CN112069738A - Method and system for predicting residual life of electric steering engine based on DBN and multi-layer fuzzy LSTM - Google Patents
Method and system for predicting residual life of electric steering engine based on DBN and multi-layer fuzzy LSTM Download PDFInfo
- Publication number
- CN112069738A CN112069738A CN202010972888.0A CN202010972888A CN112069738A CN 112069738 A CN112069738 A CN 112069738A CN 202010972888 A CN202010972888 A CN 202010972888A CN 112069738 A CN112069738 A CN 112069738A
- Authority
- CN
- China
- Prior art keywords
- steering engine
- electric steering
- data
- residual life
- lstm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012544 monitoring process Methods 0.000 claims abstract description 42
- 230000015556 catabolic process Effects 0.000 claims abstract description 19
- 238000006731 degradation reaction Methods 0.000 claims abstract description 19
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 239000000284 extract Substances 0.000 claims abstract description 14
- 238000013135 deep learning Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 17
- 230000015654 memory Effects 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 abstract 1
- 210000004027 cell Anatomy 0.000 description 13
- 230000006870 function Effects 0.000 description 12
- 238000004891 communication Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 241001391944 Commicarpus scandens Species 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Steering Control In Accordance With Driving Conditions (AREA)
Abstract
The invention discloses a method and a system for predicting the residual life of an electric steering engine based on a DBN (database network) and a multi-layer fuzzy LSTM (Linear transformation TM), wherein the method comprises the following steps: acquiring real-time monitoring data of the electric steering engine; preprocessing the acquired real-time monitoring data; inputting the preprocessed data into a trained steering engine state degradation model, and outputting the predicted residual life of the electric steering engine; the steering engine state degradation model extracts a characteristic rule from the preprocessed data through a deep belief network, and then extracts a time characteristic from a data sequence through a multilayer fuzzy LSTM network; and obtaining the predicted residual life of the electric steering engine based on the characteristic rule and the time characteristic. The method adopts a deep learning network model based on DBN and multi-layer fuzzy LSTM to predict the residual life of the electric steering engine, can effectively extract the characteristic rules and the time characteristics of the sequence in the multi-dimensional electric steering engine sensor monitoring data, and improves the precision of the residual life prediction; the safety and the reliability of the steering engine during operation are improved.
Description
Technical Field
The invention relates to the technical field of equipment residual life prediction, in particular to a method and a system for predicting the residual life of an electric steering engine based on a DBN (database network) and a multi-layer fuzzy LSTM (least squares).
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The electric steering engine is used as core equipment of an advanced aircraft self-driving system such as a helicopter, an unmanned aerial vehicle and the like, and is an important control component in the aircraft. If the electric steering engine fails, particularly if the main control steering engine fails, such as a rudder, an elevator, an aileron and the like, the airplane is in an out-of-control state, catastrophic consequences of airplane damage and death can be caused seriously, and the safety and reliability of an aircraft avionic system, a helicopter and an unmanned aerial vehicle are severely restricted. The electric steering engine has poor reliability in a plurality of airborne systems and is easy to break down. Therefore, the fault monitoring and service life prediction of the electric steering engine have important significance on the flight safety of the aircraft.
Compared with a hydraulic steering engine and a pneumatic steering engine, the electric steering engine consisting of the servo direct current motor and the transmission mechanism has the advantages of high precision, convenience in maintenance, small size, light weight, easiness in transmission control and the like, and is widely applied to advanced aircrafts such as unmanned planes, airplanes, helicopters and spacecrafts. According to statistics of 'reliability of non-electronic parts', for small and medium-sized permanent magnet direct current motors used for aircrafts such as helicopters, unmanned planes and the like, the fault of an electric brush accounts for more than 34% of the fault probability of the motor, the fault of a rotor winding accounts for about 20%, the fault of magnetic steel accounts for about 20%, and the fault of a bearing accounts for 15%. Therefore, the faults of the electric steering engine mainly occur at the positions of the motor, the transmission mechanism and the position sensor, and the rotor winding, the permanent magnet, the electric brush and the rotating shaft are weak links of the reliability of the steering engine.
The prior art generally adopts a method of after-the-fact diagnosis or off-line monitoring to monitor the fault of the steering engine, and the method has low efficiency and can not ensure the safety and the reliability of the steering engine during operation.
Disclosure of Invention
In order to solve the problems, the invention provides a method and a system for predicting the residual life of an electric steering engine based on a DBN (database network) and a multi-layer fuzzy LSTM (least squares), which can monitor the running state of the steering engine in real time and predict the residual life of the steering engine on line.
In some embodiments, the following technical scheme is adopted:
a method for predicting the residual life of an electric steering engine based on a DBN and multi-layer fuzzy LSTM comprises the following steps:
acquiring real-time monitoring data of the electric steering engine;
preprocessing the acquired real-time monitoring data;
inputting the preprocessed data into a trained steering engine state degradation model, and outputting the predicted residual life of the electric steering engine;
the steering engine state degradation model extracts a characteristic rule from the preprocessed data through a deep confidence network, reduces the characteristic dimension of the data, and extracts time characteristics in a data sequence through a multilayer fuzzy LSTM network; and obtaining the predicted residual life of the electric steering engine based on the characteristic rule and the time characteristic.
In other embodiments, the following technical solutions are adopted:
an electric steering engine residual life prediction system based on DBN and multi-layer fuzzy LSTM comprises:
the data acquisition module is used for acquiring real-time monitoring data of the electric steering engine;
the data preprocessing module is used for preprocessing the acquired real-time monitoring data;
the residual life prediction module is used for inputting the preprocessed data into the trained steering engine state degradation model and outputting the predicted residual life of the electric steering engine;
the steering engine state degradation model extracts a characteristic rule from the preprocessed data through a deep confidence network, reduces the characteristic dimension of the data, and extracts time characteristics in a data sequence through a multilayer fuzzy LSTM network; and obtaining the predicted residual life of the electric steering engine based on the characteristic rule and the time characteristic.
In other embodiments, the following technical solutions are adopted:
the terminal device comprises a server, wherein the server comprises a storage, a processor and a computer program which is stored on the storage and can run on the processor, and when the processor executes the program, the method for predicting the residual life of the electric steering engine based on the DBN and the multi-layer fuzzy LSTM is realized.
Compared with the prior art, the invention has the beneficial effects that:
(1) the method adopts a deep learning network model based on DBN and multi-layer fuzzy LSTM to predict the residual life of the electric steering engine, can effectively extract the characteristic rules and the time characteristics of the sequence in the multi-dimensional electric steering engine sensor monitoring data, and improves the precision of the residual life prediction; the safety and the reliability of the steering engine during operation are improved.
(2) Before real-time monitoring data are input into a steering engine state degradation model, missing values are filled, and the model training effect and the prediction accuracy are improved. Meanwhile, the variables with larger relevance are determined by calculating the correlation coefficient among the variables, the data volume is further compressed, the information of the input data is more compact, and the calculated amount of deep learning model training is reduced.
(3) The invention can ensure that the real-time state of each aircraft can be observed and reasonably arrange flight and maintenance tasks based on the signal transmission of the Beidou short message communication function.
Drawings
FIG. 1 is a flow chart of a DBN and multi-layer fuzzy LSTM-based method for predicting the remaining life of an electric steering engine in the embodiment of the invention;
FIG. 2 is a schematic diagram of an LSTM cell expanded in time series in an embodiment of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example one
In one or more embodiments, an electric steering engine remaining life prediction method based on a DBN and a multi-layer fuzzy LSTM is disclosed, referring to fig. 1, comprising the following steps:
step (1): the layout sensor is used for acquiring real-time monitoring data of the electric steering engine;
the main faults of the electric steering engine comprise transmission mechanism faults, motor faults and sensor faults. Current, rotational speed and vibration signals are readily available and contain a large amount of steering engine state information. Therefore, two current sensors are installed to monitor the currents of the motor 1 and the motor 2; mounting four vibration sensors, and monitoring vibration signals of the motor 1, the motor 2, the transmission mechanism and the shell; three rotating speed sensors are arranged to monitor the rotating speeds of the motor 1, the motor 2 and the output shaft; four temperature sensors are installed to monitor the temperature of the motor 1, the motor 2, the transmission mechanism and the shell.
Step (2): preprocessing the acquired real-time monitoring data;
specifically, the raw sensor monitoring data of the electric steering engines collected from the sensor monitoring system is a multidimensional time series, and the sensor monitoring data of each electric steering engine is represented as Xi＝[x1,x2,...,xt,...xT]. Where T represents the maximum number of runtime steps of the device, xtIs n-dimensional sensor monitoring data at the moment t, i represents the current steering engine id, and all the steering engines of the idThe data constitutes the entire data set.
The collected sensor monitoring data usually has the problem of missing values, which will cause discontinuity of the time range. Moreover, the sensor monitoring system has multidimensional sensor data, and redundant information will reduce the accuracy of life prediction. Factors such as external environment interference, load change, sensor noise and the like can influence the training effect of the model. The embodiment of the invention adopts the following method to preprocess data.
1) Missing value handling
Due to abnormal data transmission and abnormal sensors of the electric steering engine, the sensor monitoring data usually loses values. The abnormal data is directly input into the deep learning model, and the training effect of the model is poor. The invention adopts local mean value replacement to fill missing values, and the specific calculation can be expressed as:
wherein xmIs the data value of the missing point, k is the number of missing values before and after the missing point for mean value replacement, and this embodiment sets k to 3 to smooth the curve.
2) Sensor variable selection
As can be known from the foregoing, the collected monitoring data of the electric steering engine includes various variables, such as temperature, rotational speed, vibration, current, etc., and if the state correlation of the variables and the electric steering engine is small, the fitting will be insufficient, and the effect of model training will be affected. In order to screen out variables which can represent or greatly influence the state of the electric steering engine, the data volume is further compressed, the information of the input data is more compact, and the calculated amount of deep learning model training is reduced. The embodiment adopts Pearson product-moment correlation coefficient (Pearson product-moment correlation coefficient) to calculate the correlation between each variable, selects valuable variables through correlation analysis, and determines the final input of the model.
The pearson product-moment correlation coefficient is expressed as follows:
where n is the sample size, xiAnd yiIs the individual sample point indexed by i,
and
is the sample mean. Pearson product-moment correlation coefficients are used to measure the degree of correlation between variables, and if the correlation coefficient of a variable with other variables is small, meaning that the variable has more randomness, the variable should be discarded.
3) Data normalization
In order to eliminate the influence of dimension and value range difference between indexes, standardization processing is required, and data is scaled according to a proportion so as to fall into a specific area, thereby facilitating comprehensive analysis. The invention processes data by zero-mean normalization (z-score normalization), and the formula is as follows:
wherein
σ is the standard deviation of the raw data, which is the mean of the raw data. The mean of the processed data was 0 and the standard deviation was 1.
And (3): and (3) constructing a steering engine state degradation model based on the deep confidence network and the multilayer fuzzy LSTM network, acquiring historical sensor data of the electric steering engine, processing by adopting the preprocessing method in the step (2), generating a training sample in a mode of translating a time window, and taking the residual life corresponding to the last moment in the time window as a label of the sample.
Through the preprocessing in the step (2), the continuity and the effectiveness of the sensor data are improved, in order to meet the input requirement of the subsequent deep learning network model, the embodiment generates the training sample by adopting a method of translating a time window, the data of the model input each time is a two-dimensional tensor of num _ time × num _ sensor size, wherein num _ sensor is the sensor dimension selected by the sensor variable selection method, num _ time is the time window size, the value of the embodiment is 30, and a time step slides forward each time.
The maximum time step collected by each steering engine is TiThen T can be generatedi+1-num _ time training samples.
Training the constructed steering engine state degradation model through the training sample, and outputting the residual life of the electric steering engine.
The state characteristics of the electric steering engine are contained in multidimensional data, and a deep learning network needs to learn the complex characteristics. A plurality of sensors installed on different positions of the electric steering engine acquire different monitoring signals, sensor variables at different positions can be mutually influenced with sensor variables at other positions, and inherent spatial characteristics exist among the sensor variables.
The steering engine state degradation model constructed in the embodiment adopts a deep confidence network (DBN) for deep learning to extract deep spatial features, the DBN is formed by stacking a plurality of limited boltzmann machines (RBMs), each RBM is composed of a visible layer and a hidden layer, the number of neurons of a first visible layer is determined by an input data dimension, a weighted value between any two connected neurons of the visible layer and the hidden layer is W, b and c are bias values of the visible layer and the hidden layer respectively, v is an input vector, h is an output vector, and an energy function of one RBM is expressed as follows:
when one RBM is completed, its hidden layer will serve as the visible layer for the next RBM. Through the series connection of several RBMs, a DBN is formed. Each layer of the RBM is trained in advance to serve as an initial weight, and then the back propagation error of the output layer finely adjusts the parameters of each layer of the network. The method adopts a DBN model with a two-layer RBM structure. The DBN uses a nonlinear structure to extract features and maps data from a high-dimensional space to a low-dimensional space, so that feature information of original data is retained to the maximum extent, a feature rule closer to the original essence of the data is obtained, and the dimensionality of the data is reduced. The method adopts the ReLU function as the nonlinear activation function of the hidden layer, and when the input value of the ReLU function is greater than 0, the derivative value is 1, so that the problem of gradient dispersion can be effectively solved.
After the characteristics of input sensor data are extracted, time characteristics in a data sequence are extracted through a multilayer fuzzy LSTM network, and compared with an RNN cyclic neural network, the long-short term memory neural network can effectively solve the problems of gradient disappearance and gradient explosion. The cell of the LSTM is shown in fig. 2.
In FIG. 2, xtInput representing the current time, CtIndicates the cell state (long-term memory cell), htIndicating the hidden layer state (short term memory cell), ftIndicating a forgotten gate unit, otRepresenting output gating cells, itRepresenting the input gate unit and sigma the activation function of each gate. The mathematical expression is as follows:
ft＝σ(Wfxt+W'fht-1+bf)
it＝σ(Wixt+W'iht-1+bi)
The state of the cell is updated by modulating the previous cell state to the current cell state.
The final output is determined by the cell state value and the result of the output gate together:
ot＝σ(Woxt+W'oht-1+bo)
ht＝ot*tanh(Ct)
in the formula, Wf、W'f、Wi、W'i、Wo、W'o、WC、W'CRepresents a weight, bf、bi、bo、bCThe deviation is indicated.
The blurring of the blurred LSTM is performed on different layers and elements of the original LSTM model M, the concept being to derive the blurring weights of the LSTM pre-trained model M, by using
The stress operator or function generates a variation model M'. These stress functions have different stress intensities ρ defined and verified on the Weierstrass function. Use of
Variants of stress operators or having different stress intensities of p and
the function of the stress operator stresses the weights of the LSTM cells.
Will be provided with
The stress operator is applied to the model M as a whole, affecting the weights of the LSTM units and the layers of the RUL prediction deep learning network. At i (input) of LSTM model MGate), o (output gate), f (forgetting gate) and
(component node) on-line application
Stress, the intensity of ρ -stress, affects the LSTM cell weight (W) per layerf、W'f、Wi、W'i、Wo、W'o、WC、W'C) The mathematical expression is as follows:
in the embodiment, a mode of stacking 4 layers of LSTM networks is adopted to extract deep abstract features, the output of the previous layer is used as the input of the next layer, and the nonlinear fitting capability of the model is improved. The state of the nth layer at the time t is expressed as follows:
in the formula (I), the compound is shown in the specification,
indicating the hidden layer state at time t of layer n-1.
A fully connected layer is connected behind the LSTM layer, and final output information is extracted from the characteristic law, wherein the final output is represented as:
in the formula, WqAnd bqAnd finally outputting the predicted residual service life of the electric steering engine by the full-connection layer as weight and deviation.
Network parameter setting is carried out through adaptive moment estimation (Adam optimization algorithm), and in order to prevent the overfitting of the network in the training process, dropout is added in the training process to enable a part of neurons to be inactivated randomly.
And (4): inputting the preprocessed real-time monitoring data into a trained steering engine state degradation model, and outputting the predicted residual life of the electric steering engine;
as an optional implementation mode, after the predicted residual service life of the electric steering engine is obtained, the residual service life of the electric steering engine is displayed in real time, and the real-time state of the electric steering engine and the predicted value of the residual service life are sent to the monitoring platform.
Example two
In one or more embodiments, an electric steering engine remaining life prediction system based on a DBN and multi-layer fuzzy LSTM is disclosed, comprising:
the data acquisition module is used for acquiring real-time monitoring data of the electric steering engine;
the data preprocessing module is used for preprocessing the acquired real-time monitoring data;
the residual life prediction module is used for inputting the preprocessed data into the trained steering engine state degradation model and outputting the predicted residual life of the electric steering engine;
the steering engine state degradation model extracts a characteristic rule from the preprocessed data through a deep confidence network, reduces the characteristic dimension of the data, and extracts time characteristics in a data sequence through a multilayer fuzzy LSTM network; and obtaining the predicted residual life of the electric steering engine based on the characteristic rule and the time characteristic.
As an optional implementation, the method further includes:
the display module is used for displaying the state of the electric steering engine and the predicted value of the residual service life in real time;
and the data transmission module is used for transmitting the real-time state and the residual life predicted value of the electric steering engine to the remote monitoring platform. Specifically, the real-time state of the electric steering engine is sent to a ground monitoring and dispatching platform through a wireless communication module based on the Beidou short message communication function, the collected original data is not sent, and the predicted real-time state and the predicted residual life value of each electric steering engine are only sent. The Beidou short message communication function can be used in areas where the common mobile communication signals cannot cover the areas where extreme environments or disaster area communication base stations are damaged.
It should be noted that the specific implementation manner of the modules is implemented by the manner disclosed in the first embodiment, and is not described again.
In addition, the modules can be integrated on a controller and used for realizing the prediction of the residual service life of the steering engine; the system of the embodiment is combined with an embedded Linux technology and a Jetson TX2 embedded platform, a residual life prediction UI interface is manufactured, and the modules are integrated on a TX2 embedded GPU platform to run.
EXAMPLE III
In one or more embodiments, a terminal device is disclosed, which includes a server, where the server includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the method for predicting the remaining life of an electric steering engine based on a DBN and a multi-layer fuzzy LSTM in example one. For brevity, no further description is provided herein.
It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and so on.
A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The memory may include both read-only memory and random access memory, and may provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.
In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software.
The method for predicting the remaining life of the electric steering engine based on the DBN and the multi-layer fuzzy LSTM in the first embodiment may be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor. The software modules may be located in ram, flash, rom, prom, or eprom, registers, among other storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor. To avoid repetition, it is not described in detail here.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. A method for predicting the residual life of an electric steering engine based on a DBN and multi-layer fuzzy LSTM is characterized by comprising the following steps:
acquiring real-time monitoring data of the electric steering engine;
preprocessing the acquired real-time monitoring data;
inputting the preprocessed data into a trained steering engine state degradation model, and outputting the predicted residual life of the electric steering engine;
the steering engine state degradation model extracts a characteristic rule from the preprocessed data through a deep confidence network, reduces the characteristic dimension of the data, and extracts time characteristics in a data sequence through a multilayer fuzzy LSTM network; and obtaining the predicted residual life of the electric steering engine based on the characteristic rule and the time characteristic.
2. The method for predicting the residual life of the electric steering engine based on the DBN and the multi-layer fuzzy LSTM as claimed in claim 1, wherein the real-time monitoring data at least comprises: the electric steering engine comprises current signals and rotating speed signals of all motors, vibration signals and temperature signals of all motors and a transmission shaft.
3. The method for predicting the residual life of the electric steering engine based on the DBN and the multilayer fuzzy LSTM, as claimed in claim 1, wherein the preprocessing is performed on the acquired real-time monitoring data, and specifically comprises:
and calculating the average value of the numerical values of the set number before and after the data loss point, and filling the missing value of the data loss point by adopting the average value.
4. The method for predicting the residual life of the electric steering engine based on the DBN and the multilayer fuzzy LSTM, as claimed in claim 3, wherein the preprocessing is performed on the acquired real-time monitoring data, further comprising:
and calculating the correlation between each variable in the monitoring data by adopting a Pearson product-moment correlation coefficient, and selecting the variable with a large correlation coefficient as a variable input into the deep learning neural network.
5. The method for predicting the residual life of the electric steering engine based on the DBN and the multilayer fuzzy LSTM, as claimed in claim 3, wherein the preprocessing is performed on the acquired real-time monitoring data, further comprising:
and carrying out normalization processing on the data by adopting zero-mean normalization.
6. The method for predicting the residual life of the electric steering engine based on the DBN and the multi-layer fuzzy LSTM is characterized in that the training process of the steering engine state degradation model comprises the following steps:
acquiring historical monitoring data of the electric steering engine, and constructing a training data set;
preprocessing the acquired historical monitoring data;
generating a training sample by adopting a method of translating a time window;
and inputting the training sample into a steering engine state degradation model to be trained, and outputting the predicted residual life of the electric steering engine.
7. The method for predicting the residual life of the electric steering engine based on the DBN and the multilayer fuzzy LSTM is characterized in that after the predicted residual life of the electric steering engine is obtained, the residual life of the electric steering engine is displayed in real time, and the real-time state of the electric steering engine and the predicted value of the residual life are sent to a monitoring platform.
8. An electric steering engine residual life prediction system based on DBN and multi-layer fuzzy LSTM is characterized by comprising:
the data acquisition module is used for acquiring real-time monitoring data of the electric steering engine;
the data preprocessing module is used for preprocessing the acquired real-time monitoring data;
the residual life prediction module is used for inputting the preprocessed data into the trained steering engine state degradation model and outputting the predicted residual life of the electric steering engine;
the steering engine state degradation model extracts a characteristic rule from the preprocessed data through a deep confidence network, reduces the characteristic dimension of the data, and extracts time characteristics in a data sequence through a multilayer fuzzy LSTM network; and obtaining the predicted residual life of the electric steering engine based on the characteristic rule and the time characteristic.
9. The system of claim 8, wherein the system further comprises:
the display module is used for displaying the state of the electric steering engine and the predicted value of the residual service life in real time;
and the data transmission module is used for transmitting the real-time state and the residual life predicted value of the electric steering engine to the remote monitoring platform.
10. A terminal device comprising a server, wherein the server comprises a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the method for predicting the remaining life of an electric steering engine based on DBN and multi-layer fuzzy LSTM as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010972888.0A CN112069738B (en) | 2020-09-16 | 2020-09-16 | Electric steering engine residual life prediction method and system based on DBN and multilayer fuzzy LSTM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010972888.0A CN112069738B (en) | 2020-09-16 | 2020-09-16 | Electric steering engine residual life prediction method and system based on DBN and multilayer fuzzy LSTM |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112069738A true CN112069738A (en) | 2020-12-11 |
| CN112069738B CN112069738B (en) | 2024-04-26 |
Family
ID=73696004
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010972888.0A Active CN112069738B (en) | 2020-09-16 | 2020-09-16 | Electric steering engine residual life prediction method and system based on DBN and multilayer fuzzy LSTM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112069738B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114218872A (en) * | 2021-12-28 | 2022-03-22 | 浙江大学 | Method for predicting remaining service life based on DBN-LSTM semi-supervised joint model |
| CN114819350A (en) * | 2022-04-28 | 2022-07-29 | 天津大学 | RUL prediction method under sensor fault condition based on multiple tasks |
| CN117031956A (en) * | 2023-08-23 | 2023-11-10 | 无锡纬途流体科技有限公司 | Control method and system of intelligent embedded electric actuator |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109102066A (en) * | 2018-07-12 | 2018-12-28 | 山东师范大学 | Online time series data prediction technique, system and storage medium based on fuzzy reasoning |
| CN110738360A (en) * | 2019-09-27 | 2020-01-31 | 华中科技大学 | equipment residual life prediction method and system |
| KR20200023672A (en) * | 2018-08-14 | 2020-03-06 | 오토시맨틱스 주식회사 | Diagnosis method of battery using Deep Learning |
| CN111274737A (en) * | 2020-02-25 | 2020-06-12 | 山东大学 | Method and system for predicting remaining service life of mechanical equipment |
| CN111460728A (en) * | 2020-03-09 | 2020-07-28 | 华南理工大学 | Method and device for predicting residual life of industrial equipment, storage medium and equipment |
-
2020
- 2020-09-16 CN CN202010972888.0A patent/CN112069738B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109102066A (en) * | 2018-07-12 | 2018-12-28 | 山东师范大学 | Online time series data prediction technique, system and storage medium based on fuzzy reasoning |
| KR20200023672A (en) * | 2018-08-14 | 2020-03-06 | 오토시맨틱스 주식회사 | Diagnosis method of battery using Deep Learning |
| CN110738360A (en) * | 2019-09-27 | 2020-01-31 | 华中科技大学 | equipment residual life prediction method and system |
| CN111274737A (en) * | 2020-02-25 | 2020-06-12 | 山东大学 | Method and system for predicting remaining service life of mechanical equipment |
| CN111460728A (en) * | 2020-03-09 | 2020-07-28 | 华南理工大学 | Method and device for predicting residual life of industrial equipment, storage medium and equipment |
Non-Patent Citations (1)
| Title |
|---|
| GU YUHAI: "Research on failure prediction using DBN and LSTM neural network", 2018 57TH ANNUAL CONFERENCE OF SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS OF JSPAN * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114218872A (en) * | 2021-12-28 | 2022-03-22 | 浙江大学 | Method for predicting remaining service life based on DBN-LSTM semi-supervised joint model |
| CN114819350A (en) * | 2022-04-28 | 2022-07-29 | 天津大学 | RUL prediction method under sensor fault condition based on multiple tasks |
| CN117031956A (en) * | 2023-08-23 | 2023-11-10 | 无锡纬途流体科技有限公司 | Control method and system of intelligent embedded electric actuator |
| CN117031956B (en) * | 2023-08-23 | 2024-03-19 | 无锡纬途流体科技有限公司 | Control method and system of intelligent embedded electric actuator |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112069738B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112069738B (en) | Electric steering engine residual life prediction method and system based on DBN and multilayer fuzzy LSTM | |
| Luo et al. | Convolutional neural network based on attention mechanism and Bi-LSTM for bearing remaining life prediction | |
| Tao et al. | Bearing fault diagnosis method based on stacked autoencoder and softmax regression | |
| US8036789B2 (en) | System, method and computer program product for real-time event identification and course of action interpretation | |
| CN110216680B (en) | Cloud-ground cooperative fault diagnosis system and method for service robot | |
| CN112947385B (en) | Aircraft fault diagnosis method and system based on improved Transformer model | |
| Ning et al. | Applications of deep learning in big data analytics for aircraft complex system anomaly detection | |
| Li et al. | A Siamese hybrid neural network framework for few-shot fault diagnosis of fixed-wing unmanned aerial vehicles | |
| Nasser et al. | A hybrid of convolutional neural network and long short-term memory network approach to predictive maintenance | |
| WO2016053748A1 (en) | Vibration signatures for prognostics and health monitoring of machinery | |
| CN115510950A (en) | Aircraft telemetry data anomaly detection method and system based on time convolution network | |
| CN114692786B (en) | Civil aircraft fault diagnosis method based on multi-source data fusion | |
| Ruan et al. | Remaining useful life prediction for aero-engine based on LSTM and CNN | |
| Wang et al. | CNN-based hybrid optimization for anomaly detection of rudder system | |
| de Beaulieu et al. | Unsupervised remaining useful life prediction through long range health index estimation based on encoders-decoders | |
| Lang et al. | Data augmentation for fault prediction of aircraft engine with generative adversarial networks | |
| Fan et al. | UAV engine fault and diagnosis with parameter models based on telemetry data | |
| CN112560252A (en) | Prediction method for residual life of aircraft engine | |
| Zhang et al. | Simulation-to-reality UAV Fault Diagnosis with Deep Learning | |
| Verstraete et al. | A deep adversarial approach based on multi-sensor fusion for remaining useful life prognostics | |
| Yang et al. | Aircraft actuator fault diagnosis using deep learning based sparse representation and TSM | |
| Rounak et al. | Prediction of remaining useful life for aero-engines | |
| Kumar et al. | Building on prior lightweight CNN model combined with LSTM-AM framework to guide fault detection in fixed-wing UAVs | |
| Zhang et al. | Difference-based Deep Convolutional Neural Network for Simulation-to-reality UAV Fault Diagnosis | |
| Amiri et al. | Monitoring UAV status and detecting insulator faults in transmission lines with a new classifier based on aggregation votes between neural networks by interval type-2 TSK fuzzy system |
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 |