WO2015146295A1 - Système de diagnostic d'état de soupape - Google Patents

Système de diagnostic d'état de soupape Download PDF

Info

Publication number
WO2015146295A1
WO2015146295A1 PCT/JP2015/053046 JP2015053046W WO2015146295A1 WO 2015146295 A1 WO2015146295 A1 WO 2015146295A1 JP 2015053046 W JP2015053046 W JP 2015053046W WO 2015146295 A1 WO2015146295 A1 WO 2015146295A1
Authority
WO
WIPO (PCT)
Prior art keywords
valve
diagnosis system
degree
feature amount
state diagnosis
Prior art date
Application number
PCT/JP2015/053046
Other languages
English (en)
Japanese (ja)
Inventor
遼一 高島
洋平 川口
真人 戸上
Original Assignee
株式会社日立ハイテクノロジーズ
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社日立ハイテクノロジーズ filed Critical 株式会社日立ハイテクノロジーズ
Publication of WO2015146295A1 publication Critical patent/WO2015146295A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
    • G05B23/0227—Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions
    • G05B23/0229—Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions knowledge based, e.g. expert systems; genetic algorithms

Definitions

  • the present invention relates to a valve state diagnosis system, and relates to a diagnosis technique for determining a valve state based on vibration or the like accompanying opening and closing of a valve.
  • Patent Document 1 As background arts in this technical field, there are Patent Documents 1 and 2, etc., and the summary of Patent Document 1 includes a cycle phase for supplying a vibration sensor installed in a fuel supply valve and a signal indicating opening / closing timing of the fuel supply valve.
  • the vibration measurement signal supplied from the supply device and the vibration sensor and the fuel supply valve opening / closing timing display signal are input, the abnormality of the fuel supply valve is determined based on the vibration accompanying the opening and closing of the fuel supply valve, and the abnormality signal is output.
  • An abnormality transmitting device is provided to detect and alarm the abnormality of the fuel supply valve based on the vibration intensity at the time of opening and closing.
  • Patent Document 1 describes an apparatus and a method for diagnosing an abnormality of a fuel supply valve in a gas engine using a vibration intensity observed by a vibration sensor.
  • Patent Document 2 describes a device that detects an abnormality of a fuel injection valve by using a vibration level.
  • JP 2012-132420 A Japanese Patent Laid-Open No. 10-318027
  • Cited Documents 1 and 2 describe a technique for diagnosing and detecting a valve abnormality using the intensity of vibration, but when diagnosing a valve mounted on some device, it is observed by a vibration sensor. Not only the vibration of the valve but also the mechanical vibration of the device itself is mixed in the signal as noise. And, depending on the type of valve and the device on which the valve is mounted, the effect of these noises on the vibration of the valve is large. There is.
  • An object of the present invention is to provide a valve state diagnosis system that can solve the above-described problems and can monitor and diagnose the valve state robustly against the influence of noise.
  • a valve state diagnosis system includes a sensor that reads valve operation information and a feature amount calculation unit that calculates a feature amount representing a time-varying shape of an output signal from the sensor. And a state determination unit that calculates a degree of abnormality from a feature amount representing a time-varying shape and determines a state of the valve based on the degree of abnormality.
  • a valve state diagnosis system a sensor for reading valve operation information, and concentration of energy in a specific frequency band in a frequency spectrum of an output signal from the sensor.
  • a valve state diagnosis system comprising: a feature amount calculation unit that calculates a feature amount based on the degree; and a state determination unit that calculates an abnormality degree from the feature amount based on the concentration degree and determines a state of the valve based on the abnormality degree I will provide a.
  • FIG. It is a figure which shows an example of the hardware block diagram of the valve state diagnostic system of Example 1.
  • FIG. It is a functional block diagram of the valve state diagnostic system of Example 1.
  • FIG. It is a figure which shows an example of the process flowchart of the valve state diagnostic system of Example 1.
  • FIG. It is a figure which shows typically the valve opening / closing section cutout process in the valve opening / closing section cutout part based on Example 1.
  • FIG. It is a figure which shows an example of the waveform of the vibration signal when the valve of a normal state based on Example 1 is closed, and when it is closed in the state where the foreign material was mixed.
  • FIG. 1 It is a figure which shows an example of an acoustic signal waveform when a valve closes to a normal state or a foreign material mixing state based on Example 1. It is a figure for comparing and explaining the vibration signal waveform at the time of occlusion with the presence or absence of a noise signal in the state where a valve is normal concerning Example 1. It is a figure for comparing and explaining the vibration waveform at the time of occlusion with the presence or absence of a noise signal in the occlusion defective state due to foreign matter mixing, according to the first embodiment. It is a figure for demonstrating the process of normal signal database preparation for learning the normal signal model based on Example 1. FIG. It is a figure which shows an example of the process which learns the normal signal model based on Example 1.
  • FIG. It is a figure which shows an example of the user interface part of the valve state diagnostic system based on Example 1.
  • FIG. It is a figure which shows the frequency spectrum which the vibration signal obtained when the valve of the state which concerns on Example 2 and the state in which the foreign material mixed in closed.
  • Embodiment 1 describes an embodiment of a valve state diagnosis system that monitors and diagnoses the state of a valve.
  • FIG. 1 is a diagram illustrating an example of a hardware configuration diagram of the valve state diagnosis system according to the first embodiment.
  • the valve state diagnosis system 100 includes a central processing unit 101, a storage medium 102, a volatile memory 103, a sensor 104, an AD conversion unit 105, a user interface unit 106, and a power source 107.
  • the valve state diagnosis system 100 diagnoses the valve 111 installed in the device 110 to be diagnosed.
  • the diagnosis target device 110 opens and closes the valve 111 through the device control circuit 112.
  • the sensor 104 observes the signal of the valve 111, and the AD converter 105 converts the analog signal observed by the sensor 104 into a digital signal.
  • the central processing unit 101 stores the converted digital signal in the volatile memory 103.
  • the central processing unit 101 uses the reference signal sent by the device control circuit of the diagnosis target device 110 to cut out only the signal in the section where the valve 111 is opened / closed from the signal stored in the volatile memory 103. After that, the central processing unit 101 calculates a time change shape of the amplitude value from the extracted signal, in other words, calculates a feature amount based on the time change shape.
  • the central processing unit 101 reads the normal signal model 205 stored in the storage medium 102 and calculates the degree of abnormality.
  • the central processing unit 101 discriminates the state according to the degree of abnormality, and outputs the discrimination result to the user interface unit 106 together with information about the extracted waveform.
  • the series of processing is executed by the central processing unit 101 based on a valve state diagnosis program stored in the storage medium 102.
  • Examples of the type of sensor 104 used include a vibration sensor and a microphone.
  • the sensor 104 may be directly attached to the valve 111.
  • the sensor 104 may be installed at a location away from the valve 111 as long as the signal of the valve 111 can be observed.
  • a vibration sensor it can be placed in a place where the vibration of the valve 111 is transmitted, and in the case of a microphone, it can be placed in any place within the range where the sound of the valve 111 can reach.
  • the AD converter 105 may not be introduced when the signal obtained from the sensor 104 is a digital signal.
  • the central processing unit 101, the storage medium 102, and the volatile memory 103 may be newly introduced to construct the valve state diagnosis system 100. If the diagnosis target device 110 has its own central processing unit, storage medium, and volatile memory, and the valve 111 is controlled by software, these may be used.
  • the power source 107 may be introduced separately for each of the valve state diagnosis system 100 and the diagnosis target device 110, and the same power source may be used if possible.
  • the user interface unit 106 may be, for example, a monitor provided in the diagnosis target apparatus 110, or may be a monitor via another PC connected via a network.
  • FIG. 2 is a functional block diagram of the valve state diagnosis system 100 of the present embodiment.
  • an analog signal observed by the observation sensor 104 is converted into a digital signal by the AD conversion unit 105.
  • the converted digital signal is cut out only by the valve opening / closing section cutout unit 201 when the valve is opened or closed.
  • the valve opening / closing section cutout unit 201 receives an opening / closing command signal sent from the device control circuit 112 provided in the diagnosis target apparatus 110 as a reference signal, and uses this reference signal to cut out the valve opening / closing section.
  • the switching delay time is calculated by taking the difference between the switching time read from the information of the reference signal and the time when the signal peak is detected at the surrounding time.
  • the noise signal suppression processing unit 202 reads the extracted signal, suppresses the noise signal included in the signal, and outputs it.
  • a normally used band filter (BPF) or the like may be used as the noise signal suppression processing unit 202.
  • the feature amount calculation unit 203 reads the noise-suppressed signal output from the noise signal suppression processing unit 202, calculates a feature amount representing a time-varying shape of the signal, and outputs it.
  • the abnormality degree calculation unit 204 reads the feature amount output from the feature amount calculation unit 203 and the normal signal model 205 stored in the storage medium 102, calculates the abnormality degree, and outputs it.
  • the state determination unit 206 reads the abnormality level output from the abnormality level calculation unit 204, determines the state of the valve 111, and outputs the determination result.
  • the determined result is presented by the diagnosis result presentation unit 207.
  • the information to be presented includes the degree of abnormality output from the abnormality degree calculation unit 204, the value of each feature amount output from the feature amount calculation unit 203, and noise signal suppression processing. Additional information such as a time signal waveform output from the section 202 or the valve opening / closing section cutout section 201 and an opening / closing delay time output from the valve opening / closing section cutout section 201 may be presented.
  • the presentation method includes, for example, image information presentation via the user interface unit 106, presentation by a braille display, presentation by voice, and printing of image information via a printer.
  • the types of valve states to be identified are the state in which the valve 111 is completely stopped, the valve opening / closing inadequate due to a sudden abnormality such as foreign matter entering the valve 111, and the valve opening / closing due to deterioration over time. It is an inadequate opening / closing state that is inadequate, and a state where deterioration over time has progressed to some extent and the replacement time is approaching.
  • FIG. 3 is a process flowchart of the valve state diagnosis system 100 of the present embodiment.
  • the valve state diagnosis system 100 also starts to operate in synchronization (300).
  • the sensor 104 starts observing a signal for the valve 111 (302).
  • the observed signal is converted into a digital signal by AD conversion processing (303).
  • the opening / closing section of the valve 111 is cut out from the converted digital signal (304).
  • a noise signal suppression process (305) is performed on the extracted signal, and the noise signal is suppressed.
  • a feature value is calculated from the signal subjected to the noise signal suppression process (306) by a feature value calculation process.
  • the degree of abnormality is calculated using the obtained feature amount (307).
  • state determination processing (308) of the valve 111 is performed, and the determination result is presented to the diagnosis result presentation unit 207 by the diagnosis result presentation processing (309).
  • the state determination unit 206 determines whether or not the device should be stopped according to the degree of abnormality (301). If it is determined that the device should be stopped, the termination processing (310) of the diagnosis target device 110 and the valve state diagnosis system 100 is performed. And finishes (311).
  • FIG. 4 is a schematic diagram for explaining a valve opening / closing section cutout processing method in the valve opening / closing section cutout section 201 of the present embodiment.
  • the valve 111 is controlled to be opened and closed by the device control circuit 112.
  • an opening / closing command signal sent from the device control circuit 112 toward the valve 111 is also sent to the valve opening / closing section cutout section 201, so that the time of the valve opening / closing section can be selected from the signals sent from the AD conversion section 105.
  • Information can be obtained. For example, as shown in FIG. 4, if the apparatus control circuit 112 outputs a command signal that is 1 when the valve 111 is open and 0 when the valve 111 is closed.
  • the time when the reference signal is switched from 0 to 1 can be cut out as a signal interval when the valve is opened, and the time when the reference signal is switched from 1 to 0 can be cut out as a signal interval when the valve is closed.
  • the valve opening / closing section cutout unit 201 detects the time Tr at which the absolute value of the signal is maximum in the surrounding section T from the valve opening / closing time Ti read from the reference signal (detection of the peak 401). Is cut out and output as a valve closing signal.
  • the difference (Tr ⁇ Ti) between the valve opening / closing time Ti based on the reference signal and the time Tr at which the peak is detected can also be output as the opening / closing delay time.
  • the noise signal is suppressed from the extracted signal by the noise signal suppression processing unit 202 using BPF or the like, and is sent to the feature amount calculation unit 203.
  • Fig. 5 shows (a) the vibration signal when the normal valve (solenoid valve) is closed and (b) the vibration signal when the valve is closed with foreign matter mixed in, using a vibration sensor.
  • the time signal waveform obtained.
  • the horizontal axis represents time (msec)
  • the vertical axis represents amplitude. The same applies to the following signal waveform diagrams.
  • 6 (a) and 6 (b) are time signal waveforms obtained by recording an acoustic signal using a microphone when the valve (solenoid valve) is closed in a normal state or a foreign matter mixed state. is there.
  • the time variation of the amplitude has a sharp and high peak shape (501 in FIG. 5)
  • the peak ( 502 in FIG. 5 is dull and low, that is, the time change of the amplitude is small and gentle. This is because the foreign matter is mixed and the valve is not sufficiently closed, and the impact when the valve is closed is weakened. Not only foreign substances but also occlusion defects due to aging deteriorate in the same manner.
  • a feature amount representing a time-varying shape of the valve signal is calculated, and a state such as a blockage failure is determined using the feature amount.
  • the feature amount expressing the dullness include a peak value, a difference between a maximum value and a minimum value, a half value width, an amplitude value variance, and a kurtosis.
  • the peak value is the maximum absolute value of the amplitude value in the extracted signal, and takes a high value in a normal state and a low value in a switching failure state.
  • the maximum value and the minimum value are obtained by calculating the difference between the maximum value and the minimum value of the amplitude in the extracted signal. This also takes a high value in a normal state, and takes a low value in a switching failure state.
  • the half-value width represents the width of the peak waveform, and takes a low value in a normal state and a high value in a switching failure state.
  • the dispersion value and kurtosis of the amplitude represent the intensity of fluctuation of the amplitude value, and take a high value in the normal state and a low value in the open / close state.
  • the variance var (x) and kurtosis kur (x) of the amplitude value are calculated by the following equations 1 and 2, respectively.
  • x (n) is the amplitude value of the signal at time n
  • m is the average value of x (n) in the peak peripheral section N.
  • the abnormality is detected using only the intensity of the signal such as the peak value, but in the valve state diagnosis system of the present embodiment, not only the peak value but also these signals are detected. It is possible to diagnose the state robustly against the influence of the noise signal by using the feature amount expressing the time-varying shape.
  • the upper left stage and the upper right stage in FIG. 7 respectively show (a) a vibration signal waveform at closing when there is no noise signal and (b) when there is a noise signal when the valve (solenoid valve) is normal.
  • This is a vibration signal at the time of closing when the driving vibrations are mixed as a noise signal.
  • the amplitude value at the time of closing is shifted in the positive direction due to noise. For this reason, a peak value becomes low compared with the case where there is no noise signal.
  • a normal state may be erroneously detected as an open / close failure.
  • the lower part of FIG. 7 is a graph obtained by normalizing and plotting the difference between each feature value in the normal state (with a noise signal) and each feature amount in the normal state (without a noise signal).
  • the difference in feature quantity representing the time-varying shape according to the present embodiment is small with respect to the difference in vibration level (peak value) with and without the noise signal. It shows that the influence is small.
  • the upper left stage and upper right stage in FIG. 8 are (a) a vibration signal waveform at the time of closing when there is no noise signal and (b) a noise signal being mixed, when the valve (solenoid valve) is in a closed state due to foreign matter mixing. It is a vibration signal at the time of occlusion.
  • the lower left column is (c) a vibration waveform when the valve is closed in a normal state when there is no noise signal.
  • the amplitude value is shifted in the negative direction, contrary to the example of FIG. Therefore, the peak value is higher than when there is no noise signal.
  • the lower right row in FIG. 8 is a difference between (d) each feature amount in the blockage failure state (upper left and upper right) and each feature amount in the normal state (lower left). If there is no noise signal, there is a difference between the normal state and the occlusion failure state for any feature value, but if there is a noise signal, the vibration level (peak value) is the difference between the normal state and the occlusion failure state. Is close to zero. That the difference is small means that it is difficult to distinguish between the occlusion failure state and the normal state.
  • the difference is not as small as in the case of the peak value. Note that the calculation of these feature amounts is performed in a section shorter than the time section displayed in (a) and (b) of FIG. From the above, by using not only the peak value but also the feature value representing the time-varying shape of the amplitude value according to the present embodiment, it is possible to diagnose the open / close failure robustly against the influence of the noise signal.
  • the feature amount output from the feature amount calculation unit 203 of the valve state diagnosis system of FIG. 2 and the normal signal model 205 stored in the storage medium 102 are read, and the abnormality degree calculation unit 204 calculates the degree of abnormality. .
  • FIG. 9 shows the process of creating the normal signal database 208 for learning the normal signal model 205.
  • the process of creating the normal signal database 208 may be performed when the user operates the control target device 110 and the valve state diagnosis system 100. Or you may carry out at the time of apparatus production. For the signal of the valve 111 that operates normally, the valve opening / closing section is cut out and the feature amount is calculated in the same manner as the processing so far. At this time, the noise signal suppression processing unit 202 is not necessary if driving of components other than the valve can be stopped. However, when a noise signal is mixed, the noise signal suppression processing unit 202 should be used as necessary. You can also.
  • valve ⁇ Operate the valve a sufficient number of times, collect a sufficient amount of valve signal features, and save it as a normal signal database 208.
  • the storage destination stores in the storage medium 102 if this processing is performed during operation of the apparatus. If it is performed at the time of production, a storage medium can be separately prepared for processing and stored there.
  • FIG. 10 shows processing for learning the normal signal model 205 in the present embodiment. This processing may also be performed at the time of device operation, or at the time of device production, similarly to the processing of the normal signal database 208.
  • the model learning unit 209 learns the normal signal model 205.
  • a model learning method a known technique such as normal distribution, mixed normal distribution, or 1-class support vector machine may be used.
  • the model learning unit 209 stores the learned normal signal model 208 in the storage medium 102.
  • the abnormality degree calculation unit 204 reads the feature amount output from the feature amount calculation unit 203 and the normal signal model 205 learned and stored in the storage medium 102, and calculates the degree of abnormality. For example, if the mixed normal distribution is used for the learning model, the anomaly can be transformed using an appropriate function such as inputting the likelihood for the mixed normal distribution into the sigmoid function or simply multiplying the coefficient. It is sufficient to use a known method such as
  • the state determination unit 206 reads the degree of abnormality output from the degree of abnormality calculation unit 204, and diagnoses the state of the valve based on the degree of abnormality.
  • the state determination unit 206 determines that the valve is normal if the degree of abnormality is equal to or less than the threshold Th1. If the degree of abnormality is greater than or equal to the threshold Th1, it is determined that there is an abnormality. At this time, the difference from the abnormality degree output at the time of the past N diagnoses is calculated, and if the difference in abnormality degree is equal to or greater than Th2, the abnormality degree is suddenly increased, and thus a sudden blockage failure state Judge as. If the difference in the degree of abnormality is equal to or less than Th2, the degree of abnormality gradually increases, so that it is determined as a blockage failure state due to aged deterioration.
  • the state determination unit 206 determines that the valve 111 becomes a definite abnormality due to deterioration over time. Even if it is not yes, it is determined that the degree of abnormality has increased to some extent, and it is determined that the replacement time of the valve 111 is approaching.
  • the result determined by the state determination unit 206 is output to the diagnosis result presentation unit 207.
  • the determination result is output to the diagnosis result presentation unit 207, and at the same time, a device stop command is output to the device control circuit 112, and the diagnosis target device 110 is stopped. It is also possible to make it.
  • FIG. 11 is a diagram illustrating an example of the user interface unit 106 of the valve state diagnosis system according to the present embodiment.
  • the user interface unit 106 includes a display panel 210, an overall waveform presentation unit 211 that shows an overall waveform, a discrimination target signal presentation unit 212 that presents a discrimination target signal, and discrimination information such as an abnormality degree and a feature amount. And a discrimination information presentation unit 213 that presents a discrimination result, and a discrimination result presentation unit 214 that presents a discrimination result, and an area for displaying each information output from each functional block from the AD conversion unit 105 to the status discrimination unit 206 ing.
  • the discrimination result presentation unit 214 corresponds to the diagnosis result presentation unit 207 shown in FIG. Only the determination result output by the state determination unit 206 may be displayed, but by presenting other information, the user can see the information to make the determination result more reliable.
  • an operation input unit 215 may be added to the display panel 210 so that the user can arbitrarily switch between displaying and hiding these pieces of information.
  • the whole waveform presentation unit 211 displays the signal observed by the sensor 104 converted into a digital signal by the AD conversion unit 105 as it is. By viewing this display, the user can visually confirm the overall operation around the valve.
  • the noise signal suppression processing unit 202 suppresses the noise signal and outputs the signal waveform cut out in the valve opening / closing section output from the valve opening / closing section cut-out unit 201 or the signal.
  • a signal is presented (FIG. 2 shows an example in which a signal waveform after noise signal suppression processing is displayed). By displaying this signal, the user can grasp the operation at the time of opening and closing the valve in more detail than looking at the entire waveform.
  • the discrimination information presentation unit 213 displays the opening / closing delay time output from the valve opening / closing section cutout unit 201, the value of each feature amount output from the feature amount calculation unit 203, and the degree of abnormality output from the abnormality degree calculation unit 204. . By viewing this information, the user can know the basis of the result of the valve state diagnosis system 100 diagnosing the valve 111.
  • the discrimination result presentation unit 214 displays the status discrimination result output from the status discrimination unit 206.
  • the displayed states are a complete stop state of the valve, a sudden opening / closing failure state, an opening / closing failure state due to aging deterioration, and a replacement time recommended state due to aging deterioration. As described above, when the peak value is not detected when the valve is opened and closed, it can be determined that the valve is completely stopped.
  • the user interface unit 106 may not include the operation input unit 215, but can be added.
  • the operation input unit 215 may use a touch panel or a button attached to the apparatus. If the user interface unit 106 is a monitor via another personal computer (PC) connected via a network, a mouse or a keyboard may be used. If an operation input part is added, it becomes possible to switch display / non-display of each feature amount or the like when the operation input part receives an input from the user. Further, when the user inputs the current time and the operation input unit 215 accepts the current time and stores it in the storage medium 102, the determination result is output to the determination result presenting unit 214 together with the state determination result. Displayed time can be displayed. As a result, the user can grasp when the abnormality has occurred in the valve.
  • the difference between the present embodiment and the first embodiment is only the processing contents in the feature amount calculation unit 203 in the system shown in FIG.
  • the feature amount calculation unit 203 reads the valve vibration signal or the acoustic signal, and calculates the feature amount that represents and represents the time-varying shape of the signal.
  • the signal is subjected to frequency analysis. Apply and calculate the feature quantity that represents the shape of the frequency spectrum.
  • FIG. 12 is a frequency spectrum obtained by performing frequency analysis on a vibration signal when a valve (solenoid valve) in a normal state and (b) a foreign substance is mixed is closed. Both frequency spectra when the valve is closed are shaped with a single peak. Since the valve vibration in the normal state has a time waveform having a sharp peak as shown in FIG. 5, the frequency spectrum has energy over a wide area as compared with the foreign substance mixed state. On the other hand, since the vibration of the valve in the foreign substance mixed state has a time waveform having a gradual peak, energy is concentrated in a lower frequency region than in the normal state.
  • a feature amount based on the degree of concentration of energy in a specific frequency band in the frequency spectrum is calculated, and the state is determined using this feature amount.
  • the feature amount expressing the degree of concentration for example, a sparse degree using a norm, a ratio of energy in a specific band to energy of the entire spectrum, and the like are known.
  • the sparseness has a high value when the spectrum energy is concentrated only in a specific frequency band and the energy is close to zero in other frequency bands.
  • known methods such as L0 norm, L1 / L2 norm ratio, and entropy can be used.
  • the energy ratio of the specific band to the energy of the entire spectrum for example, the ratio of the sum of the power and amplitude in the specific frequency band such as 0 to 1.5 kHz in FIG. 12 and the sum of the power and amplitude in the entire frequency band is calculated. Can be obtained.
  • the state of the valve is diagnosed using a feature value representing the spectral shape of the vibration signal or acoustic signal of the valve.
  • the noise signal has periodicity, the noise signal components are concentrated in a specific frequency band on the frequency spectrum, so if the frequency band of the noise signal is known in advance, that band is used to calculate the feature value. Processing such as not using it is possible. For this reason, there are cases where the diagnosis of the state can be performed more robustly against noise than when the feature amount calculated on the time waveform as in the first embodiment is used.
  • the present invention is not limited to the above-described embodiments, and includes various modifications.
  • the above-described embodiments have been described in detail for better understanding of the present invention, and are not necessarily limited to those having all the configurations described.
  • a part of the configuration of one embodiment can be replaced with the configuration of another embodiment, and the configuration of another embodiment can be added to the configuration of one embodiment.
  • DESCRIPTION OF SYMBOLS 100 Valve state diagnostic system 101 Central processing unit 102 Storage medium 103 Volatile memory 104 Sensor 105 AD conversion part 106 User interface part 107 Power supply 110 Diagnosis target apparatus 111 by Example 1 Valve 112 Apparatus control circuit 201 Valve opening / closing section cutout part 202 Noise Signal suppression processing unit 203 Feature amount calculation unit 204 Abnormality calculation unit 205 Normal signal model 206 State determination unit 207 Diagnosis result presentation unit 208 Normal signal database 209 Normal signal model 210 Display panel 211 Overall waveform presentation unit 212 Discrimination target signal presentation unit 213 Discrimination information presentation unit 214 Discrimination result presentation unit 215 Operation input unit 401 Peak 501 High peak 502 Low peak.

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)

Abstract

La présente invention aborde le problème de la fourniture d'un système de surveillance et de diagnostic de l'état d'une soupape d'une manière robuste contre l'effet du bruit. Le système de diagnostic d'état de soupape comprend un capteur (104) pour lire des informations de fonctionnement de soupape. Un signal généré lors d'un blocage de soupape est extrait par une unité d'extraction de section d'ouverture/fermeture de soupape (210) à l'aide d'un signal de référence correspondant à une commande d'ouverture/fermeture, et une quantité de caractéristiques représentant la forme de la variation temporelle du signal est calculée par une unité de calcul de quantité de caractéristiques (203). Un degré d'anomalie est calculé par une unité de calcul de degré d'anomalie (204) à l'aide de la quantité de caractéristiques et d'un paramètre de modèle pour un modèle de signal normal (205). Une unité de détermination d'état (206) détermine l'état de soupape en utilisant le degré d'anomalie, et présente un état d'arrêt de vanne complet, un défaut d'ouverture/fermeture brusque, un état d'ouverture/de fermeture défectueux en raison de la dégradation liée au vieillissement, un état de recommandation de période de remplacement dû au vieillissement, etc, jusqu'à une unité de présentation de résultat de diagnostic (207).
PCT/JP2015/053046 2014-03-25 2015-02-04 Système de diagnostic d'état de soupape WO2015146295A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2014-062396 2014-03-25
JP2014062396A JP2015185021A (ja) 2014-03-25 2014-03-25 弁状態診断システム

Publications (1)

Publication Number Publication Date
WO2015146295A1 true WO2015146295A1 (fr) 2015-10-01

Family

ID=54194834

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2015/053046 WO2015146295A1 (fr) 2014-03-25 2015-02-04 Système de diagnostic d'état de soupape

Country Status (2)

Country Link
JP (1) JP2015185021A (fr)
WO (1) WO2015146295A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6153145B1 (ja) * 2016-03-29 2017-06-28 巴バルブ株式会社 バルブ診断方法及びバルブ診断装置
US10413270B2 (en) 2016-11-15 2019-09-17 Canon Medical Systems Corporation Medical image diagnostic apparatus
US20210209871A1 (en) * 2020-01-06 2021-07-08 Hyundai Motor Company State diagnosis apparatus and method of moving system part

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7085370B2 (ja) * 2017-03-16 2022-06-16 株式会社リコー 診断装置、診断システム、診断方法およびプログラム
CN107728599B (zh) * 2017-09-01 2020-12-18 北京中燕信息技术有限公司 一种确定炼化装置阀门状态的方法和装置
JP6763910B2 (ja) * 2018-05-30 2020-09-30 横河電機株式会社 異常検出装置、異常検出方法、異常検出プログラム及び記録媒体
JP7294624B2 (ja) * 2018-07-31 2023-06-20 株式会社レクザム 眼科装置
CN110926798A (zh) * 2019-12-25 2020-03-27 北京航天测控技术有限公司 一种电磁阀开关状态判定方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63309824A (ja) * 1987-06-12 1988-12-16 Hitachi Ltd 機械の異常診断方法
JPH04296299A (ja) * 1991-03-26 1992-10-20 Hitachi Ltd スチームトラップの監視方法及び監視装置並びに診断方法及び診断装置並びにスチームトラップ製造ライン
JPH04337180A (ja) * 1991-05-15 1992-11-25 Toshiba Corp 電動弁診断装置
US5646600A (en) * 1995-01-12 1997-07-08 General Electric Company Instrument for detecting potential future failures of valves in critical control systems
JPH11282523A (ja) * 1998-03-26 1999-10-15 Osaka Gas Co Ltd プラントシステム
JP2002174549A (ja) * 2000-12-06 2002-06-21 Tomoe Tech Res Co 電動アクチュエータの制御装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3827928B2 (ja) * 2000-08-25 2006-09-27 Ｎｔｎ株式会社 機械部品の監視システム
JP3832365B2 (ja) * 2002-03-19 2006-10-11 横河電機株式会社 プロセス機器診断方法及び装置
JP4834580B2 (ja) * 2007-03-06 2011-12-14 株式会社東芝 プラント状態指標管理装置とその実現用コンピュータプログラム
JP5735383B2 (ja) * 2011-09-02 2015-06-17 アズビル株式会社 調節弁の異常診断方法および装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63309824A (ja) * 1987-06-12 1988-12-16 Hitachi Ltd 機械の異常診断方法
JPH04296299A (ja) * 1991-03-26 1992-10-20 Hitachi Ltd スチームトラップの監視方法及び監視装置並びに診断方法及び診断装置並びにスチームトラップ製造ライン
JPH04337180A (ja) * 1991-05-15 1992-11-25 Toshiba Corp 電動弁診断装置
US5646600A (en) * 1995-01-12 1997-07-08 General Electric Company Instrument for detecting potential future failures of valves in critical control systems
JPH11282523A (ja) * 1998-03-26 1999-10-15 Osaka Gas Co Ltd プラントシステム
JP2002174549A (ja) * 2000-12-06 2002-06-21 Tomoe Tech Res Co 電動アクチュエータの制御装置

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6153145B1 (ja) * 2016-03-29 2017-06-28 巴バルブ株式会社 バルブ診断方法及びバルブ診断装置
JP2017181203A (ja) * 2016-03-29 2017-10-05 巴バルブ株式会社 バルブ診断方法及びバルブ診断装置
WO2017169849A1 (fr) * 2016-03-29 2017-10-05 巴バルブ株式会社 Procédé de diagnostic de vanne et dispositif de diagnostic de vanne
CN108885154A (zh) * 2016-03-29 2018-11-23 巴阀门株式会社 阀门诊断方法及阀门诊断装置
KR20190007418A (ko) * 2016-03-29 2019-01-22 토모에 밸브 가부시키가이샤 밸브 진단 방법 및 밸브 진단 장치
KR102118818B1 (ko) 2016-03-29 2020-06-03 토모에 밸브 가부시키가이샤 밸브 진단 방법 및 밸브 진단 장치
US10920907B2 (en) 2016-03-29 2021-02-16 Tomoe Valve Co., Ltd. Valve diagnosis method and valve diagnosis device
US10413270B2 (en) 2016-11-15 2019-09-17 Canon Medical Systems Corporation Medical image diagnostic apparatus
US20210209871A1 (en) * 2020-01-06 2021-07-08 Hyundai Motor Company State diagnosis apparatus and method of moving system part
US11741761B2 (en) * 2020-01-06 2023-08-29 Hyundai Motor Company State diagnosis apparatus and method of moving system part

Also Published As

Publication number Publication date
JP2015185021A (ja) 2015-10-22

Similar Documents

Publication Publication Date Title
WO2015146295A1 (fr) Système de diagnostic d'état de soupape
KR101539896B1 (ko) 유도전동기 오류 진단 방법
JP6882397B2 (ja) 異音等検出システム、装置、方法及びプログラム
JP6200833B2 (ja) プラントと制御装置の診断装置
CN105675306A (zh) 一种汽车自检测方法及检测系统
CN117826715B (zh) 一种智能设备监控与预警系统
JP2015219078A (ja) 弁状態診断システムおよび弁状態診断方法
KR101129466B1 (ko) 웨이블렛 스레스홀딩 함수와 4차 모멘트를 이용한 회전기계의 상태 진단 방법
WO2008040019A3 (fr) Prévention d'une situation anormale dans un élément de chauffage de dispositif de cokéfaction
EP3910437B1 (fr) Appareil de surveillance, procédé de surveillance et support lisible sur ordinateur
JP2012018066A (ja) 異常検査装置
KR101347606B1 (ko) 뇌전도를 이용한 로봇기반 자폐진단 장치 및 그 방법
JPWO2015011791A1 (ja) 異常検知評価システム
Wegerich et al. Nonparametric modeling of vibration signal features for equipment health monitoring
JP2018189522A (ja) 設備故障の予兆診断方法
Wegerich Similarity‐based modeling of vibration features for fault detection and identification
JP2672576B2 (ja) プラント・機器の診断支援システム
JP2005091103A (ja) 歯車診断方法及び歯車診断装置
CN117928928A (zh) 一种调节阀开关动作的测试系统及方法
JPH04296299A (ja) スチームトラップの監視方法及び監視装置並びに診断方法及び診断装置並びにスチームトラップ製造ライン
JP2016113260A (ja) エレベーターの異常音診断装置
CN109521100A (zh) 集成的声发射换能器装置和方法
WO2017212645A1 (fr) Dispositif de diagnostic de palier et procédé de diagnostic de palier, ainsi que machine rotative et son procédé de maintenance
JP2018092403A (ja) 診断装置、および、診断方法
JPWO2020204043A1 (ja) 高炉の異常判定装置、高炉の異常判定方法、及び高炉の操業方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15767993

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15767993

Country of ref document: EP

Kind code of ref document: A1