WO2015045319A1 - 情報処理装置、及び、分析方法 - Google Patents
情報処理装置、及び、分析方法 Download PDFInfo
- Publication number
- WO2015045319A1 WO2015045319A1 PCT/JP2014/004707 JP2014004707W WO2015045319A1 WO 2015045319 A1 WO2015045319 A1 WO 2015045319A1 JP 2014004707 W JP2014004707 W JP 2014004707W WO 2015045319 A1 WO2015045319 A1 WO 2015045319A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- metric
- time series
- analysis
- unit
- correlation
- Prior art date
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
- G05B23/0243—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 model based detection method, e.g. first-principles knowledge model
-
- 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
- G01D3/00—Indicating or recording apparatus with provision for the special purposes referred to in the subgroups
- G01D3/028—Indicating or recording apparatus with provision for the special purposes referred to in the subgroups mitigating undesired influences, e.g. temperature, pressure
- G01D3/032—Indicating or recording apparatus with provision for the special purposes referred to in the subgroups mitigating undesired influences, e.g. temperature, pressure affecting incoming signal, e.g. by averaging; gating undesired signals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Definitions
- the present invention relates to an information processing apparatus and an analysis method.
- Analyzing devices that compare time series of measured values (metric values) of sensors and the like in a system to be analyzed (target system) and analyze the state of the target system are known.
- an analysis apparatus using a correlation model of a target system is described in Patent Document 1.
- the operation management device described in Patent Literature 1 determines a correlation function indicating a correlation between sensors at normal time by a system identification method based on a time series of measurement values of a plurality of sensors and the like of the target system, Generate a correlation model of the target system. Then, the operation management apparatus detects the destruction of the correlation (correlation destruction) using the generated correlation model, and determines the failure factor of the target system.
- a large time lag may occur between the measurement values of different sensors depending on the target system, compared to the measurement value measurement interval.
- the target system is a bridge and the sensor is a vibration sensor installed on the bridge.
- the vibration of the vehicle passing through the bridge is caused by the moving vehicle approaching each sensor in addition to the small time lag caused by the vibration transmitted through the steel material constituting the bridge.
- the target system is an air conditioner and the sensor is a current sensor and a surrounding temperature sensor, the temperature changes with a delay with respect to a change in the state of the air conditioner.
- the operation management apparatus of Patent Document 1 determines a correlation function as shown in Equation 1 between sensors in the analysis of the target system.
- Equation 1 X (t) and Y (t) are sensor measurement values that are the input and output of the correlation function at time t, respectively.
- Operation management apparatus each of the sensors of the plurality of sensors pairs, coefficients A 1, A 2 in the equation (1), ..., A N, B 1 , B 2, ..., determining the B M.
- the values of N and M are input in advance by a user or the like, for example. Then, the operation management apparatus detects correlation destruction between sensors using the determined correlation function.
- An object of the present invention is to provide an information processing apparatus and an analysis method capable of solving the above-described problems and preventing a decrease in analysis accuracy of a target system even when a large time lag exists between metrics of the target system. It is to be.
- An information processing apparatus includes a processing unit that compares and analyzes values of a first metric and a second metric in a system to be analyzed, and a comparison between the first metric and the second metric Pre-processing means for specifying the temporal correspondence of each use data in the analysis.
- the analysis method specifies a temporal correspondence relationship between each use data in the comparative analysis between the first metric and the second metric in the analysis target system, and the first metric and the first metric Compare and analyze the value with the metric of 2.
- the computer-readable recording medium specifies a temporal correspondence relationship between each use data in the comparative analysis between the first metric and the second metric in the analysis target system.
- a program for executing processing for comparing and analyzing values of the first metric and the second metric is stored.
- the effect of the present invention is to prevent a decrease in the analysis accuracy of the target system even when a large time lag exists between the metrics of the target system.
- FIG. 2 is a block diagram showing the configuration of the analysis system in the first embodiment of the present invention.
- the analysis system includes an analysis apparatus 100 and a target system 200 that is a system to be analyzed.
- the analysis apparatus 100 and the target system 200 are communicably connected via a network or the like.
- the analysis apparatus 100 is an embodiment of the information processing apparatus of the present invention.
- the target system 200 is various systems in which sensors for monitoring the state are arranged.
- the target system 200 is a structure such as a building or a bridge in which vibration sensors, temperature sensors, and the like for deterioration diagnosis are arranged.
- the target system 200 may be a plant such as a manufacturing plant or a power plant in which a temperature sensor, a flow rate sensor, and the like for monitoring an operating state are arranged.
- the target system 200 may be a moving body such as a vehicle, a ship, and an aircraft in which measuring devices such as various sensors for monitoring the driving state and a sequencer are incorporated.
- the target system 200 is not limited to a system using physical sensors as described above, and may be a computer system that measures performance information for operation management.
- the target system 200 may be a system in which an environmental sensor that collects power, temperature, and the like at the same time as the performance information is arranged in such a computer system.
- each sensor or each performance item measured in the target system 200 is called a metric.
- the metric corresponds to an “element” that is a generation target of the correlation model in Patent Document 1.
- the analysis apparatus 100 analyzes the state of the target system 200 based on the time series of metric measurement values collected from the target system 200.
- the analysis apparatus 100 includes a data collection unit 101, a data storage unit 111, a preprocessing unit 130, a processing unit 140, a dialogue unit 106, and a countermeasure execution unit 107.
- the data collection unit 101 collects measurement values of each metric such as measurement values detected by each sensor from the target system 200 at a predetermined collection interval.
- the data storage unit 111 stores a time series of metric measurement values collected by the data collection unit 101 as time series data 121.
- FIG. 5 is a diagram showing an example of the time-series data 121 in the first embodiment of the present invention.
- the time series data 121 includes a time series of measurement values collected every 1 ms for each of the sensors 1, 2,.
- the preprocessing unit 130 identifies temporal correspondence between metric values.
- the preprocessing unit 130 specifies the time lag of the time series change of the other metric with respect to the time series change of one metric as the temporal correspondence.
- the preprocessing unit 130 includes a time lag detection unit 102 and a time lag storage unit 112.
- the time lag detection unit 102 generates time lag information 122 based on the time series data 121 stored in the data storage unit 111.
- the time lag information 122 indicates the time lag of each pair of metrics among a plurality of metrics.
- the time lag of a metric pair causes a similar time series change to the other metric (following metric) with respect to the time series change of one metric (preceding metric) of the metric pair. Is the time difference between the time series changes.
- the time lag may be an approximate value of the time difference.
- the time lag is detected by comparing a series of time-series change patterns for a predetermined length of a metric (a period composed of a plurality of monitoring intervals). Therefore, a value that is an integral multiple of the period length for extracting the time-series change pattern is used as the time lag value.
- FIG. 6 is a diagram illustrating an example of the time lag information 122 according to the first embodiment of this invention. In the example of FIG. 6, for each pair of metrics, the time lag of the trailing metric relative to the preceding metric is shown.
- the time lag storage unit 112 stores the time lag information 122 generated by the time lag detection unit 102.
- the processing unit 140 performs comparative analysis between metric values in the target system.
- the processing unit 140 performs analysis (generation of correlation model 123, detection of correlation destruction) based on the correlation between metrics as a comparative analysis.
- the processing unit 140 includes a correlation model generation unit 103, a correlation model storage unit 113, a correlation destruction detection unit 104, and a data extraction unit 105.
- the correlation model generation unit 103 generates a correlation model 123 of the target system 200 based on the time series data 121 stored in the data storage unit 111.
- the correlation model 123 includes a correlation function (or conversion function) indicating the correlation of each pair of metrics among a plurality of metrics.
- the correlation function is expressed by, for example, the above equation (1).
- the correlation function calculates the other metric (from the measurement value before time t of one metric (input metric) and the measurement value before time t of the other metric (output metric) of the metric pair.
- the output metric is a function for predicting the value of time t.
- the correlation model generation unit 103 determines the coefficient of the correlation function, similar to the operation management apparatus disclosed in Patent Document 1. That is, the correlation model generation unit 103 performs correlation function coefficients A 1 , A 2 ,... In the equation 1 for each metric pair based on the time series data 121 of a predetermined modeling period by system identification processing. , A N , B 1 , B 2 ,..., B M are determined.
- a time series obtained by referring to the time lag information 122 stored in the time lag storage unit 112 and shifting (delaying) the time series of the preceding metric by the time lag is used.
- the correlation model generation unit 103 uses the time series obtained by shifting (delaying) the time series of the preceding metric by a time lag as the time series of the input metric and the time series of the subsequent metric as the time series of the output metric. Determine the function.
- the correlation model generation unit 103 calculates a weight for each pair of metrics based on the conversion error of the correlation function, as in the operation management apparatus of Patent Document 1, and the correlation function (effective
- the correlation model 123 may be a set of correlation functions.
- FIG. 7 is a diagram illustrating an example of the correlation model 123 according to the first embodiment of this invention.
- the correlation model storage unit 113 stores the correlation model 123 generated by the correlation model generation unit 103.
- the correlation destruction detection unit 104 uses the newly collected metric measurement value to determine whether the correlation included in the correlation model 123 is maintained or destroyed, as in the operation management apparatus of Patent Document 1. judge.
- the correlation destruction detection unit 104 uses a newly collected metric measurement value extracted by the data extraction unit 105.
- the correlation destruction detection unit 104 calculates, for each pair of metrics, a difference (prediction error) between the measured value of the output metric at time t and the predicted value of the output metric at time t calculated using the correlation function.
- the correlation destruction detection unit 104 determines that the correlation is destroyed when the calculated difference is equal to or greater than a predetermined value.
- the data extraction unit 105 extracts a newly collected metric measurement value necessary for detecting correlation destruction from the time-series data 121 stored in the data storage unit 111 and outputs it to the correlation destruction detection unit 104.
- the data extraction unit 105 refers to the time lag information 122 stored in the time lag storage unit 112 and outputs past measurement values for the time lag.
- the dialogue unit 106 presents the detection result of the correlation destruction to the user or the like.
- the dialogue unit 106 may instruct the handling execution unit 107 to execute a countermeasure against the correlation destruction in accordance with an operation from a user or the like.
- the countermeasure execution unit 107 executes the instructed countermeasure on the target system 200.
- the analysis apparatus 100 may be a computer that includes a CPU (Central Processing Unit) and a storage medium that stores a program, and operates by control based on the program.
- the data storage unit 111, the correlation model storage unit 113, and the time lag storage unit 112 may be configured as individual storage media or a single storage medium.
- FIG. 3 is a block diagram showing a configuration of the analysis apparatus 100 realized by a computer according to the first embodiment of the present invention.
- the analysis device 100 includes a CPU 161, a storage medium 162, a communication unit 163, an input unit 164, and an output unit 165.
- the CPU 161 is a computer program for realizing the functions of the data collection unit 101, the time lag detection unit 102, the correlation model generation unit 103, the correlation destruction detection unit 104, the data extraction unit 105, the dialogue unit 106, and the countermeasure execution unit 107.
- the storage medium 162 stores data in the data storage unit 111, the time lag storage unit 112, and the correlation model storage unit 113.
- the communication unit 163 receives measurement values of each metric from the target system 200.
- the input unit 164 is an input device such as a keyboard, for example, and receives input from the user or the like to the dialogue unit 106.
- the output unit 165 is a display device such as a display, for example, and displays an output from the dialogue unit 106 to a user or the like.
- FIG. 4 is a flowchart showing the operation of the analysis apparatus 100 in the first embodiment of the present invention.
- the data collection unit 101 collects measurement values of each metric from the target system 200 at a predetermined collection interval (step S101).
- the data collection unit 101 stores the collected time series of measured values of each metric in the data storage unit 111 as time series data 121.
- the data collection unit 101 stores time series data 121 as shown in FIG.
- the time lag detection unit 102 of the preprocessing unit 130 generates time lag information 122 based on the time series data 121 (step S102).
- the time lag detection unit 102 stores the generated time lag information 122 in the time lag storage unit 112.
- the time lag detection unit 102 detects a time lag by comparing a series of time-series change patterns for each predetermined length of the metric for each pair of metrics.
- FIG. 8 is a diagram showing an example of a time-series change pattern (change pattern) in the first exemplary embodiment of the present invention.
- the change pattern is a pattern of an increase / decrease tendency of the measured value of the metric in a predetermined length period.
- the change pattern of the symbol A in FIG. 8 indicates that the measured value of the metric does not change during a predetermined length period.
- the change pattern of the symbol B indicates that the metric measurement value increases during a predetermined length period.
- FIG. 9 is a diagram showing an example of time lag extraction in the first embodiment of the present invention.
- 40 msec is used as the predetermined length W for detecting the change pattern.
- the time lag detection unit 102 assigns a corresponding change pattern symbol for each period of the predetermined length W according to the change pattern as shown in FIG. Then, the time lag detection unit 102 detects a pair having a relationship between the preceding metric and the succeeding metric and a time lag of the pair by comparing the symbol series assigned to each metric for each pair of metrics.
- the time series of the sensor 1, the sensor 2, and the sensor 3 are given the symbol patterns “DBDGEEDBDEB”, “DBDGEEDBDEB”, and “CCBDDEDBDGEE”, respectively.
- the time lag detection unit 102 stores the time lag information 122 as shown in FIG. 6 in the time lag storage unit 112.
- the dialogue unit 106 may present the time lag candidates to the user or the like, and accept the selection of the time lag from the user.
- FIG. 10 is a diagram showing an example of the display screen 501 (time lag selection) in the first embodiment of the present invention.
- the time series graph shows that 200 msec and 400 msec are detected as time lag candidates for the pair in which the sensor 1 is the leading metric and the sensor 3 is the trailing metric.
- the dialogue unit 106 displays the display screen 501 of FIG. 10 to the user or the like.
- the dialogue unit 106 accepts selection of a time lag to be used for analysis in a time lag candidate from a user or the like by a time lag selection button.
- the correlation model generation unit 103 of the processing unit 140 generates a correlation model 123 for each metric pair included in the time lag information 122 (step S103).
- the correlation model generation unit 103 uses a time series obtained by shifting (delaying) the time series of the preceding metric by a time lag as the time series of the input metric and the time series of the subsequent metric as the time series of the output metric.
- the correlation model generation unit 103 stores the generated correlation model 123 in the correlation model storage unit 113.
- the correlation model generation unit 103 determines a correlation function as shown in FIG. And the correlation model production
- the data collection unit 101 collects new measurement values for each metric from the target system 200 (step S104).
- the data collection unit 101 stores the time series of the collected new measurement values of each metric as time series data 121 in the data storage unit 111.
- the data extraction unit 105 For each correlation function included in the correlation model 123, the data extraction unit 105 extracts a measurement value necessary for detecting correlation destruction from the new measurement value of each metric, and outputs the measurement value to the correlation destruction detection unit 104 (step S105). ).
- the data extraction unit 105 calculates the measurement value before the time t of the input metric and the measurement value before the time t of the output metric necessary for calculating the predicted value of the output metric of the correlation function. To extract. However, for the input metric, the data extraction unit 105 extracts past measurement values for the time lag.
- the data extraction unit 105 outputs S1 (t ⁇ 200) as the measured value of the input X (t) in the equation 1 for the pair of the sensor 1 and the sensor 3 in the correlation model 123 of FIG. S3 (t-1) is output as the measured value of -1).
- Correlation destruction detection unit 104 detects correlation destruction for each correlation function included in correlation model 123 using the new measurement value of each metric extracted by data extraction unit 105 (step S106).
- the correlation destruction detection unit 104 applies the measurement value before the time t of the input metric extracted by the data extraction unit 105 and the measurement value before the time t of the output metric to the correlation function, and outputs the correlation function.
- a predicted value of the metric time t is calculated.
- the correlation destruction detection unit 104 detects the correlation destruction based on the difference between the measured value at the time t of the output metric and the predicted value.
- the correlation destruction detection unit 104 calculates the predicted value of the sensor 3 at the time t for the pair of the sensor 1 and the sensor 3 in the correlation model 123 of FIG.
- Correlation destruction detector 104 sets the value obtained by multiplying the measured value of Y (t-1) (S3 (t-1)) by 0.96 and the measured value of X (t) (S1 (t-200)) to 70.
- the predicted value of the value of the sensor 3 at time t (Y (t)) is calculated using the multiplied value.
- the dialogue unit 106 presents the detection result of the correlation destruction to the user or the like (step S107).
- FIG. 11 is a diagram showing an example of the display screen 501 (correlation destruction display) in the first exemplary embodiment of the present invention.
- the display screen 501 in FIG. 11 shows that the correlation between the sensor 1 and the sensor 3 is broken in the abnormality ranking. Further, the time series graph shows that the measured values of the sensors 1 and 3 change with a time lag and the current measured value of the sensor 3 deviates from the predicted value.
- the dialogue unit 106 displays, for example, the display screen 501 of FIG.
- the dialogue unit 106 may receive an instruction to deal with the correlation destruction by the user or the like on the display screen 501 by using a countermeasure selection button.
- the dialogue unit 106 may further present a time series graph corrected for the detected time lag so that the time series changes between metrics can be easily compared.
- FIG. 12 is a diagram showing an example of the display screen 501 (time series comparison) in the first embodiment of the present invention.
- the time series graph of the display screen 501 of FIG. 12 the time series change of the measurement value of the sensor 1 and the time series change of the measurement value of the sensor 3 advanced by the time lag are displayed.
- the dialogue unit 106 displays, for example, the display screen 501 of FIG.
- the dialogue unit 106 instructs the coping execution unit 107 to deal with the correlation destruction in response to an operation from the user or the like.
- the countermeasure execution unit 107 executes the instructed countermeasure on the target system 200.
- analysis based on correlation is performed as a comparative analysis between metric values in the target system.
- the present invention is not limited to this, and any analysis other than the analysis based on the correlation may be performed as long as it is a comparative analysis in which a time lag between metrics is affected.
- Formula 1 is used as the correlation function.
- the present invention is not limited to this, and any other correlation function may be used as long as it is a correlation function representing the correlation between metric pairs.
- the time lag of each pair of metrics is detected by comparing time series change pattern series.
- the present invention is not limited to this, and if a time lag can be detected based on a change in the metric value, for example, a time difference in time at which the metric value indicates the maximum value or the minimum value, a phase difference between time series of the metric, etc.
- the time lag may be detected by other methods.
- a change pattern as shown in FIG. 8 is used as a time-series change pattern (change pattern).
- the present invention is not limited to this, and other change patterns may be used as long as the time lag between time series can be extracted.
- the time difference when a change pattern sequence similar to the subsequent metric (the same increase / decrease tendency) occurs with respect to the change pattern sequence of the preceding metric is used as a time lag. It was.
- the present invention is not limited to this, and a time difference when a series of change patterns having opposite increase / decrease trends may be used as the time lag.
- FIG. 1 is a block diagram showing a characteristic configuration of the first embodiment of the present invention.
- the analysis device (information processing device) 100 includes a processing unit 140 and a preprocessing unit 130.
- the processing unit 140 compares and analyzes the values of the first metric and the second metric in the analysis target system.
- the pre-processing unit 130 specifies a temporal correspondence relationship between the respective usage data in the comparative analysis between the first metric and the second metric.
- the preprocessing unit 130 specifies the temporal correspondence relationship of the respective usage data in the comparative analysis between the first metric and the second metric.
- the time lag between metrics according to the target system can be easily specified.
- the reason is that the time lag detection unit 102 compares the sequence of the time series change pattern for each predetermined length of the preceding metric with the sequence of the time series change pattern for each predetermined length of the subsequent metric. This is because the time lag is detected.
- the correlation destruction detection unit 104 needs to detect correlation destruction in real time for a large number of newly collected measurement values. For example, an analysis engine using dedicated hardware or a program is used. was there.
- the correlation destruction detection unit 104 (analysis engine) that does not support the large time lag can be used as it is. .
- the reason is that the data extraction unit 105 extracts past measurement values for a time lag from the input metric, and the correlation destruction detection unit 104 detects the correlation destruction using the measurement values extracted by the data extraction unit 105. Because.
- the second embodiment of the present invention differs from the first embodiment of the present invention in that the generation of the time lag information 122 and the generation of the correlation model 123 are performed by an apparatus different from the analysis apparatus 100. Different. Note that in the second embodiment of the present invention, the components given the same reference numerals as those in the first embodiment of the present invention are the same as those in the first embodiment of the present invention unless otherwise specified. Suppose that
- FIG. 13 is a block diagram showing the configuration of the analysis system in the second embodiment of the present invention.
- the analysis system includes an analysis device 100, a monitoring device 150, and a target system 200.
- the analysis apparatus 100 and the target system 200 are communicably connected via a network or the like.
- the analysis device 100 and the monitoring device 150 are also communicably connected via a network or the like.
- the analysis apparatus 100 includes a data collection unit 101, a data storage unit 111, a time lag storage unit 112, a correlation model storage unit 113, and a correlation destruction detection unit similar to the analysis apparatus 100 (FIG. 2) according to the first embodiment of the present invention. 104, a data extraction unit 105, and a countermeasure execution unit 107. In addition to these, the analysis apparatus 100 further includes a countermeasure determining unit 108.
- the monitoring device 150 includes a time lag detection unit 102, a correlation model generation unit 103, and a dialogue unit 106, which are the same as those of the analysis device 100 (FIG. 2) according to the first embodiment of the present invention.
- the time lag detection unit 102 of the monitoring device 150 generates time lag information 122 based on the time series data 121 stored in the data storage unit 111 of the analysis device 100.
- the correlation model generation unit 103 of the monitoring device 150 calculates the correlation model 123 based on the time series data 121 stored in the data storage unit 111 of the analysis device 100 and the time lag information 122 stored in the time lag storage unit 112. Generate.
- the countermeasure determining unit 108 of the analysis apparatus 100 determines the countermeasure to be executed under a predetermined condition according to the correlation destruction detection result by the correlation destruction detecting unit 104, and instructs the countermeasure execution unit 107 to execute the countermeasure. To do. Then, the countermeasure determining unit 108 presents the execution result of the countermeasure to the user or the like via the dialogue unit 106 of the monitoring device 150. Further, as in the first embodiment of the present invention, the countermeasure determining unit 108 instructs the countermeasure executing unit 107 to execute a countermeasure in response to an operation from a user or the like input via the dialogue unit 106. May be.
- the time lag detection unit 102 and the correlation model generation unit 103 may be further included in a device different from the monitoring device 150.
- real-time abnormality analysis of the target system 200 based on the detection of correlation destruction can be performed at a higher speed than in the first embodiment of the present invention.
- the reason is that the generation of the time lag information 122 by the time lag detection unit 102 and the generation of the correlation model 123 by the correlation model generation unit 103 are performed by a device different from the analysis device 100 that performs abnormality analysis, which has a relatively large processing load. It is to do.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Debugging And Monitoring (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
Description
次に、本発明の第2の実施の形態について説明する。
101 データ収集部
102 タイムラグ検出部
103 相関モデル生成部
104 相関破壊検出部
105 データ抽出部
106 対話部
107 対処実行部
108 対処決定部
111 データ記憶部
112 タイムラグ記憶部
113 相関モデル記憶部
121 時系列データ
122 タイムラグ情報
123 相関モデル
130 前処理部
140 処理部
150 監視装置
161 CPU
162 記憶媒体
163 通信部
164 入力部
165 出力部
200 対象システム
Claims (15)
- 分析対象のシステムにおける第1のメトリックと第2のメトリックとの値を比較分析する処理手段と、
前記第1のメトリックと前記第2のメトリックとの比較分析におけるそれぞれの使用データの時間的な対応関係を特定する前処理手段と、
を備えた情報処理装置。 - 前記第1および第2のメトリックの時系列変化は、前記対応関係に基づく補正をした時系列変化として表示される、
請求項1に記載の情報処理装置。 - 前記対応関係は、前記第1のメトリックの時系列変化に対する前記第2のメトリックの時系列変化のタイムラグである、
請求項1または2に記載の情報処理装置。 - 前記対応関係が複数特定される場合には、対応関係を一意に選択するために、特定された複数の前記対応関係が表示される、
請求項1から3のいずれか1項に記載の情報処理装置。 - 前記比較分析は、前記第1のメトリックの時系列と前記第2のメトリックの時系列との間の相関関係に基づく分析である、
請求項1から4のいずれか1項に記載の情報処理装置。 - 分析対象のシステムにおける第1のメトリックと第2のメトリックとの比較分析におけるそれぞれの使用データの時間的な対応関係を特定し、
前記第1のメトリックと第2のメトリックとの値を比較分析する、
分析方法。 - 前記第1および第2のメトリックの時系列変化は、前記対応関係に基づく補正をした時系列変化として表示される、
請求項6に記載の分析方法。 - 前記対応関係は、前記第1のメトリックの時系列変化に対する前記第2のメトリックの時系列変化のタイムラグである、
請求項6または7に記載の分析方法。 - 前記対応関係が複数特定される場合には、対応関係を一意に選択するために、特定された複数の前記対応関係が表示される、
請求項6から8のいずれか1項に記載の分析方法。 - 前記比較分析は、前記第1のメトリックの時系列と前記第2のメトリックの時系列との間の相関関係に基づく分析である、
請求項6から9のいずれか1項に記載の分析方法。 - コンピュータに、
分析対象のシステムにおける第1のメトリックと第2のメトリックとの比較分析におけるそれぞれの使用データの時間的な対応関係を特定し、
前記第1のメトリックと第2のメトリックとの値を比較分析する、
処理を実行させるプログラムを格納する、コンピュータが読み取り可能な記録媒体。 - 前記第1および第2のメトリックの時系列変化は、前記対応関係に基づく補正をした時系列変化として表示される、
請求項11に記載のプログラムを格納する、コンピュータが読み取り可能な記録媒体。 - 前記対応関係は、前記第1のメトリックの時系列変化に対する前記第2のメトリックの時系列変化のタイムラグである、
請求項11または12に記載のプログラムを格納する、コンピュータが読み取り可能な記録媒体。 - 前記対応関係が複数特定される場合には、対応関係を一意に選択するために、特定された複数の前記対応関係が表示される、
請求項11から13のいずれか1項に記載のプログラムを格納する、コンピュータが読み取り可能な記録媒体。 - 前記比較分析は、前記第1のメトリックの時系列と前記第2のメトリックの時系列との間の相関関係に基づく分析である、
請求項11から14のいずれか1項に記載のプログラムを格納する、コンピュータが読み取り可能な記録媒体。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201480053145.6A CN105579922B (zh) | 2013-09-26 | 2014-09-11 | 信息处理装置以及分析方法 |
JP2015538886A JP6406261B2 (ja) | 2013-09-26 | 2014-09-11 | 情報処理装置、及び、分析方法 |
US15/023,850 US20160231738A1 (en) | 2013-09-26 | 2014-09-11 | Information processing apparatus and analysis method |
EP14847009.9A EP3051374A4 (en) | 2013-09-26 | 2014-09-11 | Information processing device and analysis method |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2013-199943 | 2013-09-26 | ||
JP2013199943 | 2013-09-26 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015045319A1 true WO2015045319A1 (ja) | 2015-04-02 |
Family
ID=52742492
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/004707 WO2015045319A1 (ja) | 2013-09-26 | 2014-09-11 | 情報処理装置、及び、分析方法 |
Country Status (5)
Country | Link |
---|---|
US (1) | US20160231738A1 (ja) |
EP (1) | EP3051374A4 (ja) |
JP (1) | JP6406261B2 (ja) |
CN (1) | CN105579922B (ja) |
WO (1) | WO2015045319A1 (ja) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017164368A1 (ja) * | 2016-03-24 | 2017-09-28 | 三菱重工業株式会社 | 監視装置、監視方法、プログラム |
JP2017207852A (ja) * | 2016-05-17 | 2017-11-24 | Kddi株式会社 | 相互相関に基づいて時系列変化点を検出可能なプログラム、装置及び方法 |
WO2019087508A1 (ja) * | 2017-10-31 | 2019-05-09 | 三菱重工業株式会社 | 監視対象選定装置、監視対象選定方法、およびプログラム |
JP2021189717A (ja) * | 2020-05-29 | 2021-12-13 | 株式会社東芝 | プラント監視支援装置、方法及びプログラム |
JP7358791B2 (ja) | 2019-06-11 | 2023-10-11 | 中国電力株式会社 | プラント監視システムおよびプラント監視方法 |
JP7544863B2 (ja) | 2020-05-19 | 2024-09-03 | タタ コンサルタンシー サービシズ リミテッド | 製造業のための自己組織化サイバー・フィジカル・システムの開発及び展開のためのシステム及び方法 |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9295647B2 (en) | 2013-03-13 | 2016-03-29 | Transdermal Biotechnology, Inc. | Systems and methods for delivery of peptides |
US9320706B2 (en) | 2013-03-13 | 2016-04-26 | Transdermal Biotechnology, Inc. | Immune modulation using peptides and other compositions |
US9687520B2 (en) | 2013-03-13 | 2017-06-27 | Transdermal Biotechnology, Inc. | Memory or learning improvement using peptide and other compositions |
US9387159B2 (en) | 2013-03-13 | 2016-07-12 | Transdermal Biotechnology, Inc. | Treatment of skin, including aging skin, to improve appearance |
US9314423B2 (en) | 2013-03-13 | 2016-04-19 | Transdermal Biotechnology, Inc. | Hair treatment systems and methods using peptides and other compositions |
US9314417B2 (en) | 2013-03-13 | 2016-04-19 | Transdermal Biotechnology, Inc. | Treatment of skin, including aging skin, to improve appearance |
US9724419B2 (en) | 2013-03-13 | 2017-08-08 | Transdermal Biotechnology, Inc. | Peptide systems and methods for metabolic conditions |
US9295636B2 (en) | 2013-03-13 | 2016-03-29 | Transdermal Biotechnology, Inc. | Wound healing using topical systems and methods |
US9314422B2 (en) | 2013-03-13 | 2016-04-19 | Transdermal Biotechnology, Inc. | Peptide systems and methods for metabolic conditions |
US20140271937A1 (en) | 2013-03-13 | 2014-09-18 | Transdermal Biotechnology, Inc. | Brain and neural treatments comprising peptides and other compositions |
US9849160B2 (en) | 2013-03-13 | 2017-12-26 | Transdermal Biotechnology, Inc. | Methods and systems for treating or preventing cancer |
US20140271938A1 (en) | 2013-03-13 | 2014-09-18 | Transdermal Biotechnology, Inc. | Systems and methods for delivery of peptides |
JP5875726B1 (ja) * | 2015-06-22 | 2016-03-02 | 株式会社日立パワーソリューションズ | 異常予兆診断装置のプリプロセッサ及びその処理方法 |
WO2018178082A1 (en) * | 2017-03-28 | 2018-10-04 | Shell Internationale Research Maatschappij B.V. | Method, computer device and system for providing a visualization of sensor measurements |
US10841020B2 (en) * | 2018-01-31 | 2020-11-17 | Sap Se | Online self-correction on multiple data streams in sensor networks |
DE102019135493A1 (de) * | 2019-12-20 | 2021-06-24 | Trumpf Werkzeugmaschinen Gmbh + Co. Kg | Verfahren und System zur Synchronisation von Signalen |
US11853912B1 (en) * | 2020-01-30 | 2023-12-26 | Amazon Technologies, Inc. | Determining causal insights |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH01250818A (ja) * | 1988-03-31 | 1989-10-05 | Toshiba Corp | プロセスデータ解析装置 |
WO2005028838A1 (ja) * | 2003-09-24 | 2005-03-31 | A & D Company, Ltd. | 多信号解析装置 |
JP4872944B2 (ja) | 2008-02-25 | 2012-02-08 | 日本電気株式会社 | 運用管理装置、運用管理システム、情報処理方法、及び運用管理プログラム |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US3492646A (en) * | 1965-04-26 | 1970-01-27 | Ibm | Cross correlation and decision making apparatus |
US4739472A (en) * | 1984-12-07 | 1988-04-19 | Nec Corporation | Information processing device capable of rapidly processing instructions of different groups |
JPH1097306A (ja) * | 1996-09-20 | 1998-04-14 | Hitachi Ltd | 状態監視方法及びそのための装置 |
JP2003208219A (ja) * | 2002-01-10 | 2003-07-25 | Yamatake Building Systems Co Ltd | 異常検知装置および方法 |
EP1550964A1 (en) * | 2003-12-30 | 2005-07-06 | Sap Ag | A method and an appratus of forecasting demand for a product in a managed supply chain |
JP5373662B2 (ja) * | 2010-02-26 | 2013-12-18 | 大学共同利用機関法人情報・システム研究機構 | 映像表示装置 |
US9519393B2 (en) * | 2011-09-30 | 2016-12-13 | Siemens Schweiz Ag | Management system user interface for comparative trend view |
JP5616948B2 (ja) * | 2012-02-16 | 2014-10-29 | 株式会社半導体理工学研究センター | マルチビットのデルタシグマ型タイムデジタイザ回路及びその校正方法 |
DE102014005866A1 (de) * | 2013-05-09 | 2014-11-13 | Stmicroelectronics S.R.L. | Verfahren und System zum Verarbeiten von Daten von erfasstem Ionisationsstrom für Echtzeitschätzung von Brennraumdruck in einem Motor mit Funkenzündung |
-
2014
- 2014-09-11 EP EP14847009.9A patent/EP3051374A4/en not_active Withdrawn
- 2014-09-11 JP JP2015538886A patent/JP6406261B2/ja active Active
- 2014-09-11 WO PCT/JP2014/004707 patent/WO2015045319A1/ja active Application Filing
- 2014-09-11 CN CN201480053145.6A patent/CN105579922B/zh not_active Expired - Fee Related
- 2014-09-11 US US15/023,850 patent/US20160231738A1/en not_active Abandoned
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH01250818A (ja) * | 1988-03-31 | 1989-10-05 | Toshiba Corp | プロセスデータ解析装置 |
WO2005028838A1 (ja) * | 2003-09-24 | 2005-03-31 | A & D Company, Ltd. | 多信号解析装置 |
JP4872944B2 (ja) | 2008-02-25 | 2012-02-08 | 日本電気株式会社 | 運用管理装置、運用管理システム、情報処理方法、及び運用管理プログラム |
Non-Patent Citations (1)
Title |
---|
See also references of EP3051374A4 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017164368A1 (ja) * | 2016-03-24 | 2017-09-28 | 三菱重工業株式会社 | 監視装置、監視方法、プログラム |
JPWO2017164368A1 (ja) * | 2016-03-24 | 2018-11-15 | 三菱重工業株式会社 | 監視装置、監視方法、プログラム |
US10866163B2 (en) | 2016-03-24 | 2020-12-15 | Mitsubishi Heavy Industries, Ltd. | Anomaly monitoring device and method for producing anomaly signs according to combinations of sensors based on relationship of sensor fluctuations |
JP2017207852A (ja) * | 2016-05-17 | 2017-11-24 | Kddi株式会社 | 相互相関に基づいて時系列変化点を検出可能なプログラム、装置及び方法 |
WO2019087508A1 (ja) * | 2017-10-31 | 2019-05-09 | 三菱重工業株式会社 | 監視対象選定装置、監視対象選定方法、およびプログラム |
JP2019082918A (ja) * | 2017-10-31 | 2019-05-30 | 三菱重工業株式会社 | 監視対象選定装置、監視対象選定方法、およびプログラム |
JP7358791B2 (ja) | 2019-06-11 | 2023-10-11 | 中国電力株式会社 | プラント監視システムおよびプラント監視方法 |
JP7544863B2 (ja) | 2020-05-19 | 2024-09-03 | タタ コンサルタンシー サービシズ リミテッド | 製造業のための自己組織化サイバー・フィジカル・システムの開発及び展開のためのシステム及び方法 |
JP2021189717A (ja) * | 2020-05-29 | 2021-12-13 | 株式会社東芝 | プラント監視支援装置、方法及びプログラム |
JP7391765B2 (ja) | 2020-05-29 | 2023-12-05 | 株式会社東芝 | プラント監視支援装置、方法及びプログラム |
Also Published As
Publication number | Publication date |
---|---|
CN105579922A (zh) | 2016-05-11 |
EP3051374A1 (en) | 2016-08-03 |
CN105579922B (zh) | 2019-06-07 |
JP6406261B2 (ja) | 2018-10-17 |
EP3051374A4 (en) | 2017-04-05 |
JPWO2015045319A1 (ja) | 2017-03-09 |
US20160231738A1 (en) | 2016-08-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6406261B2 (ja) | 情報処理装置、及び、分析方法 | |
US10747188B2 (en) | Information processing apparatus, information processing method, and, recording medium | |
JP6160673B2 (ja) | 運用管理装置、運用管理方法、及びプログラム | |
JP6183450B2 (ja) | システム分析装置、及び、システム分析方法 | |
US10228994B2 (en) | Information processing system, information processing method, and program | |
JP6183449B2 (ja) | システム分析装置、及び、システム分析方法 | |
KR101978569B1 (ko) | 플랜트 데이터 예측 장치 및 방법 | |
JP5827425B1 (ja) | 予兆診断システム及び予兆診断方法 | |
KR20200043196A (ko) | 진동 신호를 이용하여 설비 또는 부품의 잔여 수명을 예측하는 딥러닝 기반의 분석 장치 및 방법 | |
US20190265088A1 (en) | System analysis method, system analysis apparatus, and program | |
KR20190025474A (ko) | 플랜트 데이터 예측 장치 및 방법 | |
EP3674827B1 (en) | Monitoring target selecting device, monitoring target selecting method and program | |
JP6521096B2 (ja) | 表示方法、表示装置、および、プログラム | |
EP2492829A1 (en) | Method of determining the influence of a variable in a phenomenon | |
JP2019159786A (ja) | 情報処理装置、情報処理方法、プログラム | |
KR20200010671A (ko) | 기계 학습 기반의 설비 이상 진단 시스템 및 방법 | |
JPWO2017150286A1 (ja) | システム分析装置、システム分析方法、及び、プログラム | |
JP5771317B1 (ja) | 異常診断装置及び異常診断方法 | |
US11073825B2 (en) | Causal relationship learning method, program, device, and anomaly analysis system | |
KR20200051343A (ko) | 시계열 데이터 예측 모델 평가 방법 및 장치 | |
JP6973445B2 (ja) | 表示方法、表示装置、および、プログラム | |
US20220413480A1 (en) | Time series data processing method | |
WO2019142344A1 (ja) | 分析装置、分析方法、及び、記録媒体 | |
KR102199695B1 (ko) | 가중 거리 자기 연상 양방향 커널 회귀를 이용한 온라인 신호 데이터 검증 장치 및 방법 | |
WO2019142346A1 (ja) | 分析システム、分析方法、及び、記録媒体 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201480053145.6 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14847009 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2015538886 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15023850 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
REEP | Request for entry into the european phase |
Ref document number: 2014847009 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2014847009 Country of ref document: EP |