WO2002103297A1 - Enregistreur de signaux a fonction de reconnaissance d'etat - Google Patents
Enregistreur de signaux a fonction de reconnaissance d'etat Download PDFInfo
- Publication number
- WO2002103297A1 WO2002103297A1 PCT/JP2002/005760 JP0205760W WO02103297A1 WO 2002103297 A1 WO2002103297 A1 WO 2002103297A1 JP 0205760 W JP0205760 W JP 0205760W WO 02103297 A1 WO02103297 A1 WO 02103297A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- status
- state
- feature parameters
- signal
- normal
- Prior art date
Links
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
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0275—Fault isolation and identification, e.g. classify fault; estimate cause or root of failure
- G05B23/0281—Quantitative, e.g. mathematical distance; Clustering; Neural networks; Statistical analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D1/00—Measuring arrangements giving results other than momentary value of variable, of general application
- G01D1/18—Measuring arrangements giving results other than momentary value of variable, of general application with arrangements for signalling that a predetermined value of an unspecified parameter has been exceeded
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D9/00—Recording measured values
- G01D9/005—Solid-state data loggers
Definitions
- the present invention relates to a state determination method and a signal recording device.
- a state determination method when recording a signal for a long period of time to monitor the state of an object in equipment diagnosis, medical diagnosis, earthquake monitoring, etc., it is determined that there is no abnormality or state change.
- the feature parameter that indicates the abnormality or state change and the raw signal are recorded simultaneously. It is suitable to be applied to status monitoring, status change trend management, status prediction and status change investigation. 2.
- the main signal collection method of conventional signals is
- feature parameters in the high, medium, and low frequency regions are calculated with respect to a signal measured by a sensor, and the feature parameters are set to a normal probability density.
- the distribution ⁇ Convert to normal feature parameter j, determine the state judgment criterion of the existence and dimensionless feature parameter and normal feature parameter by probability test, confidence interval and possibility theory, and integrate the judgment result of existence-dimensionless feature parameter
- the state is determined, and it is determined whether to record only the special parameters or the characteristic parameters and the raw signal of the required time length at the same time according to the degree of the state change.
- the required recording media capacity is much smaller than that of continuous raw signal recording, and long-term recording and condition monitoring are possible.
- the characteristic parameters that can be used for the signal recording device are the characteristic parameters in the time domain and the parameters in the frequency domain ((1) Peng CHEN, Masami NASU, Toshio TOYOTA: Self-reorganization of symptom parameters in frequency domain for failure diagnosis by genetic algorithms) , Journal of Intelligent & Fuzzy System, IOS Press, Vol. 6 Nol. 1, pp. 27-37, 1998.) and characteristic parameters in the time-frequency domain ((2) Peng CHEN, Toshio TOYOTA, Masatoshi TANIGUTI, Feng FANG) , and Tomoya NIHO: Failure Diagnosis Method for Machinery in Unsteady Operating Condition by Instantaneous Power Spectrum and Genetic Algorithms, Proc. of Fourth International Conference on Knowledge-Based Intelligent Engineering System & Allied Technologies (KES2000), pp.640-643, 2000. ), But here is an example of the time domain feature parameters.
- the extracted signal X (t) is normalized by the following equation.
- X is the discrete value of X (t) after AD conversion
- S are the mean and standard deviation of X, respectively.
- ⁇ ⁇ is the standard deviation of the maximum value.
- CJ L are the mean and standard deviation of the local minimum (valley), respectively.
- Equations (1) to (10) are conventional feature parameters, but in order to easily perform high-speed calculations by numerical calculation, “intersection feature parameter overnight” is newly added as shown in equations (11) to (16). To suggest.
- X i ⁇ —h a and h can be set arbitrarily.
- k 0.5, 1, 2.
- ⁇ , ⁇ h, h and p hl are the same as in equation (13).
- the measured signal is normalized as shown in equation (0).
- ⁇ is the peak value (maximum value) of the absolute value of the signal
- ⁇ ⁇ is the total number of peak values
- the recorded primitive feature parameters are denoted by p.
- ⁇ ' follows a normal distribution or its probability density.
- p follows a normal distribution or its probability density.
- p is converted to a random variable p having a normal distribution by using the following method for the recorded feature parameter ⁇ ′.
- the probability density distribution of the standard normal distribution is ⁇ ( ⁇ ,)
- the cumulative probability distribution function of the standard normal distribution is ⁇ ( ⁇ ,).
- the probability density function of is also called “frequency distribution function” or “His and Gram”, but is described below as “probability density distribution function”.
- the average value ⁇ transformed by the normal distribution is obtained by the following equation.
- ⁇ ⁇ 1 represents the inverse function of ⁇ . ⁇ . Is the standard deviation transformed by the normal distribution, and is calculated by the following equation. 0, ⁇ 0 ⁇ ))))))))))))))))))))))))))))))))))))))))))))))))))))))) (22)
- the characteristic parameter p ' ik determined at a time other than the reference time is obtained.
- State determination and state prediction are performed using ⁇ «. Direct variable conversion method
- the probability density function f k (p ' ik ) and the cumulative probability distribution function R (p' ik ) of the feature parameters p 'and k obtained from the data measured at any time are calculated.
- the average value ik converted to the normal distribution is obtained by the following equation.
- ⁇ ik is obtained by the following equation. ⁇ ": ⁇ ⁇ X))) (2 5)
- the feature parameter p is transformed into a normal random variable by Equations (21), (23) and (24).
- ⁇ , Xik , * and // ikj are called “normal feature parameters” and are unified by ⁇ . 3.
- p, k and p, y be the values of the normal feature parameter p, obtained in state k and state y, respectively.
- i l to M (M is the total number of normal feature parameters to be used).
- the average value and standard deviation are calculated by the following formulas. I do.
- the degree of state change from state y to state k is determined by checking whether or not equation (28) or equation (29) is satisfied.
- Table 1 shows an example of determining the degree of state change based on the significance level a. In the case of equipment diagnosis, if state k is normal, state y is normal, cautionary, or dangerous, as shown in Table 1. (A 2 ) and “danger” (a 3 ). Table 1. Example of judging degree of state change based on significance level
- tricha (Jl) is the percentage point of the probability density function of the t distribution with J-1 degrees of freedom for the lower probability ⁇ / 2, where S and n are the standard values of p and u obtained from the data. Is the deviation.
- the 99% confidence interval for is approximately 10 when J ⁇ 50, approximately
- the confidence interval of obtained from the measured data can be obtained by the following equation.
- S, k is the standard deviation of p, k obtained from the day.
- the probability distribution function P k ( ⁇ ,) is obtained from the probability density function f k ( ⁇ ,) of p, using equation (36).
- the probability distribution functions (p c! ( Pi ) and ( p)) and the likelihood distribution functions (p (11 ( Pi ) and p (i2 (p,))) of “state change is large” are determined as shown in Fig. 2.
- the probability distribution function of the normal state is P k ( Pi ) and the attention state
- the possibilities of “normal”, “caution”, and “danger” are displayed as shown in Fig. 3. In addition, if it is judged as “danger”, an alarm can be issued.
- the state can also be determined by integrating several feature parameters into one feature parameter.
- the integration method include a state discrimination method using a genetic algorithm ((8) International application: No.PCT / JP00 / 03006, application number: 2000-618695), a neural network, and a principal component analysis method ((9) Otsu , Kurita, Sekida: Pattern Recognition, Asakura Shoten (1996), (10) Amari: Mathematics of Neural Networks, Industrial Books (1978), (9) K. Fukunaga: Introduction to Statistical Pattern Recognition, Academic Press (1992), (11) Toyoda Toshio: Research report on the practical application of the latest equipment diagnostic technology, Japan Plant Maintenance Association, (1999) .
- the dimensional feature parameters represent the magnitude of the signal waveform.
- the dimensionless feature parameter represents the shape characteristics of the signal waveform. For example, in the case of equipment diagnosis, even in a normal state, the dimensional feature parameters fluctuate along with a change in rotation speed and a change in load. It is more effective to determine the state change by integrating dimensional special parameters and non-dimensional parameters.
- k is set to 1 as a default, but it can be adjusted. For example, if you want to increase the sensitivity in increments of 0.2, decrease k by 0.2, and conversely, if you want to decrease sensitivity, increase k by 0.2.
- the measurement signal in the low frequency range is the vibration speed
- the measurement signal in the middle and high ranges is the acceleration.
- Figures 4, 5, and 6 show the criteria for rotating machinery and equipment, but the criteria for other measurement objects must be set in advance as shown in Figures 4, 5, and 6.
- the criterion for determining the dimensionless feature parameters is a statistical test as shown in Table 1, or a confidence interval such as the formulas (3 3), (3 4) and (3 5), or a figure. It is determined by the likelihood distribution function as shown in Fig.2.
- FIG. 7 shows the integration of the criterion between the dimensional feature parameter and the dimensionless parameter. This figure is explained as follows.
- the determination result of the feature parameter that has been determined to be “large in state change” has priority. For example, p, when performing equipment diagnosis in ⁇ p 3, low, medium, following assay results in a high frequency region is obtained.
- Figure 8 shows an example of the display of the judgment result based on the presence and absence of dimensionless feature parameters and the judgment result (status lamp) obtained by integrating the judgment criteria.
- the judgment result of the dimensionless feature parameter indicates the probability of each state or the degree of possibility.
- Figures 9 and 10 show examples of trend management charts for state changes due to regular and dimensionless feature parameters.
- Fig. 11 shows an example of a trend management chart of state changes over time for dimensional feature parameters. Note that k in FIGS. 9 and 11 is the same as k in FIG.
- the signal recording system can be configured by separating the signal recording device and the external computer. Wear. As described above, by reducing the calculation processing load of the signal recording device, the signal recording device can be manufactured in a compact form, and can be easily installed on site.
- the external computer performs data communication with the signal recording device to set measurement conditions, create judgment criteria, manage status trends, perform detailed diagnosis and analyze causes.
- Figure 14 shows an example of a time-series signal measured by a speed sensor attached to the shaft of a rotating machine. This machine changes from a normal state to an unbalanced state.
- the dimension feature parameters ( ⁇ ) are used.
- Figure 1 5 is a judgment result of the dimensionless characteristic parameter Isseki (p, ⁇ p 5)
- Figure 1 6 shows the determination result of the dimensionless characteristic parameter Isseki ( ⁇ ). Based on these determination results, ⁇ 6 is more sensitive to state determination than other non-dimensional feature parameters, so as shown in Figure 16, the determination result of ⁇ 6 is Result.
- Figure 17 shows the results of determining the dimensional feature parameters.
- Figure 18 shows the final judgment result obtained by integrating the judgment results of the existence and dimensionless feature parameters.
- the degree of status change from normal status is indicated by a status lamp, but the degree of status change from the previous status is a criterion for determining whether or not to record a raw signal. For example, record the raw waveforms of “Measurement 1 (normal)”, “Measurement 3 (state change is in progress)”, and “Measurement 7 (state change is large) J” by the comprehensive judgment in Figure 18. I will.
- Fig. 19 shows an example of a circuit diagram of the signal recording device.
- 1 is a sensor
- 2 is a charge amplifier
- 3 is a filter module
- 4 is a 1-chip CPU
- 5 is a result display
- 6 is a RAM for data
- 7 is an AD converter
- 8 is a DC port
- 9 is SCI
- 10 is CPU
- 11 is flash ROM
- 12 is an external computer.
- This signal recording device can be designed for multiple channels.
- the external computer is used for setting the recording conditions of the signal recording device, setting the condition judgment criteria, reading the recorded feature parameters and raw signals, managing the trend of state changes, and analyzing the causes.
- the present invention monitors the state of an object for a long period of time in equipment diagnosis, medical diagnosis, earthquake monitoring, etc., and when it is determined that there is no remarkable abnormality or state change, there is a dimensional dimensionless parameter reflecting the state.
- the characteristic parameter indicating the abnormality or the state change and the raw signal are recorded at the same time, and the trend analysis and cause analysis of the state change and And help determine the cause.
- the signal recording medium is less wasted, and characteristic parameters indicating a state change and raw signals can be recorded in a timely manner.
- the recorded feature parameters are converted into normal feature parameters that follow the normal probability density distribution, and the state judgment criteria for the dimensional and non-dimensional feature parameters and the normal feature parameters are determined by a probability test, confidence interval, and possibility. It is determined by theory, and state judgment is performed by integrating the judgment results of the presence and absence dimension feature parameters. In addition, if necessary, it manages the trend of state change, predicts the state and analyzes the cause of the state change, displays the state at the time of measurement, and issues an alarm when there is a danger. 7. Brief description of figures
- FIG. 1 is a graph showing an example of the probability distribution function.
- FIG. 2 is a graph showing determination of a state change by a possibility function.
- FIG. 3 is an explanatory diagram showing a display example of the possibility.
- FIG. 4 is a graph showing criteria for determining dimensional feature parameters in a low frequency region.
- FIG. 5 is a graph showing a criterion for determining a dimensional feature parameter in the middle frequency region.
- FIG. 6 is a graph showing criteria for determining dimensional feature parameters in a high frequency region.
- FIG. 7 is an explanatory diagram showing the integration of the criterion of the dimensional feature parameter and the dimensionless feature parameter.
- FIG. 8 is an explanatory diagram showing a display example of the determination result.
- FIG. 9 is a graph showing an example of a trend management chart of a state change by a normal dimensional feature parameter.
- FIG. 10 is a graph showing an example of a tendency management chart of a state change due to normal dimensionless feature parameters.
- FIG. 11 is a graph showing an example of a trend management chart of a state change by a dimensional feature parameter.
- FIG. 12 is a flowchart showing the processing flow of the signal recording system.
- FIG. 13 is a flowchart showing a signal recording processing flow in which an external computer and a signal recording / recording device are separated.
- FIG. 14 is a graph showing an example of the measured raw signal.
- Figure 1 5 is an explanatory view showing a determination example of a result of dimensionless characteristic parameter Isseki (p, ⁇ p 5).
- FIG. 16 is an explanatory diagram showing an example of the determination result of the dimensionless feature parameter.
- Figure 1 7 is an explanatory view showing a determination example of a result of chromatic dimensional feature parameters Isseki (2 3).
- FIG. 18 is an explanatory diagram showing an example of a judgment result obtained by integrating the dimensionless feature parameters.
- FIG. 19 is a circuit diagram showing an example of the circuit of the signal recording device, and the symbols in the figure are as follows. 1 sensor, 2 charge amplifier, 3 fill module, 4 1-chip CPU, 5 result display, 6 data RAM 7 AD converter, 8 DC port, 9 SCI (serial communication ace), 10 CPU , 1 1 Flash ROM, 1 2 Computer
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Algebra (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Automation & Control Theory (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
- Recording Measured Values (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Description
Claims
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP02738648A EP1411326A4 (en) | 2001-06-14 | 2002-06-10 | SIGNAL RECORDER WITH STATE RECOGNITION FUNCTION |
US10/480,454 US20040193387A1 (en) | 2001-06-14 | 2002-06-10 | Signal recorder with status recognizing function |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2001180702A JP2002372440A (ja) | 2001-06-14 | 2001-06-14 | 状態判定法並びに状態判定装置及び状態判定機能を備えた信号収録装置 |
JP2001-180702 | 2001-06-14 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2002103297A1 true WO2002103297A1 (fr) | 2002-12-27 |
Family
ID=19021079
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2002/005760 WO2002103297A1 (fr) | 2001-06-14 | 2002-06-10 | Enregistreur de signaux a fonction de reconnaissance d'etat |
Country Status (5)
Country | Link |
---|---|
US (1) | US20040193387A1 (ja) |
EP (1) | EP1411326A4 (ja) |
JP (1) | JP2002372440A (ja) |
CN (1) | CN100351610C (ja) |
WO (1) | WO2002103297A1 (ja) |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100386603C (zh) * | 2003-01-10 | 2008-05-07 | 江苏千鹏诊断工程有限公司 | 特征判定方法和特征预测方法 |
WO2004109310A1 (ja) * | 2003-06-06 | 2004-12-16 | Mitsubishi Denki Kabushiki Kaisha | 回転機の定数測定装置 |
JP4369321B2 (ja) * | 2004-07-30 | 2009-11-18 | 株式会社高田工業所 | 流体回転機械の診断方法 |
JP4369320B2 (ja) * | 2004-07-30 | 2009-11-18 | 株式会社高田工業所 | 回転機械の診断方法 |
ES2331576T3 (es) * | 2005-02-15 | 2010-01-08 | Abb Research Ltd. | Dispositivo de diagnostico para un sistema de control de proceso. |
JP4049331B2 (ja) * | 2005-08-19 | 2008-02-20 | 独立行政法人科学技術振興機構 | 診断対象物の評価方法および評価装置 |
JP5017678B2 (ja) * | 2005-08-31 | 2012-09-05 | 鵬 陳山 | 信号検査方法および信号検査モジュール |
WO2009075649A1 (en) | 2007-12-11 | 2009-06-18 | Vestas Wind Systems A/S | System and method for detecting performance |
CN101252626B (zh) * | 2008-02-29 | 2011-05-11 | 四川长虹电器股份有限公司 | 基于ip电话终端的目标用户在线状态指示方法 |
JP2010071837A (ja) * | 2008-09-19 | 2010-04-02 | Yokogawa Electric Corp | ペーパレスレコーダ |
US8793717B2 (en) * | 2008-10-31 | 2014-07-29 | The Nielsen Company (Us), Llc | Probabilistic methods and apparatus to determine the state of a media device |
CN102513650B (zh) * | 2011-11-23 | 2014-10-08 | 华南理工大学 | 一种噪声、相关、时耗三因素耦合维归约方法 |
US9692535B2 (en) | 2012-02-20 | 2017-06-27 | The Nielsen Company (Us), Llc | Methods and apparatus for automatic TV on/off detection |
JP6085862B2 (ja) * | 2012-10-10 | 2017-03-01 | 陳山 鵬 | マルチ・コンディション・モニターを用いた状態監視方法および状態監視装置システム |
CA2948193A1 (en) | 2014-05-15 | 2015-11-19 | Emerson Electric Co. | Hvac system air filter diagnostics and monitoring |
CN106461252B (zh) * | 2014-05-15 | 2019-07-16 | 艾默生电气公司 | 加热、通风或空气调节系统空气过滤器诊断和监视 |
US9924224B2 (en) | 2015-04-03 | 2018-03-20 | The Nielsen Company (Us), Llc | Methods and apparatus to determine a state of a media presentation device |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS6267411A (ja) * | 1985-09-20 | 1987-03-27 | Toshiba Corp | 補機監視システム |
JPH0778022A (ja) * | 1993-06-30 | 1995-03-20 | Toshiba Corp | 構造部品の劣化・損傷予測装置 |
JPH07280603A (ja) * | 1994-04-14 | 1995-10-27 | Shikoku Electric Power Co Inc | 機械の異常判定方法 |
JPH08320726A (ja) * | 1995-05-24 | 1996-12-03 | Hitachi Ltd | 制御システムの診断・解析方法および装置 |
JPH0954613A (ja) * | 1995-08-11 | 1997-02-25 | Toshiba Corp | プラント設備監視装置 |
US5982934A (en) * | 1992-06-30 | 1999-11-09 | Texas Instruments Incorporated | System and method for distinguishing objects |
JP2000259222A (ja) * | 1999-03-04 | 2000-09-22 | Hitachi Ltd | 機器監視・予防保全システム |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1100310C (zh) * | 1994-12-19 | 2003-01-29 | 北京唐智科技发展有限公司 | 同类、有序动信息(组)群各信息源时域样本的跟踪采集 |
JPH08230726A (ja) * | 1995-02-28 | 1996-09-10 | Mitsubishi Motors Corp | トラック |
US5710723A (en) * | 1995-04-05 | 1998-01-20 | Dayton T. Brown | Method and apparatus for performing pre-emptive maintenance on operating equipment |
US5847658A (en) * | 1995-08-15 | 1998-12-08 | Omron Corporation | Vibration monitor and monitoring method |
US6092058A (en) * | 1998-01-08 | 2000-07-18 | The United States Of America As Represented By The Secretary Of The Army | Automatic aiding of human cognitive functions with computerized displays |
US6122959A (en) * | 1998-01-14 | 2000-09-26 | Instrumented Sensor Technology, Inc. | Method and apparatus for recording physical variables of transient acceleration events |
DE19840872A1 (de) * | 1998-09-02 | 2000-03-23 | Daimler Chrysler Ag | Verfahren zur probabilistischen Schätzung gestörter Meßwerte |
US6192325B1 (en) * | 1998-09-15 | 2001-02-20 | Csi Technology, Inc. | Method and apparatus for establishing a predictive maintenance database |
GB2358253B8 (en) * | 1999-05-12 | 2011-08-03 | Kyushu Kyohan Company Ltd | Signal identification device using genetic algorithm and on-line identification system |
-
2001
- 2001-06-14 JP JP2001180702A patent/JP2002372440A/ja active Pending
-
2002
- 2002-06-10 WO PCT/JP2002/005760 patent/WO2002103297A1/ja not_active Application Discontinuation
- 2002-06-10 US US10/480,454 patent/US20040193387A1/en not_active Abandoned
- 2002-06-10 EP EP02738648A patent/EP1411326A4/en not_active Withdrawn
- 2002-06-10 CN CNB028119290A patent/CN100351610C/zh not_active Expired - Fee Related
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS6267411A (ja) * | 1985-09-20 | 1987-03-27 | Toshiba Corp | 補機監視システム |
US5982934A (en) * | 1992-06-30 | 1999-11-09 | Texas Instruments Incorporated | System and method for distinguishing objects |
JPH0778022A (ja) * | 1993-06-30 | 1995-03-20 | Toshiba Corp | 構造部品の劣化・損傷予測装置 |
JPH07280603A (ja) * | 1994-04-14 | 1995-10-27 | Shikoku Electric Power Co Inc | 機械の異常判定方法 |
JPH08320726A (ja) * | 1995-05-24 | 1996-12-03 | Hitachi Ltd | 制御システムの診断・解析方法および装置 |
JPH0954613A (ja) * | 1995-08-11 | 1997-02-25 | Toshiba Corp | プラント設備監視装置 |
JP2000259222A (ja) * | 1999-03-04 | 2000-09-22 | Hitachi Ltd | 機器監視・予防保全システム |
Non-Patent Citations (1)
Title |
---|
See also references of EP1411326A4 * |
Also Published As
Publication number | Publication date |
---|---|
CN1516807A (zh) | 2004-07-28 |
CN100351610C (zh) | 2007-11-28 |
EP1411326A1 (en) | 2004-04-21 |
JP2002372440A (ja) | 2002-12-26 |
EP1411326A4 (en) | 2004-11-10 |
US20040193387A1 (en) | 2004-09-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2002103297A1 (fr) | Enregistreur de signaux a fonction de reconnaissance d'etat | |
Kadri et al. | Seasonal ARMA-based SPC charts for anomaly detection: Application to emergency department systems | |
Sohn et al. | Structural health monitoring using statistical pattern recognition techniques | |
US7496798B2 (en) | Data-centric monitoring method | |
EP2008161B1 (en) | Process monitoring technique and related actions | |
JP4046309B2 (ja) | プラント監視装置 | |
JP4480019B2 (ja) | 製油所監視システム | |
CN105320108A (zh) | 工业噪声监视系统 | |
US9009001B2 (en) | Monitoring for invalid data from field instruments | |
CA2253931A1 (en) | Apparatus and method for monitoring a system | |
KR20130065621A (ko) | 주기적 구동계의 이상 검지 장치, 주기적 구동계를 갖는 처리 장치, 주기적 구동계의 이상 검지 방법 및 컴퓨터 프로그램 | |
CN112272763A (zh) | 异常探测装置、异常探测方法以及异常探测程序 | |
JP6714498B2 (ja) | 設備診断装置及び設備診断方法 | |
Rezaiee-Pajand et al. | An iterative order determination method for time-series modeling in structural health monitoring | |
WO2019087508A1 (ja) | 監視対象選定装置、監視対象選定方法、およびプログラム | |
JPWO2004068078A1 (ja) | 状態判定方法と状態予測方法及び装置 | |
JP3400821B2 (ja) | データ自動監視システム | |
EP0881467A1 (en) | Method of detecting abnormality and abnormality detection system | |
US20140350873A1 (en) | Method for generating a signal indicating an oscillation in an electrical energy supply network | |
US11232649B2 (en) | Method and system for automation, safety and reliable operation performance assessment | |
JP2003029818A (ja) | 故障診断システム及び故障診断プログラム | |
JP2010211440A (ja) | 異常予測装置、異常予測システム、異常予測方法、及びプログラム | |
CN115146895A (zh) | 机械系统的健康评估 | |
JP2008070292A (ja) | 渦流量計の詰まり予知診断方法 | |
Wu et al. | Stress wave analysis based prognostic health management |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): CN US |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWE | Wipo information: entry into national phase |
Ref document number: 10480454 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 028119290 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2002738648 Country of ref document: EP |
|
WWP | Wipo information: published in national office |
Ref document number: 2002738648 Country of ref document: EP |
|
WWW | Wipo information: withdrawn in national office |
Ref document number: 2002738648 Country of ref document: EP |