Information processing method, and information processing device

Abstract

To provide a technology capable of easily monitoring a state of an object.SOLUTION: An information processing device 40 according to an embodiment of the present disclosure: acquires time-series measurement signals of acoustic emission of a mechanical seal 52D; calculates energy of the acoustic emission on the basis of the measurement signals; extracts time-series signals of a periodicity-removed component obtained by removing a periodicity component from time-series signals of the calculated energy or time-series signals of the periodicity component; and calculates a standard deviation σ2 of the extracted time-series signals of the periodicity-removed component or a standard deviation σ1 of the extracted time-series signals of the periodicity component.SELECTED DRAWING: Figure 8

Description

[Technical field]

[0001] The present disclosure relates to an information processing method and the like. [Background technology]

[0002] For example, a technique is known in which high-frequency vibrations of an object are measured and the state of the object is monitored based on the measurement results (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 7-11466 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in Patent Document 1, it is necessary to use the maximum value, minimum value, average value, and variance of the effective value of the high-frequency vibration per certain time period, which requires a relatively large number of parameters for determining the state of the object, and the setting of the determination criteria may become complicated.

[0005] The present disclosure aims to provide a technology that enables easy monitoring of the state of an object. [Means for solving the problem]

[0006] In a first aspect of the present disclosure, An acquisition step in which an information processing device acquires a time-series measurement signal of acoustic emission of the object; An energy calculation step in which an information processing device calculates energy of acoustic emission of the object based on the measurement signal; a first extraction step in which an information processing device extracts a time series signal of a first component or a time series signal of the second component by removing a second component having periodicity from the time series signal of the energy; A variance calculation step in which an information processing device calculates an index value related to a variance of the time series signal of the first component or the time series signal of the second component, A method for processing information is provided.

[0007] According to this aspect, the information processing device can calculate an index value related to the variability of the time series signal of the first component or the time series signal of the second component of the acoustic emission energy of the object. Therefore, for example, the information processing device can relatively easily monitor the state of the object based on the index value. Also, for example, the information processing device can set a reference value for the index value and realize easier monitoring of the state of the object based on a comparison between the index value and the reference value.

[0008] In addition, in a second aspect of the present disclosure, based on the first aspect described above, a second extraction step of extracting a time series signal of the second component from the time series signal of the energy by the information processing device; In the first extraction step, a time series signal of the first component is extracted; The variance calculation step may include calculating index values ​​relating to variances of both the time-series signal of the first component and the time-series signal of the second component.

[0009] In addition, in a third aspect of the present disclosure, based on the first aspect described above, The information processing device may include a diagnosis step of diagnosing the presence or absence of a sign of a malfunction of the object mounted on a specified device, based on a tendency of a time change in a history of the index value relating to a variance in a time series signal of the first component or a time series signal of the second component.

[0010] In addition, in a fourth aspect of the present disclosure, based on the second aspect described above, The information processing device may include a diagnosis step of diagnosing the presence or absence of a sign of a malfunction of the object mounted on a specified device based on trends of time change in both the time series signal of the first component and the history of the index value related to the variance of the time series signal of the second component.

[0011] In addition, in a fifth aspect of the present disclosure, based on the third aspect described above, In the diagnosis step, when the history of the index value relating to the variance of the time series signal of the second component transitions from an increasing trend over time to a decreasing trend over time, it may be diagnosed that there is a sign of a malfunction of the object mounted on a specified device.

[0012] In addition, in a sixth aspect of the present disclosure, based on the third aspect described above, In the diagnosis step, when the history of the index value relating to the variance of the time series signal of the first component transitions from a state in which the change over time is relatively small to a state in which the change over time is relatively large, it may be diagnosed that there is a sign of a malfunction of the object mounted on a specified device.

[0013] In addition, in a seventh aspect of the present disclosure, based on the above-mentioned fourth aspect, In the diagnosis step, when the history of the index value related to the variation in the time-series signal of the second component transitions from an increasing trend over time to a decreasing trend over time, and thereafter the history of the index value related to the variation in the time-series signal of the first component transitions from a state in which the change over time is relatively small to a state in which the increase over time is relatively large, it may be diagnosed that there is a sign of a malfunction of the object mounted on a specified device.

[0014] In addition, in an eighth aspect of the present disclosure, based on the first aspect described above, A setting step of setting a reference value for determining whether or not there is a symptom of a failure of the object mounted on a predetermined device by an information processing device, In the acquisition step, a plurality of measurement signals of acoustic emissions of the object mounted on the predetermined device are acquired, the plurality of measurement signals including both the measurement signal in a state before the occurrence of a failure of the object and the measurement signal in a state after the occurrence of a failure of the object; In the energy calculation step, the energy corresponding to each of the plurality of measurement signals acquired in the acquisition step is calculated; In the first extraction step, the first component is extracted from the time series signal of the energy corresponding to each of the plurality of measurement signals; The variability calculation step calculates the index value related to the variability of a time series signal of the first component corresponding to each of the plurality of measurement signals; In the setting step, a first reference value may be set for the index values ​​relating to the variability in the time series signal of the first component corresponding to each of the multiple measurement signals, based on a distribution of the index values ​​relating to the variability in the time series signal of the first component corresponding to the measurement signals in a situation before a failure of the object occurs and a distribution of the index values ​​relating to the variability in the time series signal of the first component corresponding to the measurement signals in a situation after a failure of the object occurs.

[0015] In addition, in a ninth aspect of the present disclosure, based on the second aspect described above, A setting step of setting a reference value for determining whether or not there is a symptom of a failure of the object mounted on a predetermined device by an information processing device, In the acquisition step, a plurality of measurement signals of acoustic emissions of the object mounted on the predetermined device are acquired, the plurality of measurement signals including both the measurement signal in a state before the occurrence of a failure of the object and the measurement signal in a state after the occurrence of a failure of the object; In the energy calculation step, the energy corresponding to each of the plurality of measurement signals acquired in the acquisition step is calculated; In the first extraction step, the first component is extracted from the time series signal of the energy corresponding to each of the plurality of measurement signals; In the second extraction step, a time series signal of the second component is extracted by removing the first component from the time series signal of the energy corresponding to each of the plurality of measurement signals; In the variability calculation step, the index value related to the variability of a time-series signal of the first component corresponding to each of the plurality of measurement signals is calculated, and the index value related to the variability of the second component corresponding to each of the plurality of measurement signals is calculated, In the setting step, a first reference value for the index value related to the variability in the time series signal of the first component and a second reference value for the index value related to the variability in the time series signal of the second component may be set based on a distribution of combinations of index values ​​related to the variability in the time series signal of the first component and the second component corresponding to the measurement signals in a situation before a failure of the object occurs and a distribution of the index values ​​related to the variability in the time series signal of the first component and the second component corresponding to the measurement signals in a situation after a failure of the object, among combinations of the index values ​​of the time series signals of both the first component and the second component corresponding to each of the multiple measurement signals.

[0016] In addition, in a tenth aspect of the present disclosure, based on the above-mentioned eighth aspect, The plurality of measurement signals are a collection of measurement signals obtained at different timings for the same predetermined device, In the setting step, the first reference value may be set based on the index value of the signal of the first component corresponding to the measurement signal at a timing that is a predetermined time before the timing of the measurement signal that was first recorded after a failure of the object occurred.

[0017] In addition, in the above-mentioned eleventh aspect, based on the above-mentioned ninth aspect, The plurality of measurement signals are a collection of measurement signals obtained at different timings for the same predetermined device, In the setting step, the first reference value may be set based on the index value related to the variability of the signal of the first component corresponding to the measurement signal at a timing a predetermined time before the timing of the measurement signal first recorded after a failure of the object occurs, and the second reference value may be set based on the index value related to the variability of the signal of the second component corresponding to the measurement signal first recorded after a failure of the object occurs.

[0018] In addition, in a twelfth aspect of the present disclosure, on the premise of any one of the eighth to eleventh aspects described above, In the setting step, a reference value for determining whether or not the object has a sign of failure may be set for each group related to a plurality of the predetermined devices that are divided according to a use condition of the object.

[0019] In addition, in a thirteenth aspect of the present disclosure, on the premise of any one of the third to twelfth aspects described above, the predetermined device is a polymerization reaction tank, The object may be a mechanical seal for sealing a shaft.

[0020] In addition, in a fourteenth aspect of the present disclosure, based on the thirteenth aspect described above, The acquiring step may include acquiring the measurement signal recorded at a timing before a process reaction in the polymerization reaction tank.

[0021] In a fifteenth aspect of the present disclosure, obtaining a time series measurement signal of the acoustic emission of the object; Calculating the energy of the acoustic emission based on the measurement signal; extracting a time series signal of a first component obtained by removing a second component having periodicity from the time series signal of the energy, or a time series signal of the second component; calculating an index value related to variability in the time series signal of the first component or the time series signal of the second component; An information processing device is provided. Effect of the Invention

[0022] According to the above disclosure, it is possible to easily monitor the state of an object. [Brief description of the drawings]

[0023] [Figure 1] FIG. 1 illustrates an example of a diagnostic criteria setting system. [Diagram 2] FIG. 2 illustrates an example of a hardware configuration of an information processing device. [Diagram 3] FIG. 11 is a diagram illustrating an example of a processing flow for setting diagnostic criteria by an information processing device. [Figure 4] FIG. 13 is a diagram illustrating an example of a method for setting diagnostic criteria. [Diagram 5] FIG. 1 illustrates an example of a monitoring system. [Figure 6] FIG. 13 is a diagram showing an example of a processing flow for monitoring the presence or absence of a sign of leakage in a mechanical seal by an information processing device. [Figure 7] FIG. 13 is a diagram showing a specific example of the time change in the history of the standard deviation of time series data of the periodic component and the periodicity removal component of the acoustic emission energy of a mechanical seal. [Figure 8] 11A to 11C are diagrams illustrating a second example of a method for monitoring the presence or absence of a sign of leakage in a mechanical seal. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0024] Hereinafter, an embodiment will be described with reference to the drawings.

[0025] [Overview of the diagnostic criteria setting system] An overview of a diagnostic criteria setting system 1 according to this embodiment will be described with reference to FIG.

[0026] FIG. 1 is a diagram showing an example of a diagnostic criteria setting system 1. As shown in FIG.

[0027] As shown in FIG. 1, the diagnostic standard setting system 1 includes an acoustic emission (AE) sensor 10, an amplifier circuit 20, a band pass filter (BPF) 30, and an information processing device 40.

[0028] The diagnostic criteria setting system 1 sets diagnostic criteria for a predetermined index value for diagnosing the state of a mechanical seal for sealing the shaft of a polymerization reactor. Specifically, the diagnostic criteria setting system 1 sets diagnostic criteria for an index value related to the variation in time-series data of the energy of a measurement signal (hereinafter, "AE signal") of acoustic emission (AE) of the mechanical seal.

[0029] The AE sensor 10 measures the acoustic emission of the mechanical seal 52D for sealing the shaft of the polymerization reaction vessel 50, and outputs a signal (AE signal) representing the measurement result.

[0030] The polymerization reactor 50 is an experimental machine having the same specifications as a polymerization reactor (for example, a polymerization reactor 150 described later) to be diagnosed for the state of the mechanical seal. The polymerization reactor 50 includes a tank body 51 and an agitator 52.

[0031] The tank body 51 is a container that contains monomers to be polymerized, a solvent, etc. The tank body 51 has a through hole 51A at its upper portion that passes through between the inside and the outside.

[0032] Agitator 52 agitates the contents contained in tank body 51. Agitator 52 includes rotor blades 52A, a motor 52B, a rotor shaft 52C, and a mechanical seal 52D.

[0033] Rotating blade 52A is provided inside tank body 51 and rotates about rotating shaft 52C to agitate the contents of tank body 51.

[0034] The motor 52B is provided above and outside the tank body 51, and drives the rotor 52A to rotate through a rotor shaft 52C.

[0035] The rotating shaft 52C is provided so as to extend in the vertical direction, and mechanically connects between the motor 52B outside the tank body 51 and the rotor 52A inside the tank body 51. The rotating shaft 52C is provided so as to pass through the through hole 51A of the tank body 51 at its middle portion.

[0036] Mechanical seal 52D prevents leakage of the contents from inside tank body 51 to the outside through through hole 51A. Mechanical seal 52D includes a fixed ring 52D1 and a rotating ring 52D2.

[0037] The fixed ring 52D1 has a circular ring shape surrounding the outer edge of the through hole 51A in a top view, and is fixed to the outer surface of the tank body 51.

[0038] The rotating ring 52D2 is provided on the rotating shaft 52C and rotates together with the rotating shaft 52C. The rotating ring 52D2 has a disk shape concentric with the rotating shaft 52C and is disposed so as to be in contact with the upper surface of the fixed ring 52D1. As a result, in response to the rotation of the rotating shaft 52C, the rotating ring 52D2 slides with its lower surface in contact with the upper surface of the fixed ring 52D1, thereby preventing leakage of the contents through the through hole 51A.

[0039] The AE sensor 10 may be provided at any position as long as it can acquire an AE signal from the mechanical seal 52D. For example, the AE sensor 10 is provided near the fixed ring 52D1 on the outer surface of the tank body 51. The output of the AE sensor 10 is input to the amplifier circuit 20.

[0040] The amplifier circuit 20 amplifies and outputs the AE signal output from the AE sensor 10. The output signal of the amplifier circuit 20 is input to the BPF 30.

[0041] The BPF 30 passes and outputs only components of a predetermined frequency band out of the amplified AE signal input from the amplifier circuit 20. This allows the BPF 30 to output an AE signal of the predetermined frequency band. The predetermined frequency band is a frequency band in which the state of the mechanical seal 52D may occur as a characteristic in the AE of the mechanical seal 52D. The predetermined frequency band is, for example, 30 kHz to 200 kHz. The output signal of the BPF 30 is input to the information processing device 40.

[0042] The information processing device 40 calculates an index value related to the variation of the time series signal of the AE energy based on the AE signal for a predetermined period input from the BPF 30, and sets a diagnostic criterion for the index value based on the history data of the calculated index value. Specifically, the information processing device 40 periodically calculates and accumulates the index value based on the AE signal for a predetermined period during the continuous operation of the agitator 52 of the polymerization reaction tank 50, at least until leakage of the contents occurs at the mechanical seal 52D. At this time, the agitator 52 may be operated at a high load so that the load on the mechanical seal 52D is higher than that in the normal operation. This can shorten the period until leakage occurs at the mechanical seal 52D. Then, the information processing device 40 sets a diagnostic criterion for the index value based on the history data of the index value until the mechanical seal 52D breaks down and leakage of the contents occurs.

[0043] The AE signal used for setting the diagnostic criteria is preferably, for example, an AE signal recorded at a timing before the process reaction in the polymerization reaction tank 50. This is because there is a possibility that disturbances caused by the process reaction may be superimposed on the AE signal during the process reaction in the polymerization reaction tank 50.

[0044] The information processing device 40 is, for example, a server device having a relatively high processing capacity. For example, the server device is an on-premise server or a cloud server installed in a facility separate from the facility in which the polymerization reaction tank 50 is installed. The server device may also be an edge server installed in the facility in which the polymerization reaction tank 50 is installed.

[0045] Furthermore, the information processing device 40 may be a terminal device with a lower processing power than the server device, so long as it has the ability to execute necessary processing. For example, the terminal device may be a stationary terminal device such as a desktop PC (Personal Computer), or a portable terminal device (mobile terminal) such as a tablet terminal or a laptop PC.

[0046] [Hardware configuration of information processing device] Next, the hardware configuration of the information processing device 40 will be described with reference to FIG.

[0047] FIG. 2 is a diagram illustrating an example of a hardware configuration of the information processing device 40. As shown in FIG.

[0048] The functions of the information processing device 40 are realized by any hardware or any combination of hardware and software. For example, as shown in Fig. 3, the information processing device 40 includes an external interface 41, an auxiliary storage device 42, a memory device 43, a CPU 44, a high-speed calculation device 45, a communication interface 46, an input device 47, and an output device 48. The external interface 41, the auxiliary storage device 42, the memory device 43, the CPU 44, the high-speed calculation device 45, the communication interface 46, the input device 47, and the output device 48 are connected by a bus BS.

[0049] The external interface 41 functions as an interface for reading data from the recording medium 41A and writing data to the recording medium 41A. The recording medium 41A includes, for example, a versatile recording medium such as a flexible disk, a CD (Compact Disc), a DVD (Digital Versatile Disc), a BD (Blu-ray (registered trademark) Disc), an SD memory card, and a USB memory. This allows the information processing device 40 to read various data used in processing through the recording medium 41A, store the data in the auxiliary storage device 42, and install programs that realize various functions.

[0050] The auxiliary storage device 42 stores various installed programs, as well as files and data necessary for various processes. The auxiliary storage device 42 includes, for example, a hard disk drive (HDD), a solid state disk (SSD), an EEPROM, a flash memory, and the like.

[0051] When an instruction to start a program is received, the memory device 43 reads and stores the program from the auxiliary storage device 42. The memory device 43 includes, for example, a dynamic random access memory (DRAM) or a static random access memory (SRAM).

[0052] The CPU 44 executes various programs loaded from the auxiliary storage device 42 to the memory device 43, and realizes various functions related to the information processing device 40 in accordance with the programs.

[0053] The high-speed calculation device 45 works in conjunction with the CPU 44 and performs calculation processing at a higher speed than the CPU 44. The high-speed calculation device 45 includes, for example, a graphics processing unit (GPU), an application specific integrated circuit (ASIC), or a field-programmable gate array (FPGA).

[0054] Depending on the speed of arithmetic processing required for the information processing device 40, the high-speed arithmetic device 45 may be omitted.

[0055] The communication interface 46 is used as an interface for communicatively connecting to an external device. This allows the information processing device 40 to take in the output of the BPF 30 through the communication interface 46. In addition, the information processing device 40 can obtain, for example, various data and programs used in processing from an external device through the communication interface 46. The communication interface 46 may have multiple types of communication interfaces depending on the communication method between the connected device and the like.

[0056] The input device 47 accepts various inputs from the user of the information processing device 40 .

[0057] The input device 47 includes, for example, an input device (hereinafter, referred to as an "operation input device") that accepts mechanical operation input from a user of the information processing device 40. The operation input device includes, for example, a button, a toggle, a lever, a keyboard, a mouse, a touch panel, a touch pad, and the like.

[0058] The input device 47 may also include a voice input device capable of receiving voice input from the user of the information processing device 40. The voice input device includes, for example, a microphone capable of collecting the voice of the user of the information processing device 40.

[0059] The input device 47 may include a gesture input device capable of receiving a gesture input from a user of the information processing device 40. The gesture input device includes, for example, a camera capable of capturing an image of a gesture made by the user.

[0060] The input device 47 may also include a biometric input device capable of receiving biometric input from a user of the information processing device 40. The biometric input device includes, for example, a camera capable of acquiring image data including information related to a fingerprint or iris of the user.

[0061] The output device 48 outputs information to a user of the information processing device 40 .

[0062] The output device 48 is, for example, a lighting device or a display device that visually outputs information. The lighting device is, for example, an indicator lamp, etc. The display device is, for example, a liquid crystal display, an organic EL (Electroluminescence) display, etc.

[0063] The output device 48 may be a sound output device that outputs auditory information, such as a buzzer, an alarm, or a speaker.

[0064] [How diagnostic criteria are set] Next, a method for setting the diagnostic criteria will be described with reference to FIG. 3 and FIG.

[0065] Fig. 3 is a diagram showing a processing flow related to setting of diagnostic criteria by the information processing device 40. Specifically, Fig. 3 includes Fig. 3A showing a pre-processing for setting the diagnostic criteria, and Fig. 3B showing a main processing for setting the diagnostic criteria.

[0066] <Pre-processing> The pre-processing is performed periodically (e.g., every few hours) after the agitator 52 of the polymerization reaction tank 50 starts operating, for example. The pre-processing may be performed automatically at a predetermined timing, or may be performed manually in response to a request from a user via the input device 47. The pre-processing may also be performed before the process reaction in the polymerization reaction tank 50. This makes it possible to prevent a situation in which a disturbance caused by the process reaction in the polymerization reaction tank 50 is superimposed on the AE signal, and as a result, it is possible to improve the accuracy of the diagnostic criteria set in the main processing described below.

[0067] As shown in FIG. 3A, in step S102 (signal acquisition process), the information processing device 40 acquires time-series data of the AE signal for the latest predetermined period, which is taken in from the BPF 30, from a reception buffer or the like.

[0068] When step S102 is completed, the information processing device 40 proceeds to step S104.

[0069] In step S104 (energy calculation process), the information processing device 40 calculates the AE energy in a predetermined period based on the time series data of the AE signal, and outputs the time series data of the AE energy in the predetermined period. The AE energy corresponds to the area of ​​the time waveform of the AE signal, and the information processing device 40 can calculate the AE energy by time integration of the AE signal between the target time and the adjacent time.

[0070] When step S104 is completed, the information processing device 40 proceeds to steps S106 and S108.

[0071] In step S106 (periodic component extraction process), the information processing device 40 extracts a component having periodicity (periodic component) from the time series data of the AE energy. For example, the information processing device 40 extracts the time series data of the periodic component of the AE energy by calculating a moving average of a certain period immediately prior to each time for the time series data of the AE energy. The information processing device 40 may also extract the time series data of the periodic component of the AE energy by using frequency analysis or low-pass filter processing.

[0072] In step S108 (periodicity-removed component extraction process), the information processing device 40 extracts a component (periodicity-removed component) from which the periodic component has been removed, from the time series data of the AE energy. For example, the information processing device 40 extracts the time series data of the AE energy component from which the periodicity has been removed by calculating the difference between the target time and the time immediately preceding the target time for the time series data of the AE energy and converting the time series data into a difference series. The information processing device 40 may also extract the time series data of the AE energy component from which the periodicity has been removed by calculating the difference between the time series data of the AE energy and the time series data of the periodic component extracted in step S106.

[0073] When steps S106 and S108 are completed, the information processing device 40 proceeds to step S110.

[0074] In step S110 (standard deviation calculation process), the information processing device 40 calculates a standard deviation σ1 as an index value related to the variability of the time series data of the periodic component of the AE energy extracted in step S106. Similarly, in step S110, the information processing device 40 calculates a standard deviation σ2 as an index value related to the variability of the time series data of the periodicity removed component of the AE energy extracted in step S108.

[0075] When step S110 is completed, the information processing device 40 proceeds to step S112.

[0076] The processes in steps S106 and S108 may be performed in series.

[0077] In step S112 (recording process), the standard deviations σ1 and σ2 calculated in step S110 are recorded as record data in the auxiliary storage device 42 together with information indicating the time and information indicating the presence or absence of leakage in the mechanical seal 52D. The presence or absence of leakage in the mechanical seal 52D is input by the user through the input device 47, for example. The presence or absence of leakage in the mechanical seal 52D may also be automatically determined by applying a known image processing technique, a trained model, or the like to an image captured by a camera that captures the mechanical seal 52D. This allows the information processing device 40 to hold a record data group corresponding to the history data of the standard deviations σ1 and σ2 in the auxiliary storage device 42 through pre-processing that is periodically performed.

[0078] When the process of step S112 is completed, the information processing device 40 ends the pre-processing.

[0079] <Main processing> The main process is executed after leakage of the contents occurs at the mechanical seal 52D. The main process may be executed in response to a request from a user via the input device 47, or, in a case where the presence or absence of leakage at the mechanical seal 52D is automatically determined, may be executed automatically in response to the determination that there is leakage.

[0080] As shown in FIG. 3B, in step S114 (history data acquisition process), the information processing device 40 acquires the above-mentioned history data (record data group) from the auxiliary storage device .

[0081] When the process of step S114 is completed, the information processing device 40 proceeds to step S116.

[0082] In step S116 (diagnostic criterion setting process), the information processing device 40 sets diagnostic criteria for the standard deviations σ1 and σ2 based on the history data of the standard deviations σ1 and σ2. Specifically, the information processing device 40 sets diagnostic criteria for the standard deviations σ1 and σ2 based on the distribution of the combination of the standard deviations σ1 and σ2 corresponding to the situation before the occurrence of leakage in the mechanical seal 52D and the distribution of the combination of the standard deviations σ1 and σ2 corresponding to the situation after the occurrence of leakage in the mechanical seal 52D. The set diagnostic criteria are registered in the auxiliary storage device 42.

[0083] When the process of step S116 is completed, the information processing device 40 ends the main process.

[0084] <Specific example of diagnostic criteria setting process> Fig. 4 is a diagram for explaining an example of a method for setting diagnostic criteria. Specifically, Fig. 4 shows a graph in which the vertical axis represents the standard deviation σ1 of the periodic component of the AE energy, and the horizontal axis represents the standard deviation σ2 of the non-periodic component of the AE energy, and the history data P1 to P16 of the standard deviations σ1 and σ2 are plotted.

[0085] In addition, the smaller the number in the code of the historical data P1 to P16, the older the historical data, and the larger the number, the newer the historical data. For example, the historical data P1 represents the oldest historical data, and the historical data P16 represents the newest historical data. In addition, the historical data P1 to P15 correspond to the situation before leakage occurred in the mechanical seal 52D, and the historical data P16 corresponds to the situation after leakage occurred in the mechanical seal 52D.

[0086] 4, in the historical data P1 to P7, the standard deviation σ1 of the periodic component of the AE energy increases relatively greatly over time. On the other hand, in the historical data P1 to P7, the standard deviation σ2 of the non-periodic component of the AE energy changes relatively little over time. This suggests that overall wear of the sliding surfaces of the stationary ring 52D1 and the rotating ring 52D2 of the mechanical seal 52D is progressing on the time axis corresponding to the historical data P1 to P7.

[0087] Thereafter, in the historical data P8 to P16, the standard deviation σ1 of the periodic component of the AE energy converges to a certain level within a relatively narrow range. Meanwhile, in the historical data P8 to P16, the standard deviation σ2 of the periodic component removed from the AE energy is relatively larger than in the historical data P1 to P7. This suggests that, on the time axis corresponding to the historical data P8 to P16, while the overall wear of the sliding surface converges, sudden scratches and the like occur, ultimately resulting in leakage from the mechanical seal 52D.

[0088] In this way, in the mechanical seal 52D, the standard deviation σ1 of the periodic component of the AE energy increases first, and after converging to a certain level, the standard deviation σ2 of the periodicity-removed component of the AE energy becomes relatively high, and finally leakage occurs. Therefore, the information processing device 40 can set a diagnostic reference value σ2_th for indicating that the standard deviation σ2 of the periodicity-removed component of the AE energy is at a relatively high level. Therefore, the diagnosing entity (for example, the information processing device 140 described later) can diagnose that there is a sign of leakage in the mechanical seal when the standard deviation σ2 of the periodicity-removed component of the AE energy of the target mechanical seal is relatively large with respect to the diagnostic reference value σ2_th. The standard deviation σ2 being relatively large with respect to the diagnostic reference value σ2_th may be the standard deviation σ2 being equal to or larger than the diagnostic reference value σ2_th, or may be the standard deviation σ2 being larger than the diagnostic reference value σ2_th.

[0089] For example, as shown in FIG. 4, the information processing device 40 sets the diagnostic reference value σ2_th between the upper limit of the standard deviation σ2 of the history data P1 to P7 and the lower limit of the standard deviation σ2 of the history data P8 to P16. Specifically, the information processing device 40 may set the diagnostic reference value σ2_th corresponding to a value obtained by subtracting a small margin from the lower limit value of the standard deviation σ2 of the history data P8 to P16 (the standard deviation σ2 of the history data P9). Also, the information processing device 40 may set the diagnostic reference value σ2_th based on the value of the standard deviation σ2 of the history data P8 to P15 corresponding to a timing that goes back a predetermined time from the timing of the first history data P16 after the occurrence of leakage in the mechanical seal 52D. Specifically, the information processing device 40 may set the diagnostic reference value σ2_th corresponding to a value obtained by subtracting a small margin from the standard deviation σ2 of the history data P8 to P15 at a timing that goes back a predetermined time from the timing of the history data P16.

[0090] The information processing device 40 may also set a diagnostic reference value σ1_th that indicates that the standard deviation σ1 of the periodic component of the AE energy is at a certain level corresponding to the above-mentioned converged state. This allows the diagnostic subject to diagnose that there is a sign of leakage in the mechanical seal when the standard deviation σ2 of the target mechanical seal is relatively large compared to the diagnostic reference value σ2_th and the standard deviation σ1 is relatively large compared to the diagnostic reference value σ1_th. Therefore, it is possible to exclude cases where the standard deviation σ2 becomes relatively large compared to the diagnostic reference value σ2_th while the standard deviation σ1 is relatively small due to the influence of disturbances, etc. Therefore, the diagnostic subject can more appropriately diagnose the presence or absence of a sign of leakage in the target mechanical seal.

[0091] For example, the information processing device 40 sets the diagnostic reference value σ1_th based on the lower limit value of the standard deviation σ1 of the history data P8 to P16 (the standard deviation σ1 of the history data P13). Specifically, the information processing device 40 may set the diagnostic reference value σ1_th equivalent to a value obtained by subtracting a small margin from the lower limit value of the standard deviation σ1 of the history data P8 to P16. Also, as shown in FIG. 4, the information processing device 40 may set the diagnostic reference value σ1_th based on the value of the standard deviation σ1 of the first history data P16 after the occurrence of leakage in the mechanical seal 52D, among the history data P8 to P16. Specifically, the information processing device 40 may set the diagnostic reference value σ1_th equivalent to a value obtained by subtracting a predetermined margin from the value of the standard deviation σ1 of the history data P16.

[0092] In this manner, the information processing device 40 can set the diagnostic reference value σ1_th and the diagnostic reference value σ2_th for the standard deviation σ1 of the periodic component of the time-series data of the AE energy and the standard deviation σ2 of the removed periodicity component, respectively.

[0093] [Surveillance system overview] Next, an overview of the monitoring system 100 will be described with reference to FIG.

[0094] FIG. 5 is a diagram illustrating an example of a monitoring system 100. As shown in FIG.

[0095] As shown in FIG. 5, the monitoring system 100 includes an acoustic emission (AE) sensor 110, an amplifier circuit 120, a band pass filter (BPF) 130, and an information processing device 140.

[0096] The monitoring system 100 monitors the state of a shaft-sealing mechanical seal 152D mounted in a monitored polymerization reaction tank 150. Specifically, the monitoring system 100 monitors the state of the mechanical seal 152D by diagnosing the presence or absence of signs of leakage from the mechanical seal 152D.

[0097] The polymerization reaction tank 150 is a polymerization reaction tank having the same specifications as the above-mentioned polymerization reaction tank 50. Like the above-mentioned polymerization reaction tank 50, the polymerization reaction tank 150 includes a tank body 151 and an agitator 152.

[0098] The tank body 151 has the same function and structure as the above-mentioned tank body 51, and a through hole 151A is provided in the upper part of the tank body 151, penetrating between the inside and the outside.

[0099] The agitator 152 has the same function and structure as the above-described agitator 52, and includes a rotor 152A, a motor 152B, a rotor shaft 152C, and a mechanical seal 152D.

[0100] The mechanical seal 152D, like the mechanical seal 52D described above, includes a stationary ring 152D1 and a rotating ring 152D2.

[0101] The functions and structures of the rotor 152A, motor 152B, rotor shaft 152C, and mechanical seal 152D are similar to those of the rotor 52A, motor 52B, rotor shaft 52C, and mechanical seal 52D described above, and therefore detailed description thereof will be omitted.

[0102] The AE sensor 110 measures the AE of a shaft-sealing mechanical seal 152D mounted in the polymerization reaction vessel 150 to be monitored, and outputs a signal (AE signal) indicative of the measurement result.

[0103] The amplifier circuit 120 has the same function as the above-mentioned amplifier circuit 20, and amplifies and outputs the AE signal output from the AE sensor 110. The output signal of the amplifier circuit 120 is input to the BPF .

[0104] The BPF 130 has the same function as the BPF 30 described above, and passes and outputs only components of a predetermined frequency band from the amplified AE signal input from the amplifier circuit 120. This allows the BPF 30 to output an AE signal of the predetermined frequency band. The predetermined frequency band is a frequency band in which the state of the mechanical seal 152D may occur as a characteristic in the AE. The predetermined frequency band is, for example, 30 kHz to 200 kHz, as in the case of the BPF 30 described above. The output signal of the BPF 130 is input to the information processing device 140.

[0105] The information processing device 140 diagnoses whether or not there is a sign of leakage in the mechanical seal 152D, based on the AE signal for a predetermined period input from the BPF 130 and the diagnostic criteria set by the information processing device 40 described above.

[0106] The AE signal used to diagnose whether there is a sign of leakage from the mechanical seal 152D is preferably, for example, an AE signal recorded at a timing before the process reaction in the polymerization reaction tank 150. This makes it possible to prevent a situation in which disturbances caused by the process reaction are superimposed on the AE signal, and as a result, the information processing device 140 can improve the accuracy of the diagnosis.

[0107] The information processing device 140 is, for example, a server device having a relatively high processing capacity, similar to the above-mentioned information processing device 40. Also, similar to the information processing device 40, the information processing device 140 may be a terminal device having a lower processing capacity than the server device, so long as it has the ability to execute necessary processes.

[0108] The hardware configuration of the information processing device 140 may be the same as that of the above-described information processing device 40. Therefore, illustration and description of the hardware configuration of the information processing device 140 will be omitted.

[0109] [Example of how to monitor the condition of a mechanical seal] Next, a first example of a method for monitoring the state of the mechanical seal 152D will be described with reference to FIG.

[0110] FIG. 6 is a diagram showing an example of a process flow relating to monitoring for the presence or absence of a sign of leakage in the mechanical seal 152D of the information processing device 140. In FIG.

[0111] The process flow of FIG. 6 is automatically executed at each predetermined processing cycle, for example. The process flow of FIG. 6 may also be executed manually in response to a request from a user via an input device. The process flow of FIG. 6 may also be executed at a timing before the process reaction in the polymerization reaction tank 150. This can prevent a situation in which a disturbance caused by the process reaction in the polymerization reaction tank 150 is superimposed on the AE signal, and as a result, the information processing device 140 can improve the accuracy of diagnosing the presence or absence of a sign of leakage in the mechanical seal 152D.

[0112] Hereinafter, steps S202, S204, S206, S208, and S210 are the same as steps S102, S104, S106, S108, and S110 performed by the information processing device 40 described above, and therefore detailed description thereof may be omitted.

[0113] In step S202 (signal acquisition process), the information processing device 140 acquires time-series data of the AE signal for the latest predetermined period, which is taken in from the BPF 130, from a reception buffer or the like.

[0114] When the process of step S202 is completed, the information processing device 140 proceeds to step S204.

[0115] In step S204 (energy calculation process), the information processing device 140 calculates the AE energy for a predetermined period based on the time-series data of the AE signal, and outputs the time-series data of the AE energy for the predetermined period.

[0116] When step S204 is completed, the information processing device 140 proceeds to steps S206 and S208.

[0117] In step S206 (periodic component extraction process), the information processing device 140 extracts a periodic component from the time-series data of the AE energy.

[0118] In step S208 (periodicity removed component extraction process), the information processing device 140 extracts the periodicity removed component from the time series data of the AE energy.

[0119] When steps S206 and S208 are completed, the information processing device 140 proceeds to step S210.

[0120] In step S210 (standard deviation calculation process), the information processing device 140 calculates the standard deviation σ1 of the time series data of the periodic component of the AE energy extracted in step S206. Similarly, in step S210, the information processing device 140 calculates the standard deviation σ2 of the time series data of the periodicity removed component of the AE energy extracted in step S208.

[0121] When step S210 is completed, information processing device 140 proceeds to step S212.

[0122] The processes in steps S206 and S208 may be performed in series.

[0123] In step S212 (diagnosis process), the information processing device 140 diagnoses whether or not there is a sign of leakage in the mechanical seal 152D based on the standard deviations σ1 and σ2 calculated in step S210. Specifically, the information processing device 140 diagnoses whether or not there is a sign of leakage in the mechanical seal 152D based on the standard deviations σ1 and σ2 calculated in step S210 and the diagnostic reference values ​​σ1_th and σ2_th set by the information processing device 40. More specifically, when the standard deviation σ1 is relatively large with respect to the diagnostic reference value σ1_th and the standard deviation σ2 is relatively large with respect to the diagnostic reference value σ2_th, the information processing device 140 diagnoses that there is a sign of leakage in the mechanical seal 152D. On the other hand, the information processing device 140 diagnoses that there is no sign of leakage in the mechanical seal 152D in other cases.

[0124] When step S212 is completed, the information processing device 140 proceeds to step S214.

[0125] In step S214 (notification process), the information processing device 140 notifies the user of the diagnosis result in step S212. For example, the information processing device 140 notifies the user of the diagnosis result by a visual method or an audible method through an output device such as its own display device or sound output device. The information processing device 140 may also notify the user of the diagnosis result by transmitting the diagnosis result to a terminal device (user terminal) carried by the user through a communication interface. The information processing device 140 may also notify the user of the diagnosis result through email, SNS (Social Networking Service), or the like. This allows the user of the monitoring system 100 to grasp the diagnosis result of whether or not there is a sign of leakage in the mechanical seal 152D. Therefore, for example, when the user grasps the diagnosis result that there is a sign of leakage in the mechanical seal 152D, the user can order parts for replacement of the mechanical seal 152D, or adjust the timing of replacement according to the operating status of the polymerization reaction tank 150, etc.

[0126] When the process of step S214 ends, the information processing device 140 ends the process flow.

[0127] In this way, the information processing device 140 can diagnose the presence or absence of signs of leakage in the mechanical seal 152D by comparing the standard deviations σ1, σ2 of the time series data of the periodic component and periodicity removal component of the AE energy of the mechanical seal 152D with the diagnostic reference values ​​σ1_th, σ2_th.

[0128] [Second example of how to monitor the condition of a mechanical seal] Next, a second example of the method for monitoring the state of the mechanical seal 152D will be described with reference to FIGS. 7 and 8 in addition to FIG.

[0129] The following description will focus on the differences from the first example of the monitoring method described above, and descriptions of contents that are the same as or correspond to the first example may be omitted.

[0130] <Overview of monitoring method> Fig. 7 is a diagram showing a specific example of the time-dependent change in the history of standard deviations σ1 and σ2 of the time-series data of the periodic component and periodic removal component of the acoustic emission (AE) energy of the mechanical seal 152D. Fig. 7 includes Figs. 7A and 7B, which respectively show the time-dependent change in the history of standard deviations σ1 and σ2 of the time-series data of the periodic component and periodic removal component of the AE energy until leakage occurs in the mechanical seal 152D in different polymerization reaction vessels 150. Fig. 7A includes a graph 701 of the time-dependent change in the history of standard deviation σ2 of the time-series data of the periodic removal component of the AE energy of the mechanical seal 152D, and a graph 702 of the time-dependent change in the history of standard deviation σ1 of the time-series data of the periodic component of the AE energy of the mechanical seal 152D. 7B includes a graph 703 of the time history of the standard deviation σ2 of the time series data of the periodic component of the AE energy of the mechanical seal 152D and a graph 704 of the time history of the standard deviation σ1 of the time series data of the periodic component of the AE energy of the mechanical seal 152D. FIG. 8 is a diagram illustrating a second example of a method for monitoring the presence or absence of a sign of leakage in the mechanical seal 152D. Specifically, FIG. 8 is a diagram that illustrates a quadratic curve 801 that represents the tendency of the time change of the standard deviation σ1 of the time series data of the periodic component of the AE energy of the mechanical seal 152D until failure, and a quadratic curve 802 that represents the tendency of the time change of the standard deviation σ2 of the time series data of the periodic component until failure.

[0131] The solid lines in the graphs 701 to 704 are quadratic curves that approximate the time change in the historical data of the standard deviation σ1 or the standard deviation σ2, respectively.

[0132] As shown in graphs 702 and 704, the historical data for standard deviation σ1 shows a continuing upward trend over time, then transitions to a downward trend over time, and after this trend continues, mechanical seal 152D begins to leak.

[0133] Therefore, for example, as shown by the quadratic curve 801 in FIG. 8, when the history of the standard deviation σ1 transitions from a state 801A showing an increasing trend over time to a state 801B showing a decreasing trend over time, the information processing device 140 can diagnose that there is an indication of leakage from the mechanical seal 152D.

[0134] As shown in graphs 701 and 703, the historical data of the standard deviation σ2 has a relatively small value, and continues to show a relatively small change over time, and then transitions to a state in which the increase over time is relatively large. The history of the standard deviation σ2 transitions from a state in which the increase over time is relatively large to a peak of a relatively large value, and then transitions to a state in which the decrease over time is relatively large, and after this trend continues, the mechanical seal 152D reaches a relatively small value, at which point leakage occurs.

[0135] Therefore, for example, as shown by the quadratic curve 802 in FIG. 8, when the history of the standard deviation σ2 transitions from a state 802A in which there is a relatively small change over time to a state 802B in which there is a relatively large increase over time, the information processing device 140 can diagnose that there is an indication of leakage from the mechanical seal 152D.

[0136] Furthermore, a comparison of graphs 701, 702 and graphs 703, 704 reveals that there comes an earlier point in time when the history of standard deviation σ1 transitions from an increasing trend over time to a decreasing trend, and there comes a later point in time when the history of standard deviation σ2 transitions from a state in which the change over time is relatively small to a state in which the increase is relatively large.

[0137] Therefore, for example, as shown by quadratic curves 801 and 802 in Fig. 8, the information processing device 140 may diagnose that there is a sign of leakage in the mechanical seal 152D when the history of the standard deviation σ1 transitions from state 801A in which the standard deviation σ1 continues to increase over time to state 801B in which the standard deviation σ2 continues to decrease over time, and then transitions from state 802A in which the standard deviation σ2 changes relatively little over time to state 802B in which the standard deviation σ2 changes relatively much over time. This allows the information processing device 140 to more reliably diagnose whether there is a sign of leakage in the mechanical seal 152D.

[0138] <Processing flow> The process flow of the monitoring method according to this example is shown in FIG. 6, similarly to the first example described above, so illustration will be omitted and the explanation will be given with reference to FIG.

[0139] The process contents of steps S202, S204, S206, S208, and S210 are similar to those in the first example of the monitoring method described above, and therefore a description thereof will be omitted.

[0140] When step S210 is completed, information processing device 140 proceeds to step S212.

[0141] In step S212 (diagnosis process), the information processing device 140 diagnoses whether there is a sign of leakage from the mechanical seal 152D based on the data of the history of standard deviations including the standard deviations σ1 and σ2 calculated in the current step S210. Specifically, the information processing device 140 determines whether the first monitoring condition for the data of the history of standard deviation σ1 has already been satisfied in the past process, and whether the second monitoring condition for the data of the history of standard deviation σ2 has been satisfied in the current process. The first monitoring condition is a condition indicating that the history of standard deviations has transitioned from a state in which the trend of increasing over time continues to a state in which the trend of decreasing over time continues. The second monitoring condition is a condition indicating that the history of standard deviation σ2 has transitioned from a state in which the trend of relatively small change over time continues to a state in which the trend of relatively large increase over time continues.

[0142] For example, when the first monitoring condition has not been satisfied in past processing, the information processing apparatus 140 determines whether the first monitoring condition is satisfied. When the first monitoring condition is satisfied, the information processing apparatus 140 sets a flag F1 indicating that the first monitoring condition has been satisfied from "0" (not satisfied) to "1" (satisfied), and when the first monitoring condition is not satisfied, maintains the flag F1 at the initial value of "0". Then, the information processing apparatus 140 diagnoses that there are no signs of leakage in the mechanical seal 152D. On the other hand, when the first monitoring condition has been satisfied in past processing, that is, when the flag F1 is "1", the information processing apparatus 140 determines whether the second monitoring condition is satisfied. When the second monitoring condition is satisfied, the information processing apparatus 140 diagnoses that there are signs of leakage in the mechanical seal 152D, and when the second monitoring condition is not satisfied, diagnoses that there are no signs of leakage in the mechanical seal 152D.

[0143] The first monitoring condition is, for example, that for an approximation curve (e.g., a quadratic curve) representing the time change of the history of the standard deviation σ1, the decrease has continued in the most recent predetermined period (the first period), and the increase has continued in the predetermined period (the second period) before the first period. In this case, the information processing apparatus 140 performs, for example, a quadratic curve approximation on the data of the history of the standard deviation σ1 to obtain an approximation curve.

[0144] The second monitoring condition is, for example, that for an approximation curve (e.g., a quadratic curve) representing the time change of the history of the standard deviation σ2, the latest value is equal to or greater than a predetermined threshold TH1, and the average value over the entire past period or the most recent predetermined period in the past is equal to or less than a threshold TH2 (<TH1). In this case, the information processing apparatus 140 performs, for example, a quadratic curve approximation on the data of the history of the standard deviation σ2 to obtain an approximation curve.

[0145] When the processing of step S212 is completed, the information processing apparatus 140 proceeds to step S214.

[0146] Since the process content of step S214 is similar to that of the first example of the monitoring method described above, a description thereof will be omitted.

[0147] When the process of step S214 is completed, the information processing device 140 ends the process flow.

[0148] In this way, the information processing device 140 can diagnose whether or not there are signs of leakage in the mechanical seal 152D based on the tendency of time-series changes in the standard deviations σ1 and σ2 of the time series data of the periodic component and the periodicity removed component of the AE energy of the mechanical seal 152D.

[0149] [Other embodiments] Next, another embodiment will be described.

[0150] The above-described embodiment may be modified or altered as appropriate.

[0151] For example, in the above-described embodiment, in the diagnostic criteria setting system 1, the diagnostic criteria may be set by utilizing the measurement signals (AE signals) of the AE sensors 10 corresponding to the multiple polymerization reaction vessels 50, respectively.

[0152] Furthermore, in the above-described embodiments and examples of variations and modifications thereof, in the diagnostic criteria setting system 1, diagnostic criteria may be set using a polymerization reactor of the same specifications as that actually used for the manufacture of products in a factory or the like, instead of or in addition to the polymerization reactor 50 as an experimental machine.

[0153] In addition, in the above-described embodiments and examples of variations and modifications thereof, in the diagnostic criteria setting system 1, instead of a polymerization reaction tank equipped with a mechanical seal, the diagnostic criteria may be set using an experimental device that simulates a mechanical seal installed in a polymerization reaction tank.

[0154] In the above-mentioned embodiment and its modified and altered examples, the diagnostic criteria setting system 1 may set a common diagnostic criteria corresponding to mechanical seals installed in a plurality of polymerization reactors having different specifications. In this case, the information processing device 40 may set the diagnostic criteria using the AE signals of the mechanical seals corresponding to all of the target polymerization reactors, or may set the diagnostic criteria using the AE signals of the mechanical seals corresponding to some of the target polymerization reactors. For example, the information processing device 40 may set the diagnostic criteria for each group of polymerization reactors classified according to the use conditions of the mechanical seals. In this way, a plurality of polymerization reactors for which the diagnostic criteria can be shared are grouped into one group, and a common diagnostic criteria is set for the plurality of polymerization reactors included in one group. The group classified according to the use conditions of the mechanical seal is, for example, a group classified according to the material of the rotating shaft of the agitator of the polymerization reactor. The group classified according to the material of the rotating shaft of the agitator of the polymerization reactor includes, for example, a group in which the rotating shaft of the agitator is composed only of machined metal parts and a group including baked parts such as glass and resin.

[0155] In addition, in the above-described embodiments and examples of variations and modifications thereof, the diagnostic criteria setting system 1 may set diagnostic criteria for diagnosing the presence or absence of signs of leakage in a mechanical seal installed in equipment other than the polymerization reaction tank.

[0156] In the above-described embodiment and its modified and altered examples, diagnostic criteria for diagnosing the presence or absence of symptoms of failure of an object other than a mechanical seal may be set in the diagnostic criteria setting system 1. For example, the information processing device 40 may set diagnostic criteria for diagnosing the presence or absence of symptoms of failure of a bearing based on the AE signal of a bearing mounted on a specified rotating machine.

[0157] In the above-described embodiment and its modified examples, only one of the diagnostic reference values ​​σ1_th and σ2_th may be set in the diagnostic reference setting system 1, and the setting of the other diagnostic reference value may be omitted. In this case, the information processing device 140 uses one of the set diagnostic reference values ​​to diagnose the presence or absence of a sign of leakage in the mechanical seal 152D based on only one of the time series signals of the periodic component and the periodicity removed component of the AE energy of the mechanical seal 152D. In this case, one of the processes of steps S106 and S108 in FIG. 3 and one of the processes of steps S206 and S208 in FIG. 6 are omitted.

[0158] Furthermore, in the above-described embodiment and examples of modifications and alterations thereof, the information processing device 40 may generate a trained model based on historical data of at least one of the standard deviation σ1 and the standard deviation σ2, instead of setting a diagnostic criterion. In this case, the trained model corresponds to a classifier that classifies the presence or absence of a symptom of a fault of the object based on at least one of the standard deviation σ1 of the periodic component of the AE energy of the object and the standard deviation σ2 of the periodicity removed component. This allows the information processing device 140 to diagnose the presence or absence of a symptom of a fault of the object using the trained model based on at least one of the standard deviation σ1 of the periodic component of the AE energy of the object and the standard deviation σ2 of the periodicity removed component.

[0159] In the process flow (FIG. 6) of the second example of the monitoring method of the above embodiment, a symptom of leakage from the mechanical seal 152D may be diagnosed based on only one of the standard deviations σ1 and σ2. In this case, one of the processes of steps S206 and S208 in FIG. 6 is omitted.

[0160] In addition, in the above-described embodiment and the examples of the variations and modifications thereof, the information processing device 40 and the information processing device 140 may be the same information processing device. That is, the setting of the diagnostic criteria and the monitoring of the state of the object based on the set diagnostic criteria may be performed by a common information processing device.

[0161] In addition, in the above-described embodiment and its modified and altered examples, at least one of the amplifier circuit 20 and the BPF 30 may be omitted in the diagnostic criteria setting system 1. Similarly, in the monitoring system 100, at least one of the amplifier circuit 120 and the BPF 130 may be omitted.

[0162] [Effect] Next, the operation of the information processing device and information processing method according to the present embodiment will be described.

[0163] In a first aspect of this embodiment, an information processing device acquires a time-series measurement signal of an acoustic emission (AE) of an object. The information processing device is, for example, the above-mentioned information processing device 40 or information processing device 140. The object is, for example, the above-mentioned mechanical seal 52D or mechanical seal 152D. The information processing device calculates the energy of the AE of the object based on the measurement signal. The information processing device extracts a time-series signal of a first component obtained by removing a second component having periodicity from the time-series signal of the energy, or a time-series signal of the second component. The first component is, for example, the above-mentioned periodicity-removed component. The second component is, for example, the above-mentioned periodic component. Then, the information processing device calculates an index value related to the variability of the time-series signal of the first component or the time-series signal of the second component. The index value related to the variability of the time-series signal of the first component is, for example, the above-mentioned standard deviation σ2. The index value relating to the variance of the time series signal of the second component is, for example, the above-mentioned standard deviation σ1.

[0164] In a first aspect of this embodiment, the information processing method includes an acquisition step, an energy calculation step, a first extraction step, and a variation calculation step. The acquisition step is, for example, the above-mentioned step S102 or step S202. The energy calculation step is, for example, the above-mentioned step S104 or step S204. The first extraction step is, for example, the above-mentioned step S108, step S208, or step S206. The variation calculation step is, for example, the above-mentioned step S110 or step S210. Specifically, in the acquisition step, the information processing device acquires a time-series measurement signal of the AE of the object. In addition, in the energy calculation step, the information processing device calculates the energy of the AE of the object based on the measurement signal. In addition, in the first extraction step, the information processing device extracts a time-series signal of a first component obtained by removing a second component having periodicity from the time-series signal of the energy, or a time-series signal of the second component. Then, in the variance calculation step, an information processing device calculates an index value relating to variance of the time-series signal of the first component or the time-series signal of the second component.

[0165] This allows the information processing device to calculate an index value relating to the variability of the time series signal of the first component or the time series signal of the second component of the AE energy of the object. Therefore, for example, the information processing device can relatively easily monitor the state of the object based on the index value. Also, for example, the information processing device can set a reference value for the index value and more easily monitor the state of the object based on a comparison between the index value and the reference value.

[0166] In a second aspect of the present embodiment, on the premise of the above-mentioned first aspect, the information processing method may include a second extraction step. The second extraction step is, for example, the above-mentioned step S106 or step S206. Specifically, in the first extraction step, a time series signal of the first component may be extracted. In addition, in the second extraction step, the information processing device may extract a time series signal of the second component from the time series signal of the energy. Then, in the variability calculation step, an index value related to the variability of both the time series signal of the first component and the time series signal of the second component may be calculated.

[0167] This allows the information processing device to calculate index values ​​relating to the variations in the time series signals of both the first and second components of the AE energy of the object. Therefore, for example, the information processing device can relatively easily monitor the state of the object based on both index values. In addition, for example, the information processing device can set reference values ​​for each of both index values, thereby more easily monitoring the state of the object based on a comparison between the index values ​​and the reference values.

[0168] In addition, in a third aspect of this embodiment, based on the first aspect described above, the information processing method may include a diagnosis step in which the information processing device diagnoses the presence or absence of a sign of a malfunction of the object mounted on a specified device based on a tendency of a time change in a history of the index value related to the variance of the time series signal of the first component or the time series signal of the second component.

[0169] This enables the information processing device to easily monitor the presence or absence of signs of failure of an object mounted on a specified device based on an index value relating to the variance in the time series signal of the first component or the time series signal of the second component of the AE energy of the object.

[0170] In addition, in a fourth aspect of this embodiment, based on the second aspect described above, the information processing method may include a diagnosis step in which the information processing device diagnoses the presence or absence of signs of a malfunction of the object mounted on a specified device based on trends of time change in both the time-series signal of the first component and the history of the index value related to the variance of the time-series signal of the second component.

[0171] This enables the information processing device to easily monitor the presence or absence of signs of failure of an object mounted on a specified device, based on index values ​​relating to the variance in both the time series signal of the first component and the time series signal of the second component of the AE energy of the object.

[0172] In addition, in a fifth aspect of this embodiment, based on the third aspect described above, the diagnosis step may diagnose that there is a sign of a malfunction of the object mounted on a specified device when the history of the index value relating to the variability in the time series signal of the second component transitions from an increasing trend over time to a decreasing trend over time.

[0173] This enables the information processing device to easily monitor the presence or absence of signs of failure of an object mounted on a specified device, based on the index value related to the variation in the time-series signal of the second component of the AE energy of the object.

[0174] In addition, in a sixth aspect of this embodiment, based on the third aspect described above, the diagnosis step may diagnose that there is a sign of a malfunction of the object mounted on a specified device when the history of the index value relating to the variability of the time series signal of the first component transitions from a state in which the change over time is relatively small to a state in which the change over time is relatively large.

[0175] This enables the information processing device to easily monitor the presence or absence of signs of failure of an object mounted on a specified device, based on the index value related to the variation in the time-series signal of the first component of the AE energy of the object.

[0176] Furthermore, in a seventh aspect of this embodiment, based on the above-mentioned fourth aspect, in the diagnosis step, when the history of the index value related to the variation in the time-series signal of the second component transitions from an increasing trend over time to a decreasing trend over time, and thereafter, the history of the index value related to the variation in the time-series signal of the first component transitions from a state in which the change over time is relatively small to a state in which the increase over time is relatively large, it may be diagnosed that there is a sign of a malfunction of the object mounted on a specified device.

[0177] This enables the information processing device to easily monitor the presence or absence of signs of failure of an object mounted on a specified device, based on index values ​​relating to the variance in both the time series signal of the first component and the time series signal of the second component of the AE energy of the object.

[0178] In an eighth aspect of the present embodiment, on the premise of the first aspect described above, the information processing method may include a setting step. The setting step is, for example, step S116 described above. Specifically, in the setting step, the information processing device sets a reference value for determining the presence or absence of a symptom of a failure of the object mounted on a predetermined device. The information processing device is, for example, the information processing device 40 described above. The predetermined device is, for example, the polymerization reaction tank 50 described above. The object is, for example, the mechanical seal 52D described above. In addition, in the acquisition step, a plurality of measurement signals of the AE of the object mounted on the predetermined device may be acquired, the plurality of measurement signals including both the measurement signal in a state before the occurrence of a failure of the object and the measurement signal in a state after the occurrence of a failure of the object. In addition, in the energy calculation step, the energy corresponding to each of the plurality of measurement signals acquired in the acquisition step may be calculated. In addition, in the first extraction step, the first component may be extracted from a time series signal of the energy corresponding to each of the plurality of measurement signals. In the variation calculation step, the index value relating to the variation of the time-series signal of the first component corresponding to each of the plurality of measurement signals may be calculated. In the setting step, a first reference value for the index value relating to the variation of the time-series signal of the first component may be set based on a distribution of the index value relating to the variation of the time-series signal of the first component corresponding to the measurement signal in a state before the occurrence of a failure of the object and a distribution of the index value relating to the variation of the time-series signal of the first component corresponding to the measurement signal in a state after the occurrence of a failure of the object, among the index values ​​relating to the variation of the time-series signal of the first component corresponding to each of the plurality of measurement signals. The first reference value is, for example, the above-mentioned diagnostic reference value σ2_th.

[0179] This allows the information processing device to set a first reference value for an index value related to the variation in the time series signal of the first component of AE energy in order to determine the presence or absence of a symptom of failure of the object, and therefore the information processing device can realize monitoring of the presence or absence of a symptom of failure of the object based on a comparison between the index value related to the variation in the time series signal of the first component of AE energy and the first reference value.

[0180] In addition, in a ninth aspect of the present embodiment, on the premise of the above-mentioned second aspect, the information processing device may include a setting step. Specifically, in the setting step, a reference value for judging the presence or absence of a sign of a failure of the object mounted on a predetermined device may be set. In the acquisition step, a plurality of measurement signals of the AE of the object mounted on the predetermined device may be acquired, the plurality of measurement signals including both the measurement signal in a state before the occurrence of a failure of the object and the measurement signal in a state after the occurrence of a failure of the object. In addition, in the energy calculation step, the energy corresponding to each of the plurality of measurement signals acquired in the acquisition step may be calculated. In addition, in the first extraction step, the first component may be extracted from a time series signal of the energy corresponding to each of the plurality of measurement signals. In addition, in the second extraction step, a time series signal of the second component obtained by removing the first component from the time series signal of the energy corresponding to each of the plurality of measurement signals may be extracted. The variation calculation step may calculate the index value related to the variation of the time-series signal of the first component corresponding to each of the plurality of measurement signals, and calculate the index value related to the variation of the time-series signal of the second component corresponding to each of the plurality of measurement signals. The setting step may set a first reference value for the index value related to the variation of the time-series signal of the first component and a second reference value for the index value related to the variation of the time-series signal of the second component based on a distribution of combinations of the index values ​​related to the variation of the time-series signal of both the first component and the second component corresponding to the measurement signals in a situation before the occurrence of a failure of the object and a distribution of combinations of the index values ​​of the time-series signal of the first component and the second component corresponding to the measurement signals in a situation after the occurrence of a failure of the object, among combinations of the index values ​​related to the variation of the time-series signal of both the first component and the second component corresponding to each of the plurality of measurement signals. The first and second reference values ​​are, for example, the above-mentioned diagnostic reference value σ2_th and diagnostic reference value σ1_th, respectively.

[0181] This allows the information processing device to set a first reference value and a second reference value for determining the presence or absence of a symptom of failure of the object, the first reference value and the second reference value being for index values ​​relating to the variations in the time-series signals of the first component and the second component of the AE energy, respectively. Therefore, the information processing device can realize monitoring of the presence or absence of a symptom of failure of the object based on a comparison of the index values ​​relating to the variations in the time-series signals of the first component and the second component of the AE energy with the first reference value and the second reference value, respectively.

[0182] In a tenth aspect of this embodiment, based on the eighth aspect described above, the plurality of measurement signals may be a collection of measurement signals at different timings for the same predetermined device. In the setting step, the first reference value may be set based on the index value related to the variation in the signal of the first component corresponding to the measurement signal at a timing that is a predetermined time before the timing of the measurement signal that is first recorded after the occurrence of a failure of the object.

[0183] This enables the information processing device to appropriately set a first reference value for determining whether or not there are signs of a failure occurring in the object, based on the change over time in the index value relating to the variation in the time-series signal of the first component of the AE energy of the object for the same specified equipment.

[0184] In an eleventh aspect of this embodiment, based on the above-mentioned ninth aspect, the plurality of measurement signals may be a collection of measurement signals at different timings for the same predetermined device. In the setting step, the first reference value may be set based on the index value related to the variation of the signal of the first component corresponding to the measurement signal at a timing a predetermined time back from the timing of the measurement signal recorded first after the occurrence of a failure of the object, and the second reference value may be set based on the index value related to the variation of the signal of the second component corresponding to the measurement signal recorded first after the occurrence of a failure of the object.

[0185] This enables the information processing device to appropriately set a first reference value and a second reference value for determining whether or not there are signs of a failure of the object, based on the change over time in the index values ​​relating to the variation in the time-series signals of the first and second components of the AE energy of the object for the same specified equipment.

[0186] In addition, in a twelfth aspect of this embodiment, based on any one of the eighth to eleventh aspects described above, in the setting step, a reference value for determining whether or not there are signs of a malfunction of the object may be set for each group related to a plurality of the specified devices, which are divided according to the usage conditions of the object.

[0187] This allows the information processing device to set a reference value for each group of multiple predetermined devices according to the usage conditions, thereby improving the accuracy of determining whether or not there is a symptom of failure of the object for each group of multiple predetermined devices.

[0188] In a thirteenth aspect of the present embodiment, based on any one of the third to twelfth aspects, the predetermined device may be a polymerization reaction vessel, and the target object may be a mechanical seal for sealing a shaft.

[0189] This enables the information processing device to set a reference value for determining whether or not there is a sign of a malfunction such as leakage of contents in a mechanical seal for sealing a shaft mounted in a polymerization reaction vessel.

[0190] In addition, in a 14th aspect of this embodiment, based on the above-mentioned 13th aspect, the acquisition step may acquire the measurement signal recorded at a timing before the process reaction in the polymerization reaction tank.

[0191] This makes it possible for the information processing device to prevent a situation in which disturbances caused by the process reaction inside the polymerization reaction tank are superimposed on the measurement signal, thereby improving the accuracy of setting the reference value.

[0192] Although the embodiments have been described above, it will be understood that various changes in form and details are possible without departing from the spirit and scope of the claims. [Explanation of symbols]

[0193] 1 Diagnostic Criteria Setting System 10 Acoustic Emission Sensor 40 Information processing device 50 Polymerization Reactor 51 Tank body 52 Mixer 52D Mechanical Seal 52D1 Fixed ring 52D2 Rotating Ring 100 Surveillance System 110 Acoustic Emission Sensor 140 Information processing equipment 150 Polymerization Reactor 151 Tank body 152 Mixer 152D Mechanical Seal 152D1 Fixed ring 152D2 Rotating Ring

Claims

1. An acquisition step in which an information processing device acquires a time-series measurement signal of acoustic emission of the object; An energy calculation step in which an information processing device calculates energy of acoustic emission of the object based on the measurement signal; a first extraction step in which an information processing device extracts a time series signal of a first component or a time series signal of the second component by removing a second component having periodicity from the time series signal of the energy; A variance calculation step in which the information processing device calculates an index value related to a variance of the time series signal of the first component or the time series signal of the second component, Information processing methods.

2. a second extraction step of extracting a time series signal of the second component from the time series signal of the energy, In the first extraction step, a time series signal of the first component is extracted; In the variability calculation step, index values ​​related to variability of both the time series signal of the first component and the time series signal of the second component are calculated. The information processing method according to claim 1 .

3. a diagnosis step of diagnosing the presence or absence of a symptom of a failure of the object mounted on a predetermined device, based on a tendency of a time change in a history of the index value related to a variation in the time series signal of the first component or the time series signal of the second component, by the information processing device; The information processing method according to claim 1 .

4. a diagnosis step of diagnosing the presence or absence of a symptom of a failure of the object mounted on a predetermined device based on trends of time changes of both the time-series signal of the first component and the history of the index value related to the variation of the time-series signal of the second component, by the information processing device; The information processing method according to claim 2 .

5. In the diagnosis step, when a history of the index value related to the variation in the time series signal of the second component transitions from an increasing trend over time to a decreasing trend over time, it is diagnosed that there is a symptom of a failure of the object mounted on the predetermined device. The information processing method according to claim 3.

6. In the diagnosis step, when a history of the index value related to the variance of the time series signal of the first component transitions from a state in which the change over time is relatively small to a state in which the increase over time is relatively large, it is diagnosed that there is a symptom of a failure of the object mounted on the predetermined device. The information processing method according to claim 3.

7. In the diagnosis step, when the history of the index value related to the variation in the time-series signal of the second component transitions from an increasing trend over time to a decreasing trend over time, and thereafter, the history of the index value related to the variation in the time-series signal of the first component transitions from a state in which the change over time is relatively small to a state in which the increase over time is relatively large, it is diagnosed that there is a symptom of a failure of the object mounted on a predetermined device. The information processing method according to claim 4.

8. A setting step of setting a reference value for determining whether or not there is a symptom of a failure of the object mounted on a predetermined device by an information processing device, In the acquisition step, a plurality of measurement signals of acoustic emissions of the object mounted on the predetermined device are acquired, the plurality of measurement signals including both the measurement signal in a state before the occurrence of a failure of the object and the measurement signal in a state after the occurrence of a failure of the object; In the energy calculation step, the energy corresponding to each of the plurality of measurement signals acquired in the acquisition step is calculated; In the first extraction step, the first component is extracted from the time series signal of the energy corresponding to each of the plurality of measurement signals; The variance calculation step calculates the index value related to the variance of a time series signal of the first component corresponding to each of the plurality of measurement signals; In the setting step, a first reference value is set for the index value related to the variability of the time-series signal of the first component, based on a distribution of the index value related to the variability of the time-series signal of the first component corresponding to the measurement signals in a state before a failure of the object occurs and a distribution of the index value related to the variability of the time-series signal of the first component corresponding to the measurement signals in a state after a failure of the object occurs, among the index values ​​related to the variability of the time-series signal of the first component corresponding to each of the plurality of measurement signals. The information processing method according to claim 1 .

9. A setting step of setting a reference value for determining whether or not there is a symptom of a failure of the object mounted on a predetermined device by an information processing device, In the acquisition step, a plurality of measurement signals of acoustic emissions of the object mounted on the predetermined device are acquired, the plurality of measurement signals including both the measurement signal in a state before the occurrence of a failure of the object and the measurement signal in a state after the occurrence of a failure of the object; In the energy calculation step, the energy corresponding to each of the plurality of measurement signals acquired in the acquisition step is calculated; In the first extraction step, the first component is extracted from the time series signal of the energy corresponding to each of the plurality of measurement signals; In the second extraction step, a time series signal of the second component is extracted by removing the first component from the time series signal of the energy corresponding to each of the plurality of measurement signals; In the variability calculation step, the index value related to the variability of a time series signal of the first component corresponding to each of the plurality of measurement signals is calculated, and the index value related to the variability of a time series signal of the second component corresponding to each of the plurality of measurement signals is calculated, In the setting step, a first reference value for the index value related to the variability of the time-series signal of the first component and a second reference value for the index value related to the variability of the time-series signal of the second component are set based on a distribution of the combinations of the index values ​​related to the variability of the time-series signal of the first component and the second component corresponding to the measurement signals in a situation before the occurrence of a failure of the object and a distribution of the index values ​​related to the variability of the time-series signal of the first component and the second component corresponding to the measurement signals in a situation after the occurrence of a failure of the object, among combinations of the index values ​​of the time-series signals of both the first component and the second component corresponding to each of the multiple measurement signals. The information processing method according to claim 2 .

10. The plurality of measurement signals are a collection of measurement signals obtained at different timings for the same predetermined device, In the setting step, the first reference value is set based on the index value related to the variation of the signal of the first component corresponding to the measurement signal at a timing that is a predetermined time before the timing of the measurement signal that is first recorded after the occurrence of a failure of the object. The information processing method according to claim 8.

11. The plurality of measurement signals are a collection of measurement signals obtained at different timings for the same predetermined device, In the setting step, the first reference value is set based on the index value related to the variation of the signal of the first component corresponding to the measurement signal at a timing a predetermined time before the timing of the measurement signal that is first recorded after the occurrence of a failure of the object, and the second reference value is set based on the index value related to the variation of the signal of the second component corresponding to the measurement signal that is first recorded after the occurrence of a failure of the object. The information processing method according to claim 9.

12. In the setting step, a reference value for determining whether or not the object has a sign of failure is set for each group related to the plurality of predetermined devices that are classified according to a use condition of the object.

12. The information processing method according to claim 8.

13. the predetermined device is a polymerization reaction tank, The object is a mechanical seal for sealing a shaft.

12. The information processing method according to claim 3.

14. In the acquiring step, the measurement signal recorded at a timing before the process reaction in the polymerization reaction tank is acquired. The information processing method according to claim 13.

15. obtaining a time series measurement signal of the acoustic emission of the object; Calculating the energy of the acoustic emission based on the measurement signal; extracting a time series signal of a first component obtained by removing a second component having periodicity from the time series signal of the energy, or a time series signal of the second component; calculating an index value related to a variability of the time series signal of the first component or the time series signal of the second component; Information processing device.

Images