WO2011104760A1 - 故障原因診断システムおよびその方法 - Google Patents
故障原因診断システムおよびその方法 Download PDFInfo
- Publication number
- WO2011104760A1 WO2011104760A1 PCT/JP2010/001303 JP2010001303W WO2011104760A1 WO 2011104760 A1 WO2011104760 A1 WO 2011104760A1 JP 2010001303 W JP2010001303 W JP 2010001303W WO 2011104760 A1 WO2011104760 A1 WO 2011104760A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- cause
- abnormality
- failure
- diagnosis
- unit
- 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
- G05B23/0221—Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
-
- 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
- G05B23/0278—Qualitative, e.g. if-then rules; Fuzzy logic; Lookup tables; Symptomatic search; FMEA
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24019—Computer assisted maintenance
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24042—Signature analysis, compare recorded with current data, if error then alarm
Definitions
- the present invention relates to a system for diagnosing the cause of failure in industrial equipment, plants, and the like, and more particularly to a system and method for estimating the cause of failure including failure phenomenon and failure parts from operation data of the device at the time of abnormality.
- the technology for diagnosing plant conditions from the distance to case data cannot recognize differences in data characteristics due to individual differences in the devices to be diagnosed or differences in the usage environment, making accurate diagnosis difficult. there were.
- the technology for estimating the cause of failure from the distance between the diagnosis target data and the abnormal space cannot estimate the correct abnormal cause unless the abnormal space has been accurately learned in advance.
- the present invention has been made in view of the above circumstances, and it is possible to change data used for diagnosis according to individual differences of diagnosis target devices and differences in use environments, and it is possible to apply failures even when there are few failure cases.
- a system and method for realizing cause diagnosis are provided.
- a failure cause diagnosis system comprising a cause diagnosis device for diagnosing the cause of failure of a device to achieve the above-mentioned problem, wherein the cause diagnosis device converts operation data and operation data when the device is in a normal state.
- a normal case storage unit for storing the measured values
- an abnormal case storage unit for storing the operation data when the device breaks down and a value converted from the operation data
- a diagnostic data input unit for inputting the operation data of the diagnosis target device
- An abnormality diagnosis unit that determines whether or not there is an abnormality using the diagnosis data and normal data stored in the normal case storage unit, and when the abnormality diagnosis unit determines that there is an abnormality, the abnormality diagnosis Cause diagnosis unit for estimating the cause of failure from the similarity between the abnormality contribution output from the unit and the abnormality contribution stored for each failure cause including the failure phenomenon and the faulty part stored in the abnormality case storage unit, and the cause diagnosis Part It is characterized in further comprising a diagnosis result output unit for outputting a diagnostic result.
- the abnormality contribution is normalized by decomposing the distance between normal data stored in the normal case storage unit and operation data of the diagnosis target device for each parameter. It is characterized by being a value.
- the cause diagnosis unit includes a specific cause input unit that inputs a name of a failure cause specified by a maintenance staff, a cause name input by the specific cause input unit, and the abnormality
- the cause names stored in the case storage unit are compared, and if they match, the abnormality contribution for each parameter of the cause name in the abnormality case storage unit is output for each parameter output from the abnormality diagnosis unit.
- An abnormality case update unit that updates using the contribution degree, and adds the cause name and the abnormality contribution degree for each parameter output from the abnormality diagnosis unit to the abnormality case storage unit when they do not match, It is characterized by providing.
- the cause diagnosis unit includes a design information storage unit that stores design information generated using design document information or designer knowledge
- the cause diagnosis unit includes the design information storage unit.
- the degree of coincidence between the operation data at the time of abnormality output from the abnormality diagnosis unit and the abnormality condition for each cause of failure stored in the design information storage unit is calculated, and the degree of abnormality contribution output from the abnormality diagnosis unit and the Calculating a similarity with the abnormality contribution for each failure cause stored in the abnormality case storage unit, and estimating the cause of the failure using a weight for setting the degree of coincidence and the similarity for each failure cause It is a feature.
- the present invention is characterized in that, in the failure cause diagnosis system, the design information includes a name of the failure cause and a condition satisfied by each parameter when the failure occurs as a constituent factor.
- the abnormality case is characterized in that the name of the failure cause and an abnormality contribution degree of each parameter when the failure occurs are constituent factors.
- the present invention is characterized in that, in the failure cause diagnosis system, the abnormal case includes a number of cases indicating the number of times the failure has occurred.
- the present invention relates to a failure cause diagnosis method for diagnosing a cause of failure of a device, storing operation data when the device is in a normal state and a value obtained by converting the operation data, The operation data at the time of failure and the value converted from the operation data are stored, the diagnosis data of the diagnosis target device is input, and the presence of abnormality is determined using the diagnosis data and the stored normal data
- the cause of the failure is estimated from the similarity between the output abnormality contribution and the abnormality contribution for each failure cause including the failure phenomenon and the failure part. is there.
- the present invention provides a failure cause diagnosis method for diagnosing the cause of failure of a device with a normalized value obtained by decomposing the distance between normal data and operation data of the diagnosis target device for each parameter. It is characterized by being.
- the present invention provides a method for diagnosing a cause of failure by inputting the name of the cause of the abnormality, comparing the input cause name with the stored cause name, and storing them if they match.
- the abnormality contribution degree for each parameter of the cause name being updated is updated using the abnormality contribution degree for each input parameter, and if there is no match, the abnormality contribution degree for each cause name and output parameter Is added.
- the present invention provides a failure cause diagnosis method that stores design information generated using design document information and designer's knowledge, operation data at the time of abnormality, and each cause of failure.
- the degree of coincidence with the abnormal condition is calculated, the degree of similarity between the output abnormality contribution and the degree of abnormality contribution for each failure cause is calculated, and the weight for setting the degree of coincidence and the degree of similarity for each failure cause is used.
- the cause of the failure is estimated.
- the present invention provides the failure cause diagnosis method, wherein the design information includes a name of the cause of failure and a condition satisfied by each parameter when the failure occurs. Is.
- the abnormality case includes a name of a failure cause and the abnormality contribution degree of each parameter when the failure occurs. It is what.
- the present invention is characterized in that, in the failure cause diagnosis method, the abnormal case includes a number of cases indicating the number of times the failure has occurred.
- the present invention it is possible to carry out a failure cause diagnosis according to individual differences of diagnosis target devices and differences in use environments. In addition, it is possible to realize a failure cause diagnosis applicable even when there are few failure cases.
- FIG. 1 shows a failure cause diagnosis system according to a first embodiment of the present invention.
- the hardware configuration of the cause diagnosis apparatus shown in FIG. 1 is shown.
- the example of the cause diagnosis flow implemented with the failure cause diagnostic system of Example 1 of this invention is shown.
- the example of the concept of the abnormality contribution utilized in this invention is shown.
- the example of the concept of the cause diagnosis method utilized by this invention is shown.
- the example of the structure of the abnormal case of Example 1 of this invention is shown.
- the structure of the failure cause diagnostic system of Example 2 of this invention is demonstrated.
- the example of the update flow of the abnormality example implemented with the failure cause diagnostic system of Example 2 of this invention is shown.
- the example of the concept of the update method of the abnormal case of Example 2 of this invention is shown.
- Example of the structure of the abnormal case of Example 2 of this invention is shown.
- the structure of the failure cause diagnostic system of Example 3 of this invention is demonstrated.
- the example of the cause diagnosis flow implemented with the failure cause diagnostic system of Example 3 of this invention is shown.
- the example of the structure of the design information of Example 3 of this invention is shown.
- FIG. 1 is a configuration diagram of the failure cause diagnosis system according to the first embodiment of the present invention.
- the failure cause diagnosis system includes a cause diagnosis apparatus 10 as illustrated in FIG.
- the cause diagnosis apparatus 10 includes a normal case storage unit 101 for storing operation data when the device is in a normal state and a value obtained by converting the operation data, and a value obtained by converting the operation data and operation data when the device fails.
- Abnormal case storage unit 102 to be stored diagnostic data input unit 103 for inputting data to be diagnosed from the outside, diagnostic data acquired from the diagnostic data input unit 103, and data stored in the normal case storage unit 101
- An abnormality diagnosis unit 104 that performs an abnormality diagnosis using the abnormality diagnosis unit 104, a cause diagnosis unit 105 that performs a cause diagnosis using the abnormality contribution degree generated by the abnormality diagnosis unit 104 and data stored in the abnormality case storage unit 102,
- a diagnosis result output unit 106 for outputting the cause diagnosis result generated by the cause diagnosis unit 105.
- FIG. 2 is a diagram illustrating a hardware configuration of the cause diagnosis apparatus 10.
- the cause diagnosing device 10 includes a communication device 11, an input / output device 12, a storage device 13, a CPU 14, a memory 15, and a reading device 16 connected by an internal signal line 18 such as a bus.
- the processing flow in the failure cause diagnosis system of this embodiment will be described.
- the processing flow described below is executed by each processing unit embodied on a device constituting the failure cause diagnosis system by loading a program stored in the storage device of the cause diagnosis device into the memory and executing it by the CPU. Is to be executed.
- Each program may be stored in a storage device in advance, or may be introduced when necessary via another storage medium or communication medium (a network or a carrier wave propagating through the network).
- FIG. 3 is a diagram showing a cause diagnosis flow executed by the cause diagnosis apparatus 10.
- diagnosis data refers to data obtained by converting sensor information, warning information, and sensor information of a device using a technique such as FFT.
- diagnosis data input unit 103 transmits the input diagnosis data (A301) to the abnormality diagnosis unit 104.
- the abnormality diagnosis unit 104 reads normal case data from the normal case storage unit 101 (S302).
- the normal case data may indicate the normal range of the designed sensor or device, or may be data obtained by collecting and converting the sensor data of the normal device.
- abnormality diagnosis is performed using diagnosis data (A301) and normal case data (S303).
- the abnormality diagnosis may be simple threshold determination or determination using a technique such as clustering.
- the presence or absence of an abnormality is determined from the abnormality diagnosis result (S304).
- the diagnosis result output unit 106 outputs the received normal result (S305).
- the abnormality contribution degree (A303) output from the abnormality diagnosis unit 104 is transmitted to the cause diagnosis unit 105.
- the degree of abnormal contribution is obtained by decomposing and normalizing the degree of separation between normal case data and diagnostic data for each parameter, and details are shown in FIG.
- the cause diagnosis unit 105 reads the abnormality case data from the abnormality case storage unit 102 (S306).
- the abnormality case data means an abnormality contribution degree of a failure that has occurred in the past and whose cause including a phenomenon or a part is specified.
- the case similarity is calculated using the received abnormality contribution (A303) and the abnormality case data (S307).
- the case similarity is a value calculated from the angle between the abnormality contribution degree of the diagnostic data and the abnormality contribution degree of each failure cause including the failure phenomenon and the failure part, and details are shown in FIG.
- the case with the highest case similarity is calculated as the estimated abnormality cause (S308).
- the calculation method of the presumed abnormality cause not only the one with the highest case similarity but the top five of the cases with the highest case similarity may be calculated, or the case similarity has a certain threshold or more May all be calculated.
- the calculated estimated abnormality cause (A304) is transmitted to the diagnosis result output unit 106.
- the diagnosis result output unit 106 outputs the received estimated abnormality cause (S309).
- FIG. 4 is a diagram showing details of the degree of abnormality contribution calculated by the abnormality diagnosis unit 104 of the cause diagnosis apparatus 10.
- the calculation method of the degree of abnormal contribution is shown with 2 input parameters.
- the center point (X0, Y0) (A401) of normal operation data is acquired.
- a distance D (A403) between the diagnostic data (X1, X2) (A402) and the center of normal data is calculated.
- the distance D can be calculated by the following formula (1).
- the degree of abnormality contribution is calculated by the following formulas (2) and (3) from the center (A401) of normal data, diagnosis data (A402), and distance D.
- the abnormal contribution is calculated for each parameter, and can be calculated in the same manner even when the number of parameters is increased.
- the parameter having a greater degree of separation from normal data has a larger absolute value of the abnormal contribution, and the sum of the absolute values of the abnormal contribution is 1.
- FIG. 5 is a diagram illustrating a method for calculating the case similarity calculated by the cause diagnosis unit 105 of the cause diagnosis apparatus 10 and a method for calculating the estimated abnormal cause.
- a case similarity calculation method when the number of input parameters is 2 and the number of causes collected as an abnormal case is 2 is shown.
- the abnormal contribution degree (A502, A503) for each cause based on normal data (A501) is acquired.
- the abnormality contribution degree (A504) of the diagnosis target data is acquired.
- an angle d 1 (A505) between the abnormality contribution degree of diagnosis data and the abnormality contribution degree of cause 1 and an angle d 2 (A506) between the abnormality contribution degree of cause 2 are calculated.
- a value obtained by subtracting the calculated angle from 90 is calculated as a case similarity by the following formula (4).
- FIG. 6 is a diagram illustrating a configuration of an abnormality case held in the abnormality case storage unit 102 in the first embodiment of the present invention.
- the abnormality case (A601) includes a cause 1 name (A602 1 ) indicating a name for identifying a failure cause including a failure phenomenon and a failed part, and an abnormality contribution degree (A603 11 to A603 1N ) of each parameter.
- a plurality of failure causes included in the abnormality case a plurality of the above configurations (A602 1 , A603 11 to A603 1N ) are arranged according to the number of failure causes. It should be noted that the order of the elements of the abnormality case is not limited to this, and it is sufficient that it includes at least the above-described constituent elements.
- FIG. 7 shows a configuration diagram of the failure cause diagnosis system according to the second embodiment of the present invention.
- the failure cause diagnosis system includes a cause diagnosis apparatus 10 as illustrated in FIG.
- the cause diagnosis apparatus 10 includes a normal case storage unit 101 for storing operation data when the device is in a normal state and a value obtained by converting the operation data, and a value obtained by converting the operation data and operation data when the device fails.
- Abnormal case storage unit 102 to be stored diagnostic data input unit 103 for inputting data to be diagnosed from the outside, diagnostic data acquired from the diagnostic data input unit 103, and data stored in the normal case storage unit 101
- An abnormality diagnosis unit 104 that performs an abnormality diagnosis using the abnormality diagnosis unit 104, a cause diagnosis unit 105 that performs a cause diagnosis using the abnormality contribution degree generated by the abnormality diagnosis unit 104 and data stored in the abnormality case storage unit 102,
- a diagnosis result output unit 106 that outputs a cause diagnosis result generated by the cause diagnosis unit 105, and a failure cause including a failure phenomenon or a failure part specified by a designer or maintenance personnel Using the specific cause input unit 107 to be input, the specific cause input by the specific cause input unit 107 and the abnormality
- the processing flow in the failure cause diagnosis system of this embodiment will be described.
- the processing flow described below is executed by each processing unit embodied on a device constituting the failure cause diagnosis system by loading a program stored in the storage device of the cause diagnosis device into the memory and executing it by the CPU. Is to be executed.
- Each program may be stored in a storage device in advance, or may be introduced when necessary via another storage medium or communication medium (a network or a carrier wave propagating through the network).
- FIG. 8 is a diagram showing a part for updating an abnormal case in the cause diagnosis flow executed by the cause diagnosis apparatus 10.
- the process up to S304 in FIG. 3 is performed.
- the abnormality contribution degree (A801) output as a result of the abnormality diagnosis is transmitted to the abnormality case update unit 108.
- the abnormality case update unit 108 stores the received abnormality contribution degree (S801).
- the designer or maintenance staff inputs the cause of failure specified by the maintenance work to the specified cause input unit 107 (S802).
- the input cause name (A 802) is transmitted to the abnormality case update unit 108.
- abnormality case update unit 108 stores the received cause name (S803).
- an abnormality case acquisition command (A803) is transmitted to the abnormality case storage unit 102.
- the abnormality case storage unit 102 acquires an abnormality case based on the received command (S804).
- the acquired abnormality case (A804) is transmitted to the abnormality case update unit 108.
- the abnormality case update unit 108 determines whether the stored cause name is included in the received abnormality case (S805). If it is an existing abnormality case, the abnormality contribution degree of the cause name is updated using the abnormality contribution degree stored in S801 (S806). A specific abnormality case update method is shown in FIG. On the other hand, if there is no item that matches the received abnormality case, the cause name and the degree of abnormality contribution are added as a new abnormality (S807). Next, the updated abnormality case (A805) is transmitted to the abnormality case storage unit 102.
- the abnormality case storage unit 102 stores the received updated abnormality case (S808).
- FIG. 9 is a diagram exemplifying a method of updating an abnormal case performed in S806 of FIG.
- the abnormality contribution degree (A901) of cause 1 and the abnormality contribution degree (A902) of cause 2 are acquired from the abnormality case storage unit 102.
- the abnormality contribution degree (A903) output as a result of performing abnormality diagnosis on the diagnosis data is acquired.
- the designer, maintenance personnel, etc. identify the cause including the failure phenomenon or the failed part, and input that the cause of failure in the diagnostic data is the cause 1 (S901).
- the abnormal contribution degree (A901) of the original cause 1 and the abnormal contribution degree (A903) of the diagnosis data are used to generate a new abnormal contribution degree (A904) of the cause 1.
- the new abnormality contribution ⁇ n is, for example, an average of the abnormality contributions collected in the past, and the following is used by using the previous abnormality contribution ⁇ n ⁇ 1 , the number n of cases, and the abnormality contribution x n of the diagnosis data. (5).
- the updating method of the abnormality case is not limited to the above method, and the new abnormality contribution degree may be updated by changing the influence degree of the abnormality contribution degree of the diagnosis data according to the identification accuracy of the failure cause. Good.
- FIG. 10 is a diagram showing a configuration of an abnormality case held in the abnormality case storage unit 102 in the second embodiment of the present invention.
- the abnormality case (A1001) includes a cause 1 name (A1002 1 ) indicating a name for identifying a failure cause including a failure phenomenon and a failure part, the number of cases collected in the past (A1003 1 ), and an abnormality contribution degree (A1004) of each parameter. 11 to A1004 1N ).
- a plurality of causes included in the abnormality case a plurality of the above configurations (A1002 1 , A1003 1 , A1004 11 to A1004 1N ) are arranged according to the number of causes. It should be noted that the order of the elements of the abnormality case is not limited to this, and it is sufficient that it includes at least the above-described constituent elements.
- FIG. 11 is a configuration diagram of the failure cause diagnosis system according to the third embodiment of the present invention.
- the failure cause diagnosis system includes a cause diagnosis apparatus 10 as illustrated in FIG.
- the cause diagnosis apparatus 10 includes a normal case storage unit 101 for storing operation data when the device is in a normal state and a value obtained by converting the operation data, and a value obtained by converting the operation data and operation data when the device fails.
- Abnormal case storage unit 102 to be stored diagnostic data input unit 103 for inputting data to be diagnosed from the outside, diagnostic data acquired from the diagnostic data input unit 103, and data stored in the normal case storage unit 101
- An abnormality diagnosis unit 104 that performs an abnormality diagnosis using a design information, a design information storage unit 109 that stores design information extracted from a design document or a designer, and diagnosis data and abnormality contributions at the time of abnormality generated by the abnormality diagnosis unit 104
- a cause diagnosis unit 105 that performs cause diagnosis using data stored in the abnormality case storage unit 102 and data stored in the design information storage unit 109; Configured to include a diagnostic result output section 106 for outputting the cause diagnostic results generated by the cause diagnostic unit 105.
- the processing flow in the failure cause diagnosis system of this embodiment will be described.
- the processing flow described below is executed by each processing unit embodied on a device constituting the failure cause diagnosis system by loading a program stored in the storage device of the cause diagnosis device into the memory and executing it by the CPU. Is to be executed.
- Each program may be stored in a storage device in advance, or may be introduced via another storage medium or communication medium (a network or a carrier wave propagating through the network) when necessary.
- FIG. 12 is a diagram showing a cause diagnosis flow executed by the cause diagnosis apparatus 10.
- the user inputs diagnosis data to be diagnosed into the diagnosis data input unit 103 of the cause diagnosis apparatus 10 (S1201).
- the diagnosis data input unit 103 transmits the input diagnosis data (A1201) to the abnormality diagnosis unit 104.
- the abnormality diagnosis unit 104 reads normal case data from the normal case storage unit 101 (S1202). Next, an abnormality diagnosis is performed using the diagnosis data (A1201) and normal case data (S1203). Next, the presence or absence of an abnormality is determined from the abnormality diagnosis result (S1204). As a result, when it is determined that there is no abnormality, the normal result (A1202) is transmitted to the diagnosis result output unit 106. Then, the diagnosis result output unit 106 outputs the received normal result (S1205). On the other hand, if it is determined that there is an abnormality, the diagnosis data at the time of abnormality output as a result of the abnormality diagnosis and the degree of abnormality contribution (A1203) are transmitted to the cause diagnosis unit 105.
- the diagnostic data at the time of abnormality refers to the diagnostic data of the part determined by the abnormality diagnosis unit 104 as not normal.
- the cause diagnosis unit 105 reads design information from the design information storage unit 109 (S1206).
- the design information is information indicating design abnormal conditions for each cause, and details are shown in FIG.
- the design coincidence is set to 90 when the diagnosis data at the time of the abnormality and the design information coincide with each other, and the design coincidence is designated when it does not coincide.
- the degree of coincidence is 0 or -90.
- the abnormal case data is read from the abnormal case storage unit 102 (S1208).
- the case similarity is calculated using the input abnormality contribution (A1203) and the abnormality case data (S1209).
- the method for calculating the case similarity is the same as the method shown in FIG.
- an estimated abnormality cause is calculated from the calculated design coincidence and the case similarity (S1210).
- the estimated abnormality cause is the largest value obtained by multiplying the design matching degree dd and the case similarity degree de by multiplying them by a certain weighting coefficient (wd, we). Specifically, it is calculated by the following formula (6).
- the weighting factor is a fixed or variable value for each cause of abnormality, the cause of abnormality that can be specified by design information has a large value of wd, and the cause of abnormality that can be specified by case information has a large value of we. Set.
- the weighting coefficient is changed according to the number of cases n stored in the abnormal case storage device 102. You may let them.
- the calculation method of the presumed abnormality cause not only the case having the highest case similarity but also the top five cases having the highest case similarity may be calculated, or cases having a case similarity higher than a threshold value may be calculated. All may be calculated.
- the calculated estimated abnormality cause (A1204) is transmitted to the diagnosis result output unit 106.
- diagnosis result output unit 106 outputs the received estimated abnormality cause (S1211).
- FIG. 13 is a diagram showing a configuration of design information held in the design information storage unit 109.
- the design information (A1301) includes a cause 1 name (A1302 1 ) indicating a name for identifying a failure cause including a failure phenomenon and a failed part, and abnormal conditions (A1303 11 to A1303 1N ) of each parameter.
- the abnormal condition means, for example, a simple threshold condition when a certain parameter exceeds 100, or an abnormal determination condition assumed in design such as a case where the parameter has occurred 10 times in the past 5 minutes.
- a plurality of the above-described configurations (A1302 1 , A1303 11 to A1303 1N ) are arranged according to the number of causes. Note that the order of the elements of the design information is not limited to this, as long as it includes at least the above-described components.
- this invention is not limited to said Example, A various deformation
- transformation is possible within the range of the summary.
- the abnormality diagnosis unit and the processing unit such as the cause diagnosis unit in the cause diagnosis apparatus 10 are independent from each other and necessary data is transmitted / received via a network or the like.
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
Description
このように異常寄与度とはパラメータ毎に算出するものであり、パラメータ数が増加した場合でも同様に算出することが可能である。また、正常データからの離れ度合いが大きいパラメータほど異常寄与度の絶対値が大きい値となるものであり、異常寄与度の絶対値の総和は1となる。
ここで、重み係数は異常原因毎に固定もしくは可変の値であり、設計情報により特定が可能な異常原因はwdの値を大きく、事例情報により特定が可能な異常原因はweの値を大きく予め設定する。また、事例情報があまり収集できていない状態では事例情報を用いた診断の信頼性は低いと考えられるため、異常事例保管装置102に格納されている事例数nの数に応じて重み係数を変化させてもよい。さらに、推定異常原因の算出方法にあたっては、事例類似度が最も大きいものだけではなく、事例類似度が大きいもののうち上位5個を算出してもよいし、事例類似度がある閾値以上のものを全て算出してもよい。
11 通信装置
12 入出力装置
13 記憶装置
14 CPU
15 メモリ
16 読取装置
17 記憶媒体
18 内部信号線
101 正常事例保管部
102 異常事例保管部
103 診断データ入力部
104 異常診断部
105 原因診断部
106 診断結果出力部
107 特定原因入力部
108 異常事例更新部
109 設計情報保管部
A301,A402,A1201 診断データ
A302,A1202 正常結果
A303,A801 異常寄与度
A304,A1204 推定異常原因
A401 正常データの中心
A403 正常データと診断データの距離
A501 正常データ
A502,A901 原因1異常寄与度
A503,A902 原因2異常寄与度
A504,A903 診断データ異常寄与度
A505 原因1距離
A506 原因2距離
A601,A804,A1001 異常事例
A6021~A602N,A802,A10021~A1002N,A13021~A1302N 原因名称
A60311~A603NN,A100411~A1004NN パラメータ異常寄与度
A803 異常事例取得コマンド
A805 更新異常事例
A904 原因1異常寄与度(更新後)
A10031~A1003N 原因事例数
A1203 異常時の診断データ,異常寄与度
A1301 設計情報
A130311~A1303NN パラメータ異常条件
Claims (14)
- 機器の故障原因を診断する原因診断装置を備えた故障原因診断システムにおいて、
前記原因診断装置は、
機器が正常な状態である際の稼動データや稼動データを変換した値を保管する正常事例保管部と、
機器が故障した際の稼動データや稼動データを変換した値を保管する異常事例保管部と、
診断対象機器の稼動データを入力する診断データ入力部と、
該診断データと前記正常事例保管部に格納されている正常時のデータを用いて異常の有無を判断する異常診断部と、
該異常診断部で異常があると判定された場合に、前記異常診断部から出力される異常寄与度と前記異常事例保管部に格納されている故障現象や故障部品を含む故障原因毎の異常寄与度の類似度から故障原因を推定する原因診断部と、
該原因診断部の診断結果を出力する診断結果出力部とを備えることを特徴とする故障原因診断システム。 - 請求項1の故障原因診断システムにおいて、
前記異常寄与度は、
前記正常事例保管部に格納されている正常時のデータと診断対象機器の稼動データの距離をパラメータ毎に分解して正規化した値であることを特徴とする故障原因診断システム。 - 請求項1又は、請求項2のいずれか1つの故障原因診断システムにおいて、
前記原因診断部は、
保守員によって特定された故障原因の名称を入力する特定原因入力部と、
該特定原因入力部で入力された原因名称と前記異常事例保管部に格納されている原因名称を比較し、一致した場合には前記異常事例保管部の該原因名称のパラメータ毎の前記異常寄与度を前記異常診断部から出力されるパラメータ毎の前記異常寄与度を用いて更新し、
一致しなかった場合には前記異常事例保管部に新たに該原因名称と前記異常診断部から出力されるパラメータ毎の前記異常寄与度を追加する異常事例更新部とを備えることを特徴とする故障原因診断システム。 - 請求項1ないし3のいずれか1つの故障原因診断システムにおいて、
前記原因診断部は、設計書の情報や設計者の知識を用いて生成する設計情報を格納する設計情報保管部を備え、
前記原因診断部は、前記異常診断部から出力される異常時の稼動データと前記設計情報保管部に格納されている故障原因毎の異常条件との一致度を算出し、前記異常診断部から出力される前記異常寄与度と前記異常事例保管部に格納されている故障原因毎の異常寄与度との類似度を算出し、前記一致度と該類似度を故障原因毎に設定する重み情報を用いて故障原因を推定することを特徴とする故障原因診断システム。 - 請求項4の故障原因診断システムにおいて、
前記設計情報は、故障原因の名称と該故障が発生した際の各パラメータが満たす条件を構成要因とすることを特徴とする故障原因診断システム。 - 請求項1ないし4のいずれか1つの故障原因診断システムにおいて、
前記異常事例は、故障原因の名称と該故障が発生した際の各パラメータの前記異常寄与度を構成要因とすることを特徴とする故障原因診断システム。 - 請求項6の故障原因診断システムにおいて、
前記異常事例には、故障が発生した回数を示す事例数が含まれることを特徴とする故障原因診断システム。 - 機器の故障原因を診断する故障原因診断方法において、
前記機器が正常な状態である際の稼動データや稼動データを変換した値を保管すること、
機器が故障した際の稼動データや稼動データを変換した値を保管すること、
診断対象機器の診断データを入力すること、
該診断データと格納されている正常時のデータを用いて異常の有無を判定すること、
異常があると判定された場合に、出力される異常寄与度と故障現象や故障部品を含む故障原因毎の異常寄与度の類似度から故障原因を推定することを特徴とする故障原因診断方法。 - 請求項8の故障原因診断方法において、
前記異常寄与度は、
正常時のデータと診断対象機器の稼動データの距離をパラメータ毎に分解して正規化した値であることを特徴とする故障原因診断方法。 - 請求項8又は、請求項9のいずれか1つの故障原因診断方法において、
異常原因の名称を入力すること、
入力された原因名称と格納されている原因名称を比較し、一致した場合には既に格納されている原因名称のパラメータ毎の前記異常寄与度を入力されたパラメータ毎の前記異常寄与度を用いて更新し、
一致しなかった場合には原因名称と出力されるパラメータ毎の前記異常寄与度を追加することを特徴とする故障原因診断方法。 - 請求項8ないし10のいずれか1つの故障原因診断方法において、
設計書の情報や設計者の知識を用いて生成する設計情報を格納すること、
異常時の稼動データと、故障原因毎の異常条件との一致度を算出し、出力される前記異常寄与度と故障原因毎の前記異常寄与度との類似度を算出し、前記一致度と該類似度を故障原因毎に設定する重みを用いて故障原因を推定することを特徴とする故障原因診断方法。 - 請求項11の故障原因診断方法において、
前記設計情報は、故障原因の名称と該故障が発生した際の各パラメータが満たす条件を構成要因とすることを特徴とする故障原因診断方法。 - 請求項8ないし11のいずれか1つの故障原因診断方法において、
前記異常事例は、故障原因の名称と該故障が発生した際の各パラメータの前記異常寄与度を構成要因とすることを特徴とする故障原因診断方法。 - 請求項13の故障原因診断方法であって、
前記異常事例には、故障が発生した回数を示す事例数が含まれることを特徴とする故障原因診断方法。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/578,034 US9122273B2 (en) | 2010-02-26 | 2010-02-26 | Failure cause diagnosis system and method |
PCT/JP2010/001303 WO2011104760A1 (ja) | 2010-02-26 | 2010-02-26 | 故障原因診断システムおよびその方法 |
CN201080063535.3A CN102844721B (zh) | 2010-02-26 | 2010-02-26 | 故障原因诊断系统及其方法 |
JP2012501528A JP5454671B2 (ja) | 2010-02-26 | 2010-02-26 | 故障原因診断システムおよびその方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2010/001303 WO2011104760A1 (ja) | 2010-02-26 | 2010-02-26 | 故障原因診断システムおよびその方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2011104760A1 true WO2011104760A1 (ja) | 2011-09-01 |
Family
ID=44506210
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2010/001303 WO2011104760A1 (ja) | 2010-02-26 | 2010-02-26 | 故障原因診断システムおよびその方法 |
Country Status (4)
Country | Link |
---|---|
US (1) | US9122273B2 (ja) |
JP (1) | JP5454671B2 (ja) |
CN (1) | CN102844721B (ja) |
WO (1) | WO2011104760A1 (ja) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012058885A (ja) * | 2010-09-07 | 2012-03-22 | Hitachi-Ge Nuclear Energy Ltd | 故障原因診断方法及び故障原因診断装置 |
JP2013199804A (ja) * | 2012-03-26 | 2013-10-03 | Sumitomo Heavy Ind Ltd | 作業機械の異常診断装置 |
JP2015103146A (ja) * | 2013-11-27 | 2015-06-04 | 株式会社豊田中央研究所 | 障害診断支援システム、障害診断支援装置および障害診断支援方法 |
WO2016088362A1 (ja) * | 2014-12-05 | 2016-06-09 | 日本電気株式会社 | システム分析装置、システム分析方法および記憶媒体 |
JP2018109851A (ja) * | 2016-12-28 | 2018-07-12 | 三菱日立パワーシステムズ株式会社 | 診断装置、診断方法及びプログラム |
JP2018132910A (ja) * | 2017-02-15 | 2018-08-23 | 株式会社日立製作所 | 保守装置、提示システム及びプログラム |
JP2019008354A (ja) * | 2017-06-20 | 2019-01-17 | 株式会社日立ビルシステム | 監視装置、監視システム、異常検知方法 |
JP6456580B1 (ja) * | 2018-06-14 | 2019-01-23 | 三菱電機株式会社 | 異常検知装置、異常検知方法及び異常検知プログラム |
JP2019036061A (ja) * | 2017-08-10 | 2019-03-07 | 株式会社東芝 | 要因分析装置、要因分析方法、およびプログラム |
JP2019124984A (ja) * | 2018-01-12 | 2019-07-25 | 株式会社明電舎 | 設備診断装置、設備診断方法 |
CN111542791A (zh) * | 2018-01-29 | 2020-08-14 | 云泰株式会社 | 使用设施诊断系统的设施诊断方法 |
JP2020170357A (ja) * | 2019-04-03 | 2020-10-15 | 株式会社日立パワーソリューションズ | 予兆保全設備、予兆保全方法及び予兆保全プログラム |
CN114490213A (zh) * | 2021-12-31 | 2022-05-13 | 深圳市智仁科技有限公司 | 电脑主板故障的监测诊断方法、系统、装置及存储介质 |
WO2022259446A1 (ja) * | 2021-06-10 | 2022-12-15 | 日本電気株式会社 | 異常原因推定装置、異常原因推定方法、及びコンピュータ読み取り可能な記録媒体 |
Families Citing this family (65)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9298182B2 (en) * | 2011-12-15 | 2016-03-29 | Xeonet Co., Ltd | Method of displaying abnormal status in plant operation monitoring system |
JP2015184942A (ja) * | 2014-03-25 | 2015-10-22 | 株式会社日立ハイテクノロジーズ | 故障原因分類装置 |
KR20160025664A (ko) * | 2014-08-27 | 2016-03-09 | 삼성에스디에스 주식회사 | 이상 조기 감지 장치 및 방법 |
US10176032B2 (en) * | 2014-12-01 | 2019-01-08 | Uptake Technologies, Inc. | Subsystem health score |
KR101657369B1 (ko) * | 2014-12-16 | 2016-09-19 | 주식회사 에스원 | 침입감지 시스템 |
US10254751B2 (en) | 2015-06-05 | 2019-04-09 | Uptake Technologies, Inc. | Local analytics at an asset |
US10579750B2 (en) | 2015-06-05 | 2020-03-03 | Uptake Technologies, Inc. | Dynamic execution of predictive models |
US10176279B2 (en) | 2015-06-05 | 2019-01-08 | Uptake Technologies, Inc. | Dynamic execution of predictive models and workflows |
US10878385B2 (en) | 2015-06-19 | 2020-12-29 | Uptake Technologies, Inc. | Computer system and method for distributing execution of a predictive model |
DE102016008987B4 (de) | 2015-07-31 | 2021-09-16 | Fanuc Corporation | Maschinenlernverfahren und Maschinenlernvorrichtung zum Lernen von Fehlerbedingungen, und Fehlervorhersagevorrichtung und Fehlervorhersagesystem, das die Maschinenlernvorrichtung einschließt |
JP6148316B2 (ja) * | 2015-07-31 | 2017-06-14 | ファナック株式会社 | 故障条件を学習する機械学習方法及び機械学習装置、並びに該機械学習装置を備えた故障予知装置及び故障予知システム |
US10579971B1 (en) * | 2015-08-10 | 2020-03-03 | State Farm Mutual Automobile Insurance Company | Systems and methods for scheduling repair of home equipment |
US10217068B1 (en) | 2015-08-10 | 2019-02-26 | State Farm Mutual Automobile Insurance Company | Systems and methods for pre-scheduling repair of home equipment |
US10229394B1 (en) | 2015-08-10 | 2019-03-12 | State Farm Mutual Automobile Insurance Company | Systems and methods for sending diagnostic information during scheduling of home equipment repair |
US10291732B2 (en) | 2015-09-17 | 2019-05-14 | Uptake Technologies, Inc. | Computer systems and methods for sharing asset-related information between data platforms over a network |
KR102384742B1 (ko) * | 2015-10-27 | 2022-04-07 | 삼성에스디에스 주식회사 | 센서 데이터를 이용한 이상 감지 장치 및 방법 |
CN106610602B (zh) * | 2015-10-27 | 2019-04-02 | 西门子公司 | 一种用于异常检测的方法和装置 |
US10623294B2 (en) | 2015-12-07 | 2020-04-14 | Uptake Technologies, Inc. | Local analytics device |
US11295217B2 (en) | 2016-01-14 | 2022-04-05 | Uptake Technologies, Inc. | Localized temporal model forecasting |
US10510006B2 (en) | 2016-03-09 | 2019-12-17 | Uptake Technologies, Inc. | Handling of predictive models based on asset location |
MY196229A (en) | 2016-03-15 | 2023-03-24 | Hitachi Ltd | Abnormality Diagnostic System |
US10796235B2 (en) | 2016-03-25 | 2020-10-06 | Uptake Technologies, Inc. | Computer systems and methods for providing a visualization of asset event and signal data |
US10333775B2 (en) | 2016-06-03 | 2019-06-25 | Uptake Technologies, Inc. | Facilitating the provisioning of a local analytics device |
JP6591937B2 (ja) * | 2016-06-29 | 2019-10-16 | 株式会社日立製作所 | 運用保守知識情報の策定支援システムおよび策定支援方法 |
US10210037B2 (en) | 2016-08-25 | 2019-02-19 | Uptake Technologies, Inc. | Interface tool for asset fault analysis |
US10474932B2 (en) | 2016-09-01 | 2019-11-12 | Uptake Technologies, Inc. | Detection of anomalies in multivariate data |
US10228925B2 (en) | 2016-12-19 | 2019-03-12 | Uptake Technologies, Inc. | Systems, devices, and methods for deploying one or more artifacts to a deployment environment |
US11080161B2 (en) * | 2016-12-21 | 2021-08-03 | Mitsubishi Electric Corporation | Control device, and processing method in event of failure in control device |
US10579961B2 (en) | 2017-01-26 | 2020-03-03 | Uptake Technologies, Inc. | Method and system of identifying environment features for use in analyzing asset operation |
US10671039B2 (en) | 2017-05-03 | 2020-06-02 | Uptake Technologies, Inc. | Computer system and method for predicting an abnormal event at a wind turbine in a cluster |
US10102693B1 (en) * | 2017-05-30 | 2018-10-16 | Deere & Company | Predictive analysis system and method for analyzing and detecting machine sensor failures |
JP6795093B2 (ja) * | 2017-06-02 | 2020-12-02 | 富士通株式会社 | 判定装置、判定方法及び判定プログラム |
US10255526B2 (en) | 2017-06-09 | 2019-04-09 | Uptake Technologies, Inc. | Computer system and method for classifying temporal patterns of change in images of an area |
EP3644152A4 (en) * | 2017-06-19 | 2020-07-01 | JFE Steel Corporation | METHOD FOR DIAGNOSIS OF ABNORMAL PROCESS STATES AND DEVICE FOR DIAGNOSIS OF ABNORMAL STATES |
CN107516414A (zh) * | 2017-08-21 | 2017-12-26 | 中国电力科学研究院 | 一种用电信息采集系统故障诊断分析方法及系统 |
US11232371B2 (en) | 2017-10-19 | 2022-01-25 | Uptake Technologies, Inc. | Computer system and method for detecting anomalies in multivariate data |
US10552246B1 (en) | 2017-10-24 | 2020-02-04 | Uptake Technologies, Inc. | Computer system and method for handling non-communicative assets |
US10379982B2 (en) | 2017-10-31 | 2019-08-13 | Uptake Technologies, Inc. | Computer system and method for performing a virtual load test |
US10635519B1 (en) | 2017-11-30 | 2020-04-28 | Uptake Technologies, Inc. | Systems and methods for detecting and remedying software anomalies |
US10815966B1 (en) | 2018-02-01 | 2020-10-27 | Uptake Technologies, Inc. | Computer system and method for determining an orientation of a wind turbine nacelle |
US10169135B1 (en) | 2018-03-02 | 2019-01-01 | Uptake Technologies, Inc. | Computer system and method of detecting manufacturing network anomalies |
US10554518B1 (en) | 2018-03-02 | 2020-02-04 | Uptake Technologies, Inc. | Computer system and method for evaluating health of nodes in a manufacturing network |
US10635095B2 (en) | 2018-04-24 | 2020-04-28 | Uptake Technologies, Inc. | Computer system and method for creating a supervised failure model |
US10860599B2 (en) | 2018-06-11 | 2020-12-08 | Uptake Technologies, Inc. | Tool for creating and deploying configurable pipelines |
US10579932B1 (en) | 2018-07-10 | 2020-03-03 | Uptake Technologies, Inc. | Computer system and method for creating and deploying an anomaly detection model based on streaming data |
JP7032261B2 (ja) * | 2018-07-24 | 2022-03-08 | 日立グローバルライフソリューションズ株式会社 | 異常検知システムおよび異常検知方法 |
US11119472B2 (en) | 2018-09-28 | 2021-09-14 | Uptake Technologies, Inc. | Computer system and method for evaluating an event prediction model |
JP7134051B2 (ja) * | 2018-10-01 | 2022-09-09 | 三菱電機株式会社 | 劣化検知システム |
US11181894B2 (en) | 2018-10-15 | 2021-11-23 | Uptake Technologies, Inc. | Computer system and method of defining a set of anomaly thresholds for an anomaly detection model |
EP3889864A4 (en) * | 2018-11-27 | 2021-12-01 | Fujitsu Frontech Limited | CAUSE ESTIMATE DEVICE, CAUSE ESTIMATE OUTPUT METHOD AND DEVICE FOR HANDLING A PAPER SHEET |
CN113330379A (zh) * | 2019-01-21 | 2021-08-31 | 三菱电机株式会社 | 异常原因推定装置、异常原因推定方法及程序 |
US11480934B2 (en) | 2019-01-24 | 2022-10-25 | Uptake Technologies, Inc. | Computer system and method for creating an event prediction model |
US11030067B2 (en) | 2019-01-29 | 2021-06-08 | Uptake Technologies, Inc. | Computer system and method for presenting asset insights at a graphical user interface |
US11797550B2 (en) | 2019-01-30 | 2023-10-24 | Uptake Technologies, Inc. | Data science platform |
CN109992600B (zh) * | 2019-03-28 | 2021-09-07 | 佛山市百斯特电器科技有限公司 | 一种设备故障的响应方法及设备 |
US11208986B2 (en) | 2019-06-27 | 2021-12-28 | Uptake Technologies, Inc. | Computer system and method for detecting irregular yaw activity at a wind turbine |
US10975841B2 (en) | 2019-08-02 | 2021-04-13 | Uptake Technologies, Inc. | Computer system and method for detecting rotor imbalance at a wind turbine |
FI20195989A1 (en) * | 2019-11-19 | 2021-05-20 | Elisa Oyj | Analysis of measurement results using deviation detection and identification of deviating variables |
JP7191807B2 (ja) * | 2019-11-29 | 2022-12-19 | 株式会社日立製作所 | 診断装置および診断方法 |
JP7333281B2 (ja) * | 2020-02-06 | 2023-08-24 | 株式会社日立製作所 | 設計支援システム |
CN111782434A (zh) * | 2020-06-30 | 2020-10-16 | 联想(北京)有限公司 | 异常检测方法、装置和电子设备 |
US11892830B2 (en) | 2020-12-16 | 2024-02-06 | Uptake Technologies, Inc. | Risk assessment at power substations |
CN112820090A (zh) * | 2020-12-30 | 2021-05-18 | 苏州绿科智能机器人研究院有限公司 | 一种基于大数据的报警系统及其实现方法 |
CN112734138B (zh) * | 2021-01-27 | 2023-07-07 | 珠海格力电器股份有限公司 | 一种故障预警方法、装置、设备及存储介质 |
CN116026403A (zh) * | 2022-11-09 | 2023-04-28 | 国能四川西部能源股份有限公司 | 开关柜故障预警方法、装置、介质和电子设备 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007293489A (ja) * | 2006-04-24 | 2007-11-08 | Mitsubishi Electric Corp | 設備機器用故障診断装置および設備機器用故障診断方法 |
JP2008071270A (ja) * | 2006-09-15 | 2008-03-27 | Omron Corp | プロセス異常分析装置およびプロセス異常分析方法並びにプログラム |
JP2009199289A (ja) * | 2008-02-21 | 2009-09-03 | Fujifilm Corp | 製造設備の診断装置及び方法 |
JP2010501091A (ja) * | 2006-05-07 | 2010-01-14 | アプライド マテリアルズ インコーポレイテッド | 故障診断のための範囲を定めた故障サイン |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3631118B2 (ja) | 2000-09-21 | 2005-03-23 | 株式会社東芝 | プラント診断装置 |
JP4265982B2 (ja) | 2004-02-25 | 2009-05-20 | 三菱電機株式会社 | 機器診断装置、冷凍サイクル装置、冷凍サイクル監視システム |
US20070028220A1 (en) * | 2004-10-15 | 2007-02-01 | Xerox Corporation | Fault detection and root cause identification in complex systems |
US7477960B2 (en) * | 2005-02-16 | 2009-01-13 | Tokyo Electron Limited | Fault detection and classification (FDC) using a run-to-run controller |
US7587296B2 (en) | 2006-05-07 | 2009-09-08 | Applied Materials, Inc. | Adaptive multivariate fault detection |
CN101438249A (zh) * | 2006-05-07 | 2009-05-20 | 应用材料股份有限公司 | 用于错误诊断的多种错误特征 |
WO2008140363A1 (en) * | 2007-05-14 | 2008-11-20 | Volvo Technology Corporation | Remote diagnosis modellin |
CA2689252C (en) * | 2007-06-15 | 2016-08-30 | Shell Internationale Research Maatschappij B.V. | Methods and systems for predicting equipment operation |
-
2010
- 2010-02-26 JP JP2012501528A patent/JP5454671B2/ja active Active
- 2010-02-26 US US13/578,034 patent/US9122273B2/en active Active
- 2010-02-26 CN CN201080063535.3A patent/CN102844721B/zh active Active
- 2010-02-26 WO PCT/JP2010/001303 patent/WO2011104760A1/ja active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007293489A (ja) * | 2006-04-24 | 2007-11-08 | Mitsubishi Electric Corp | 設備機器用故障診断装置および設備機器用故障診断方法 |
JP2010501091A (ja) * | 2006-05-07 | 2010-01-14 | アプライド マテリアルズ インコーポレイテッド | 故障診断のための範囲を定めた故障サイン |
JP2008071270A (ja) * | 2006-09-15 | 2008-03-27 | Omron Corp | プロセス異常分析装置およびプロセス異常分析方法並びにプログラム |
JP2009199289A (ja) * | 2008-02-21 | 2009-09-03 | Fujifilm Corp | 製造設備の診断装置及び方法 |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012058885A (ja) * | 2010-09-07 | 2012-03-22 | Hitachi-Ge Nuclear Energy Ltd | 故障原因診断方法及び故障原因診断装置 |
JP2013199804A (ja) * | 2012-03-26 | 2013-10-03 | Sumitomo Heavy Ind Ltd | 作業機械の異常診断装置 |
JP2015103146A (ja) * | 2013-11-27 | 2015-06-04 | 株式会社豊田中央研究所 | 障害診断支援システム、障害診断支援装置および障害診断支援方法 |
US10719577B2 (en) | 2014-12-05 | 2020-07-21 | Nec Corporation | System analyzing device, system analyzing method and storage medium |
WO2016088362A1 (ja) * | 2014-12-05 | 2016-06-09 | 日本電気株式会社 | システム分析装置、システム分析方法および記憶媒体 |
JPWO2016088362A1 (ja) * | 2014-12-05 | 2017-09-07 | 日本電気株式会社 | システム分析装置、システム分析方法および記憶媒体 |
JP2018109851A (ja) * | 2016-12-28 | 2018-07-12 | 三菱日立パワーシステムズ株式会社 | 診断装置、診断方法及びプログラム |
JP2018132910A (ja) * | 2017-02-15 | 2018-08-23 | 株式会社日立製作所 | 保守装置、提示システム及びプログラム |
JP2019008354A (ja) * | 2017-06-20 | 2019-01-17 | 株式会社日立ビルシステム | 監視装置、監視システム、異常検知方法 |
US11379493B2 (en) | 2017-08-10 | 2022-07-05 | Kabushiki Kaisha Toshiba | Factor analysis apparatus, factor analysis method, and non-transitory storage medium |
JP2019036061A (ja) * | 2017-08-10 | 2019-03-07 | 株式会社東芝 | 要因分析装置、要因分析方法、およびプログラム |
JP2019124984A (ja) * | 2018-01-12 | 2019-07-25 | 株式会社明電舎 | 設備診断装置、設備診断方法 |
JP2021182393A (ja) * | 2018-01-12 | 2021-11-25 | 株式会社明電舎 | 設備診断方法 |
JP7006282B2 (ja) | 2018-01-12 | 2022-01-24 | 株式会社明電舎 | 設備異常診断装置 |
JP7238921B2 (ja) | 2018-01-12 | 2023-03-14 | 株式会社明電舎 | 設備診断方法 |
CN111542791A (zh) * | 2018-01-29 | 2020-08-14 | 云泰株式会社 | 使用设施诊断系统的设施诊断方法 |
WO2019239542A1 (ja) * | 2018-06-14 | 2019-12-19 | 三菱電機株式会社 | 異常検知装置、異常検知方法及び異常検知プログラム |
JP6456580B1 (ja) * | 2018-06-14 | 2019-01-23 | 三菱電機株式会社 | 異常検知装置、異常検知方法及び異常検知プログラム |
US11657121B2 (en) | 2018-06-14 | 2023-05-23 | Mitsubishi Electric Corporation | Abnormality detection device, abnormality detection method and computer readable medium |
JP2020170357A (ja) * | 2019-04-03 | 2020-10-15 | 株式会社日立パワーソリューションズ | 予兆保全設備、予兆保全方法及び予兆保全プログラム |
WO2022259446A1 (ja) * | 2021-06-10 | 2022-12-15 | 日本電気株式会社 | 異常原因推定装置、異常原因推定方法、及びコンピュータ読み取り可能な記録媒体 |
CN114490213A (zh) * | 2021-12-31 | 2022-05-13 | 深圳市智仁科技有限公司 | 电脑主板故障的监测诊断方法、系统、装置及存储介质 |
Also Published As
Publication number | Publication date |
---|---|
US20120310597A1 (en) | 2012-12-06 |
CN102844721A (zh) | 2012-12-26 |
JP5454671B2 (ja) | 2014-03-26 |
CN102844721B (zh) | 2015-11-25 |
US9122273B2 (en) | 2015-09-01 |
JPWO2011104760A1 (ja) | 2013-06-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5454671B2 (ja) | 故障原因診断システムおよびその方法 | |
EP3776113B1 (en) | Apparatus and method for controlling system | |
EP2905665B1 (en) | Information processing apparatus, diagnosis method, and program | |
CN107463161B (zh) | 预测飞行器中的故障的方法和系统以及监控系统 | |
US7496798B2 (en) | Data-centric monitoring method | |
KR101825809B1 (ko) | 플랜트 이상 감지 시스템 및 방법 | |
US20140365179A1 (en) | Method and Apparatus for Detecting and Identifying Faults in a Process | |
US20230081892A1 (en) | Abnormality diagnosis method, abnormality diagnosis device and non-transitory computer readable storage medium | |
TW201823896A (zh) | 診斷裝置、診斷方法及程式 | |
CN105579922A (zh) | 信息处理装置以及分析方法 | |
JP6655926B2 (ja) | 異常診断システム | |
KR102102346B1 (ko) | 함정설비의 상태기반 정비지원 시스템 및 방법 | |
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 | |
JP2018139085A (ja) | 異常予測方法、異常予測装置、異常予測システムおよび異常予測プログラム | |
EP3910437B1 (en) | Monitoring apparatus, monitoring method, and computer-readable medium | |
WO2020188696A1 (ja) | 異常検知装置および異常検知方法 | |
JP6714498B2 (ja) | 設備診断装置及び設備診断方法 | |
JP4922265B2 (ja) | プラント監視装置およびプラント監視方法 | |
US20190329807A1 (en) | Method and arrangement for fault detection in a switch system | |
ITCO20090068A1 (it) | Metodo e sistema per diagnosticare compressori | |
JP2010276339A (ja) | センサ診断方法およびセンサ診断装置 | |
KR102483210B1 (ko) | Xai를 활용한 제조설비 이상발생확률 예측에 의한, 설비 건강지수 도출 시스템 및 설비 건강지수 도출 방법 | |
US11747035B2 (en) | Pipeline for continuous improvement of an HVAC health monitoring system combining rules and anomaly detection | |
KR20230102431A (ko) | 인공지능 기반의 오일가스 플랜트 설비 고장 예측 및 진단시스템 | |
JP7413205B2 (ja) | 自律管制制御装置、自律管制制御システム、および設計方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201080063535.3 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 10846429 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2012501528 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13578034 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 10846429 Country of ref document: EP Kind code of ref document: A1 |