Nothing Special   »   [go: up one dir, main page]

CN110633792B - End-to-end bearing health index construction method based on convolution cyclic neural network - Google Patents

End-to-end bearing health index construction method based on convolution cyclic neural network Download PDF

Info

Publication number
CN110633792B
CN110633792B CN201911004003.1A CN201911004003A CN110633792B CN 110633792 B CN110633792 B CN 110633792B CN 201911004003 A CN201911004003 A CN 201911004003A CN 110633792 B CN110633792 B CN 110633792B
Authority
CN
China
Prior art keywords
crnn
neural network
bearing
convolution
network model
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.)
Active
Application number
CN201911004003.1A
Other languages
Chinese (zh)
Other versions
CN110633792A (en
Inventor
徐光华
陈龙庭
张四聪
况佳臣
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.)
Xian Jiaotong University
Original Assignee
Xian Jiaotong University
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 Xian Jiaotong University filed Critical Xian Jiaotong University
Priority to CN201911004003.1A priority Critical patent/CN110633792B/en
Publication of CN110633792A publication Critical patent/CN110633792A/en
Application granted granted Critical
Publication of CN110633792B publication Critical patent/CN110633792B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M13/00—Testing of machine parts
    • G01M13/04—Bearings
    • G01M13/045—Acoustic or vibration analysis
    • 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
    • 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
    • G06N3/045—Combinations of networks
    • 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
    • G06N3/048—Activation functions
    • 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
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Acoustics & Sound (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)

Abstract

A bearing health index construction method based on a convolution cyclic neural network from end to end is characterized by firstly constructing a convolution cyclic neural network model CRNN to obtain a health index CRNN-HI capable of measuring the degradation degree of a bearing; then carrying out convolution cyclic neural network model CRNN model training; finally, carrying out convolution cyclic neural network model CRNN evaluation; according to the invention, by integrating the structural advantages of convolutional neural networks CNNs and recurrent neural networks RNNs and utilizing the time sequence information of the characteristic diagram output by RNNs coding CNNs, the defects that CNNs cannot code time sequence characteristics and the reception field is small are eliminated on one hand, and the defect that RNNs cannot adaptively extract HI related characteristics from original data is also eliminated on the other hand, so that CRNN-HI obtains higher correlation, monotonicity and accuracy in the aspect of degradation evaluation of the health state of a bearing; meanwhile, the CRNN-HI index constructed by the invention approximately represents the nonlinear degradation process of the bearing as a linear process changing along with time, thereby providing convenience for the health state evaluation and the degradation degree determination of the rolling bearing.

Description

End-to-end bearing health index construction method based on convolution cyclic neural network
Technical Field
The invention belongs to the technical field of fault diagnosis of rotary machines, and particularly relates to a bearing health index construction method based on a convolution cyclic neural network from end to end.
Background
In recent years, with the development of internet of things (IoT) technology and network collaborative manufacturing technology, researchers can collect a large amount of status monitoring data of mechanical equipment, which is very important for further improving the intelligent manufacturing level. The rolling bearing is one of key parts in rotary mechanical power equipment, and the unexpected failure of the rolling bearing can cause great economic loss and catastrophic accidents. In order to solve the above problems, it is important to perform planned predictive maintenance on a bearing part of a rotary machine, and under the background of the above big data, many researchers have focused on the study of a fault prediction method based on a data-driven type.
In general, the data-driven fault prediction method mainly comprises 3 steps: (1) collecting fault related data; (2) constructing a health index HI; (3) and predicting the failure time. The quality of the construction of the health index HI has a crucial influence on the accuracy of quantitative evaluation of the degradation degree of the bearing. In recent years, artificial intelligence technology centering on big data analysis makes great progress in the field of construction of a bearing health index HI, and a typical representative method is a method based on deep learning DL. The HI construction method based on DL is mainly divided into two types, the first type is a method based on convolutional neural network CNNs, the core is that the HI related characteristics are self-adaptively learned from original data such as vibration signals by utilizing the hierarchical characteristic learning and hierarchical characteristic expression capability of the CNNs, and through the weight sharing and local receptive field attribute of the network, a shallow layer network can learn local characteristics, and a high layer network can learn characteristics which are more global and have rich semantic information; some establish an HI index for the rolling bearing by using a one-dimensional convolutional neural network, take the burr fluctuation phenomenon in HI into consideration, and obtain great performance improvement in the aspects of correlation and monotonicity. However, the method has the disadvantages that on one hand, the classified CNNs network structure is directly adopted for HI regression, and the regression capability is poor; on the other hand, CNNs cannot encode time series information of the input data, which is important for the construction of the bearing HI. The second type is a method based on recurrent neural networks RNNs, the core of the method is that the RNNs network can learn the memory of the long-term dependency relationship to encode the time sequence information of the input characteristics, and someone inputs the characteristics which are manually defined and comprise classical time domain characteristics, frequency domain characteristics and time-frequency domain characteristics into the RNNs network, so that the health index RNN-HI is constructed for the rolling bearing. RNN-HI has high monotonicity in measuring the performance degradation of the rolling bearing. However, the method has the defects that manual self-defining characteristics are required to be input into the network, namely certain prior knowledge is required, and the whole network cannot be optimized end to end.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide an end-to-end bearing health index construction method based on a convolutional recurrent neural network, which utilizes the time sequence information of a characteristic diagram output by RNNs coding CNNs by integrating the structural advantages of the convolutional neural network and the recurrent neural network, so that the defects that the CNNs cannot code the time sequence characteristic and the receptive field is small are eliminated, and the defect that the RNNs cannot adaptively extract HI related characteristics from original data is also eliminated.
In order to achieve the purpose, the invention adopts the technical scheme that:
an end-to-end convolution cyclic neural network-based bearing health index construction method comprises the following steps:
1) constructing a convolution cyclic neural network model CRNN: the input of the convolution cyclic neural network model CRNN is standardized original bearing vibration signal data, the convolution cyclic neural network model CRNN comprises two components, one component is a convolution neural network CNNs used for extracting local characteristics and consists of convolution layers and pooling layers which are stacked alternately, and in order to accelerate the training process and the convergence speed of the network, a BatchNorm layer and a residual error connecting structure are added into the convolution neural network CNNs; the convolutional neural networks CNNs comprise 4 groups of residual error units, each residual error unit comprises 2 convolutional layers, each residual error unit performs down-sampling on input data, the first convolutional layer of the convolutional neural networks CNNs adopts a pre-activation design, and the sizes of convolutional cores in the whole convolutional layer are all 16; the other component is used for extracting global characteristics with time series information and circularly connecting the cyclic neural network of the local characteristics, and is realized by adopting a long-short term memory network LSTM, the input of the long-short term memory network LSTM at each moment is each characteristic point on a characteristic diagram output by the convolutional neural network CNNs, and the time length is equal to the dimension of the characteristic diagram; the output of the long-short term memory network LSTM at the time t is calculated by the following formula:
ft＝σ(Wf·[ht-1,xt]+bf) (1)
Figure BDA0002242201670000031
it＝σ(Wi·[ht-1,xt]+bi) (3)
Figure BDA0002242201670000032
ot＝σ(Wo·[ht-1,xt]+bo) (5)
ht＝ot⊙tanh(Ct) (6)
wherein h ist-1And xtRespectively representing the hidden layer state of the long-short term memory network LSTM at the time t-1 and the input characteristics at the time t; wf，WiAnd WoRespectively representing the weight parameters of a long-short term memory network LSTM forgetting gate, an input gate and an output gate; bf，biAnd boRespectively representing the bias parameters of a long-short term memory network LSTM forgetting gate, an input gate and an output gate; f. oft，itAnd otRespectively representing the activation values of a long-short term memory network LSTM forgetting gate, an input gate and an output gate; the activation function sigma is a sigmoid function; the notation tanh denotes a hyperbolic tangent function; the symbols & · denote element-by-element multiplication and matrix multiplication, respectively;
Figure BDA0002242201670000033
representing newly learned feature information, W, of long-and short-term memory networks LSTMCAnd bCRespectively corresponding weight parameters and bias parameters; ctRepresenting the internal state of the LSTM cell at the current time t; hidden layer state h at the current momenttThe method comprises the steps of containing global characteristics with time series information, and then carrying out nonlinear mapping on the global characteristics through a full connection layer to obtain a health index CR capable of measuring the degradation degree of a bearingNN-HI；
2) Training a convolution cyclic neural network model (CRNN): the loss function of the convolution cyclic neural network model CRNN adopts a root mean square regression error, a training set chi is composed of a full life cycle vibration signal of a rolling bearing, and chi { (x)t,yt) L 1 is less than or equal to T is less than or equal to T, wherein xt∈RN,yt∈[0,1]N represents the length of a data sample of each vibration signal acquired, T represents the life of the rolling bearing, ytIs a real number representing the percentage of residual life of the bearing at the current time t; the loss function J of the convolutional recurrent neural network model CRNN is calculated by:
Figure BDA0002242201670000041
wherein,
Figure BDA0002242201670000042
is the predicted value of HI for a bearing
Figure BDA0002242201670000043
A value very close to 0 indicates that the bearing is in a failure state; the whole convolution cyclic neural network model CRNN is trained by adopting a back propagation algorithm BP, an optimizer selects Adam, the initial learning rate lr is set to be 0.001, and the sample size of each batch is set to be 32;
3) evaluating a convolution cycle neural network model (CRNN), selecting an optimal trained convolution cycle neural network model (CRNN) to predict a health index (CRNN-HI) of a rolling bearing to be evaluated, wherein a correlation index (Corr) and a monotonicity index (Mono) are adopted to quantitatively evaluate the performance of the convolution cycle neural network model (CRNN) on a verification set in a training process, the correlation index (Corr) measures the correlation between the attenuation trend of the CRNN-HI and the equipment running time, and the value calculation is as follows:
Figure BDA0002242201670000044
symbol IiAnd tiRespectively representing the value of CRNN-HI and the running time,
Figure BDA0002242201670000045
the monotonicity index Mono measures the increasing or decreasing trend of the CRNN-HI along with time, and the calculation formula is as follows:
Figure BDA0002242201670000051
and dI represents a first-order difference between two CRNN-HI at adjacent moments, the value ranges of the values of Corr and Mono are both between 0 and 1, and after the optimal model parameters are selected, the acquired vibration signals of the bearing to be analyzed are input into the optimal model, so that the output of the optimal model and the CRNN-HI value of the bearing at the current moment are obtained, and the current degradation degree of the rolling bearing is quantitatively evaluated.
The invention has the beneficial effects that:
according to the invention, the structural advantages of the convolutional neural network and the cyclic neural network are combined, an end-to-end bearing health index method based on the convolutional cyclic neural network is constructed, the defects of the HI construction method based on the CNNs model and the RNNs model are overcome, and the CRNN-HI obtains higher correlation, monotonicity and accuracy in the aspect of bearing health state degradation evaluation. Meanwhile, the CRNN-HI index constructed by the invention approximately represents the nonlinear degradation process of the bearing as a linear process changing along with time, thereby providing convenience for the health state evaluation and the degradation degree determination of the rolling bearing.
Drawings
FIG. 1 is a diagram of a convolutional recurrent neural network model according to the present invention.
FIG. 2 is a schematic structural diagram of the LSTM neural network model of the present invention.
FIG. 3 is a diagram illustrating the effect of the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and examples.
Referring to fig. 1, an end-to-end convolution cyclic neural network-based bearing health index construction method includes the following steps:
1) constructing a convolution cyclic neural network model CRNN: the input of the convolution cyclic neural network model CRNN is standardized original bearing vibration signal data, the convolution cyclic neural network model CRNN comprises two components, one component is a convolution neural network CNNs used for extracting local characteristics and consists of convolution layers and pooling layers which are stacked alternately, and in order to accelerate the training process and the convergence speed of the network, a BatchNorm layer and a residual error connecting structure are added into the convolution neural network CNNs; the convolutional neural networks CNNs comprise 4 groups of residual error units, each residual error unit comprises 2 convolutional layers, each residual error unit performs down-sampling on input data, the first convolutional layer of the convolutional neural networks CNNs adopts a pre-activation design, and the sizes of convolutional cores in the whole convolutional layer are all 16; the other component is used for extracting global features with time series information and circularly connecting the cyclic neural network of the local features, and is realized by adopting a long-short term memory network (LSTM), and the reference is made to fig. 2. The input of the long-short term memory network LSTM at each moment is each characteristic point on the characteristic diagram output by the convolutional neural network CNNs, and the time length is equal to the dimension of the characteristic diagram; the output of the long-short term memory network LSTM at the time t is calculated by the following formula:
ft＝σ(Wf·[ht-1,xt]+bf) (1)
Figure BDA0002242201670000061
it＝σ(Wi·[ht-1,xt]+bi) (3)
Figure BDA0002242201670000062
ot＝σ(Wo·[ht-1,xt]+bo) (5)
ht＝ot⊙tanh(Ct) (6)
wherein h ist-1And xtRespectively representing the hidden layer state of the long-short term memory network LSTM at the time t-1 and the input characteristics at the time t; wf，WiAnd WoRespectively representing the weight parameters of a long-short term memory network LSTM forgetting gate, an input gate and an output gate; bf，biAnd boRespectively representing the bias parameters of a long-short term memory network LSTM forgetting gate, an input gate and an output gate; f. oft，itAnd otRespectively representing the activation values of a long-short term memory network LSTM forgetting gate, an input gate and an output gate; the activation function sigma is a sigmoid function; the notation tanh denotes a hyperbolic tangent function; the symbols & · denote element-by-element multiplication and matrix multiplication, respectively;
Figure BDA0002242201670000063
representing newly learned feature information, W, of long-and short-term memory networks LSTMCAnd bCRespectively corresponding weight parameters and bias parameters; ctRepresenting the internal state of the LSTM cell at the current time t; hidden layer state h at the current momenttThe method comprises the steps that global characteristics with time series information are included, and then the global characteristics are subjected to nonlinear mapping through a full connection layer, so that a health index CRNN-HI capable of measuring the degradation degree of a bearing is obtained;
2) training a convolution cyclic neural network model (CRNN): the loss function of the convolution cyclic neural network model CRNN adopts a root mean square regression error, a training set chi is composed of a full life cycle vibration signal of a rolling bearing, and chi { (x)t,yt) L 1 is less than or equal to T is less than or equal to T, wherein xt∈RN,yt∈[0,1]N represents the length of a data sample of each vibration signal acquired, T represents the life of the rolling bearing, ytIs a real number representing the percentage of residual life of the bearing at the current time t; the loss function J of the convolutional recurrent neural network model CRNN is calculated by:
Figure BDA0002242201670000071
wherein,
Figure BDA0002242201670000072
is the predicted value of HI for a bearing
Figure BDA0002242201670000073
A value very close to 0 indicates that the bearing is in a failure state; the whole convolution cyclic neural network model CRNN is trained by adopting a back propagation algorithm BP, an optimizer selects Adam, the initial learning rate lr is set to be 0.001, and the sample size of each batch is set to be 32;
3) evaluating a convolution cycle neural network model (CRNN), selecting an optimal trained convolution cycle neural network model (CRNN) to predict a health index (CRNN-HI) of a rolling bearing to be evaluated, wherein a correlation index (Corr) and a monotonicity index (Mono) are adopted to quantitatively evaluate the performance of the convolution cycle neural network model (CRNN) on a verification set in a training process, the correlation index (Corr) measures the correlation between the attenuation trend of the CRNN-HI and the equipment running time, and the value calculation is as follows:
Figure BDA0002242201670000074
symbol IiAnd tiRespectively representing the value of CRNN-HI and the running time,
Figure BDA0002242201670000081
the monotonicity index Mono measures the increasing or decreasing trend of the CRNN-HI along with time, and the calculation formula is as follows:
Figure BDA0002242201670000082
and dI represents a first-order difference between two CRNN-HI at adjacent moments, the value ranges of the values of Corr and Mono are both between 0 and 1, and after the optimal model parameters are selected, the acquired vibration signals of the bearing to be analyzed are input into the optimal model, so that the output of the optimal model and the CRNN-HI value of the bearing at the current moment are obtained, and the current degradation degree of the rolling bearing is quantitatively evaluated.
The invention has been successfully applied to the health state evaluation of the rolling bearing, and reference is made to fig. 3, which is a prediction result of the health state of 4 bearing full-life cycle vibration data under two operating conditions, wherein the abscissa is the operating time, and the ordinate is the predicted value of CRNN-HI, as can be seen from fig. 3, CRNN-HI shows higher correlation and monotonicity in the prediction of the degradation trend of 4 bearings, and the nonlinear degradation process of the rolling bearing is characterized as a linear process changing along with time, even if the bearings work under different operating conditions.
The above examples are only for illustrating the technical idea and features of the present invention, and are not to be construed as limiting the scope of the present invention. It will be appreciated by those skilled in the art that various modifications and changes may be made without departing from the spirit of the invention.

Claims (1)

1. An end-to-end convolution cyclic neural network-based bearing health index construction method is characterized by comprising the following steps:
1) constructing a convolution cyclic neural network model CRNN: the input of the convolution cyclic neural network model CRNN is standardized original bearing vibration signal data, the convolution cyclic neural network model CRNN comprises two components, one component is a convolution neural network CNNs used for extracting local characteristics and consists of convolution layers and pooling layers which are stacked alternately, and in order to accelerate the training process and the convergence speed of the network, a BatchNorm layer and a residual error connecting structure are added into the convolution neural network CNNs; the convolutional neural networks CNNs comprise 4 groups of residual error units, each residual error unit comprises 2 convolutional layers, each residual error unit performs down-sampling on input data, the first convolutional layer of the convolutional neural networks CNNs adopts a pre-activation design, and the sizes of convolutional cores in the whole convolutional layer are all 16; the other component is used for extracting global characteristics with time series information and circularly connecting the cyclic neural network of the local characteristics, and is realized by adopting a long-short term memory network LSTM, the input of the long-short term memory network LSTM at each moment is each characteristic point on a characteristic diagram output by the convolutional neural network CNNs, and the time length is equal to the dimension of the characteristic diagram; the output of the long-short term memory network LSTM at the time t is calculated by the following formula:
ft＝σ(Wf·[ht-1,xt]+bf) (1)
Figure FDA0002242201660000011
it＝σ(Wi·[ht-1,xt]+bi) (3)
Figure FDA0002242201660000012
ot＝σ(Wo·[ht-1,xt]+bo) (5)
ht＝ot⊙tanh(Ct) (6)
wherein h ist-1And xtRespectively representing the hidden layer state of the long-short term memory network LSTM at the time t-1 and the input characteristics at the time t; wf，WiAnd WoRespectively representing the weight parameters of a long-short term memory network LSTM forgetting gate, an input gate and an output gate; bf，biAnd boRespectively representing the bias parameters of a long-short term memory network LSTM forgetting gate, an input gate and an output gate; f. oft，itAnd otRespectively representing the activation values of a long-short term memory network LSTM forgetting gate, an input gate and an output gate; the activation function sigma is a sigmoid function; the notation tanh denotes a hyperbolic tangent function; the symbols & · denote element-by-element multiplication and matrix multiplication, respectively;
Figure FDA0002242201660000021
representing newly learned feature information, W, of long-and short-term memory networks LSTMCAnd bCRespectively corresponding weight parameters and bias parameters; ctRepresenting the internal state of the LSTM cell at the current time t; hidden layer state h at the current momenttThe method comprises the steps that global characteristics with time series information are included, and then the global characteristics are subjected to nonlinear mapping through a full connection layer, so that a health index CRNN-HI capable of measuring the degradation degree of a bearing is obtained;
2) training a convolution cyclic neural network model (CRNN): the loss function of the convolution cyclic neural network model CRNN adopts a root mean square regression error, a training set chi is composed of a full life cycle vibration signal of a rolling bearing, and chi { (x)t,yt) L 1 is less than or equal to T is less than or equal to T, wherein xt∈RN,yt∈[0,1]N represents the length of a data sample of each vibration signal acquired, T represents the life of the rolling bearing, ytIs a real number representing the percentage of residual life of the bearing at the current time t; the loss function J of the convolutional recurrent neural network model CRNN is calculated by:
Figure FDA0002242201660000022
wherein,
Figure FDA0002242201660000023
is the predicted value of HI for a bearing
Figure FDA0002242201660000024
A value very close to 0 indicates that the bearing is in a failure state; the whole convolution cyclic neural network model CRNN is trained by adopting a back propagation algorithm BP, an optimizer selects Adam, the initial learning rate lr is set to be 0.001, and the sample size of each batch is set to be 32;
3) evaluating a convolution cycle neural network model (CRNN), selecting an optimal trained convolution cycle neural network model (CRNN) to predict a health index (CRNN-HI) of a rolling bearing to be evaluated, wherein a correlation index (Corr) and a monotonicity index (Mono) are adopted to quantitatively evaluate the performance of the convolution cycle neural network model (CRNN) on a verification set in a training process, the correlation index (Corr) measures the correlation between the attenuation trend of the CRNN-HI and the equipment running time, and the value calculation is as follows:
Figure FDA0002242201660000031
symbol IiAnd tiRespectively representing the value of CRNN-HI and the running time,
Figure FDA0002242201660000032
the monotonicity index Mono measures the increasing or decreasing trend of the CRNN-HI along with time, and the calculation formula is as follows:
Figure FDA0002242201660000033
and dI represents a first-order difference between two CRNN-HI at adjacent moments, the value ranges of the values of Corr and Mono are both between 0 and 1, and after the optimal model parameters are selected, the acquired vibration signals of the bearing to be analyzed are input into the optimal model, so that the output of the optimal model and the CRNN-HI value of the bearing at the current moment are obtained, and the current degradation degree of the rolling bearing is quantitatively evaluated.
CN201911004003.1A 2019-10-22 2019-10-22 End-to-end bearing health index construction method based on convolution cyclic neural network Active CN110633792B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911004003.1A CN110633792B (en) 2019-10-22 2019-10-22 End-to-end bearing health index construction method based on convolution cyclic neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911004003.1A CN110633792B (en) 2019-10-22 2019-10-22 End-to-end bearing health index construction method based on convolution cyclic neural network

Publications (2)

Publication Number Publication Date
CN110633792A CN110633792A (en) 2019-12-31
CN110633792B true CN110633792B (en) 2022-03-22

Family

ID=68976959

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911004003.1A Active CN110633792B (en) 2019-10-22 2019-10-22 End-to-end bearing health index construction method based on convolution cyclic neural network

Country Status (1)

Country Link
CN (1) CN110633792B (en)

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111291673A (en) * 2020-02-04 2020-06-16 贵州省人民医院 Method, device, server and storage medium for predicting time sequence signal classification
CN111832216B (en) * 2020-04-14 2022-07-12 新疆大学 Rolling bearing residual service life prediction method based on EEMD-MCNN-GRU
CN111680661A (en) * 2020-06-19 2020-09-18 哈尔滨工业大学 Mechanical rotating part performance degradation tracking method based on multi-feature fusion
CN111856287B (en) * 2020-07-17 2021-07-13 上海交通大学 Lithium battery health state detection method based on stacked residual causal convolutional neural network
CN112033463B (en) * 2020-09-02 2022-09-06 哈尔滨工程大学 Nuclear power equipment state evaluation and prediction integrated method and system
CN112347898B (en) * 2020-11-03 2024-04-09 重庆大学 Rolling bearing health index construction method based on DCAE neural network
CN112729825A (en) * 2020-12-18 2021-04-30 中车永济电机有限公司 Method for constructing bearing fault diagnosis model based on convolution cyclic neural network
CN112992119B (en) * 2021-01-14 2024-05-03 安徽大学 Accent classification method based on deep neural network and model thereof
CN112766182B (en) * 2021-01-22 2024-02-02 浙江工业大学 Broaching tool wear state identification method
CN113283155B (en) * 2021-03-22 2024-04-09 中国农业科学院农业资源与农业区划研究所 Near-surface air temperature estimation method, system, storage medium and equipment
CN113553903B (en) * 2021-06-11 2022-11-22 东南大学 Rotary machine health assessment method of deep time convolution network
CN113505535B (en) * 2021-07-08 2023-11-10 重庆大学 Motor life prediction method based on gating self-adaptive hierarchical attention unit network
EP4124529B1 (en) 2021-07-29 2023-08-23 Volvo Truck Corporation Method for detecting a failure in a vehicle pneumatic system
CN114036691B (en) * 2021-11-26 2024-06-21 江苏科技大学 Bearing degradation evaluation method and system based on recursion complex network
CN114925723B (en) * 2022-05-06 2023-04-07 盐城工学院 Method for predicting residual service life of rolling bearing by adopting encoder and decoder
CN115033984B (en) * 2022-05-26 2024-09-24 西北工业大学 LSTM-based comprehensive modularized avionics system health assessment method
WO2024108577A1 (en) * 2022-11-25 2024-05-30 深圳先进技术研究院 Method for interpreting pancreatitis diagnosis model by using layer-wise relevance propagation

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106934126A (en) * 2017-02-28 2017-07-07 西安交通大学 Component of machine health indicator building method based on Recognition with Recurrent Neural Network fusion
CN108960077A (en) * 2018-06-12 2018-12-07 南京航空航天大学 A kind of intelligent failure diagnosis method based on Recognition with Recurrent Neural Network
CN109522600A (en) * 2018-10-16 2019-03-26 浙江大学 Complex equipment remaining life prediction technique based on combined depth neural network
CN109726524A (en) * 2019-03-01 2019-05-07 哈尔滨理工大学 A kind of rolling bearing remaining life prediction technique based on CNN and LSTM
CN110108456A (en) * 2019-04-16 2019-08-09 东南大学 A kind of rotating machinery health evaluating method of depth convolutional neural networks

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10410116B2 (en) * 2014-03-11 2019-09-10 SparkCognition, Inc. System and method for calculating remaining useful time of objects
KR102555362B1 (en) * 2017-06-05 2023-07-13 아다스카이, 엘티디. Shutterless Far Infrared (FIR) Cameras for Automotive Safety and Driving Systems

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106934126A (en) * 2017-02-28 2017-07-07 西安交通大学 Component of machine health indicator building method based on Recognition with Recurrent Neural Network fusion
CN108960077A (en) * 2018-06-12 2018-12-07 南京航空航天大学 A kind of intelligent failure diagnosis method based on Recognition with Recurrent Neural Network
CN109522600A (en) * 2018-10-16 2019-03-26 浙江大学 Complex equipment remaining life prediction technique based on combined depth neural network
CN109726524A (en) * 2019-03-01 2019-05-07 哈尔滨理工大学 A kind of rolling bearing remaining life prediction technique based on CNN and LSTM
CN110108456A (en) * 2019-04-16 2019-08-09 东南大学 A kind of rotating machinery health evaluating method of depth convolutional neural networks

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
"Deep Recurrent Convolutional Neural Network for Remaining Useful Life Prediction";Meng Ma 等;《2019 IEEE International Conference on Prognostics and Health Management (ICPHM)》;20190829;全文 *
"基于全矢卷积循环神经网络的滚动轴承诊断研究";谢远东;《中国优秀博硕士学位论文全文数据库(硕士)-工程科技Ⅱ辑》;20190815;第2019年卷(第8期);C029-133 *

Also Published As

Publication number Publication date
CN110633792A (en) 2019-12-31

Similar Documents

Publication Publication Date Title
CN110633792B (en) End-to-end bearing health index construction method based on convolution cyclic neural network
CN114611792B (en) Atmospheric ozone concentration prediction method based on mixed CNN-converter model
CN112149316A (en) Aero-engine residual life prediction method based on improved CNN model
CN111860982A (en) Wind power plant short-term wind power prediction method based on VMD-FCM-GRU
CN111339712A (en) Method for predicting residual life of proton exchange membrane fuel cell
CN111723527B (en) Method for predicting residual life of gear based on cocktail long-short-term memory neural network
CN110222387B (en) Multi-element drilling time sequence prediction method based on mixed leaky integration CRJ network
CN114169091B (en) Method for establishing prediction model of residual life of engineering machinery part and prediction method
CN112132102B (en) Intelligent fault diagnosis method combining deep neural network with artificial bee colony optimization
CN111680788A (en) Equipment fault diagnosis method based on deep learning
CN111783362A (en) Method and system for determining residual service life of electric gate valve
CN114282443A (en) Residual service life prediction method based on MLP-LSTM supervised joint model
CN114861778B (en) Rolling bearing state rapid classification method under different loads for improving width transfer learning
CN113435321A (en) Method, system and equipment for evaluating state of main shaft bearing and readable storage medium
CN112101659A (en) Complex equipment service life prediction method based on stacking denoising autoencoder
CN116050504A (en) Wind power short-term prediction model based on deep learning
Hongwei et al. An interpretable data-driven method for degradation prediction of proton exchange membrane fuel cells based on temporal fusion transformer and covariates
CN118171162A (en) Gear fault diagnosis method and system based on non-local attention metering network
CN118040678A (en) Short-term offshore wind power combination prediction method
CN117709524A (en) Bayesian optimization-based carbon emission prediction method and system for steel industry
CN116842358A (en) Soft measurement modeling method based on multi-scale convolution and self-adaptive feature fusion
CN116337441A (en) Fault diagnosis method for key parts of fan with attention depth self-coding function
CN116247658A (en) Photovoltaic power generation amount prediction method based on DLRM deep learning model
CN116304587A (en) Rolling bearing degradation trend prediction method based on CAE and AGRU
Wang et al. A novel multiscale deep health indicator with bidirectional LSTM network for bearing performance degradation trend prognosis

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