JPS63169536A - Abnormality diagnosing method for rotary machine - Google Patents
Abnormality diagnosing method for rotary machineInfo
- Publication number
- JPS63169536A JPS63169536A JP89287A JP89287A JPS63169536A JP S63169536 A JPS63169536 A JP S63169536A JP 89287 A JP89287 A JP 89287A JP 89287 A JP89287 A JP 89287A JP S63169536 A JPS63169536 A JP S63169536A
- Authority
- JP
- Japan
- Prior art keywords
- abnormality
- cause
- data
- time
- analytic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000005856 abnormality Effects 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 12
- 238000001514 detection method Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims description 15
- 230000006866 deterioration Effects 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 230000001364 causal effect Effects 0.000 claims description 4
- 239000003638 chemical reducing agent Substances 0.000 abstract description 3
- 238000012517 data analytics Methods 0.000 abstract 2
- 238000003745 diagnosis Methods 0.000 description 8
- 238000007405 data analysis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
Description
【発明の詳細な説明】
〔産業上の利用分野〕
本発明は回転機械の状態を表わす機械的あるいは電気的
信号を利用してその回転機械に発生する異常原因を自動
的に判定する回転機械の異常診断方法に関するものであ
る。[Detailed Description of the Invention] [Industrial Application Field] The present invention relates to a rotating machine that automatically determines the cause of an abnormality occurring in the rotating machine using mechanical or electrical signals representing the state of the rotating machine. The present invention relates to an abnormality diagnosis method.
従来の回転機械の異常診断においては、回転機械の状態
を表わす機械的あるいは電気的信号の時系列データの解
析結果から算出した複数個の特徴量から求める劣化指数
をすべて独立とみなして。In conventional abnormality diagnosis of rotating machines, all deterioration indices determined from multiple feature quantities calculated from the analysis results of time-series data of mechanical or electrical signals representing the state of the rotating machine are considered to be independent.
この劣化指数と、回転機械に発生する複数個の異常原因
との因果関数の程度を表わす重み係数と、の２つのみの
単純な線形結合による合成によって各異常原因の発生の
可能性を推定していた１例えば特開昭５９−９４０１８
号公報に記載の方法は、故障診断の対象となる回転機械
から得られる振動信号の時系列データから複数個の特徴
量を算出し、予め記憶部に記憶させであるところの特徴
量と故障原因との因果関係を定めた故障因果表に基づい
て複数個の故障原因を推定し、前記複数個の各特徴量の
値から、各故障原因別に劣化程度を示す劣化指数に換算
するとともに、これら劣化指数と各故障原因との相関関
係の程度を示す重み係数とを線形結合して故障原因の自
動診断を行うようにした回転機械の故障診断方法である
。The possibility of occurrence of each cause of abnormality is estimated by combining this deterioration index and a weighting coefficient representing the degree of causal function of multiple causes of abnormality occurring in rotating machinery through a simple linear combination. For example, JP-A-59-94018
The method described in the publication calculates a plurality of feature quantities from time-series data of vibration signals obtained from a rotating machine that is the target of failure diagnosis, and stores the feature quantities and the cause of the failure in advance in a storage unit. A plurality of causes of failure are estimated based on a failure cause-and-effect table that defines the causal relationship between This is a fault diagnosing method for a rotating machine in which an index and a weighting coefficient indicating the degree of correlation between each fault cause are linearly combined to automatically diagnose the fault cause.
しかし上記従来の方法では、線形結合の項数の増加に伴
って発生している可能性の小さい異常原因についても見
掛は上大きな可能性があるような結果が得られ、最終判
定を下す際に判断が雌しくなるという欠点があった。However, with the above conventional method, as the number of terms in the linear combination increases, results that appear to have a large possibility even for abnormal causes with a small possibility of occurring are obtained, and when making the final judgment, had the disadvantage of being biased in its judgment.
本発明の目的は、回転機械に発生している異常の原因を
明確にかつ自動的に判定できる回転機械の異常診断方法
を提供することである。An object of the present invention is to provide a method for diagnosing an abnormality in a rotating machine that can clearly and automatically determine the cause of an abnormality occurring in the rotating machine.
本発明は、回転機械の状態を表わす振動などの機械的あ
るいはモータ電流などの電気的信号の時系列データの種
々の解析結果から算出した複数の特徴量をもとにして回
転機械の異常を診断する方法において、複数の特徴量と
回転機械に発生する複数の異常原因との因果関係の程度
を予め定めた重み係数群と、前記算出した特徴量の値か
ら異常原因毎に劣化程度を示す劣化指数に変換するため
の予め定めた変換係数群と、各々の異常原因について特
徴量間の独立性を表わす指標群とで構成したデータベー
スに基づいて回転機械に発生する異常原因を判定するこ
とを特徴とする回転機械の異常診断方法である。The present invention diagnoses abnormalities in rotating machines based on a plurality of feature quantities calculated from various analysis results of time-series data of mechanical signals such as vibrations or electrical signals such as motor current that represent the state of rotating machines. In the method of It is characterized by determining the causes of abnormalities that occur in rotating machinery based on a database consisting of a predetermined group of conversion coefficients for conversion into indexes and a group of indicators that represent the independence of feature quantities for each abnormality cause. This is a method for diagnosing abnormalities in rotating machinery.
以下実施例に基づき本発明の詳細な説明する。 The present invention will be described in detail below based on Examples.
第１図は本発明の実施例における異常診断のフローを示
すブロック図である。第１図において１は始点ターミナ
ルを、２は診断仕様入力部を、３は時系列信号入力部を
、４はデータ解析部を、５は異常原因推定部を、６はデ
ータベースを格納するファイルを、７は終点ターミナル
を、それぞれ示す、第１図において１診断仕様入力部２
では。FIG. 1 is a block diagram showing the flow of abnormality diagnosis in an embodiment of the present invention. In Figure 1, 1 is the starting point terminal, 2 is the diagnostic specification input section, 3 is the time series signal input section, 4 is the data analysis section, 5 is the abnormality cause estimation section, and 6 is the file storing the database. , 7 indicate the end terminals, respectively. In FIG. 1, 1 diagnostic specification input section 2
Well then.
診断の対象となるモータ、ポンプ、減速機などの回転機
械の構成、減速機の段数、歯車の歯数などの回転要素仕
様や軸受仕様などで示される設備仕様、振動、電流など
の検出信号の種類と検出位置。The configuration of rotating machinery such as motors, pumps, and reducers to be diagnosed; the equipment specifications indicated by rotating element specifications such as the number of stages in reducers and the number of gear teeth; and bearing specifications; and the detection signals such as vibration and current. Type and detection position.
データ長、解析周波数などの解析条件を入力する。Enter analysis conditions such as data length and analysis frequency.
時系列信号入力３部では、図示しない信号検出端から入
力される時系列の検出信号に対して例えばフィルタリン
グなどの信号処理を行い、また入力される信号がアナロ
グ信号であって４以降の処理をディジタルで行う場合に
は、エリアジングの除去、アナログ／ディジタル変換等
を行うことによって、時系列データを取込む、第２図に
検出信号の例として振動信号の例（イ）、（ロ）、（ハ
）を示す、データ解析部４では、取込んだ時系列データ
の周波数領域解析および振幅領域解析を行う。解析の例
として第３ａ図に振動信号（第２図の信号（イ））の周
波数分析結果の例を示し、第３ｂ図に振幅確率密度解析
結果の例を示す。異常原因推定部５では、データ解析部
４で得られた時系列データの周波数領域解析結果および
振幅領域解析結果から複数個の特徴量を算出する０次に
回転機械に発生すると考えられる複数個の異常原因につ
いて診断時にそれぞれがどの程度の可能性で発生してい
るかを算出する。この計算には予めファイルとして格納
されているデータベース６が利用される。The time-series signal input section 3 performs signal processing such as filtering on the time-series detection signal inputted from a signal detection end (not shown), and also performs the processing from 4 onwards if the inputted signal is an analog signal. When performing digitally, time series data is captured by removing aliasing, analog/digital conversion, etc. Figure 2 shows examples of vibration signals (a), (b), and (b) as examples of detection signals. The data analysis unit 4 shown in (c) performs frequency domain analysis and amplitude domain analysis of the captured time series data. As an example of analysis, FIG. 3a shows an example of a frequency analysis result of a vibration signal (signal (a) in FIG. 2), and FIG. 3b shows an example of an amplitude probability density analysis result. The abnormality cause estimation unit 5 calculates a plurality of feature quantities from the frequency domain analysis results and amplitude domain analysis results of the time series data obtained by the data analysis unit 4. At the time of diagnosis, the probability of occurrence of each cause of abnormality is calculated. A database 6 stored in advance as a file is used for this calculation.
次に異常原因の推定方法について説明する。Next, a method for estimating the cause of the abnormality will be explained.
異常原因の推定部５では、第３ａ図に例示した時系列デ
ータの周波数分析結果における基本スペクトル（ニ）の
値Ｓ１と全スペクトル値の総和Ｓ ５ｕｖａとの比（Ｓ
１／５ｓｕｎ）とか、基本スペクトル（ニ）の値Ｓ１と
その高調波（ホ）、（へ）のスペクトル値Ｓ２．Ｓ、の
和との比
（（Ｓ２ ＋５３ ）／Ｓ ｔ ） 。The abnormality cause estimating unit 5 calculates the ratio (S
1/5 sun) or the fundamental spectrum (d) value S1 and its harmonics (e) and (f) spectrum values S2. ((S2 + 53)/S t ).
あるいは第３ｂ図に例示した振幅確率密度解析結果から
求まる振幅の最大値と実効値との比といった、複数個の
特徴量を算出する。データベースファイル６には、これ
らの特徴量と回転機械に発生する異常原因との因果関係
を示すデータベースが格納されている。第５図にデータ
ベースの構造の例を示す、このデータベースは、例えば
回転機械のアンバランス、取付はボルトのゆるみなどの
考えられる複数個の異常原因毎に、前記した複数個の特
徴量を０〜１に正規化した劣化指数Ｐｉｊに変換するた
めの係数ａｉｊ、 ｂｉｊ （ここにｉは異常原因に対
応した添字、ｊは特徴量に対応した添字）と、複数個の
劣化指数の各々が各異常原因とどの程度の相関関係を有
するかを示す重み係数ｗｉｊと、各々の異常原因につい
て各特徴量間の独立性を表わす指標ｎｉｊとを要素とす
る行列構造をとる。係数ａｉｊおよびｂｉｊは特徴量ｘ
ｊと同じ単位を持つ（係数ａｉｊ、 ｂｉｊと劣化指数
Ｐｉｊの関係については後述する）。Alternatively, a plurality of feature quantities such as the ratio between the maximum amplitude value and the effective value obtained from the amplitude probability density analysis results illustrated in FIG. 3b are calculated. The database file 6 stores a database showing the causal relationship between these feature amounts and causes of abnormalities occurring in the rotating machine. Fig. 5 shows an example of the structure of the database. This database stores the above-mentioned feature quantities from 0 to The coefficients aij and bij (here, i is the subscript corresponding to the cause of the abnormality, and j is the subscript corresponding to the feature amount) for converting to the deterioration index Pij normalized to 1, and each of the multiple deterioration indices is calculated for each abnormality. It has a matrix structure in which the elements are a weighting coefficient wij indicating the degree of correlation with the cause and an index nij indicating the independence of each feature for each abnormality cause. The coefficients aij and bij are the feature quantity x
It has the same unit as j (the relationship between the coefficients aij, bij and the deterioration index Pij will be described later).
ここで独立性を表わす指標ｎｉｊについて説明する。い
まある特徴量ｘｋが他の特徴量ｘＱが有意であるときに
はじめである異常原因に対して意味を持つような場合、
例えば取付はボルトのゆるみに対しては、前記第３ａ図
の例で求めた特徴量（（Ｓ２ ＋Ｓａ ）／Ｓ １）は
別の特徴量（Ｓｔ／Ｓｓｕｍ）が十分大きいときにのみ
はじめて意味を持つ［（Ｓ １ ／５ｓｕｓ）が、小さ
いときに（（Ｓ ２ ＋ ８３）／ Ｓ ｔ ）の大小
を評価しても無意味〕
ので、このような場合は当該異常原因に対する特徴量ｘ
ｋ（例えば上記（（Ｓ２ ＋Ｓａ ）／Ｓｔ ） ）の
独立性を表わす指標ｎｉｋとして、
ｘｋと最も相関の強い別の特徴量ｘＱ〔例えば上記（Ｓ
１ ／Ｓｓｕ謬））に対応しかつ同じ異常原因ｉに関
する劣化指数ＰｉＱの数値を指標値とするよう設定する
。あるいはまた、別の特徴量ｘｍが他のすべての特徴量
とは独立と考えられる場合には指標ｎｉ■の値として「
１」を設定する。Here, the index nij representing independence will be explained. In the case where the current feature quantity xk has a meaning for a certain abnormality cause when the other feature quantity xQ is significant,
For example, regarding loosening of bolts during installation, the feature value ((S2 + Sa)/S1) obtained in the example of Figure 3a becomes meaningful only when another feature value (St/Ssum) is sufficiently large. [When (S 1 /5sus) is small, it is meaningless to evaluate the magnitude of ((S 2 + 83) / S t )], so in such a case, the feature quantity x for the cause of the abnormality
As an index nik representing the independence of k (for example, ((S2 + Sa)/St) above), another feature xQ that has the strongest correlation with xk [for example, (S2 + Sa)/St) above] is used.
1/Ssu error)) and is set to be the numerical value of the deterioration index PiQ related to the same abnormality cause i as the index value. Alternatively, if another feature xm is considered independent of all other features, the value of the index ni■
1”.
これらの係数ａｉｊ、 ｂｉｊ、 ｗｉｊと指標ｎｉｊ
は、回転機械の異常現象の物理的性質および長年の経験
に基づいて決定された簡易な知識ベースであり、データ
ベースファイル６においては、データベースは必要に応
じて変更可能な構成になっている。These coefficients aij, bij, wij and index nij
is a simple knowledge base determined based on the physical properties of abnormal phenomena in rotating machines and many years of experience, and the database file 6 has a configuration that allows the database to be changed as necessary.
異常原因推定部５では、前記したような複数個の特徴量
ｘｊを、前記した変換係数”ｊｙ １）ＩＪを用いて、
例えば次の関係式（１）を用いて劣化指数Ｐｉｊに変換
する。The abnormality cause estimation unit 5 converts the plurality of feature quantities xj as described above using the transformation coefficient "jy1)IJ" as described above,
For example, it is converted into a deterioration index Pij using the following relational expression (1).
ｘｊ（ａｉｊならば、Ｐｉｊ＝Ｏ１
ａｉｊ≦ｘｊ（ｂｉｊならば、
Ｐｉｊ＝（ｘｊ−ａ ｉｊ）／（ｂ ｉｊ −ａ １ｊ
）ｘｊ≧ｂｉｊならば、 Ｐｉｊ＝ １ ・・・”（
ｌ）式（１）の関係を、第４図に示す。xj (if aij, then Pij = O1 aij≦xj (if bij, then Pij = (xj - a ij) / (b ij - a 1j
) If xj≧bij, then Pij=1...”(
l) The relationship of equation (1) is shown in FIG.
ある１つの異常原因についての発生の可能性を示す値Ｆ
ｉは、複数の劣化指数Ｐｉｊと各々のＰｉｊに対応する
特徴量の独立性を表わす一指標ｎｉｊの合成により算出
する０例えば線形結合による合成ならば、次式（２）よ
り算出される。Value F that indicates the possibility of occurrence of one abnormality cause
i is calculated by combining a plurality of deterioration indices Pij and one index nij representing the independence of the feature amount corresponding to each Pij.For example, if the combination is a linear combination, it is calculated from the following equation (2).
Ｆｉ＝すｉｌ ｎｉＩ Ｐｉｌ ＋Ｗｉ２ ｎｉ２ Ｆ
ｉ２ ＋−・＋ＶｉｔｎｉｔＰｉｔ、 ・・・（２）こ
こで、添字ｔは特徴量ｘｊの総数を表わし、また各々の
ｉにおけるＷｉｌ 、 Ｗｉ２・・・、 Ｗｉｔの総和
は１とする。Fi=Sil niI Pil +Wi2 ni2 F
i2 +-.+VitnitPit, (2) Here, the subscript t represents the total number of feature quantities xj, and the sum of Wil, Wi2,..., Wit for each i is 1.
Ｆｉは０から１までの値をとり、この値が１に近いほど
回転機械に異常原因ｉが発生している可能性が高いこと
を意味し、０に近いほど発生の可能性が低いことを意味
する。式（２）の演算を、回転機械に発生すると考えら
れるすべての異常原因について行えば、診断時に発生し
ている可能性の高い異常原因がどれであるかが容易にわ
かる。Fi takes a value from 0 to 1, and the closer this value is to 1, the higher the possibility that abnormality cause i has occurred in the rotating machine, and the closer it is to 0, the lower the probability of occurrence. means. If the calculation of equation (2) is performed for all causes of abnormality that are thought to occur in a rotating machine, it can be easily determined which causes of abnormality are likely to occur at the time of diagnosis.
以上述べたごとく本発明では、回転機械の状態を表わす
検出信号の時系列データの解析結果から算出した複数個
の特徴量に関して、各特徴量が複数個の各々の異常原因
に対して他の特徴量と相関を有するか否か（独立かどう
か）によって異なる指標値を与え、異常原因の発生の可
能性を示す値を算出するために、特徴量から変換した劣
化指数と、特徴量と異常原因の相関の程度を示す重み係
数と、特徴量の独立性を表わす指標を用いるようにした
ので、回転機械の異常原因を精度よく判定することが可
能になる。As described above, in the present invention, with respect to a plurality of feature quantities calculated from the analysis results of time-series data of detection signals representing the state of a rotating machine, each feature quantity corresponds to another characteristic for each of the plurality of abnormality causes. In order to give different index values depending on whether or not there is a correlation with the amount (independent or not), and to calculate a value indicating the possibility of occurrence of the cause of an abnormality, we use the deterioration index converted from the feature amount, the feature amount and the cause of the abnormality. Since a weighting coefficient indicating the degree of correlation between the two and an index indicating the independence of the feature values are used, it becomes possible to accurately determine the cause of an abnormality in a rotating machine.
第１図は本発明の実施例における異常診断のフローを示
すブロック図、ｉ２図は回転機械から取込まれる検出信
号の例を示す波形図、第３ａ図および第３ｂ図は、時系
列データの解析結果の例を示す平面図、第４図は特徴量
と劣化指数の関係の一例を示すグラフ、第５図は特徴量
から異常原因を判定するデータベースを示す平面図であ
る。
１：始点ターミナル ２：診断仕様入力部３：
時系列信号データ入力部 ４：データ解析部５：異常原
因推定部 ６：データベースフアイル７：終点
ターミナル
第１ 図
声２囚
第３ａ図
第３ｂ図
第４図
一騎軒（Ｘｊ）Fig. 1 is a block diagram showing the flow of abnormality diagnosis in an embodiment of the present invention, Fig. i2 is a waveform diagram showing an example of a detection signal taken in from a rotating machine, and Figs. 3a and 3b are graphs of time series data. FIG. 4 is a plan view showing an example of an analysis result, FIG. 4 is a graph showing an example of the relationship between a feature amount and a deterioration index, and FIG. 5 is a plan view showing a database for determining the cause of abnormality from the feature amount. 1: Starting point terminal 2: Diagnosis specification input section 3:
Time series signal data input section 4: Data analysis section 5: Anomaly cause estimation section 6: Database file 7: End point terminal 1 Zusei 2 Prisoner Figure 3a Figure 3b Figure 4 Ikkiken (Xj)
Claims (1)
結果から算出した複数の特徴量をもとにして回転機械の
異常を診断する方法において、複数の特徴量と回転機械
に発生する複数の異常原因との因果関係の程度を予め定
めた重み係数群と、前記算出した特徴量の値から異常原
因毎に劣化程度を示す劣化指数に変換するための予め定
めた変換係数群と、各々の異常原因について特徴量間の
独立性を表わす指標群とで構成したデータベースに基づ
いて回転機械に発生する異常原因を判定することを特徴
とする回転機械の異常診断方法。In a method for diagnosing an abnormality in a rotating machine based on a plurality of feature quantities calculated from the analysis results of time-series data of a detection signal representing the state of the rotating machine, the method uses a plurality of feature quantities and a plurality of abnormalities occurring in the rotating machine. A group of weighting coefficients predetermining the degree of causal relationship with the cause, a group of predetermined conversion coefficients for converting the calculated feature value into a deterioration index indicating the degree of deterioration for each abnormality cause, and a group of conversion coefficients predetermined for each abnormality. 1. A method for diagnosing an abnormality in a rotating machine, characterized in that the cause of an abnormality occurring in the rotating machine is determined based on a database including a group of indicators representing independence between feature quantities regarding the cause.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP89287A JPH07122604B2 (en) | 1987-01-06 | 1987-01-06 | Abnormality diagnosis method for rotating machinery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP89287A JPH07122604B2 (en) | 1987-01-06 | 1987-01-06 | Abnormality diagnosis method for rotating machinery |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPS63169536A true JPS63169536A (en) | 1988-07-13 |
| JPH07122604B2 JPH07122604B2 (en) | 1995-12-25 |
Family
ID=11486330
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP89287A Expired - Fee Related JPH07122604B2 (en) | 1987-01-06 | 1987-01-06 | Abnormality diagnosis method for rotating machinery |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPH07122604B2 (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02159526A (en) * | 1988-12-13 | 1990-06-19 | Mitsubishi Atom Power Ind Inc | Diagnosing apparatus for non-linear vibration |
| JP2008058030A (en) * | 2006-08-29 | 2008-03-13 | Matsushita Electric Works Ltd | Abnormality monitoring apparatus and abnormality monitoring method |
| JP2010071984A (en) * | 2008-08-21 | 2010-04-02 | Asahi Kasei Corp | Detection device |
| JP2011132862A (en) * | 2009-12-24 | 2011-07-07 | Diesel United:Kk | Method for monitoring sliding state of piston ring of diesel engine |
| JP2012055047A (en) * | 2010-08-31 | 2012-03-15 | Hitachi Automotive Systems Ltd | Overcurrent detection device and overcurrent detection method for electrically-driven controller |
| JP2013019874A (en) * | 2011-07-14 | 2013-01-31 | Chugoku Electric Power Co Inc:The | Bearing diagnosis device and bearing diagnosis method |
| WO2021234815A1 (en) * | 2020-05-19 | 2021-11-25 | 株式会社日立製作所 | Rotary machine diagnosis system and method |
| WO2023105908A1 (en) * | 2021-12-09 | 2023-06-15 | 株式会社日立インダストリアルプロダクツ | Cause-of-abnormality estimation device for fluid machine, cause-of-abnormality estimation method therefor, and cause-of-abnormality estimation system for fluid machine |
-
1987
- 1987-01-06 JP JP89287A patent/JPH07122604B2/en not_active Expired - Fee Related
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02159526A (en) * | 1988-12-13 | 1990-06-19 | Mitsubishi Atom Power Ind Inc | Diagnosing apparatus for non-linear vibration |
| JP2008058030A (en) * | 2006-08-29 | 2008-03-13 | Matsushita Electric Works Ltd | Abnormality monitoring apparatus and abnormality monitoring method |
| JP2010071984A (en) * | 2008-08-21 | 2010-04-02 | Asahi Kasei Corp | Detection device |
| JP2011132862A (en) * | 2009-12-24 | 2011-07-07 | Diesel United:Kk | Method for monitoring sliding state of piston ring of diesel engine |
| JP2012055047A (en) * | 2010-08-31 | 2012-03-15 | Hitachi Automotive Systems Ltd | Overcurrent detection device and overcurrent detection method for electrically-driven controller |
| US8947838B2 (en) | 2010-08-31 | 2015-02-03 | Hitachi Automotive Systems, Ltd. | Overcurrent fault detection device for electrical drive control system |
| JP2013019874A (en) * | 2011-07-14 | 2013-01-31 | Chugoku Electric Power Co Inc:The | Bearing diagnosis device and bearing diagnosis method |
| WO2021234815A1 (en) * | 2020-05-19 | 2021-11-25 | 株式会社日立製作所 | Rotary machine diagnosis system and method |
| WO2023105908A1 (en) * | 2021-12-09 | 2023-06-15 | 株式会社日立インダストリアルプロダクツ | Cause-of-abnormality estimation device for fluid machine, cause-of-abnormality estimation method therefor, and cause-of-abnormality estimation system for fluid machine |
Also Published As
| Publication number | Publication date |
|---|---|
| JPH07122604B2 (en) | 1995-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111521400B (en) | Bearing early fault diagnosis method based on EDM and spectral kurtosis | |
| CN105134456B (en) | Hydraulic turbine fault pre-diagnosing method based on on-line monitoring | |
| CN1679042A (en) | Method for consistent forewarning of critical events across multiple data channels | |
| CN110940917B (en) | Motor fault early warning method and system | |
| KR102067344B1 (en) | Apparatus and Method for Detecting Abnormal Vibration Data | |
| CN112326213B (en) | Abnormal data detection method and device and mechanical fault detection method and device | |
| JPS63169536A (en) | Abnormality diagnosing method for rotary machine | |
| CN105865794A (en) | Engine misfire fault diagnosis method based on short-time Fourier transformation and principal component analysis | |
| CN113074941A (en) | Variable-speed gear fault signal extraction method, diagnosis method and system based on adaptive time-varying comb filtering and storage medium | |
| JPS5994018A (en) | Trouble diagnosing apparatus for rotary machine | |
| CN117109923A (en) | Rolling bearing fault diagnosis method and system | |
| CN113123956B (en) | Water hammer fault diagnosis method for water pump | |
| CN113702861B (en) | Power failure position prediction method and device based on big data analysis | |
| CN112901472B (en) | Diagnosis method for automatically identifying plunger pump fault based on signal characteristic frequency | |
| Mukhopadhyay et al. | A feature-based approach to monitor motor-operated valves used in nuclear power plants | |
| CN114398922A (en) | CNN-BilSTM-based fault diagnosis method for looseness of high-voltage shunt reactor winding | |
| CN115186707A (en) | Simple gear box fault detection method | |
| CN114412447A (en) | Fault detection method and device for screw pump well | |
| He et al. | Signal nonstationary degree evaluation method based on moving statistics theory | |
| CN113418685A (en) | Vibration monitoring device and fault analysis system and method based on vibration monitoring | |
| JPS59211896A (en) | Detector responce abnormality diagnosing device | |
| CN113514713B (en) | Method and device for detecting performance of traction converter of motor train unit and terminal equipment | |
| CN117268535B (en) | Motor rotating shaft state monitoring method based on vibration data | |
| CN116610939B (en) | Asymmetric penalty sparse regularization pulse extraction method under Coiflet discrete wavelet | |
| CN112816213B (en) | Fault diagnosis method for wind turbine transmission system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| LAPS | Cancellation because of no payment of annual fees |