JPH04276539A - Method for estimating life of rotary machine due to damage and deterioration - Google Patents
Method for estimating life of rotary machine due to damage and deteriorationInfo
- Publication number
- JPH04276539A JPH04276539A JP6245391A JP6245391A JPH04276539A JP H04276539 A JPH04276539 A JP H04276539A JP 6245391 A JP6245391 A JP 6245391A JP 6245391 A JP6245391 A JP 6245391A JP H04276539 A JPH04276539 A JP H04276539A
- Authority
- JP
- Japan
- Prior art keywords
- life
- time
- series
- damage
- deterioration
- 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
- 230000006866 deterioration Effects 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 title claims description 16
- 239000011159 matrix material Substances 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims description 15
- 230000003595 spectral effect Effects 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 abstract description 11
- 238000003745 diagnosis Methods 0.000 abstract description 4
- 230000015572 biosynthetic process Effects 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 description 20
- 230000000875 corresponding effect Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 8
- 238000013075 data extraction Methods 0.000 description 6
- 238000007796 conventional method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 239000003638 chemical reducing agent Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000012886 linear function Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012887 quadratic function Methods 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000001845 vibrational spectrum Methods 0.000 description 1
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
Description
【０００１】0001
【産業上の利用分野】本発明は、ファン，ブロア，減速
機等の回転機械の損傷・劣化（以下、損傷という）の徴
候が認められた場合、適切な修理時期を決定する際に必
要となる機械が使用不能状態となるまでの期間（以下、
寿命という）や使用限度到達日を精度良く予測する寿命
予測方法に関するものである。[Industrial Application Field] The present invention is useful for determining the appropriate repair time when signs of damage or deterioration (hereinafter referred to as damage) are observed in rotating machinery such as fans, blowers, reducers, etc. The period until the machine becomes unusable (hereinafter referred to as
The present invention relates to a lifespan prediction method that accurately predicts the lifespan (called lifespan) and the date when the usage limit is reached.
【０００２】0002
【従来の技術】従来の寿命予測方法は、回転機械の振動
を検出してフィルタリングや包絡線処理等の信号処理を
行った後に、周波数分析を行い、各種損傷に対応する振
動スペクトル値（以下、特定スペクトル成分値という）
を求め、特定の損傷に対応する特定スペクトル成分値の
時系列データ分析結果から計算された損傷の進展に関す
る特徴量の時系列データを用い、時間を独立変数とし、
その後の損傷の進展に関する特徴量を従属変数とする予
測式、例えば一次関数式，二次関数式，指数関数式等を
最小自乗法等の方法で作成して時間軸に対し外挿するこ
とにより、損傷の進展に関する特徴量の予測値が所定の
限界値に達するまでの時間を寿命として予測するように
している。[Prior Art] Conventional life prediction methods detect the vibrations of rotating machinery, perform signal processing such as filtering and envelope processing, and then perform frequency analysis to obtain vibration spectrum values corresponding to various types of damage (hereinafter referred to as (referred to as specific spectral component value)
, using time series data of features related to damage progression calculated from the time series data analysis results of specific spectral component values corresponding to specific damage, with time as an independent variable,
By creating a prediction formula, such as a linear function formula, quadratic function formula, or exponential function formula, using a feature quantity related to the subsequent development of damage as a dependent variable, using a method such as the method of least squares, and extrapolating it to the time axis. , the time required for the predicted value of the feature amount related to the progression of damage to reach a predetermined limit value is predicted as the lifespan.
【０００３】0003
【発明が解決しようとする課題】しかしながら、従来の
方法では、特定周波数成分値の時系列データを数学的，
統計的に処理した結果、得られる予測式を使用している
ため、場合によっては損傷の進展が必ずしも数式で表現
できないことがあり、この場合は寿命予測値と実際の寿
命との間にかなりの誤差を生じるという問題があった。
一方、このような誤差が生じた場合に従来の方法は、寿
命予測式を実情に合致する形に変更し、この結果、ソフ
トウェアを修正・追加することが必要となるため、関連
ソフトウェアのメンテナンスコストが上昇したり、また
、ソフトメンテナンスが実施されないために別途人手を
介して寿命予測作業を行うことにもなり工数が増大する
等の問題があった。本発明の目的は、ソフトウェアを変
更することなしに、各種回転機械の状態や損傷の種類等
の実情に合致して損傷の進展が予測可能な複雑な形状の
寿命曲線を実用上忠実にかつ簡単に使用可能とすること
により、良好な寿命予測精度を得ることにある。[Problem to be Solved by the Invention] However, in the conventional method, time series data of specific frequency component values cannot be calculated mathematically.
Because we use prediction formulas obtained as a result of statistical processing, in some cases the progression of damage may not necessarily be expressed mathematically, and in this case there may be a considerable difference between the predicted lifespan and the actual lifespan. There was a problem in that errors occurred. On the other hand, when such an error occurs, the conventional method requires changing the life prediction formula to match the actual situation, and as a result, it is necessary to modify or add software, which reduces maintenance costs for related software. In addition, since software maintenance is not carried out, life prediction work has to be performed separately, resulting in an increase in man-hours. The purpose of the present invention is to create a life curve of a complex shape that can be predicted in accordance with the actual situation such as the condition of various rotating machines and the type of damage, without changing the software, in a practical and simple manner. The objective is to obtain good life prediction accuracy by making it usable for
【０００４】0004
【課題を解決するための手段】上述の目的を達成するた
めに本発明は、時系列的にスペクトル相対値を演算して
時系列特徴マトリックスを形成し、この時系列特徴マト
リックスから損傷・劣化の進展に関する特徴量を生成さ
せ、この特徴量と実際の回転機械で認識された損傷・劣
化の程度との対応を複数の定数値で関係づけることによ
り、回転機械の使用可能限界時期を予測するようにした
方法である。即ち、各回転機械毎，各損傷毎の進展の程
度を実際の回転機械で生起するパターンに合致させるた
めに、寿命曲線を各部分期間区分に対応した部分平均寿
命変化定数の集合体により表現させ、この各部分平均寿
命変化定数をシステムにデータとして入力可能とするこ
とにより、現実に起こる一般関係式では表現が困難な複
雑な形状の寿命曲線を任意に、かつ、ソフトウェアを変
更することなしに、簡便かつ精度良く使用可能とした方
法である。[Means for Solving the Problems] In order to achieve the above object, the present invention calculates relative spectral values in a time-series manner to form a time-series feature matrix, and uses this time-series feature matrix to determine damage/deterioration. By generating feature quantities related to progress and correlating the correspondence between these feature quantities and the degree of damage and deterioration recognized in actual rotating machines using multiple constant values, the usable limit of rotating machines can be predicted. This is the method I used. That is, in order to match the degree of progress of each damage for each rotating machine to the pattern that occurs in actual rotating machines, the life curve is expressed by a collection of partial average life change constants corresponding to each partial period division. By making it possible to input each partial mean life change constant into the system as data, it is possible to arbitrarily create life curves with complex shapes that are difficult to express using general relational expressions that occur in reality, and without changing the software. This method is simple and can be used with high accuracy.
【０００５】[0005]
【作用】本発明による回転機械の寿命予測方法は、実際
の回転機械の損傷の進展過程を各設備毎，各損傷毎に忠
実かつ簡便に表現可能とすることにより、回転機械の設
備診断データと複雑な形状をした実際の回転機械の損傷
進展による寿命曲線とを精度良くかつ簡便に対応させる
ことが可能となるもので、この結果、従来の方法に比し
て寿命予測の精度向上が可能となる。[Function] The life prediction method of rotating machinery according to the present invention enables accurate and simple representation of the progress of damage in actual rotating machinery for each piece of equipment and damage, thereby making it possible to use equipment diagnostic data for rotating machinery. This makes it possible to accurately and easily correspond to the life curve due to the damage progression of an actual rotating machine with a complex shape, and as a result, it is possible to improve the accuracy of life prediction compared to conventional methods. Become.
【０００６】[0006]
【実施例】以下、図面を用いて本発明の実施例を詳細に
説明する。図１は、本発明に係る回転機械の損傷・劣化
の寿命予測方法を適用したシステムの一実施例を示すブ
ロック系統図である。同図において、１は設備諸元入力
部、２は分析条件設定部、３は分析条件記憶部、４は振
動検出部、５は増幅器、６は信号処理部、７はＡ／Ｄ変
換器、８はディジタル周波数分析部である。また、９は
時系列データ演算部、１０は時系列特徴マトリックス記
憶部、１１は診断データ抽出部、１２は余寿命演算部、
１３は使用限度到達日演算部、１４は初期値スペクトル
記憶部、１５は制御部、１６は部分平均寿命定数設定部
、１７は寿命曲線演算部である。Embodiments Hereinafter, embodiments of the present invention will be explained in detail with reference to the drawings. FIG. 1 is a block system diagram showing an embodiment of a system to which a method for predicting the life of damage and deterioration of a rotating machine according to the present invention is applied. In the figure, 1 is an equipment specification input section, 2 is an analysis condition setting section, 3 is an analysis condition storage section, 4 is a vibration detection section, 5 is an amplifier, 6 is a signal processing section, 7 is an A/D converter, 8 is a digital frequency analysis section. Further, 9 is a time series data calculation unit, 10 is a time series feature matrix storage unit, 11 is a diagnostic data extraction unit, 12 is a remaining life calculation unit,
Reference numeral 13 designates a usage limit date calculation unit, 14 an initial value spectrum storage unit, 15 a control unit, 16 a partial average life constant setting unit, and 17 a life curve calculation unit.
【０００７】図１において、設備諸元入力部１は、診断
の対象となるファン，ブロア，減速機，ポンプ等の回転
機械の構成，減速機の歯車の枚数等の回転要素や軸受の
仕様等で示される設備諸元を入力する。分析条件設定部
２は、振動，回転数等の検出信号の種類と検出位置，信
号処理の種類，周波数分析周波数帯域，回転機械の各種
の異常に対応する周波数等の信号分析を自動的に実施す
るための条件・方法を規定するデータを設定し、分析条
件記憶部３においてこれらのデータは記憶される。また
、振動検出部４は、回転機械から発生する振動を検出し
、増幅器５でその振動信号を増幅し、信号処理部６でフ
ィルタリング等の信号処理を行った後、Ａ／Ｄ変換器７
によりアナログ／ディジタル変換を行う。また、ディジ
タル周波数分析器８はその周波数分析を行い、得られた
周波数スペクトルは時系列データ演算部９へ入力される
。初期値スペクトル記憶部１４には、ベースラインデー
タとしての初期値スペクトルが予め記憶されており、こ
のデータは時系列データ演算部９に入力される。時系列
データ演算部９は、回転機械の各種異常に対応する時系
列的特徴量を演算し、時系列特徴マトリックス記憶部１
０はこれを記憶する。In FIG. 1, an equipment specification input section 1 inputs the configuration of rotating machines such as fans, blowers, reducers, pumps, etc. to be diagnosed, specifications of rotating elements such as the number of gears of the reducer, bearings, etc. Enter the equipment specifications shown in . The analysis condition setting unit 2 automatically performs signal analysis such as the type and detection position of detection signals such as vibration and rotation speed, the type of signal processing, frequency analysis frequency band, and frequencies corresponding to various abnormalities in rotating machinery. Data defining conditions and methods for the analysis are set, and these data are stored in the analysis condition storage section 3. Further, the vibration detection unit 4 detects vibrations generated from the rotating machine, amplifies the vibration signal with the amplifier 5, performs signal processing such as filtering in the signal processing unit 6, and then sends the A/D converter 7 to the vibration signal.
performs analog/digital conversion. Further, the digital frequency analyzer 8 performs frequency analysis, and the obtained frequency spectrum is input to the time series data calculation section 9. The initial value spectrum storage unit 14 stores an initial value spectrum as baseline data in advance, and this data is input to the time series data calculation unit 9. The time-series data calculation unit 9 calculates time-series feature quantities corresponding to various abnormalities of the rotating machine, and the time-series feature matrix storage unit 1
0 remembers this.
【０００８】次に、表１に時系列特徴マトリックスの構
造例を示す。表１は、特定周波数における時系列の各デ
ータを示し、Ｓ０ （ｉ）は初期値スペクトル、Ｒ（ｉ
，１），Ｒ（ｉ，２）は時系列的相対スペクトル比であ
る。Next, Table 1 shows an example of the structure of a time-series feature matrix. Table 1 shows each time series data at a specific frequency, S0 (i) is the initial value spectrum, R (i
, 1), R(i, 2) is the time-series relative spectral ratio.
【０００９】[0009]
【表１】[Table 1]
【００１０】また、診断データ抽出部１１は、時系列特
徴マトリックス記憶部１０の中から時系列的相対スペク
トル比Ｒ（ｉ，ｊ）や診断実施時間情報等の寿命予測に
必要な各種の診断データを抽出する。余寿命演算部１２
は、診断データ抽出部１１で得られたデータと寿命曲線
演算部１７で生成された寿命曲線とから余寿命を演算す
る。使用限度到達日演算部１３は、余寿命演算部１２で
得られた余寿命と診断データ抽出部１１で得られたデー
タとを基に、使用限度到達日を演算する。部分平均寿命
定数設定部１６では、各部分期間区分に対応する部分平
均寿命変化率等の定数を設定する。寿命曲線演算部１７
では、部分平均寿命定数設定部１６で設定された定数を
基に寿命曲線を演算して生成する。制御部１５は、上記
の一連のプロセスを実行制御する機能を有している。[0010] The diagnostic data extraction unit 11 also extracts various diagnostic data necessary for life prediction, such as time-series relative spectral ratio R(i, j) and diagnosis implementation time information, from the time-series feature matrix storage unit 10. Extract. Remaining life calculation section 12
calculates the remaining life from the data obtained by the diagnostic data extraction section 11 and the life curve generated by the life curve calculation section 17. The use limit reaching date calculation unit 13 calculates the use limit reaching date based on the remaining life obtained by the remaining life calculating unit 12 and the data obtained by the diagnostic data extraction unit 11. The partial average life constant setting unit 16 sets constants such as partial average life change rate corresponding to each partial period division. Life curve calculation section 17
Now, a life curve is calculated and generated based on the constant set by the partial average life constant setting section 16. The control unit 15 has a function of controlling execution of the series of processes described above.
【００１１】次に、寿命予測の方法について説明する。
時系列データ演算部９は、図２（ａ）に例示した初期値
スペクトルＳ０ （ｉ）と、ディジタル周波数分析部８
で得られた図２（ｂ）に例示した時系列スペクトルＳ（
ｉ，ｊ）とから、時系列的スペクトル比Ｒ（ｉ，ｊ）＝
Ｓ（ｉ，ｊ）／Ｓ０ （ｉ）といったような、異常に対
応するスペクトル成分や、スペクトルの特徴を表現する
指標についての時系列的相対値等の時系列的特徴量を演
算し、時系列特徴マトリックスを形成する。部分平均寿
命定数設定部１６は、図３に例示したような寿命曲線を
各部分期間区分に対応する部分平均寿命変化定数で定義
するための定数類を設定する。寿命曲線演算部１７は、
部分平均寿命定数設定部１６で設定された定数を基に、
図３に例示したような寿命曲線を演算して生成する。[0011] Next, a method for predicting life will be explained. The time series data calculation section 9 uses the initial value spectrum S0 (i) illustrated in FIG. 2(a) and the digital frequency analysis section 8.
The time series spectrum S(
i, j), the time-series spectral ratio R(i, j)=
Time-series features such as spectral components corresponding to abnormalities such as S(i, j)/S0 (i) and time-series relative values of indicators expressing spectral characteristics are calculated, and time-series Form a feature matrix. The partial average life constant setting unit 16 sets constants for defining the life curve as illustrated in FIG. 3 by partial average life change constants corresponding to each partial period division. The life curve calculation unit 17
Based on the constant set by the partial average life constant setting section 16,
A life curve as illustrated in FIG. 3 is calculated and generated.
【００１２】次に、余寿命演算部１２は、診断データ抽
出部１１で得られた時系列的相対スペクトル比Ｒ（ｉ，
ｊ）に対応する余寿命ｌ（ｉ，ｊ）を寿命曲線演算部１
７で生成された寿命曲線から演算する。使用限界到達日
演算部１３は、余寿命演算部１２で得られた余寿命ｌ（
ｉ，ｊ）と診断データ抽出部１１で得られた診断データ
とから当該回転機械での各種損傷に対応する使用限度到
達日を演算する。Next, the remaining life calculation unit 12 calculates the time-series relative spectral ratio R(i,
The remaining life l(i, j) corresponding to j) is calculated by the life curve calculation unit 1
Calculate from the life curve generated in step 7. The usage limit arrival date calculation unit 13 calculates the remaining life l(
i, j) and the diagnostic data obtained by the diagnostic data extraction unit 11, the use limit reaching date corresponding to various types of damage in the rotating machine is calculated.
【００１３】上記の例のように、実際の回転機械で起こ
る相当複雑な寿命曲線を実用上任意にかつ容易に定義し
て使用可能としているため、一次関数，二次関数，指数
関数等の関数においては表現できないタイプの損傷の寿
命予測を精度良く行うことができる。As shown in the above example, since it is possible to define and use fairly complex life curves that occur in actual rotating machines arbitrarily and easily, functions such as linear functions, quadratic functions, and exponential functions can be used. It is possible to accurately predict the lifespan of types of damage that cannot be expressed in the conventional method.
【００１４】[0014]
【発明の効果】以上説明したように本発明は、設備診断
で得られる時系列的スペクトル比等の診断データと実際
の機械で生起する損傷の時系列的進展過程を部分期間区
分毎に定義される平均寿命変化定数の集合化により、複
雑な形状の寿命曲線を定数の入力により生成させて互い
に関連づけることにより、機械の損傷による寿命予測を
精度良く行えるとともに、ソフトウェアの変更を必要と
せずに簡便に少ない労力で予測できるという効果がある
。また、年々蓄積される設備診断データと点検整備デー
タとを対応させて整理・分析することより得られる寿命
予測に関する知見，ノウハウを定数化して入力すること
により、寿命予測の大幅な精度向上が期待できるという
効果がある。[Effects of the Invention] As explained above, the present invention defines diagnostic data such as time-series spectral ratios obtained in equipment diagnosis and the time-series progression process of damage occurring in actual machinery for each partial period. By aggregating average life change constants, complex-shaped life curves can be generated by inputting constants and correlated with each other, making it possible to accurately predict the life of a machine due to damage, and making it easy to predict without changing the software. This has the effect of allowing predictions to be made with little effort. In addition, by inputting the knowledge and know-how related to lifespan prediction obtained by correlating and analyzing equipment diagnosis data and inspection and maintenance data accumulated year by year in a constant form, it is expected that the accuracy of lifespan prediction will be significantly improved. There is an effect that it can be done.
【図１】本発明に係る回転機械の損傷・劣化の寿命予測
方法を適用したシステムの一実施例を示すブロック系統
図である。FIG. 1 is a block system diagram showing an embodiment of a system to which a method for predicting the life of damage and deterioration of a rotating machine according to the present invention is applied.
【図２】スペクトル成分値と周波数との関係を示す特性
図である。FIG. 2 is a characteristic diagram showing the relationship between spectral component values and frequency.
【図３】本発明の一実施例が適用される寿命曲線の特性
図である。FIG. 3 is a characteristic diagram of a life curve to which an embodiment of the present invention is applied.
１ 設備諸元入力部
２ 分析条件設定部
３ 分析条件記憶部
４ 振動検出部
５ 増幅器
６ 信号処理部
７ Ａ／Ｄ変換器
８ ディジタル周波数分析部
９ 時系列データ演算部
１０ 時系列特徴マトリックス記憶部１１
診断データ抽出部
１２ 余寿命演算部
１３ 使用限度到達日演算部
１４ 初期値スペクトル記憶部
１５ 制御部
１６ 部分平均寿命定数設定部
１７ 寿命曲線演算部1 Equipment specification input section 2 Analysis condition setting section 3 Analysis condition storage section 4 Vibration detection section 5 Amplifier 6 Signal processing section 7 A/D converter 8 Digital frequency analysis section 9 Time series data calculation section 10 Time series feature matrix storage section 11
Diagnostic data extraction unit 12 Remaining life calculation unit 13 Usage limit date calculation unit 14 Initial value spectrum storage unit 15 Control unit 16 Partial average life constant setting unit 17 Life curve calculation unit
Claims (1)
時系列データの分析結果から計算された複数の特徴量に
基づき回転機械の損傷・劣化の進行を予測する寿命予測
方法において、時系列的にスペクトル相対値を演算して
時系列特徴マトリックスを形成し、この時系列特徴マト
リックスから損傷・劣化の進展に関する特徴量を生成さ
せ、この特徴量と実際の回転機械で認識された損傷・劣
化の程度との対応を複数の定数値で関係づけることによ
り、回転機械の使用可能限界時期を予測するようにした
ことを特徴とする回転機械の損傷・劣化の寿命予測方法
。Claim 1. A life prediction method for predicting the progression of damage and deterioration of a rotating machine based on a plurality of feature quantities calculated from detection signals representing the state of the rotating machine and analysis results of time-series data. A time-series feature matrix is formed by calculating the relative spectral values, a feature value related to the progress of damage/deterioration is generated from this time-series feature matrix, and this feature value is compared with the degree of damage/deterioration recognized in the actual rotating machine. A method for predicting the lifespan of damage and deterioration of a rotating machine, characterized in that the usable limit period of the rotating machine is predicted by correlating the correspondence with a plurality of constant values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP6245391A JP2924243B2 (en) | 1991-03-05 | 1991-03-05 | Life prediction method for damage / deterioration of rotating machinery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP6245391A JP2924243B2 (en) | 1991-03-05 | 1991-03-05 | Life prediction method for damage / deterioration of rotating machinery |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPH04276539A true JPH04276539A (en) | 1992-10-01 |
| JP2924243B2 JP2924243B2 (en) | 1999-07-26 |
Family
ID=13200643
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP6245391A Expired - Lifetime JP2924243B2 (en) | 1991-03-05 | 1991-03-05 | Life prediction method for damage / deterioration of rotating machinery |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP2924243B2 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002014067A (en) * | 2000-06-30 | 2002-01-18 | Toshiba Corp | Method and apparatus for diagnosing deterioration of coating film |
| KR20190064916A (en) * | 2017-12-01 | 2019-06-11 | 한국생산기술연구원 | Efficiency Prediction System And Method For Rotating Device Using Transformation Of Learning data |
| CN113609666A (en) * | 2021-07-30 | 2021-11-05 | 北京瑞凯软件科技开发有限公司 | Method and system for predicting service life of isolating switch of rail transit equipment |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3449194B2 (en) * | 1997-01-28 | 2003-09-22 | 松下電工株式会社 | Method and apparatus for diagnosing abnormalities in rotating equipment |
| DE10144076A1 (en) * | 2001-09-07 | 2003-03-27 | Daimler Chrysler Ag | Method for early recognition and prediction of unit damage or wear in machine plant, particularly mobile plant, based on vibration analysis with suppression of interference frequencies to improve the reliability of diagnosis |
| JP3967245B2 (en) * | 2002-09-30 | 2007-08-29 | 株式会社東芝 | Method for predicting life of rotating machine and manufacturing apparatus having rotating machine |
| KR101992238B1 (en) * | 2017-11-28 | 2019-06-25 | 한국생산기술연구원 | System For Diagnosis of Degradation Status and Predicting Remaining Useful Life of Rotating Device |
| KR102014820B1 (en) * | 2017-12-01 | 2019-08-27 | 한국생산기술연구원 | Efficiency Prediction System For Rotating Device Using Deep Learning |
-
1991
- 1991-03-05 JP JP6245391A patent/JP2924243B2/en not_active Expired - Lifetime
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002014067A (en) * | 2000-06-30 | 2002-01-18 | Toshiba Corp | Method and apparatus for diagnosing deterioration of coating film |
| KR20190064916A (en) * | 2017-12-01 | 2019-06-11 | 한국생산기술연구원 | Efficiency Prediction System And Method For Rotating Device Using Transformation Of Learning data |
| CN113609666A (en) * | 2021-07-30 | 2021-11-05 | 北京瑞凯软件科技开发有限公司 | Method and system for predicting service life of isolating switch of rail transit equipment |
| CN113609666B (en) * | 2021-07-30 | 2024-04-19 | 北京瑞凯软件科技开发有限公司 | Method and system for predicting service life of isolating switch of rail transit equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2924243B2 (en) | 1999-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7216063B2 (en) | Method and apparatus for comparing a data set to a baseline value | |
| CN110008565B (en) | Industrial process abnormal working condition prediction method based on operation parameter correlation analysis | |
| CN109033930B (en) | Equipment fault diagnosis method based on fault mechanism and statistical model online learning | |
| CN110785717B (en) | Abnormal state diagnostic device and abnormal state diagnostic method for process | |
| CN107291991B (en) | Early defect early warning method for wind turbine generator based on dynamic network sign | |
| KR20060100248A (en) | Inspection apparatus, aid device for creating judgment model therefor, abnormality detection device for endurance test apparatus and endurance test method | |
| CN111307438B (en) | Rotary machine vibration fault diagnosis method and system based on information entropy | |
| CN111401584A (en) | Automatic diagnosis method and system for equipment fault | |
| CN115516395A (en) | Abnormality diagnosis method, abnormality diagnosis device, and abnormality diagnosis program | |
| CN111122191B (en) | Equipment health alarm threshold setting method based on EWMA control | |
| CN111337237A (en) | Equipment fault diagnosis method and system | |
| CN114330834A (en) | Charging pile power consumption prediction method based on self-updating cubic exponential smoothing method | |
| JPH04276539A (en) | Method for estimating life of rotary machine due to damage and deterioration | |
| JP3108405B2 (en) | Device diagnosis method | |
| JPH0843257A (en) | Method for diagnosing planetary gear | |
| JP2002090266A (en) | Remaining life-predicting device | |
| US11449781B2 (en) | Plant abnormality prediction system and method | |
| JP2004361286A (en) | Method of diagnosing deterioration of rotary machine | |
| JPH0399234A (en) | Diagnosing method for abnormality of rotary machine | |
| JP2924242B2 (en) | Diagnosis method for fluctuating rotating machinery | |
| CN115408897A (en) | Harbor machine health assessment method based on vibration spectrum discontinuous reverse correction | |
| JPH02141897A (en) | Preventive maintenance expert system | |
| CN115099106A (en) | Structure safe operation state evaluation method based on self-healing closed convex coefficient | |
| CN115034116A (en) | Structural health state assessment method based on healing regulatory factor | |
| CN116464626A (en) | Method for diagnosing running state of motor of feed pump |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20090507 Year of fee payment: 10 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20090507 Year of fee payment: 10 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20100507 Year of fee payment: 11 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20110507 Year of fee payment: 12 |
|
| EXPY | Cancellation because of completion of term |