CN111353482A - LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method - Google Patents

LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method Download PDF

Info

Publication number
CN111353482A
CN111353482A CN202010445803.3A CN202010445803A CN111353482A CN 111353482 A CN111353482 A CN 111353482A CN 202010445803 A CN202010445803 A CN 202010445803A CN 111353482 A CN111353482 A CN 111353482A
Authority
CN
China
Prior art keywords
data
lstm
fault
model
abnormal
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
Application number
CN202010445803.3A
Other languages
Chinese (zh)
Other versions
CN111353482B (en
Inventor
冯海领
焦正杉
孙敬哲
王汉奇
王向敏
赵宜斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin Development Zone Jingnuo Hanhai Data Technology Co ltd
Original Assignee
Tianjin Development Zone Jingnuo Hanhai Data Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin Development Zone Jingnuo Hanhai Data Technology Co ltd filed Critical Tianjin Development Zone Jingnuo Hanhai Data Technology Co ltd
Priority to CN202010445803.3A priority Critical patent/CN111353482B/en
Publication of CN111353482A publication Critical patent/CN111353482A/en
Application granted granted Critical
Publication of CN111353482B publication Critical patent/CN111353482B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/08—Feature extraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching

Abstract

The invention discloses a fatigue factor recessive anomaly detection and fault diagnosis method based on LSTM, which comprises the following steps: s1, collecting time sequence data of target equipment of a diagnosis object, and carrying out empirical mode decomposition on the data; s2, constructing an equipment vibration signal prediction model based on the LSTM by using normal data; s3, classifying the collected abnormal data, and constructing a fault time sequence data classification model based on the LSTM; s4, taking the mean square error MSE of the obtained vibration signal prediction model based on the LSTM as an initial fatigue factor threshold; s5, predicting the equipment production data by using a vibration signal prediction model based on the LSTM, calculating the mean square error of a predicted value and an actual value, and comparing the mean square error with an initial fatigue factor threshold value to detect an abnormal signal; and S6, classifying the abnormal signals through a fault time sequence data classification model to obtain a fault diagnosis result.

Description

LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method
Technical Field
The invention relates to the field of equipment fault diagnosis, in particular to a fatigue factor recessive abnormality detection and fault diagnosis method based on LSTM.
Background
With the explosion of the technology of the internet of things, 5G, artificial intelligence, cloud computing and the like in the form of "nuclear fusion", the strategy of "re-industrialization" made by major industrial countries around intelligent manufacturing is also very dust-laden. China firstly proposes an intelligent plus concept in a government work report of 2019, and determines intelligent manufacturing as an important development direction of new kinetic energy for national economic development.
The current fault diagnosis methods are mainly classified into two categories: a signal processing based method and a machine learning based method. Common methods based on signal processing include Spectral Kurtosis Analysis (Spectral Kurtosis), sparse Decomposition Analysis (sparse Decomposition Analysis), Time-frequency domain Analysis (Time-frequency Analysis), Wavelet Transform (WT), Empirical Mode Decomposition (EMD); the Machine learning-based methods mainly include Hidden Markov Models (HMMs), bayesian networks (bayesian networks), Support Vector Machines (SVMs) and Recurrent Neural Networks (RNNs), and the methods have achieved better research results in the field of fault diagnosis. Signal processing-based methods generally require a large number of highly experienced engineers to analyze the fault information contained in the signal, making it difficult to obtain a fault diagnosis result in a programmed manner; the method based on machine learning just makes up for the above defects of the signal processing method, and well expands the fault diagnosis method, but brings new challenges on fault diagnosis data. Generally, data recorded by a digital infrastructure in an industrial scene are mostly normal data, the data contain huge amount of information, and influence factors in aspects of product quality, energy consumption, production cost and the like are concerned, but the fault information in the data is few and few, so that how much equipment reliability is, how much fault data is, and fault information extraction is another new challenge in a large intelligent manufacturing background. In order to deal with the problem of unbalanced data, technologies such as undersampling, oversampling, and synthesizing a few classes of oversampling have been provided, and these methods have achieved good results in corresponding documents, but the undersampling technology may result in a reduction in data volume, and the oversampling technology may result in an increase in noise, and these problems may ultimately affect the accuracy of the training model.
Disclosure of Invention
In order to solve the problems caused by characteristics of unbalanced equipment data, high noise, time sequence and the like in the field of intelligent manufacturing, the invention provides a fatigue factor recessive abnormality detection and fault diagnosis method based on LSTM. The invention improves the unbalanced data processing method, the classification model and the abnormality detection method in the traditional fault diagnosis, can effectively avoid the problems caused by unbalanced data, can detect the slight change of equipment, and can early warn abnormal signals in time so as to detect the problems of equipment abrasion, aging and the like.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a fatigue factor recessive abnormality detection and fault diagnosis method based on LSTM comprises the following steps:
s1, collecting time sequence sample data of the target equipment of the diagnosis object, wherein the sample comprises normal data, abnormal data and fault types of the abnormal data, and performing empirical mode decomposition on the time sequence sample data of the equipment by using an EMD method;
s2, extracting normal data samples in the time sequence sample data, and constructing an equipment vibration signal prediction model by using an LSTM-based deep neural network;
s3, extracting abnormal data samples in the time sequence sample data, and constructing a fault time sequence data classification model by using an LSTM-based deep neural network;
s4, acquiring the Mean Square Error (MSE) of the vibration signal prediction model based on the LSTM, and taking the MSE as an initial fatigue factor threshold;
s5, using vibration signal prediction model based on LSTMPredicting the production data of the equipment, calculating the mean square error between the predicted value and the actual value, comparing the mean square error with the initial fatigue factor threshold value to detect abnormal signals, and dynamically adjusting the threshold value according to the actual situation
Figure 183636DEST_PATH_IMAGE001
；
And S6, classifying the abnormal signals through a fault time sequence data classification model to obtain a fault diagnosis result.
Further, the process of constructing the device vibration signal prediction model based on the LSTM deep neural network in step S2 includes the following steps:
s2-1: characteristic engineering: firstly, processing collected original data, performing auxiliary judgment by using EMD (empirical mode decomposition) and waveform visualization technology, and identifying abnormal vibration frequency by observing IMF (intrinsic mode function) components;
s2-2: resampling: original data are re-sampled, abnormal data fragments in the original data are deleted, the fact that continuous normal data exist in the remaining data and only exist in the remaining data is guaranteed, and the problem of data unbalance caused by unbalanced data is solved;
s2-3: data normalization: normalizing the data of each dimension in the time series, and calculating the mean value of each dimension
Figure 835197DEST_PATH_IMAGE002
And standard deviation of
Figure 83776DEST_PATH_IMAGE003
The time-series sample data X is normalized by the following formula, and the normalized data is X':
Figure 440502DEST_PATH_IMAGE004
（1）
s2-4: and (3) carrying out format conversion on the data set: converting the unsupervised data set into a supervised data set, dividing the normalized data into a continuous time series X of length lr，XrLength of (d) is input by the model as length lsAnd an output length lpDetermined together, their relationship is the total length
Figure 989295DEST_PATH_IMAGE005
Dividing time series sample data X into XsAnd XpTwo parts, which are used as input and output samples of the model;
s2-5: dividing the data set: randomly arranging data, and dividing input data X according to same proportionsAnd output data XpObtaining a training data set
Figure 280599DEST_PATH_IMAGE006
And validating the data set
Figure 16474DEST_PATH_IMAGE007
；
S2-6: constructing a model: setting check points, saving model parameters once per Epoch, adjusting Epoch and Dropout parameters, and observing trainloss and valloss, using an early stop mechanism when an over-fit condition occurs;
s2-7: classification using models: inputting a segment of time sequence sample data X to obtain a prediction vector
Figure 684216DEST_PATH_IMAGE008
Then, calculating a mean square error MSE according to the actual value y for evaluating the prediction effect, wherein n is the sequence number:
Figure 87516DEST_PATH_IMAGE009
（2）。
further, the process of constructing the fault time series data classification model based on the LSTM deep neural network in step S3 includes the following steps:
s3-1: firstly, processing fault data samples of time sequence sample data of equipment, using data which has abnormality and has determined fault types, and additionally adding normal samples with the same quantity as each fault sample;
s3-2: empirical mode decomposition of time series sample data(EMD) to obtain an m-dimensional vector containing IMF components
Figure 549721DEST_PATH_IMAGE010
M is determined by empirical mode decomposition, imfiIs the ith dimension component;
s3-3: numbering imf of n-type time sequence data to obtain model input data Xc
Figure 772892DEST_PATH_IMAGE011
（3）
Determining the output data y of the model from the numbersc
Figure 244324DEST_PATH_IMAGE012
（4）
S3-4: normalizing the data and calculating the mean of the samples
Figure 236551DEST_PATH_IMAGE002
And standard deviation of
Figure 633772DEST_PATH_IMAGE003
Normalized data is
Figure 609819DEST_PATH_IMAGE013
：
Figure 353784DEST_PATH_IMAGE014
（5）
S3-5: dividing data set, randomly arranging data, and dividing input data X according to same proportioncAnd output data ycObtaining a training data set
Figure 466096DEST_PATH_IMAGE006
And validating the data set
Figure 535683DEST_PATH_IMAGE007
；
S3-6: training model, setupChecking points, saving model parameters once per Epoch, adjusting Epoch and Dropout parameters, and observing trainloss and valloss, using an early stop mechanism when an over-fit condition occurs;
s3-7: classifying by using model, inputting a time sequence XcObtaining a classification vector y', then the fault number
Figure 733446DEST_PATH_IMAGE015
The corresponding fault is found by numbering, argmax being the parameter of the maximum value.
Further, the step S5 of predicting the equipment production data by using the vibration signal prediction model based on LSTM specifically includes:
predicting the value of time t using a prediction model
Figure 281102DEST_PATH_IMAGE016
Calculated according to the actual value
Figure 513501DEST_PATH_IMAGE017
Calculating a prediction error:
Figure 753989DEST_PATH_IMAGE018
（6）
wherein
Figure 672004DEST_PATH_IMAGE019
I is the dimension of the true monitor value, and then every error is calculated
Figure 23351DEST_PATH_IMAGE020
Added to the vector of prediction errors:
Figure 844677DEST_PATH_IMAGE021
（7）
h is the number of historical errors used to estimate the current error, lsFor the length of the input sequence, the set of errors e is then smoothed, and an error threshold is selected for the set of errors
Figure 256066DEST_PATH_IMAGE022
-the value of the mean square error above the threshold is classified as abnormal:
Figure 428422DEST_PATH_IMAGE023
（8）
Figure 317880DEST_PATH_IMAGE022
is a vector of threshold errors, esIs a sequence error vector, z is a constant,
Figure 259292DEST_PATH_IMAGE002
is a mean value
Figure 841583DEST_PATH_IMAGE003
Is a standard deviation of wherein
Figure 235655DEST_PATH_IMAGE022
Determined by equation (9):
Figure 692919DEST_PATH_IMAGE024
（9）
wherein:
Figure 223257DEST_PATH_IMAGE025
（10）
e in the formula (9)seqIs composed of
Figure 976450DEST_PATH_IMAGE026
A continuous sequence of (a).
Figure 857818DEST_PATH_IMAGE022
Is estimated by
Figure 620238DEST_PATH_IMAGE027
Determining that z is an ordered set of positive integers representing greater than
Figure 270662DEST_PATH_IMAGE028
The number of standard deviations, the value of z depending on experimental data, once
Figure 194755DEST_PATH_IMAGE029
Is determined to produce a sequence of anomalies for each of the mean square errors
Figure 563420DEST_PATH_IMAGE030
A score is made and the score s is used to indicate the severity of the anomaly, i.e. the fatigue factor:
Figure 863951DEST_PATH_IMAGE031
（11）
the highest mean square error in each anomalous error sequence is then determined based on its correlation with a selected threshold
Figure 634461DEST_PATH_IMAGE001
Is normalized.
Further, in the step S5, the threshold is dynamically adjusted according to the actual situation
Figure 968271DEST_PATH_IMAGE001
The method specifically comprises the following steps:
in the step S5, the threshold is dynamically adjusted according to the actual situation
Figure 824232DEST_PATH_IMAGE001
The method specifically comprises the following steps:
creating a new collection
Figure 928454DEST_PATH_IMAGE032
Including all in descending order
Figure 287891DEST_PATH_IMAGE033
Maximum value of
Figure 819367DEST_PATH_IMAGE034
Then, howeverPost-cursor maximum non-abnormal mean square error
Figure 897044DEST_PATH_IMAGE035
Is added to
Figure 539378DEST_PATH_IMAGE032
At the end, the sequence is gradually decreased, and the decrease of the ith step is:
Figure 18901DEST_PATH_IMAGE036
（12）
if the amplitude d is reduced at a certain step i(i)Greater than the minimum drop amplitude p, all satisfy
Figure 455699DEST_PATH_IMAGE037
Figure 784787DEST_PATH_IMAGE038
Is still an abnormal sequence; if the amplitude is decreased by d(i)Less than the minimum reduction p, then the reduction of all subsequent errors
Figure 965232DEST_PATH_IMAGE039
Are reclassified as normal values.
Adopt the produced beneficial effect of above-mentioned technical scheme to lie in:
(1) aiming at the problem that enough fault samples are difficult to collect in the initial stage of a production environment, an LSTM-based vibration signal prediction model anomaly detection method is provided, the existing data non-equilibrium characteristics are fully utilized, and anomaly signals generated by equipment are effectively detected;
(2) aiming at the problem that the equipment aging wear condition is not evaluated in the current research situation, a fatigue factor recessive fault detection method is provided on the basis of (1), a threshold value can be found in fluctuating data to distinguish normal data from abnormal data, and the threshold value is dynamically adjusted in incremental learning so as to achieve the purpose of detecting potential abnormality;
(3) in consideration of the characteristic that fault time sequence data have complex time relevance, a fault time sequence data classification model fusing EMD feature extraction is provided, the fault diagnosis method uses EMD to perform feature processing and denoising, and uses a LSTM structure-based deep neural network to extract features on a time dimension so as to improve the fault classification accuracy.
Drawings
FIG. 1 is a flow chart of a vibration signal prediction model based on LSTM;
FIG. 2 is a fault timing data classification model incorporating EMD feature extraction;
FIG. 3 is a flowchart of the overall structure of the LSTM-based incremental learning latent fault diagnosis method;
FIG. 4 ARIMA, RNN, Stacked LSTM predict effect;
FIG. 5 a vibration signal;
FIG. 6 Normal data EMD decomposition;
fig. 7 inner ring fault data EMD decomposition.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
S1, collecting time sequence sample data of the target equipment of the diagnosis object, wherein the sample comprises normal data, abnormal data and fault types of the abnormal data, and performing empirical mode decomposition on the time sequence sample data of the equipment by using an EMD method;
the experimental verification of the invention uses experimental data containing three faults of an Inner ring (Inner Raceway Fault), an Outer ring (Outer Raceway Fault) and a rolling body (Ball Fault);
s2, extracting normal data samples in the time sequence sample data, and constructing an equipment vibration signal prediction model by using an LSTM-based deep neural network;
the flow of the vibration signal prediction model based on the LSTM proposed by the present invention is described as follows, and the flow chart of the model is shown in fig. 1.
Step 1: characteristic engineering: firstly, processing collected original data, performing auxiliary judgment by using EMD (empirical mode decomposition) and waveform visualization technology, and identifying abnormal vibration frequency by observing IMF (intrinsic mode function) components;
step 2: resampling: original data are re-sampled, abnormal data fragments in the original data are deleted, the fact that continuous normal data exist in the remaining data and only exist in the remaining data is guaranteed, and the problem of data unbalance caused by unbalanced data is solved;
and step 3: data normalization: normalizing the data of each dimension in the time series, and calculating the mean value of each dimension
Figure 299262DEST_PATH_IMAGE002
And standard deviation of
Figure 906960DEST_PATH_IMAGE003
The time-series sample data X is normalized by the following formula. The data normalization processing is beneficial to the initialization of the model, avoids the influence on the updating of the gradient value due to the numerical value deviation problem, and is convenient to use the fixed learning rate to iterate the model, thereby accelerating the convergence speed of the model;
Figure 959230DEST_PATH_IMAGE004
（1）
and 4, step 4: and (3) carrying out format conversion on the data set: converting the unsupervised data set into a supervised data set, dividing the normalized data into a continuous time series X of length lr，XrLength of (d) is input by the model as length lsAnd an output length lpAre determined jointly, their relationship is
Figure 943367DEST_PATH_IMAGE005
Dividing time series sample data X into XsAnd XpTwo parts, which are used as input and output samples of the model;
and 5: dividing the data set: randomly arranging data, and dividing input data X according to same proportionsAnd output data XpObtaining a training data set
Figure 397482DEST_PATH_IMAGE006
And validating the data set
Figure 176082DEST_PATH_IMAGE007
；
Step 6: constructing a model: setting check points, saving model parameters once per Epoch, adjusting Epoch and Dropout parameters, and observing trainloss and valloss, using an Early Stop mechanism (Early-Stop) when an overfitting condition occurs;
and 7: classification using models: inputting a segment of time sequence sample data X to obtain a prediction vector
Figure 981227DEST_PATH_IMAGE008
Then, calculating a mean square error MSE according to the actual value y for evaluating the prediction effect, wherein n is the sequence number:
Figure 2010DEST_PATH_IMAGE009
（2）。
s3, extracting abnormal data samples in the time sequence sample data, and constructing a fault time sequence data classification model by using an LSTM-based deep neural network;
the fault time sequence data classification model process integrating EMD feature extraction provided by the invention is described as follows, and a model flow chart is shown in FIG. 2.
Step 1: firstly, processing fault samples of equipment time sequence data, using data which has abnormality and has determined fault types, and additionally adding normal samples with the same quantity as each fault sample;
step 2: EMD decomposition is carried out on the sample time sequence data to obtain an m-dimensional vector containing IMF components
Figure 576211DEST_PATH_IMAGE010
M is determined by empirical mode decomposition, imfiIs the ith dimension component;
and step 3: numbering imf of n-type time sequence data to obtain model input data Xc，
Figure 525712DEST_PATH_IMAGE011
（3）
Determining the output data y of the model from the numbersc：
Figure 552574DEST_PATH_IMAGE012
（4）
And 4, step 4: normalizing the data and calculating the mean of the samples
Figure 878513DEST_PATH_IMAGE002
And standard deviation of
Figure 41641DEST_PATH_IMAGE003
Inputting data X to the model by equation (5)cNormalization was performed:
Figure 427623DEST_PATH_IMAGE014
（5）；
and 5: dividing data set, randomly arranging data, and dividing model input data X according to same proportioncAnd output data ycObtaining a training data set
Figure 941781DEST_PATH_IMAGE006
And validating the data set
Figure 805832DEST_PATH_IMAGE007
；
Step 6: training the model, setting check points, storing model parameters once per Epoch, adjusting Epoch and Dropout parameters, and observing trainloss and valloss, using an Early Stop mechanism (Early-Stop) when an overfitting condition occurs;
and 7: classifying by using model, inputting a time sequence XcObtaining a classification vector y', then the fault number
Figure 89046DEST_PATH_IMAGE015
And finding out the corresponding fault through the number.
S4, acquiring the Mean Square Error (MSE) of the vibration signal prediction model based on the LSTM, and taking the MSE as an initial fatigue factor threshold;
s5, predicting the production data of the equipment by using a vibration signal prediction model based on LSTM, calculating the mean square error between a predicted value and an actual value, comparing the mean square error with an initial fatigue factor threshold value to detect an abnormal signal, and dynamically adjusting the threshold value according to the actual condition
Figure 144464DEST_PATH_IMAGE001
(ii) a Predicting the value of time t using a prediction model
Figure 880339DEST_PATH_IMAGE016
Calculating, from the actual value, a prediction error:
Figure 813660DEST_PATH_IMAGE018
（6）
wherein
Figure 685801DEST_PATH_IMAGE019
And i is the dimension of the true monitoring value. Then each error is compared
Figure 413586DEST_PATH_IMAGE020
Added to the vector of prediction errors:
Figure 636757DEST_PATH_IMAGE021
（7）
h is the number of historical errors used to estimate the current error, lsIs the length of the input sequence. This set of errors e is then smoothed to suppress abrupt changes in errors that often occur in LSTM-based prediction-abrupt changes that are typically difficult for prediction models to predict, and that can also lead to abrupt changes in error values even if such data is normal. To determine whether these values are normal, the present invention sets a threshold for their smoothed prediction error-values of mean square error above the threshold are classified as abnormal.
In calculating the prediction error threshold, the method can be implemented by using a supervisor with a sample labelThe method learns to find a suitable anomaly threshold, but in general there are not enough label samples, especially if the device is operating properly without a large amount of fault data. The threshold calculation method provided by the invention does not need to use sample label data or statistical hypothesis test about errors, and can have higher performance under the condition of lower resource consumption. Selecting an error threshold in the error set
Figure 108189DEST_PATH_IMAGE022
：
Figure 100416DEST_PATH_IMAGE023
（8）
Figure 264681DEST_PATH_IMAGE022
Is a vector of threshold errors, esIs a sequence error vector, z is a constant,
Figure 709569DEST_PATH_IMAGE002
is a mean value
Figure 500806DEST_PATH_IMAGE003
Is a standard deviation of wherein
Figure 613118DEST_PATH_IMAGE022
Determined by equation (9):
Figure 417126DEST_PATH_IMAGE024
（9）
wherein:
Figure 880469DEST_PATH_IMAGE025
（10）
e in the formula (9)seqIs composed of
Figure 428125DEST_PATH_IMAGE026
A continuous sequence of (a).
Figure 660523DEST_PATH_IMAGE022
Is estimated by
Figure 635432DEST_PATH_IMAGE027
Determining that z is an ordered set of positive integers representing greater than
Figure 586071DEST_PATH_IMAGE028
Number of standard deviations. The value of z depends on experimental data, the normal range in the experiment of the invention is 2-8, and when z is less than 2, the false alarm is generally excessive. Once the cover is closed
Figure 937418DEST_PATH_IMAGE029
Is determined to produce a sequence of anomalies for each of the mean square errors
Figure 758743DEST_PATH_IMAGE030
A score is made and the score s is used to indicate the severity of the anomaly, i.e. the fatigue factor:
Figure 934247DEST_PATH_IMAGE031
（11）
in short, if a threshold is found
Figure 841023DEST_PATH_IMAGE001
The minus score s is greater than
Figure 996061DEST_PATH_IMAGE001
Then the mean square error e of the remaining sequencesMean value of
Figure 937472DEST_PATH_IMAGE028
And standard deviation of
Figure 519763DEST_PATH_IMAGE040
Will be greatly reduced. This method is also applicable to sequences with a large number of anomalies (
Figure 913836DEST_PATH_IMAGE041
) Penalizing to avoid excessive deviation, then, the highest mean square error in each abnormal error sequence according to the selected threshold
Figure 872564DEST_PATH_IMAGE001
Is normalized.
In order to reduce the false alarm rate and the calculation amount, the invention provides the following threshold value adjusting strategy: creating a new collection
Figure 668482DEST_PATH_IMAGE042
Including all in descending order
Figure 421674DEST_PATH_IMAGE033
Maximum value of
Figure 568622DEST_PATH_IMAGE034
Then the maximum non-abnormal mean square error
Figure 298418DEST_PATH_IMAGE035
Is added to
Figure 948842DEST_PATH_IMAGE032
And (5) ending. The sequence is gradually decreased, and the decreasing amplitude of each step is d(i),
Figure 138515DEST_PATH_IMAGE036
（12）
If the amplitude d is reduced at a certain step i(i)Greater than the minimum drop amplitude p, all satisfy
Figure 507180DEST_PATH_IMAGE037
Figure 807711DEST_PATH_IMAGE038
Is still an abnormal sequence. If the amplitude is decreased by d(i)Less than the minimum reduction p, then the reduction of all subsequent errors
Figure 312642DEST_PATH_IMAGE039
Are reclassified as normal values. This approach helps to ensure that the sequence of anomalies is not a regular noise in the time series data stream, and identification of the sequence of outliers is achieved by thresholding, detecting only sequence segments with potential anomalies, more efficiently than comparing sequence values one by one without using a threshold.
And S6, classifying the abnormal signals through a fault time sequence data classification model to obtain a fault diagnosis result.
The general structural flow of the specific fault diagnosis method is shown in fig. 3.
The invention discloses a fatigue factor recessive anomaly detection and fault diagnosis method based on LSTM, which comprises the following steps:
description of data
The experimental data are derived from bearing fault data of a university of Kaiser West reservoir (CWRU) electrical engineering laboratory, and total 1,341,856 data points, wherein the bearing model is 6205-2RS JEM SKF deep groove ball bearing. Single-point failures of 3 failure levels are respectively arranged on an Inner ring (Inner Raceway Fault), an Outer ring (Outer Raceway Fault) and a rolling body (ballFault) on a bearing by using an electric spark machining technology, the failure diameters are respectively 0.007 inches, 0.014 inches and 0.021 inches, and the failure depths are respectively 0.011 inches, 0.050 inches and 0.150 inches. Three kinds of faults are respectively arranged at a motor driving End (Driver End) and a Fan End (Fan End), and 21 groups of data including 6 fault types are collected by vibration sensors arranged at the motor driving End, the Fan End and a base. A description of specific bearing failure data is shown in table 1.
TABLE 1 bearing failure data description (in inches)
Figure 407637DEST_PATH_IMAGE043
Four types of vibration data drawing graphs are selected, as shown in fig. 5, a normal signal, a rolling element fault signal, an inner ring fault signal and an outer ring fault signal are sequentially arranged from top to bottom, and a sequence with larger amplitude can be periodically shown in the fault signal, wherein the amplitude of the fault vibration signal is obviously larger than that of the normal signal, and the sequence with larger amplitude can be observed from the graph of sample data.
And decomposing the original vibration signal by using EMD, and observing the IMF component characteristics of each stage. After the original signal decomposition, 7 components (called IMF 1-IMF 7 respectively) and a residual map are obtained, wherein each IMF component represents an connotative modal component existing in the original signal. FIG. 6 is an EMD decomposition of normal data, FIG. 7 is an EMD decomposition of inner ring fault data, in the diagram, IMFs 1-7 represent signal components under different frequencies, the signal components are sequentially arranged from high frequency to low frequency, and the right side part is the instantaneous frequency of each IMF component. It can be seen from the graph that the normal signal and the abnormal signal have a large difference in residual error and instantaneous frequency distribution, the instantaneous frequency distribution of the normal signal is smooth, and the instantaneous frequency distribution of the abnormal signal has a large fluctuation.
In order to compare the effect difference between the LSTM-based vibration signal prediction model and ARIMA and RNN methods, the used experimental data comprise normal data of a driving end and a fan end, the data are divided into single-step prediction data and multi-step prediction data, the multi-step prediction data are provided with two prediction lengths of 30 and 100, 6 data sets are provided in total, and each data set comprises 20000 training samples and 4000 test samples.
The ARIMA Model is called an autoregressive Moving Average Model (ARIMA, Autoregesived Moving Average Model). Also known as ARIMA (p, d, q), is the most common one of statistical models (statisticmodel) for time series prediction. The ARIMA model parameters p (Auto-Regressive), d (integrated), q (moving average) are shown in Table 2.
TABLE 2 ARIMA model parameters
p(Auto-Regressive) d(Integrated) q(Moving Average)
1 1 1
RNN (Recurrent Neural Network) processes the most common, most traditional deep learning model of sequence data. The RNN model parameters used for the comparative experiments are shown in table 3.
TABLE 3RNN model parameters
Figure 529177DEST_PATH_IMAGE044
The test was performed with the above-identified model parameters and structure, and the comparative experiment results are shown in table 4.
TABLE 4 comparative experiment test results
Figure 102240DEST_PATH_IMAGE045
As can be seen from the experimental test results in Table 4, the mean square errors of the three models have strong correlation with the data prediction length (the mean square errors of the RNN and StackedLSTM models are subject to ValLoss in Table 4), that is, the mean square error is smaller when the data prediction length is shorter, and the effect of single-step prediction is significantly better than that of multi-step prediction. Fig. 4(a), (b) and (c) are graphs of the prediction effect with prediction step size of 30 for the three models respectively. The dark grey lines represent the true value (TrueValue), the light grey lines represent the predicted value (Prediction), which represent the Acceleration value (left y-axis, Acceleration), and the dashed lines represent the Residual of the actual and predicted values (Residual, right y-axis, Res). ARIMA has a slight advantage in single-step prediction experiments (datasets 1 and 2) over both RNN and StackedLSTM neural networks, and its higher MSE is not as satisfactory in long-term prediction ( datasets 3, 4, 5, 6). The ARIMA and the neural network show two different characteristics, the neural network has better effect than the ARIMA in the aspect of long-term prediction and has more advantage in the aspect of short-term prediction. The prediction model effect based on the StackLSTM is superior to that of the RNN model, so that a better prediction effect can be obtained, and the StackLSTM is more suitable for long-term prediction. Structurally, the ARIMA is a linear model, and the neural network is a nonlinear model, so that the ARIMA can obtain good effect in a short time when the relationship is simple, but the fault data prediction model based on the StackedLSTM is very suitable for the scene when the complex association relationship is faced.

Claims (5)

1. A fatigue factor recessive abnormality detection and fault diagnosis method based on LSTM is characterized by comprising the following steps:
s1, collecting time sequence sample data of the target equipment of the diagnosis object, wherein the sample comprises normal data, abnormal data and fault types of the abnormal data, and performing empirical mode decomposition on the time sequence sample data of the equipment by using an EMD method;
s2, extracting normal data samples in the time sequence sample data, and constructing an equipment vibration signal prediction model by using an LSTM-based deep neural network;
s3, extracting abnormal data samples in the time sequence sample data, and constructing a fault time sequence data classification model by using an LSTM-based deep neural network;
s4, taking the Mean Square Error (MSE) of the vibration signal prediction model based on the LSTM acquired in the S2 as an initial fatigue factor threshold;
s5, predicting the production data of the equipment by using a vibration signal prediction model based on LSTM, calculating the mean square error between a predicted value and an actual value, comparing the mean square error with an initial fatigue factor threshold value to detect an abnormal signal, and dynamically adjusting the threshold value according to the actual condition
Figure 100212DEST_PATH_IMAGE001
；
And S6, classifying the abnormal signals through a fault time sequence data classification model to obtain a fault diagnosis result.
2. The LSTM-based fatigue factor latent anomaly detection and fault diagnosis method of claim 1, wherein the process of constructing the device vibration signal prediction model based on the LSTM deep neural network in step S2 comprises the following steps:
s2-1: characteristic engineering: firstly, processing collected original data, performing auxiliary judgment by using EMD (empirical mode decomposition) and waveform visualization technology, and identifying abnormal vibration frequency by observing IMF (intrinsic mode function) components;
s2-2: resampling: original data are re-sampled, abnormal data fragments in the original data are deleted, the fact that continuous normal data exist in the remaining data and only exist in the remaining data is guaranteed, and the problem of data unbalance caused by unbalanced data is solved;
s2-3: data normalization: normalizing the data of each dimension in the time series, and calculating the mean value of each dimension
Figure 631688DEST_PATH_IMAGE002
And standard deviation of
Figure 207900DEST_PATH_IMAGE003
The time-series sample data X is normalized by the following formula, and the normalized data is X':
Figure 115813DEST_PATH_IMAGE004
（1）
s2-4: and (3) carrying out format conversion on the data set: converting the unsupervised data set into a supervised data set, dividing the normalized data into a continuous time series X of length lr，XrLength of (d) is input by the model as length lsAnd an output length lpDetermined together, their relationship is the total length
Figure 595336DEST_PATH_IMAGE005
Dividing time series sample data X into XsAnd XpTwo parts, which are used as input and output samples of the model;
s2-5: dividing the data set: randomly arranging data, and dividing input data X according to same proportionsAnd output data XpObtaining a training data set
Figure 32134DEST_PATH_IMAGE006
And validating the data set
Figure 597107DEST_PATH_IMAGE007
；
S2-6: constructing a model: setting check points, saving model parameters once per Epoch, adjusting Epoch and Dropout parameters, and observing trainloss and valloss, using an early stop mechanism when an over-fit condition occurs;
s2-7: classification using models: inputting a segment of time sequence sample data X to obtain a prediction vector
Figure 777553DEST_PATH_IMAGE008
Then, calculating a mean square error MSE according to the actual value y for evaluating the prediction effect, wherein n is the sequence number:
Figure 377161DEST_PATH_IMAGE009
（2）。
3. the LSTM-based fatigue factor latent anomaly detection and fault diagnosis method of claim 1, wherein the process of constructing the fault timing sequence data classification model based on the LSTM deep neural network in step S3 comprises the following steps:
s3-1: firstly, processing fault data samples of time sequence sample data of equipment, using data which has abnormality and has determined fault types, and additionally adding normal samples with the same quantity as each fault sample;
s3-2: performing Empirical Mode Decomposition (EMD) on the time sequence sample data to obtain an m-dimensional vector containing IMF components
Figure 984860DEST_PATH_IMAGE010
M is determined by empirical mode decomposition, imfiIs the ith dimension component;
s3-3: numbering imf of n-type time sequence data to obtain model input data Xc
Figure 302709DEST_PATH_IMAGE011
（3）
Determining the output data y of the model from the numbersc
Figure 21266DEST_PATH_IMAGE012
（4）
S3-4: normalizing the data and calculating the mean of the samples
Figure 979776DEST_PATH_IMAGE002
And standard deviation of
Figure 758376DEST_PATH_IMAGE003
Normalized data is
Figure 563521DEST_PATH_IMAGE013
：
Figure 85769DEST_PATH_IMAGE014
（5）
S3-5: dividing data set, randomly arranging data, and dividing input data X according to same proportioncAnd output data ycObtaining a training data set
Figure 659970DEST_PATH_IMAGE006
And validating the data set
Figure 609472DEST_PATH_IMAGE007
；
S3-6: training the model, setting check points, and storing one for each EpochSecondary model parameters, adjust Epoch and Dropout parameters, and observe trainloss and valloss, using an early stop mechanism when an over-fit condition occurs;
s3-7: classifying by using model, inputting a segment of model input data XcObtaining a classification vector y', then the fault number
Figure 370754DEST_PATH_IMAGE015
The corresponding fault is found by numbering, argmax being the parameter of the maximum value.
4. The LSTM-based fatigue factor latent anomaly detection and fault diagnosis method of claim 1, wherein the step S5 of predicting the equipment production data by using the LSTM-based vibration signal prediction model specifically comprises:
predicting the value of time t using a prediction model
Figure 962273DEST_PATH_IMAGE016
Calculated according to the actual value
Figure 125401DEST_PATH_IMAGE017
Calculating a prediction error:
Figure 511383DEST_PATH_IMAGE018
（6）
wherein
Figure 524076DEST_PATH_IMAGE019
I is the dimension of the true monitor value, and then every error is calculated
Figure 388127DEST_PATH_IMAGE020
Added to the vector of prediction errors:
Figure 671340DEST_PATH_IMAGE021
（7）
h is the number of historical errors used to estimate the current error, lsFor the length of the input sequence, the set of errors e is then smoothed, and an error threshold is selected for the set of errors
Figure 228224DEST_PATH_IMAGE022
-the value of the mean square error above the threshold is classified as abnormal:
Figure 964099DEST_PATH_IMAGE023
（8）
Figure 366261DEST_PATH_IMAGE022
is a vector of threshold errors, esIs a sequence error vector, z is a constant,
Figure 769561DEST_PATH_IMAGE002
is a mean value
Figure 497345DEST_PATH_IMAGE003
Is a standard deviation of wherein
Figure 720516DEST_PATH_IMAGE022
Determined by equation (9):
Figure 690484DEST_PATH_IMAGE024
（9）
wherein:
Figure 682711DEST_PATH_IMAGE025
（10）
e in the formula (9)seqIs composed of
Figure 581396DEST_PATH_IMAGE026
A continuous sequence of (a);
Figure 291864DEST_PATH_IMAGE022
is estimated by
Figure 566987DEST_PATH_IMAGE027
Determining that z is an ordered set of positive integers representing greater than
Figure 413720DEST_PATH_IMAGE028
The number of standard deviations, the value of z depending on experimental data, once
Figure 483307DEST_PATH_IMAGE029
Is determined to produce a sequence of anomalies for each of the mean square errors
Figure 415491DEST_PATH_IMAGE030
A score is made and the score s is used to indicate the severity of the anomaly, i.e. the fatigue factor:
Figure 494306DEST_PATH_IMAGE031
（11）
the highest mean square error in each anomalous error sequence is then determined based on its correlation with a selected threshold
Figure 461125DEST_PATH_IMAGE001
Is normalized.
5. The LSTM-based fatigue factor latent anomaly detection and fault diagnosis method of claim 1, wherein the threshold is dynamically adjusted according to actual conditions in step S5
Figure 200148DEST_PATH_IMAGE001
The method specifically comprises the following steps:
creating a new collection
Figure 885208DEST_PATH_IMAGE032
Including all in descending order
Figure 236555DEST_PATH_IMAGE033
Maximum value of
Figure 323459DEST_PATH_IMAGE034
Then the maximum non-abnormal mean square error
Figure 469270DEST_PATH_IMAGE035
Is added to
Figure 641625DEST_PATH_IMAGE032
At the end, the sequence is gradually decreased, and the decrease of the ith step is:
Figure 796663DEST_PATH_IMAGE036
if the amplitude d is reduced at a certain step i(i)Greater than the minimum drop amplitude p, all satisfy
Figure 738074DEST_PATH_IMAGE037
Figure 320365DEST_PATH_IMAGE038
Is still an abnormal sequence; if the amplitude is decreased by d(i)Less than the minimum reduction p, then the reduction of all subsequent errors
Figure 980017DEST_PATH_IMAGE039
Are reclassified as normal values.
CN202010445803.3A 2020-05-25 2020-05-25 LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method Active CN111353482B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010445803.3A CN111353482B (en) 2020-05-25 2020-05-25 LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010445803.3A CN111353482B (en) 2020-05-25 2020-05-25 LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method

Publications (2)

Publication Number Publication Date
CN111353482A true CN111353482A (en) 2020-06-30
CN111353482B CN111353482B (en) 2020-12-08

Family

ID=71197733

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010445803.3A Active CN111353482B (en) 2020-05-25 2020-05-25 LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method

Country Status (1)

Country Link
CN (1) CN111353482B (en)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111539393A (en) * 2020-07-08 2020-08-14 浙江浙能天然气运行有限公司 Oil-gas pipeline third-party construction early warning method based on EMD decomposition and LSTM
CN111931872A (en) * 2020-09-27 2020-11-13 北京工业大数据创新中心有限公司 Method and device for determining abnormity of trend symptom
CN112101532A (en) * 2020-11-18 2020-12-18 天津开发区精诺瀚海数据科技有限公司 Self-adaptive multi-model driving equipment fault diagnosis method based on edge cloud cooperation
CN112101489A (en) * 2020-11-18 2020-12-18 天津开发区精诺瀚海数据科技有限公司 Equipment fault diagnosis method driven by united learning and deep learning fusion
CN112149868A (en) * 2020-08-20 2020-12-29 汉威科技集团股份有限公司 Intelligent diagnosis method for gas use habit and safety analysis
CN112288021A (en) * 2020-11-02 2021-01-29 广东柯内特环境科技有限公司 Medical wastewater monitoring data quality control method, device and system
CN112328588A (en) * 2020-11-27 2021-02-05 哈尔滨工程大学 Industrial fault diagnosis unbalanced time sequence data expansion method
CN112578213A (en) * 2020-12-23 2021-03-30 交控科技股份有限公司 Fault prediction method and device for rail power supply screen
CN112804336A (en) * 2020-10-29 2021-05-14 浙江工商大学 Fault detection method, device, system and computer readable storage medium
CN112862459A (en) * 2021-03-02 2021-05-28 岭东核电有限公司 Test abnormity monitoring method and device, computer equipment and storage medium
CN113361324A (en) * 2021-04-25 2021-09-07 杭州玖欣物联科技有限公司 Motor current anomaly detection method based on lstm
CN114169379A (en) * 2022-02-07 2022-03-11 石家庄铁道大学 Method for detecting abnormal vibration data during bearing state monitoring
CN114783044A (en) * 2022-04-20 2022-07-22 石家庄铁道大学 Anti-fatigue effect evaluation method for tunnel lighting environment, electronic device and system
CN115905835A (en) * 2022-11-15 2023-04-04 国网四川省电力公司电力科学研究院 Low-voltage alternating current arc fault diagnosis method fusing multidimensional characteristics
CN116113942A (en) * 2020-07-23 2023-05-12 Pdf决策公司 Predicting equipment failure modes based on process traces
CN116933012A (en) * 2023-08-14 2023-10-24 华北电力大学 Intelligent early warning method for typical equipment faults of thermal power generating unit based on TiDE model
CN117009791A (en) * 2023-09-28 2023-11-07 太仓点石航空动力有限公司 Method and system for identifying faults of aeroengine
CN117451489A (en) * 2023-12-26 2024-01-26 集美大学 Device and method for identifying contact fatigue failure characteristic vibration signals

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109555566A (en) * 2018-12-20 2019-04-02 西安交通大学 A kind of turbine rotor method for diagnosing faults based on LSTM
CN109919082A (en) * 2019-03-05 2019-06-21 东南大学 Modal identification method based on LSTM and EMD
CN110702418A (en) * 2019-10-10 2020-01-17 山东超越数控电子股份有限公司 Aircraft engine fault prediction method
CN111053549A (en) * 2019-12-23 2020-04-24 威海北洋电气集团股份有限公司 Intelligent biological signal abnormality detection method and system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109555566A (en) * 2018-12-20 2019-04-02 西安交通大学 A kind of turbine rotor method for diagnosing faults based on LSTM
CN109919082A (en) * 2019-03-05 2019-06-21 东南大学 Modal identification method based on LSTM and EMD
CN110702418A (en) * 2019-10-10 2020-01-17 山东超越数控电子股份有限公司 Aircraft engine fault prediction method
CN111053549A (en) * 2019-12-23 2020-04-24 威海北洋电气集团股份有限公司 Intelligent biological signal abnormality detection method and system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
董静怡: "集成LSTM的航天器遥测数据异常检测方法", 《仪器仪表学报》 *
赵建鹏 等: "基于长短时记忆网络的旋转机械状态预测研究", 《噪声与振动控制》 *

Cited By (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111539393B (en) * 2020-07-08 2020-10-09 浙江浙能天然气运行有限公司 Oil-gas pipeline third-party construction early warning method based on EMD decomposition and LSTM
CN111539393A (en) * 2020-07-08 2020-08-14 浙江浙能天然气运行有限公司 Oil-gas pipeline third-party construction early warning method based on EMD decomposition and LSTM
CN116113942A (en) * 2020-07-23 2023-05-12 Pdf决策公司 Predicting equipment failure modes based on process traces
CN112149868A (en) * 2020-08-20 2020-12-29 汉威科技集团股份有限公司 Intelligent diagnosis method for gas use habit and safety analysis
CN111931872B (en) * 2020-09-27 2021-11-16 北京工业大数据创新中心有限公司 Method and device for determining abnormity of trend symptom
CN111931872A (en) * 2020-09-27 2020-11-13 北京工业大数据创新中心有限公司 Method and device for determining abnormity of trend symptom
CN112804336A (en) * 2020-10-29 2021-05-14 浙江工商大学 Fault detection method, device, system and computer readable storage medium
CN112288021A (en) * 2020-11-02 2021-01-29 广东柯内特环境科技有限公司 Medical wastewater monitoring data quality control method, device and system
CN112288021B (en) * 2020-11-02 2022-04-29 广东柯内特环境科技有限公司 Medical wastewater monitoring data quality control method, device and system
CN112101532A (en) * 2020-11-18 2020-12-18 天津开发区精诺瀚海数据科技有限公司 Self-adaptive multi-model driving equipment fault diagnosis method based on edge cloud cooperation
CN112101489A (en) * 2020-11-18 2020-12-18 天津开发区精诺瀚海数据科技有限公司 Equipment fault diagnosis method driven by united learning and deep learning fusion
CN112101532B (en) * 2020-11-18 2021-02-12 天津开发区精诺瀚海数据科技有限公司 Self-adaptive multi-model driving equipment fault diagnosis method based on edge cloud cooperation
CN112328588A (en) * 2020-11-27 2021-02-05 哈尔滨工程大学 Industrial fault diagnosis unbalanced time sequence data expansion method
CN112328588B (en) * 2020-11-27 2022-07-15 哈尔滨工程大学 Industrial fault diagnosis unbalanced time sequence data expansion method
CN112578213A (en) * 2020-12-23 2021-03-30 交控科技股份有限公司 Fault prediction method and device for rail power supply screen
CN112862459A (en) * 2021-03-02 2021-05-28 岭东核电有限公司 Test abnormity monitoring method and device, computer equipment and storage medium
CN113361324A (en) * 2021-04-25 2021-09-07 杭州玖欣物联科技有限公司 Motor current anomaly detection method based on lstm
CN113361324B (en) * 2021-04-25 2023-06-30 杭州玖欣物联科技有限公司 Lstm-based motor current anomaly detection method
CN114169379B (en) * 2022-02-07 2022-04-26 石家庄铁道大学 Method for detecting abnormal vibration data during bearing state monitoring
CN114169379A (en) * 2022-02-07 2022-03-11 石家庄铁道大学 Method for detecting abnormal vibration data during bearing state monitoring
CN114783044A (en) * 2022-04-20 2022-07-22 石家庄铁道大学 Anti-fatigue effect evaluation method for tunnel lighting environment, electronic device and system
CN114783044B (en) * 2022-04-20 2023-03-24 石家庄铁道大学 Anti-fatigue effect evaluation method for tunnel lighting environment, electronic device and system
CN115905835A (en) * 2022-11-15 2023-04-04 国网四川省电力公司电力科学研究院 Low-voltage alternating current arc fault diagnosis method fusing multidimensional characteristics
CN115905835B (en) * 2022-11-15 2024-02-23 国网四川省电力公司电力科学研究院 Low-voltage alternating current arc fault diagnosis method integrating multidimensional features
CN116933012A (en) * 2023-08-14 2023-10-24 华北电力大学 Intelligent early warning method for typical equipment faults of thermal power generating unit based on TiDE model
CN117009791A (en) * 2023-09-28 2023-11-07 太仓点石航空动力有限公司 Method and system for identifying faults of aeroengine
CN117009791B (en) * 2023-09-28 2023-12-12 太仓点石航空动力有限公司 Method and system for identifying faults of aeroengine
CN117451489A (en) * 2023-12-26 2024-01-26 集美大学 Device and method for identifying contact fatigue failure characteristic vibration signals
CN117451489B (en) * 2023-12-26 2024-03-08 集美大学 Device and method for identifying contact fatigue failure characteristic vibration signals

Also Published As

Publication number Publication date
CN111353482B (en) 2020-12-08

Similar Documents

Publication Publication Date Title
CN111353482B (en) LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method
CN110276416B (en) Rolling bearing fault prediction method
KR101316486B1 (en) Error detection method and system
Yang An intelligent condition-based maintenance platform for rotating machinery
CN111695598B (en) Monitoring data abnormity diagnosis method based on generation countermeasure network
KR101948604B1 (en) Method and device for equipment health monitoring based on sensor clustering
Dou et al. A rule-based intelligent method for fault diagnosis of rotating machinery
CN107003663A (en) The monitoring of device with movable part
CN111562108A (en) Rolling bearing intelligent fault diagnosis method based on CNN and FCMC
CN112414694B (en) Equipment multistage abnormal state identification method and device based on multivariate state estimation technology
CN107862108A (en) A kind of industrial machinery health status analysis and Forecasting Methodology and its system
CN116380445B (en) Equipment state diagnosis method and related device based on vibration waveform
CN111474475A (en) Motor fault diagnosis system and method
CN111504647A (en) AR-MSET-based performance degradation evaluation method for rolling bearing
Li et al. Unsupervised machine anomaly detection using autoencoder and temporal convolutional network
CN111678699B (en) Early fault monitoring and diagnosing method and system for rolling bearing
Jiang et al. A multisensor cycle-supervised convolutional neural network for anomaly detection on magnetic flux leakage signals
EP3712728A1 (en) Apparatus for predicting equipment damage
TWI780434B (en) Abnormal diagnosis device and method
CN110749443B (en) Rolling bearing fault diagnosis method and system based on high-order origin moment
Hu et al. Fault diagnosis based on multi-scale redefined dimensionless indicators and density peak clustering with geodesic distances
CN113435228A (en) Motor bearing service life prediction and analysis method based on vibration signal modeling
CN111474476B (en) Motor fault prediction method
Yu et al. Novelty class detection in machine learning-based condition diagnosis
Mishra et al. Condition monitoring of elevator systems using deep neural network

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
PE01 Entry into force of the registration of the contract for pledge of patent right
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: A LSTM based implicit anomaly detection and fault diagnosis method for fatigue factors

Effective date of registration: 20230628

Granted publication date: 20201208

Pledgee: Tianjin SME Credit Financing Guarantee Co.,Ltd.

Pledgor: Tianjin Development Zone Jingnuo Hanhai Data Technology Co.,Ltd.

Registration number: Y2023120000049