; calculate a degree of deviation of the acquired sound pressure level for each operation segment and each frequency band from a sound pressure level during normal operation of the same facility, operation segment, and frequency band; detect the operation information on the basis of the extracted operation monitoring sensor signals for each operation segment; and determine an abnormal part or an operational abnormality of the facility on the basis of the degree of deviation and the operation information.

Description

Acoustic diagnostic device and acoustic diagnostic method

[0001] The present invention relates to an acoustic diagnostic device and an acoustic diagnostic method.

[0002] Equipment diagnostic techniques using acoustic sensors and other sensors have been known for some time. Specifically, Patent Document 1 describes a diagnostic device that diagnoses an equipment by comparing an observed waveform observed from the equipment with a reference waveform. Patent Document 2 describes a state estimation device that estimates changes in the state of equipment based on waveform and frequency information detected by multiple sensors installed on the equipment. Patent Document 3 describes a diagnostic device that detects chattering of rolling rolls using the frequency of an acoustic signal detected by an acoustic sensor installed on a rolling mill.

[0003] Japanese Patent Publication No. 2008-164490, International Publication No. 2019 / 017345, International Publication No. 2020 / 157818

[0004] In the devices described in Patent Documents 1 to 3, particularly in equipment composed of multiple parts, there is a possibility that the abnormal part of the equipment cannot be accurately identified. In response to this, it is conceivable to use a technology that detects abnormal sounds by focusing on the operating section of the equipment and identifies the part from which the abnormal sound is originating. However, abnormal sounds include not only those caused by equipment malfunctions, but also those caused by operational abnormalities, such as those caused by improper setting of operating conditions or abnormal sounds caused by the products being manufactured, which occur even when no equipment malfunction is occurring. Misidentifying abnormal sounds caused by operational abnormalities as abnormal sounds caused by equipment malfunctions can lead to unnecessary inspections and equipment shutdowns.

[0005] However, even if abnormalities are detected based on abnormal sounds using the devices described in Patent Documents 1 to 3, it may not be possible to determine whether the abnormal sound is caused by equipment malfunction or operational malfunction. Furthermore, for equipment composed of multiple parts, it may not be possible to accurately identify the abnormal part of the equipment. Specifically, when equipment is composed of multiple parts such as bearings, reducers, cranks, molds, rolls, and blocks, the timing of the operation noise differs depending on the part. Therefore, without considering the timing and frequency of the abnormal sound, it may not be possible to determine which part is producing the abnormal sound, and thus the abnormal part of the equipment may not be able to be accurately identified.

[0006] Furthermore, an example of a manufacturing facility composed of multiple pieces of equipment is a rolling mill in the steelmaking process. For example, a hot rolling mill consists of various pieces of equipment, such as a scale removal device for sheet bars before rolling, a crop shear for cutting the crop at the leading and trailing ends of the sheet bars, a heating device for the sheet bars, multiple rolling mills, numerous steel sheet cooling devices located after the rolling mills, and a coiler for winding up the rolled material. With such a manufacturing facility composed of multiple pieces of equipment, the devices described in Patent Documents 1 to 3 may not be able to accurately identify which piece of equipment is malfunctioning.

[0007] The present invention has been made to solve the above problems, and its objective is to provide an acoustic diagnostic device and acoustic diagnostic method that can suppress the misdetection of operational abnormalities as equipment abnormalities and prevent the shutdown of operations and equipment due to unnecessary inspections.

[0008] The acoustic diagnostic device according to the present invention comprises: a sensor signal collection unit that collects operation monitoring sensor signals for detecting equipment operation information including operating sounds and operational abnormalities; an operation section sensor signal extraction unit that extracts operating sounds and operation monitoring sensor signals for predetermined operating sections of the equipment from the operating sounds and operation monitoring sensor signals collected by the sensor signal collection unit; a sound pressure level acquisition unit that acquires sound pressure levels for predetermined frequency bands for each operating section for the operating sounds extracted by the operation section sensor signal extraction unit; a deviation degree calculation unit that calculates the degree of deviation from the sound pressure level during normal operation of the same equipment, operating section, and frequency band for each operating section and each frequency band acquired by the sound pressure level acquisition unit; an operation information detection unit that detects the operational information based on the operation monitoring sensor signals for each operating section extracted by the operation section sensor signal extraction unit; and an abnormal part / operational abnormality identification unit that determines an abnormal part or operational abnormality of the equipment based on the deviation degree and the operational information.

[0009] The sound pressure level acquisition unit classifies each operating sound based on predetermined operating conditions of the equipment and acquires the sound pressure level, and the deviation calculation unit calculates the degree of deviation from the sound pressure level during normal operation of the same equipment, operating section, frequency band, and operating conditions for each operating section, frequency band, and operating condition, based on the sound pressure level acquired by the sound pressure level acquisition unit.

[0010] The operational information detection unit may obtain information from a database for each operational anomaly regarding the operational monitoring sensor signal and the method of processing the operational monitoring sensor signal, which are used to calculate an operational anomaly index for determining operational anomalies. Based on the obtained information, it may calculate an operational anomaly index for each operational index and use the calculated operational anomaly index to determine whether or not each operational anomaly exists.

[0011] The abnormal part / operational abnormality identification unit may identify the abnormal part or operational abnormality of the equipment based on the deviation degree pattern, which is composed of the deviation degree in each frequency band determined for each operating section, and the presence or absence of the operational abnormality.

[0012] The system includes a database unit that stores data necessary for collecting operating sounds of the equipment, identifying abnormal parts of the equipment, and identifying operational abnormalities. The abnormal part / operational abnormality identification unit may identify the abnormal part of the equipment or operational abnormality by referring to a table stored in the database unit that contains information showing the relationship between the patterns of the operating interval and the degree of deviation and the abnormal parts of the equipment and the types of operational abnormalities.

[0013] The table includes information showing the relationship between the operating interval, the deviation pattern, and the operating conditions of the equipment, and the abnormal parts and operational abnormalities of the equipment. The abnormal part / operational abnormality identification unit may refer to the table and identify the abnormal parts or operational abnormalities of the equipment, taking into account the operating interval, the deviation pattern, and the operating conditions of the equipment.

[0014] The system includes a result output unit that outputs information regarding the identified abnormal part of the equipment or operational abnormalities, and the result output unit may output an alert based on the information regarding the abnormal part of the equipment or operational abnormalities, or output a command to stop the equipment to the equipment's control device.

[0015] The system may include: a normal sound pressure level acquisition unit that acquires the sound pressure level for each predetermined frequency band for each operating section of the operating sound extracted by the operating section sensor signal extraction unit during normal operation of the equipment; and a normal distribution determination and recording unit that classifies the sound pressure levels acquired by the normal sound pressure level acquisition unit by equipment, by operating section, and by frequency band, and records them as the sound pressure levels during normal operation of the equipment.

[0016] The normal distribution determination and recording unit may record a table for each piece of equipment that includes information relating the abnormal operation of the equipment to information showing the relationship between the deviation pattern, which is determined by the degree of deviation of the sound pressure level from the normal operation sound pressure level in each frequency band obtained for each operating interval, and the abnormal part of the equipment.

[0017] The normal distribution determination and recording unit may record a table containing information showing the relationship between the operating interval, the pattern of the degree of deviation, and the operating conditions of the equipment, as well as the abnormal parts of the equipment and the operational abnormalities.

[0018] The acoustic diagnostic method according to the present invention includes: a sensor signal collection step of collecting operation monitoring sensor signals for detecting equipment operation information including equipment operating sounds and operational abnormalities; an operation section sensor signal extraction step of extracting operating sounds and operation monitoring sensor signals for predetermined operating sections of the equipment from the operating sounds and operation monitoring sensor signals collected in the sensor signal collection step; a sound pressure level acquisition step of acquiring sound pressure levels for predetermined frequency bands for each operating section with respect to the operating sounds for each operating section extracted in the operation section sensor signal extraction step; a deviation degree calculation step of calculating the degree of deviation from the sound pressure level during normal operation of the same equipment, operating section, and frequency band with respect to the sound pressure levels for each operating section and each frequency band acquired in the sound pressure level acquisition step; an operation information detection step of detecting the operational information based on the operation monitoring sensor signals for each operating section extracted in the operation section sensor signal extraction step; and an abnormal part / operational abnormality identification step of determining an abnormal part or operational abnormality of the equipment based on the deviation degree and the operational information.

[0019] The procedure may include a step of outputting an alert regarding the abnormal part of the equipment or the operational abnormality, or a command to stop the equipment to the equipment's control device, based on the determination of the abnormal part of the equipment or the operational abnormality.

[0020] According to the acoustic diagnostic device and acoustic diagnostic method of the present invention, it is possible to suppress the misdetection of operational abnormalities as equipment abnormalities and to suppress the occurrence of operational and equipment shutdowns due to unnecessary inspections.

[0021] Figure 1 is a block diagram showing the configuration of an acoustic diagnostic device according to one embodiment of the present invention. Figure 2 is a flowchart showing the flow of data recording processing according to one embodiment of the present invention. Figure 3 is a diagram illustrating data recording processing according to one embodiment of the present invention. Figure 4 is a flowchart showing the flow of abnormal location / operational abnormality identification processing according to one embodiment of the present invention. Figure 5 is a diagram showing an example of a data table. Figure 6 is a diagram showing an example of an operational abnormality information table. Figure 7 is a diagram showing an example of searching for equipment abnormalities and operational abnormalities using a table of deviation patterns associated with equipment abnormalities and operational abnormalities. Figure 8 is a diagram showing the frequency distribution of sound pressure levels when the operating conditions of the press equipment are not limited and when they are limited. Figure 9 is a diagram showing an example of changes in mold adjustment abnormalities before and after adjustment of mold protrusion. Figure 10 is a diagram illustrating the abnormal location / operational abnormality identification processing using deviation patterns in the embodiment. Figure 11 is a diagram illustrating the abnormal location / operational abnormality identification processing using deviation patterns in the embodiment.

[0022] The configuration and operation of an acoustic diagnostic device, which is one embodiment of the present invention, will be described below with reference to the drawings.

[0023] [Configuration] First, with reference to Figure 1, the configuration of an acoustic diagnostic device, which is one embodiment of the present invention, will be described. Figure 1 is a block diagram showing the configuration of an acoustic diagnostic device, which is one embodiment of the present invention.

[0024] As shown in Figure 1, an acoustic diagnostic device 1, which is one embodiment of the present invention, identifies abnormal parts of equipment A using acoustic signals during the operation of one or more predetermined pieces of equipment A (hereinafter abbreviated as "equipment") detected by an acoustic sensor 30a. The acoustic diagnostic device 1 also determines the operating status of equipment A using an operation monitoring sensor 30b and identifies abnormalities caused by operational abnormalities of equipment A based on the determination result. The acoustic diagnostic device 1 is composed of an information processing device such as a computer. Equipment A is equipment composed of multiple parts, and examples of such equipment include steelmaking equipment such as press equipment and rolling equipment. The operation monitoring sensor 30b is a sensor other than the acoustic sensor that detects the status of equipment A and equipment related to equipment A, and is a sensor for detecting operational information of equipment A, including operational abnormalities. Details of the operation monitoring sensor 30b will be described later.

[0025] The acoustic diagnostic device 1 comprises a sensor signal acquisition unit 11, an operating section sensor signal extraction unit 12, a normal sound pressure level acquisition unit 13, a normal distribution determination and recording unit 14, an operational abnormality information recording unit 15, a sound pressure level acquisition unit 16, a deviation degree calculation unit 17, an operational information detection unit 18, and an abnormal location / operational abnormality identification unit 19, and a result output unit 20. Each of these units is realized by a computing processing unit such as a CPU within the information processing device constituting the acoustic diagnostic device 1 executing a computer program. The functions of each of these units will be described later.

[0026] The acoustic diagnostic device 1 includes a database unit 60. The database unit 60 is composed of a storage device such as an HDD that constitutes the information processing device, and includes an extraction condition database 60a, a frequency band database 60b, a normal distribution database 60c, an operating condition database 60d, a deviation pattern database 60e, and an operating abnormality database 60f. Details of each database will be described later. The database unit 60 may be located outside the acoustic diagnostic device 1, and the acoustic diagnostic device 1 may be configured to acquire data from the database unit 60 via a telecommunications line.

[0027] The acoustic diagnostic device 1, having this configuration, identifies the abnormal part or operational abnormality of equipment A by performing the data recording process and abnormal part / operational abnormality identification process described below. The operation of the acoustic diagnostic device 1 when performing the data recording process and abnormal part / operational abnormality identification process will be explained below.

[0028] [Data Recording Process] First, the operation of the acoustic diagnostic device 1 when performing data recording processing will be explained with reference to Figures 2 and 3. Figure 2 is a flowchart showing the flow of data recording processing according to one embodiment of the present invention. Figure 3 is a diagram illustrating data recording processing according to one embodiment of the present invention. The flowchart shown in Figure 2 starts when an execution command for data recording processing is input to the acoustic diagnostic device 1, and the data recording processing proceeds to step S1.

[0029] In step S1, the sensor signal acquisition unit 11 uses an acoustic sensor 30a, such as a microphone, installed near the equipment A to collect sound pressure signals of the operating sound of equipment A at predetermined time intervals during normal operation, including the operating sections of k types (k≧1) of equipment A that have been classified in advance. The sensor signal acquisition unit 11 also uses operation monitoring sensors 30b installed on equipment A and related equipment to collect operation monitoring sensor signals at predetermined time intervals during normal operation, including the operating sections of k types (k≧1) of equipment A that have been classified in advance. Operation monitoring sensor signals are sensor signals other than acoustic sensor signals that indicate the status of equipment A and related equipment. For example, in the case of a press machine, these may be load cell signals indicating the press load. Alternatively, temperature measurements of the material being pressed may be included. In the case of conveying equipment, conveying speed signals may also be included, and in the case of a rolling mill, in addition to measured values ​​such as acceleration, the reduction position of the rolling rolls, the peripheral speed of the rolling rolls and motor torque, sensor signals indicating the equipment and operating status may be included. This completes the process in step S1, and the data recording process proceeds to the process in step S2.

[0030] In step S2, the operating section sensor signal extraction unit 12 extracts k types of sound pressure signals and operation monitoring sensor signals for each operating section from the sound pressure signals and operation monitoring sensor signals collected in step S1. Specifically, the operating section sensor signal extraction unit 12 reads the extraction conditions (extraction start time and extraction end time, etc.) for the k types of sound pressure signals and operation monitoring sensor signals for each operating section from the extraction condition database 60a. For example, in the examples shown in Figures 3(a) to (d), the operating section sensor signal extraction unit 12 reads information regarding the start and end times of operating section 1, where the load rises and returns to a predetermined value, and the start and end times of operating section 2, where the load maintains a predetermined value, as extraction conditions. The operating section sensor signal extraction unit 12 extracts k types of sound pressure signals for each operating section (see Figure 3(b)) by extracting signals that satisfy the extraction conditions from the sound pressure signals and operation monitoring sensor signals collected in step S1. Furthermore, the operation monitoring sensor signals may also include load signals (load cell signals) as shown in Figure 3(a), for example. In the case of a slab sizing press equipment, the load cell signals corresponding to the press loads on both sides under slab pressure may be extracted together as operation monitoring sensor signals. With this, the processing in step S2 is completed, and the data recording process proceeds to the processing in step S3.

[0031] In step S3, the normal sound pressure level acquisition unit 13 first converts the sound pressure signals for each operating section extracted in step S2 into sound pressure levels relative to frequency using a Fourier transform, octave band filter, etc. Next, the normal sound pressure level acquisition unit 13 reads information (minimum and maximum frequencies, etc.) for l types (l≧1) of frequency bands used for anomaly detection, predetermined for each operating section, from the frequency band database 60b. Then, the normal sound pressure level acquisition unit 13 uses a bandpass filter, etc., to acquire the sound pressure levels for each of the l types of frequency bands (sound pressure levels of normal operating sound) from the converted sound pressure level data. For example, in the example shown in Figure 3(d), the normal sound pressure level acquisition unit 13 acquires the sound pressure levels of normal operating sound for each predetermined frequency band 1 to 3. With this, the process of step S3 is completed, and the data recording process proceeds to step S4.

[0032] In the process of step S4, the normal distribution determination and recording unit 14 classifies the sound pressure levels of the normal operation sounds acquired in the process of step S3 for each operation interval and each frequency band, and records the data of the sound pressure level distribution of the normal operation sounds and its characteristic quantities (such as the average value and the standard deviation) in the normal distribution database 60c. Similarly, the normal distribution determination and recording unit 14 records the data of the characteristic quantities such as the average value and the standard deviation of each operation monitoring sensor signal during normal operation in the normal distribution database 60c. The normal distribution determination and recording unit 14 may further classify the sound pressure level and the operation monitoring sensor signal for each operation condition in consideration of a plurality of operation conditions (for example, m types of operation conditions). Thereby, the process of step S4 is completed, and the data recording process proceeds to the process of step S5.

[0033] In the process of step S5, the normal distribution determination and recording unit 14 records a deviation pattern table in which the relationship between the deviation pattern from normal described later and the abnormal part and operation abnormality of the equipment A is pre-arranged in the deviation pattern database 60e. In addition, the operation abnormality information recording unit 15 stores in advance in the operation abnormality database 60f an operation abnormality information table (see FIG. 6) that associates various operation abnormalities, operation abnormality indexes that can evaluate various operation abnormalities, operation monitoring sensor signals and calculation formulas necessary for calculating each operation abnormality index, and related equipment abnormalities. Details of the deviation pattern, the deviation pattern table, and the operation abnormality information table will be described in the following abnormal part and operation abnormality identification process. Thereby, the process of step S5 is completed, and a series of data recording processes are terminated.

[0034] 〔Abnormal part and operation abnormality identification process〕 Next, referring to FIGS. 4 to 7, the operation of the acoustic diagnosis device 1 when executing the abnormal part and operation abnormality identification process will be described. FIG. 4 is a flowchart showing the flow of the abnormal part and operation abnormality identification process according to an embodiment of the present invention. The flowchart shown in FIG. 4 starts at the timing when an execution command for the abnormal part and operation abnormality identification process is input to the acoustic diagnosis device 1, and the abnormal part and operation abnormality identification process proceeds to the process of step S11.

[0035] In step S11, the sensor signal acquisition unit 11 uses an acoustic sensor 30a, such as a microphone, installed near equipment A to collect sound pressure signals of the operating sound of equipment A at predetermined time intervals during normal operation, including the operating sections of k types (k≧1) of equipment A that have been classified in advance. The sensor signal acquisition unit 11 also uses operation monitoring sensors 30b installed on equipment A and related equipment to collect operation monitoring sensor signals of equipment A at predetermined time intervals during normal operation, including the operating sections of k types (k≧1) of equipment A that have been classified in advance. With this, the process of step S11 is completed, and the abnormal part / operational abnormality identification process proceeds to step S12.

[0036] In step S12, the operating section sensor signal extraction unit 12 extracts k types of sound pressure signals and operation monitoring sensor signals for each operating section from the sound pressure signals and operation monitoring sensor signals collected in step S11. Specifically, the operating section sensor signal extraction unit 12 reads the extraction conditions (extraction start time and extraction end time, etc.) for the sound pressure signals and operation monitoring sensor signals for each k types of operating sections from the extraction condition database 60a. Then, the operating section sensor signal extraction unit 12 extracts the k types of sound pressure signals and operation monitoring sensor signals for each operating section by extracting the sound pressure signals and operation monitoring sensor signals that satisfy the extraction conditions from the sound pressure signals and operation monitoring sensor signals collected in step S11. Regarding the extraction conditions for the k types of sound pressure signals and operation monitoring sensor signals for each operating section, a method may be used to determine the start and end positions of the operating sections based on data indicating the operating position of the equipment, in addition to the method of reading information regarding the start and end times of each operating section. This completes the process in step S12, and the abnormal part / operational abnormality identification process proceeds to the process in step S13.

[0037] In the process of step S13, the sound pressure level acquisition unit 16 acquires the sound pressure levels for each of the k types of operation intervals and each of the l types of frequency bands from the sound pressure signal of the operation sound cut out in the process of step S12. Since the flow of the process of this step S13 is the same as the flow of the process of step S3 described above, the detailed description thereof is omitted. The sound pressure level acquisition unit 16 may read out information on m types of operating conditions that affect the operation of equipment A from the operating condition database 60d, and acquire the sound pressure levels for each of the k types of operation intervals, each of the l types of frequency bands, and each of the m types of operating conditions. Thereby, the process of step S13 is completed, and the abnormal part / operation abnormality identification process proceeds to the process of step S14.

[0038] In the process of step S14, the deviation degree calculation unit 17 reads out information on the sound pressure level distribution and its characteristic quantities during normal operation from the normal distribution database 60c for each of the k types of operation intervals of equipment A and each of the l types of frequency bands. Next, the deviation degree calculation unit 17 uses the read information to calculate the deviation degree of the sound pressure level of the operation sound acquired in the process of step S13 with respect to the sound pressure level during normal operation for each of the k types of operation intervals and each of the l types of frequency bands. Then, the deviation degree calculation unit 17 determines whether equipment A is normal (0) or abnormal (1) for each deviation degree using the calculated deviation degree, and generates an array pattern vector y' of the determination results (0, 1) for each of the l types of frequency bands in each operation interval as a deviation pattern. The deviation degree can be calculated, for example, by the following formula (1).

[0039]

[0040] In step S13, if m types of operating conditions are considered, the deviation calculation unit 17 calculates the deviation by referring to a data table as shown in Figure 5. The data table shown in Figure 5 shows information on the sound pressure level distribution and its features during normal operation for each k types of operating intervals, each l type of frequency band, and each m type of operating condition. The data table shown in Figure 5 corresponds to the contents of the extraction condition database 60a, the frequency band database 60b, the normal distribution database 60c, and the operating condition database 60d. With this, the processing in step S14 is completed, and the abnormal location / operational abnormality identification process proceeds to step S15.

[0041] In step S15, the operation information detection unit 18 detects operation information of equipment A using the operation monitoring sensor signals extracted in step S12. Operation information refers to information about specific operational abnormalities, or, if no operational abnormalities are detected, information indicating that the operating state is normal. The method for detecting operation information will now be explained. Among the deviation patterns of acoustic signals associated with specific abnormal parts, some are identical to the deviation patterns of acoustic signals caused by operational abnormalities or changes in operational settings. For example, in a sizing press equipment that reduces the width of a slab in the steel manufacturing process, if the balance of press loads from both sides in the slab width direction is disrupted, the press noise from one side may become louder. In such cases, by adjusting the protrusion of the press dies on both sides (OP side and DR side) that reduce the slab width, the load balance is restored and the sound distribution returns to normal.

[0042] Therefore, abnormal noises related to such press equipment are abnormal noises caused by operational abnormalities, not by equipment malfunctions. However, when the press load increases, the sound pressure level in a specific frequency band of the press noise increases, and a specific deviation pattern is observed. In this case, the load balance index of the press from both sides of the slab (e.g., the difference or ratio of both loads) is monitored, and if this load balance index of the press falls outside a predetermined range, it is recognized as an operational abnormality. In the case of an operational abnormality, the deviation pattern of the corresponding acoustic signal is treated as an operational abnormality, not as an equipment malfunction. Furthermore, it is ideal for the slab temperature to be above the specified value and for the slab to be in a soft state. However, if the slab is not sufficiently heated and the slab temperature is low, the slab will be hard and cannot be processed, resulting in an operational abnormality and abnormally loud noise. In such cases, the slab temperature is monitored, and if it falls below the predetermined temperature, it is recognized as an operational abnormality, not as an equipment malfunction.

[0043] Therefore, in this embodiment, with respect to operational information, various operational anomalies and operational anomaly indicators that can evaluate these anomalies are defined, and an operational anomaly information table, which associates the operational monitoring sensor signals and calculation formulas necessary for calculating each operational anomaly indicator, is stored in advance in the operational anomaly database 60f. In addition, associations with related equipment anomalies are also made. For example, as shown in Figure 6, the type of operational anomaly, the operational monitoring sensor signals used for operational anomaly determination, the operational anomaly indicator calculation formula, the determination criteria, and related equipment anomalies are compiled into a table and registered in the operational anomaly database 60f as an operational anomaly information table. This process is carried out in step S5 of the data recording process as described above.

[0044] Then, in step S15, the operation information detection unit 18 first reads the operation anomaly information table from the operation anomaly database 60f and uses the operation monitoring sensor signals extracted in step S12 to calculate the operation anomaly index corresponding to each operation anomaly in the operation anomaly information table for each section of the extracted operation monitoring sensor signals. Next, based on the calculation results of the operation anomaly index, the operation information detection unit 18 determines whether the operation anomaly index is above a threshold value and outputs an anomaly, or below the threshold value and outputs a normal value. The operation information detection unit 18 then outputs and records the determination result as operation information for each section of the extracted operation monitoring sensor signals. Although it has been stated that operation information is generated and acquired within the acoustic diagnostic device 1, it is also possible to install a separate operation anomaly determination device and acquire operation information (presence or absence of various operation anomalies) from there. With this, the processing of step S15 is completed, and the abnormal location / operation anomaly identification processing proceeds to step S16.

[0045] In step S16, the abnormal location / operational abnormality identification unit 19 combines the deviation pattern obtained in step S14 with the operation information detected in step S15 to identify the operational abnormality if it is an operational abnormality, or the abnormal location if it is an equipment abnormality and not an operational abnormality. Figures 7(a) and 7(b) show examples of searching for equipment abnormalities and operational abnormalities using a table of deviation patterns associated with equipment abnormalities and operational abnormalities. The abnormal location / operational abnormality identification unit 19 searches for deviation pattern y' similar to the deviation pattern y' obtained in step S14. ｋ The deviation pattern is searched from the deviation pattern table of the deviation pattern database 60e. In the example shown in Figures 7(a) and (b), the previously registered deviation pattern y shown in Figure 7(b) is searched. ｋ The table shown is the deviation pattern table, and the pattern that matches the deviation pattern y' shown in Figure 7(a) is the deviation pattern y １ , or deviation pattern y ２becomes a candidate. If there is no exactly matching deviation pattern, the similarity of the vectors of the deviation patterns may be evaluated to select the most similar deviation pattern. The abnormal part / operation abnormality specifying unit 19 uses the Euclidean distance as shown in the following formula (2) for the deviation pattern y' with respect to the deviation pattern y ｋ to calculate the similarity, and may search for a similar deviation pattern y ｋ based on the calculated similarity. The similarity shown in formula (2) becomes a value closer to 1 as the deviation pattern y' is more similar to the deviation pattern y ｋ . Then, the abnormal part / operation abnormality specifying unit 19 reads out information on the abnormal part of the facility A corresponding to the searched deviation pattern y ｋ .

[0046]

[0047] Next, the abnormal part / operation abnormality specifying unit 19 refers to the content of the operation information obtained in the process of step S15, and determines whether the operation abnormality associated with the deviation pattern y ｋ is normal (0) or abnormal (1). The abnormal part / operation abnormality specifying unit determines whether a specific equipment abnormality or operation abnormality has occurred based on a specific combination of the deviation pattern y ｋ and the corresponding operation abnormality (0, 1), and outputs the determination result. In the examples shown in FIGS. 7(a) and 7(b), the operation information of operation abnormality A and operation abnormality B is associated with the deviation patterns y １ , y ２ . In this case, since operation abnormality A is abnormal (1) and operation abnormality B is normal (0), the deviation patterns y １ , y ２ from among the candidate deviation patterns y ２ is selected. In the selected deviation pattern y ２ , since the determination result is operation abnormality A, in this case, there is no output of the abnormal part, and operation abnormality A is output as a result. For example, if operation abnormality A is normal (0), the deviation pattern y １ is selected, so in that case, part A abnormality is specified and the result is output. Thereby, the process of step S16 is completed, and the abnormal part / operation abnormality specifying process proceeds to the process of step S17.

[0048] In step S17, the result output unit 50 outputs information regarding equipment abnormalities or operational abnormalities identified in step 16 by displaying it on a display device such as a screen. The result output unit 50 may also output an emergency stop command for equipment A to the control device of equipment A (the equipment to be diagnosed) based on the information regarding equipment abnormalities or operational abnormalities, in order to prevent serious troubles that could damage equipment A from occurring. With this, the process in step S17 is completed, and the series of abnormal part / operational abnormality identification processes are finished.

[0049] As is clear from the above description, in the acoustic diagnostic device 1, which is one embodiment of the present invention, the sensor signal acquisition unit 11 collects operation monitoring sensor signals for detecting equipment operation information including operating sounds and operational abnormalities, and the operation section sensor signal extraction unit 12 extracts the operating sounds and operation monitoring sensor signals for predetermined operating sections of the equipment from the collected operating sounds and operation monitoring sensor signals. The sound pressure level acquisition unit 16 acquires the sound pressure level for each predetermined frequency band for each operating section for the extracted operating sounds, and the deviation degree calculation unit 17 calculates the deviation degree from the sound pressure level during normal operation of the same equipment, operating section, and frequency band for the acquired sound pressure levels for each operating section and frequency band. Then, the operation information detection unit 18 detects operation information based on the operation monitoring sensor signals for each extracted operating section, and the abnormal part / operational abnormality identification unit 19 determines the abnormal part of the equipment or an operational abnormality based on the deviation degree and operation information. This helps to prevent misidentification of operational abnormalities as equipment abnormalities, thereby reducing the occurrence of unnecessary shutdowns of operations and equipment due to inspections.

[0050] [Example] In this example, the range of sound pressure level distribution during normal operation of the press equipment was narrowed by limiting the operating conditions of the press equipment, and further, by combining this with the operating information of the press equipment, equipment abnormalities and operational abnormalities of the press equipment were distinguished. Figure 8(a) shows the frequency distribution of sound pressure level when the operating conditions of the press equipment are not limited (mean value: 58.9 dB, standard deviation σ: 4.2). Figure 8(b) shows the frequency distribution of sound pressure level when the operating conditions of the press equipment are limited (mean value: 58.9 dB, standard deviation σ: 0.9). In this example, the operating conditions are classified by steel type, and the total number of steel types are classified into several groups based on similar material properties. In this example, the operating conditions were limited to one of these steel type groups.

[0051] Next, assuming a mold malfunction, the degree of deviation of the press equipment when the sound pressure level is 63 dB was calculated. Formula (1) above 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 0.2, and when the operating conditions were limited, the degree of deviation of the press equipment when the sound pressure level was 63 dB was calculated to be 5.1. From this, if the threshold for the degree of deviation that determines that a malfunction has occurred in the press equipment is set to 3, then when the operating conditions are limited, it will be determined that there is a malfunction. Next, an example of an operational malfunction due to the difference in the adjustment state of the mold protrusion of the press equipment is shown. Figure 9 shows the change in mold adjustment malfunction before and after adjusting the mold protrusion. Due to the difference in balance between the left and right sides of the mold, the value of mold adjustment malfunction becomes 1, indicating a malfunction. As shown in Figure 9, when the mold protrusion is adjusted on December 15th, the value of mold adjustment malfunction becomes 0, and the operational malfunction of mold adjustment malfunction disappears. An example of malfunction judgment including such operational malfunctions is shown below.

[0052] Figures 10(a) and 10(b) show examples of deviation patterns that are judged to be operational abnormalities. The acoustic signal portion of deviation pattern y' shown in Figure 10(a) consists of two deviation patterns y １ , y ２ It is similar to the above. However, in the deviation pattern y' shown in Figure 10(a), the value of "mold load abnormality" in the operation information is "1" and the value of "slab temperature abnormality" is "0", which is the deviation pattern y of "mold adjustment abnormality". ２This matches the value. Therefore, the obtained deviation pattern y' is determined to be a "mold adjustment abnormality," which is an operational abnormality, rather than a mold abnormality in the press equipment. A mold load abnormality is an indicator that is determined to be abnormal when the difference in load balance between the left and right sides of the mold is greater than a predetermined value. In contrast, in the examples shown in Figures 11(a) and (b), the values ​​for "mold abnormality" and "slab temperature abnormality" in the operational information of deviation pattern y' are "0". Therefore, in this example, the obtained deviation pattern y' is the deviation pattern y of "mold abnormality". １ Since this matches the findings, it is determined that the issue is a mold malfunction in the press equipment, rather than a "mold adjustment malfunction."

[0053] Although embodiments applying the invention made by the present inventors have been described above, the present invention is not limited by the descriptions and drawings that constitute part of the disclosure of the present invention in this embodiment. That is, all other embodiments, examples, and operational techniques made by those skilled in the art based on this embodiment are included in the scope of the present invention.

[0054] According to the present invention, it is possible to provide an acoustic diagnostic device and acoustic diagnostic method that can suppress the misdetection of operational abnormalities as equipment abnormalities, and prevent the occurrence of operational and equipment shutdowns due to unnecessary inspections.

[0055] 1 Acoustic diagnostic device 11 Sensor signal acquisition unit 12 Operating section sensor signal extraction unit 13 Normal sound pressure level acquisition unit 14 Normal distribution determination and recording unit 15 Operational abnormality information recording unit 16 Sound pressure level acquisition unit 17 Deviance calculation unit 18 Operational information detection unit 19 Abnormal part / operational abnormality identification unit 20 Result output unit 30a Acoustic sensor 30b Operational monitoring sensor 60 Database unit 60a Extraction condition database 60b Frequency band database 60c Normal distribution database 60d Operational condition database 60e Deviation pattern database 60f Operational abnormality database A Equipment to be diagnosed, equipment

Claims

1. An acoustic diagnostic device comprising: a sensor signal acquisition unit for collecting operation monitoring sensor signals for detecting equipment operation information, including equipment operating sounds and operational abnormalities; an operation section sensor signal extraction unit for extracting operating sounds and operation monitoring sensor signals for predetermined operating sections of the equipment from the operating sounds and operation monitoring sensor signals collected by the sensor signal acquisition unit; a sound pressure level acquisition unit for acquiring sound pressure levels for predetermined frequency bands for each operating section of the operating sounds extracted by the operation section sensor signal extraction unit; a deviation degree calculation unit for calculating the degree of deviation from the sound pressure level during normal operation of the same equipment, operating section, and frequency band for each operating section and each frequency band acquired by the sound pressure level acquisition unit; an operation information detection unit for detecting the operational information based on the operation monitoring sensor signals for each operating section extracted by the operation section sensor signal extraction unit; and an abnormal part / operational abnormality identification unit for determining an abnormal part of the equipment or an operational abnormality based on the deviation degree and the operational information.

2. The sound pressure level acquisition unit classifies each operating sound based on predetermined operating conditions of the equipment and acquires the sound pressure level; the deviation calculation unit calculates the degree of deviation from the sound pressure level during normal operation of the same equipment, operating unit, frequency band, and operating conditions for each operating section, frequency band, and operating condition acquired by the sound pressure level acquisition unit.

3. The acoustic diagnostic device according to claim 1 or 2, wherein the operational information detection unit obtains from a database information on the operational monitoring sensor signal and the method of processing the operational monitoring sensor signal for each operational abnormality, calculates an operational abnormality index for each operational indicator based on the obtained information, and determines whether or not each operational abnormality exists using the calculated operational abnormality index.

4. The acoustic diagnostic device according to any one of claims 1 to 3, wherein the abnormal part / operational abnormality identification unit identifies the abnormal part or operational abnormality of the equipment based on a pattern of deviations, which is an element of the deviation in each frequency band obtained for each operating section, and the presence or absence of the operational abnormality.

5. The acoustic diagnostic device according to any one of claims 1 to 4, comprising a database unit that stores data necessary for collecting operating sounds of the equipment, identifying abnormal parts of the equipment, and identifying operational abnormalities, wherein the abnormal part / operational abnormality identification unit identifies abnormal parts of the equipment or operational abnormalities by referring to a table stored in the database unit that includes information showing the relationship between the patterns of the operating interval and the degree of deviation and the types of abnormal parts of the equipment and operational abnormalities.

6. The acoustic diagnostic device according to claim 5, wherein the table includes information showing the relationship between the operating interval, the deviation pattern, and the operating conditions of the equipment, and the abnormal part and operational abnormality of the equipment, and the abnormal part / operational abnormality identification unit identifies the abnormal part or operational abnormality of the equipment by referring to the table and considering the operating interval, the deviation pattern, and the operating conditions of the equipment.

7. The acoustic diagnostic device according to claim 5 or 6, further comprising a result output unit that outputs information relating to an abnormal part of the identified equipment or an operational abnormality, wherein the result output unit outputs an alert based on the information relating to the abnormal part of the equipment or an operational abnormality, or outputs a command to the control device of the equipment to stop the equipment.

8. An acoustic diagnostic device according to any one of claims 1 to 7, comprising: a normal sound pressure level acquisition unit that acquires the sound pressure level for each predetermined frequency band for each operating section of the operating sound extracted by the operating section sensor signal extraction unit during normal operation of the equipment; and a normal distribution determination and recording unit that classifies the sound pressure levels acquired by the normal sound pressure level acquisition unit for each piece of equipment, each operating section, and each frequency band, and records them as the sound pressure levels during normal operation of the equipment.

9. The acoustic diagnostic device according to claim 8, wherein the normal distribution determination and recording unit records a table for each piece of equipment that includes information relating the abnormal operation of the equipment to information showing the relationship between the deviation pattern, which is an element of the degree of deviation of the sound pressure level from the normal sound pressure level in each frequency band determined for each operating interval, and the abnormal part of the equipment.

10. The acoustic diagnostic apparatus according to claim 8 or 9, wherein the normal distribution determination and recording unit records a table containing information showing the relationship between the operating interval, the pattern of the degree of deviation, and the operating conditions of the equipment, the abnormal parts of the equipment, and the operational abnormalities.

11. An acoustic diagnostic method comprising: a sensor signal acquisition step for collecting operation monitoring sensor signals for detecting equipment operation information, including equipment operating sounds and operational abnormalities; an operation section sensor signal extraction step for extracting operating sounds and operation monitoring sensor signals for predetermined operating sections of the equipment from the operating sounds and operation monitoring sensor signals collected in the sensor signal acquisition step; a sound pressure level acquisition step for acquiring sound pressure levels for predetermined frequency bands for each operating section with respect to the operating sounds for each operating section extracted in the operation section sensor signal extraction step; a deviation degree calculation step for calculating the degree of deviation from the sound pressure level during normal operation of the same equipment, operating section, and frequency band with respect to the sound pressure levels for each operating section and each frequency band acquired in the sound pressure level acquisition step; an operation information detection step for detecting the operational information based on the operation monitoring sensor signals for each operating section extracted in the operation section sensor signal extraction step; and an abnormal part / operational abnormality identification step for determining an abnormal part or operational abnormality of the equipment based on the deviation degree and the operational information.

12. The acoustic diagnostic method according to claim 11, further comprising the step of outputting an alert regarding the abnormal part or operational abnormality of the equipment, or a command to stop the equipment to the control device of the equipment, based on the determination of an abnormal part or operational abnormality of the equipment.

Images