CN114919559A - System and method for predicting residual service life of braking system based on digital twinning - Google Patents
System and method for predicting residual service life of braking system based on digital twinning Download PDFInfo
- Publication number
- CN114919559A CN114919559A CN202210782812.0A CN202210782812A CN114919559A CN 114919559 A CN114919559 A CN 114919559A CN 202210782812 A CN202210782812 A CN 202210782812A CN 114919559 A CN114919559 A CN 114919559A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- service life
- brake
- digital twin
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60T—VEHICLE BRAKE CONTROL SYSTEMS OR PARTS THEREOF; BRAKE CONTROL SYSTEMS OR PARTS THEREOF, IN GENERAL; ARRANGEMENT OF BRAKING ELEMENTS ON VEHICLES IN GENERAL; PORTABLE DEVICES FOR PREVENTING UNWANTED MOVEMENT OF VEHICLES; VEHICLE MODIFICATIONS TO FACILITATE COOLING OF BRAKES
- B60T17/00—Component parts, details, or accessories of power brake systems not covered by groups B60T8/00, B60T13/00 or B60T15/00, or presenting other characteristic features
- B60T17/18—Safety devices; Monitoring
- B60T17/22—Devices for monitoring or checking brake systems; Signal devices
- B60T17/228—Devices for monitoring or checking brake systems; Signal devices for railway vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60T—VEHICLE BRAKE CONTROL SYSTEMS OR PARTS THEREOF; BRAKE CONTROL SYSTEMS OR PARTS THEREOF, IN GENERAL; ARRANGEMENT OF BRAKING ELEMENTS ON VEHICLES IN GENERAL; PORTABLE DEVICES FOR PREVENTING UNWANTED MOVEMENT OF VEHICLES; VEHICLE MODIFICATIONS TO FACILITATE COOLING OF BRAKES
- B60T17/00—Component parts, details, or accessories of power brake systems not covered by groups B60T8/00, B60T13/00 or B60T15/00, or presenting other characteristic features
- B60T17/18—Safety devices; Monitoring
- B60T17/22—Devices for monitoring or checking brake systems; Signal devices
- B60T17/221—Procedure or apparatus for checking or keeping in a correct functioning condition of brake systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a system and a method for predicting the residual service life of a braking system based on digital twinning, wherein the prediction system adopts a modular architecture and comprises a data acquisition module, a data preprocessing module, a braking system digital twinning module, a residual service life prediction module, a maintenance decision suggestion module and a data visualization module. The digital twin module of the braking system can accurately reflect the actual physical characteristics of the braking system, is used for multi-dimensional dynamic modeling of equipment, and interactively updates the model of the system; the residual service life prediction module predicts the residual service life of the brake system; the maintenance decision suggestion module makes a maintenance decision suggestion according to the residual service life prediction; the data visualization module performs visualization operation, so that the full life cycle management of the brake system is realized conveniently. The invention effectively combines the function of digital twin full life cycle management, improves the accuracy of residual service life prediction and improves the reliability of a braking system.
Description
Technical Field
The invention relates to the technical field of train braking, in particular to a system and a method for predicting the residual service life of a braking system based on digital twins.
Background
The braking system is used as a core component of a plurality of transportation means such as locomotives and high-speed trains, and has to have safe, rapid, high-efficiency and high-standard service in the running process of the trains, however, with the increase of the action times, the system will gradually age and degrade in performance until the system fails to run due to the influence of a plurality of uncertain factors such as external environment and fatigue use of system components. However, the following problems exist in the current monitoring of the aging state of the brake system, equipment diagnosis and maintenance information and other full life cycles: (1) the running state of the brake system changes all the time, and the historical monitoring information and the real-time detection information have updating barriers, so that the overall information updating of the system has serious hysteresis; (2) the intelligent degree of the operation and maintenance management of the brake system is low, the source of the system operation data set is single, and the types and the number of the data sets are small, so that the intelligence of the operation and maintenance management is difficult to improve.
The digital twin uses a data-driven approach to update, modify, connect and supplement the mathematical model by adding system history and real-time operational data. By constructing a mirror image of a physical entity, integrating a system mechanism and an operation data real-time dynamic evaluation system, a manager is helped to perform intelligent regulation and decision in the operation and maintenance management process of the brake system. The method has the advantages that the brake system is used as key equipment in the running process of locomotives and high-speed trains, the prediction of the residual service life of the brake system is always the focus of research, the full-life-cycle management digital twin body of the brake system is constructed, the real-time data of the whole running of the equipment can be integrated, the hysteresis of the whole information updating of the system is compensated, the prediction accuracy of the residual service life is improved, the full-life-cycle management of the brake system is realized, and the reliability of the brake system is improved.
Disclosure of Invention
In order to solve the technical problems existing in the prediction of the residual service life of the conventional braking system, the invention provides a system and a method for predicting the residual service life of the braking system based on digital twins, which can effectively improve the accuracy of predicting the residual service life of the braking system.
The technical scheme provided by the invention is as follows: a residual service life prediction system of a braking system based on digital twins comprises a data acquisition module, a data preprocessing module, a braking system digital twins module, a residual service life prediction module, a maintenance decision suggestion module and a data visualization module;
the data acquisition module is used for acquiring monitoring data of the bottom sensor from a physical entity of the brake system and transmitting the monitoring data to the data preprocessing module;
the data preprocessing module is used for receiving and processing the physical entity monitoring data and storing the processed data;
the digital twin module of the braking system can accurately reflect the actual physical characteristics of the equipment, is used for multi-dimensional dynamic modeling of the equipment, and interactively updates the model of the system;
the residual service life prediction module carries out feature extraction and feature learning calculation on the real-time data of the digital twin model by using a deep learning method, and predicts the residual service life of the braking system;
the maintenance decision suggestion module fuses the residual service life predicted value and the data of the digital twin module of the brake system and outputs a maintenance decision suggestion;
and the data visualization module calls the maintenance decision suggestion and the system state related information for visualization display, provides further maintenance decision and interactive operation, and feeds back the current system state to guide the physical entity to perform maintenance updating.
Furthermore, the physical entity parameters of the braking system of the data acquisition module include a feedback type, a command type and a control type, and the feedback type parameters include: the method comprises the following steps of (1) obtaining an average cylinder target pressure value Pe, a brake cylinder target pressure value Pb, a total air pressure value Pta, a train pipe pressure value Ptp, a total air flow value Fta, a BCU current value Ib and a BCU voltage value Vb; the command class arguments include: emergency brake command Ceb, penalty brake command Cpb, system self-test command Cst, sensor calibration command Csc; the control class parameters include: a high speed solenoid valve set Cve to control cylinder equalization pressure, a high speed solenoid valve set Cvb to control brake cylinder pressure, and a control brake valve cut Cvr.
Furthermore, the digital twin module of the braking system comprises a data driving module, a super-realistic simulation environment module and a real-time twin model;
the data driving module is used for analyzing data of each monitoring module, states of input and output channels, positions of brake handles, balance and brake cylinder target pressure values, and performing data preprocessing, feature extraction, data tagging and structuring on the data; the super-realistic simulation environment module is used for operating a multi-physical-field simulation model of the brake system, and analyzing the fault type and the fault mechanism of the monitored data conversion; the real-time twin model utilizes the data processed by the data driving module and the simulation model of the super-realistic simulation environment module to carry out real-time comparison verification, so that interactive comparison data flow between the twin model and the physical entity is formed, the running state of the physical entity is continuously approached, and the real-time correction of the twin model is realized.
Furthermore, the digital twin simulation module of the braking system establishes a three-dimensional structure simulation visual model corresponding to the braking system according to various structural parameters, circuit gas path attribute parameters and multi-working-condition parameters of a braking controller in a braking control unit, a valve, a cylinder, a sensor, an integrated gas path pipeline plate and a cab of the braking system and by combining with the electrical action relationship of the braking control unit, and receives real-time processed state data parameters to keep the digital twin simulation model consistent with the physical entity state.
A method for predicting the residual service life of a braking system based on digital twinning comprises the following steps:
S 1 according to the data collected by the data collection module, original data are transmitted to the data preprocessing module for processing by using the transmission technology of the Internet of things;
S 2 constructing a corresponding brake system digital twin module according to the physical entity; the digital twinning module of the braking system comprises a data driving module, a super-realistic simulation environment module and a real-time twinning model;
s3, constructing a three-dimensional structure visualization model of the brake system by using CAD (computer-aided design), AMESIM (advanced engineering simulation System) or ANSYS (ANSYS system) software, dynamically rendering the overall appearance of the brake system, receiving preprocessed data through a data driving module, and interactively mapping a twin real-time model;
S 4 normalizing each value of the system parameter by adopting a min-max method;
S 5 and inputting various parameter data of the digital twin module of the brake system into the residual service life prediction module for prediction.
Further, step S6 is included, in which the maintenance decision suggestion module outputs the maintenance decision suggestion according to the remaining service life value output by the remaining service life prediction module and according to the component and system state output by the digital twin module of the braking system.
Further, step S7 is included, where the data visualization module provides a human-computer interaction interface for displaying information related to the entire life cycle of the brake system, displays the current brake system diagnostic information and operating state information through the user interface, and provides further diagnostic decision operation options and human-computer operation interaction.
The invention has the beneficial effects that:
1. the method integrates the correlation between real-time data and historical data, provides a digital mirror image of a physical entity constructed by state data at each stage of full life cycle management, and predicts the residual service life of the brake system by comparing historical data or experimental data;
2. compared with the traditional prediction of the remaining service life of the brake system, the method can well utilize the advantages of digital twins, construct the digital twins with real-time situation perception by fusing multi-dimensional monitoring data and a dynamic simulation model, integrate various monitoring data, make up the disadvantage of insufficient data samples in the past, and be beneficial to realizing the accurate prediction of the running state, the health state and the remaining service life of the brake system.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention.
FIG. 2 is a flow diagram of a digital twin module of the braking system of the present invention.
FIG. 3 is a schematic flow chart of a remaining service life prediction module according to the present invention.
Detailed Description
The present invention is described in further detail below with reference to the attached drawing figures.
As shown in fig. 1, the system comprises a data acquisition module, a data preprocessing module, a braking system digital twin module, a residual service life prediction module, a maintenance decision suggestion module and a data visualization module. The functions of the various modules are as follows: the data acquisition module is used for acquiring monitoring data of a bottom sensor from a physical entity of the brake system and transmitting the monitoring data to the data preprocessing module; the data preprocessing module is used for receiving and processing the physical entity monitoring data and storing the processed data; the digital twin module of the braking system can accurately reflect the actual physical characteristics of the equipment, is used for multi-dimensional dynamic modeling of the equipment, and interactively updates the model of the system; the residual service life prediction module carries out feature extraction and feature learning calculation on the real-time data of the digital twin model by using a deep learning method, and predicts the residual service life of the braking system; the maintenance decision suggestion module fuses the residual service life predicted value and the data of the digital twin module of the brake system and outputs a maintenance decision suggestion; and the data visualization module calls the maintenance decision suggestion and the system state related information for visualization display, provides further maintenance decision and interactive operation, and feeds back the current system state to guide the physical entity to perform maintenance updating.
The modules complement each other, data driving is mainly used, simulation is used as complement, a digital twin body of the braking system is constructed, the running state information of the whole system is mapped into a digital mirror image, closed loop feedback processing of the whole system is formed, full life cycle management of the braking system is achieved, and accurate prediction of the residual service life of the braking system is improved.
Furthermore, the parameters related to the physical entities of the braking system of the data acquisition module comprise a feedback type, a command type and a control type. The feedback parameters include: the method comprises the following steps of (1) obtaining an average cylinder target pressure value Pe, a brake cylinder target pressure value Pb, a total air pressure value Pta, a train pipe pressure value Ptp, a total air flow value Fta, a BCU current value Ib and a BCU voltage value Vb; the command class arguments include: emergency brake command Ceb, penalty brake command Cpb, system self test command Cst, sensor calibration command Csc; the control class parameters include: a high speed solenoid valve set Cve for controlling cylinder equalization pressure, a high speed solenoid valve set Cvb for controlling brake cylinder pressure, and a brake valve cut Cvr.
Furthermore, the digital twin module of the braking system comprises a data driving module, a super-realistic simulation environment module and a real-time twin model.
The data driving module is used for analyzing data of each monitoring module, the state of an input/output channel, the position of a brake handle, balance and a brake cylinder target pressure value, carrying out data preprocessing, feature extraction, data tagging and structuring on the data, and analyzing the data by adopting one or more randomly combined algorithms including but not limited to a BP neural network algorithm, an LSTM deep learning algorithm and the like; the super-realistic simulation environment module is used for operating a multi-physical-field simulation model of the brake system, constructing a model by adopting one or more models in modeling software such as MATLAB, CAD, AMESIM, ANSYS and the like, and analyzing the fault type and the fault mechanism of the monitored data conversion; the real-time twin model utilizes the data processed by the data driving module and the simulation model of the super-realistic simulation environment module to carry out real-time comparison verification, so that interactive comparison data flow between the twin model and the physical entity is formed, the running state of the physical entity is continuously approached, and the real-time correction of the twin model is realized.
The simulation system comprises a simulation platform, a conversion valve, a balance air cylinder, a brake screen balance pipe, a relay valve, a pressure reducing valve and the like, wherein a model built by the simulation module comprises the balance module, the relay valve, the pressure reducing valve and the like, the balance module is used for simulating in the simulation platform by using an electromagnetic valve provided by software, the conversion valve realizes the functions of manually cutting off and linking the balance air cylinder and the brake screen balance pipe in the brake system, and the control is carried out by a MATLAB (matrix laboratory) controller in the simulation; the simulation platform realizes the function of a balancing module through a two-position three-way electromagnetic valve, and then simulates the flow of the electromagnetic valve according to the Cv value of an actual conversion valve; the relay valve and the pressure reducing valve reproduce the functions of each component in the simulation platform through the functions of each component in the schematic diagram.
Constructing digital twin models of various faults through a fault injection function of a simulation model, wherein the fault types comprise: failure of the electromagnetic valve, failure of the controlled valve, failure of the cylinder pipeline and failure of the sensor. The solenoid valve failure comprises: accidental actuation/disconnection of a brake solenoid valve, accidental actuation/disconnection of a release solenoid valve, accidental actuation/disconnection of a protection solenoid valve, accidental actuation/disconnection of an inflation solenoid valve, accidental actuation/disconnection of an exhaust solenoid valve, accidental actuation/disconnection of a neutral valve, and the like; the controlled valve failure comprises: the ER/BP relay valve clamping piece, the ER/BP relay valve are slow in air charging speed, the ER/BP relay valve leaks air, the ER/BP relay valve is insensitive, the BC distribution valve clamping piece, the BC distribution valve is slow in air charging speed, the BC distribution valve leaks air, the BC distribution valve is insensitive and the like; the cylinder type pipeline fault comprises the following steps: equalizing reservoir leakage, train pipe leakage, brake cylinder average pipe leakage, etc.; the sensor failure comprises: failure of a brake cylinder 1 sensor, failure of a brake cylinder 2 sensor, failure of a main air sensor, failure of a train pipe sensor, failure of a balance air cylinder sensor, failure of a brake cylinder pre-control sensor, failure of an action pipe sensor, failure of a flow sensor and the like. And simulating the influence of different fault degrees on the gas circuit by adjusting corresponding parameters, acquiring a large number of simulation data sets from simulation, performing sample training with the real-time data sets, supplementing the digital twin sample sets, and interactively synchronizing to the digital twin model of the brake system.
Furthermore, the digital twin simulation module of the braking system establishes a three-dimensional structure simulation visual model corresponding to the braking system according to various structural parameters, circuit gas path attribute parameters and multi-working-condition parameters of the braking control unit, a valve, a cylinder, a sensor, an integrated gas path pipeline board and a braking controller in a cab of the braking system and in combination with the electrical action relationship of the braking control unit, and receives real-time processed state data parameters to keep the digital twin simulation model consistent with the physical entity state.
The model of the digital Twin module of the brake system adopts a CAD drawing method, an ANSYS Twin Builder method and an approximate numerical analysis method to carry out digital modeling on each part in the brake system, and a complete digital Twin model is built in a simulation platform.
Wherein the model operating state data of the digital twin module of the braking system comprises: structured operational data, health prognosis data. The structured operational data includes pressure, flow, current, voltage, and brake system transfer function; the health prediction data comprises the number of remaining service life and the health state of the system.
Wherein the model structure parameters of the digital twin module of the braking system comprise: total reservoir volume, equalizing reservoir volume, running bit pressure, initial bit pressure, full bit pressure, emergency bit pressure, time for equalizing reservoir to rise from 0kPa to 600kPa, and the like.
The model multi-working condition parameters of the digital twin module of the braking system comprise: the number of braking times, the braking pressure, the number of solenoid valve usage times, the number of pipeline ventilation times, etc.
Further, the maintenance decision suggestion module automatically searches corresponding maintenance decision suggestions in an expert experience database according to the residual service life value output by the residual service life prediction module and the component and system states output by the digital twin module of the brake system.
Furthermore, the data visualization module provides a human-computer interaction interface for displaying relevant information of the whole life cycle of the brake system, displaying the current diagnosis information and the current running state information of the brake system through a user interface, and providing further diagnosis decision operation options and human-computer operation interaction.
A method for predicting the residual service life of a braking system based on digital twinning comprises the following steps:
S 1 and according to the data acquired by the data acquisition module, transmitting the original data to the data preprocessing module by using the transmission technology of the Internet of things for processing. The treatment comprises the following steps: noise processing, missing value processing, outlier processing, and structuring processing. The noise processing uses smooth filtering or median filtering to filter useless noise signals received by the sensor in the acquisition process; the missing value processing uses a missing judgment method to judge the NaN value or the null value in the transmission data and fill in a default value to process the missing value; the outlier processing judges outlier data by using a 6 sigma rule, cleans abnormal data, and fills abnormal data positions by using median and average; the structuralization processing loads data into a structural body according to a digital twin definition structure protocol and a protocol rule;
S 2 constructing a corresponding digital twin module of the braking system according to the physical entity; the digital twin module of the braking system comprises a data driving module, a super-realistic simulation environment module and a real-time twin model;
said S 2 The specific steps are shown in fig. 2, and comprise the following steps:
S 21 establishing a model of a brake cylinder pressure control subsystem, wherein a pressure characteristic formula of a brake cylinder is as follows:
wherein
Is the pressure of the brake cylinder, K is the universal gas constant, T is the temperature of the gas, V is the total volume of the brake cylinder, f m Is the mass flow of the compressed gas through the valve, as follows:
wherein
Is the pressure of the total reservoir, G 1 ∈[0,1]Is the valve flow coefficient 1, G 2 ∈[0,1]Is the valve flow coefficient 2, and S is the valve cross-sectional area.
Combining the above two equations, the pressure differential equation of the brake cylinder is as follows:
wherein the content of the first and second substances,
S 22 establishing connection between data accessed by the data driving module and the mathematical model, and fitting parameters G which are difficult to measure directly on line by using preprocessed data 1 And G 2 . The invention adopts the least square method to estimate parameters on line, and the formula is as follows:
g(n)＝λ -1 H(n-1)ξ(n)[1+λ -1 ξ T (n)H(n-1)ξ] -1
H(n)＝λ -1 H(n-1)-λ -1 g(n)ξ T (n)H(n-1)
where λ is the fitting constant, g (n) is the gain vector, H (n) is the correlation matrix,
the vector of the estimated parameter G (n) is a parameter to be measured, the parameter which is difficult to measure in the characteristic formula is continuously fitted through inputting preprocessing data, a digital twin data set is supplemented, and the digital twin data set is mapped to a digital twin model;
S 23 in a simulation environment, building a simulation module of each component of the brake system; model built by simulation moduleThe system comprises a balance module, a relay valve, a pressure reducing valve and the like, wherein the balance module uses electromagnetic valve simulation provided by software in a simulation platform, a conversion valve realizes the function of manually cutting and linking a balance air cylinder and a brake screen balance pipe in a brake system, the control function is controlled by a simulation controller of an MATLAB (matrix laboratory) in the simulation, the function of the balance module is realized by a two-position three-way electromagnetic valve, and the flow of the electromagnetic valve is simulated according to the Cv value of an actual conversion valve; the relay valve and the pressure reducing valve form a complete function in the simulation platform through the components of the schematic diagram, and then the simulation function of the valve is completed through simulating pressure flow;
S 24 simulating the influence of different fault degrees on a gas circuit, a component and a system by adjusting corresponding parameters, acquiring a large number of simulation data sets, carrying out sample training with a real-time data set, and continuously supplementing a digital twin sample set; the types of faults in the simulation include: failure of the electromagnetic valve, failure of the controlled valve, failure of the cylinder type pipeline and failure of the sensor. The solenoid valve failure comprises: accidental actuation/disconnection of a brake solenoid valve, accidental actuation/disconnection of a release solenoid valve, accidental actuation/disconnection of a protection solenoid valve, accidental actuation/disconnection of an inflation solenoid valve, accidental actuation/disconnection of an exhaust solenoid valve, accidental actuation/disconnection of a neutral valve, and the like; the controlled valve failure comprises: the ER/BP relay valve clamping piece, the ER/BP relay valve are low in air charging speed, the ER/BP relay valve leaks air, the ER/BP relay valve is insensitive, the BC distribution valve clamping piece, the BC distribution valve is low in air charging speed, the BC distribution valve leaks air, the BC distribution valve is insensitive and the like; the cylinder type pipeline fault comprises: equalizing reservoir leakage, train pipe leakage, brake cylinder average pipe leakage, etc.; the sensor failure comprises: failure of a brake cylinder 1 sensor, failure of a brake cylinder 2 sensor, failure of a total wind sensor, failure of a train pipe sensor, failure of a balance wind cylinder sensor, failure of a brake cylinder pre-control sensor, failure of an action pipe sensor, failure of a flow sensor and the like.
S 25 Searching a corresponding real-time twin module according to the brake fault position, the fault type and the fault type simulation model information of the super-realistic simulation environment module, supplementing a digital twin data sample, and interacting a digital twin model of the synchronous brake system;
S 26 according to various physical structure parameters, circuit and air path attribute parameters and multi-working condition parameters of a brake control unit, a valve, a cylinder, a sensor, an integrated air path pipeline plate and a brake controller in a cab of the brake system, in combination with the electrical action relation of the brake control unit, a three-dimensional structure simulation visual model corresponding to the brake system is established, and real-time state data is received to keep the digital twin simulation model consistent with a physical entity; wherein the physical structure parameters include: the total air cylinder volume, the balance air cylinder volume, the operation position pressure, the initial position pressure, the full position pressure, the emergency position pressure, the time for the balance air cylinder to rise from 0kPa to 600kPa and the like; the multi-operating-condition parameters comprise: the braking times, the braking pressure, the using times of the electromagnetic valve, the ventilation times of the pipeline and the like;
S 3 the method comprises the steps of using CAD (computer-aided design), AMESIM (automatic learning algorithm), ANSYS (ANSYS) software to construct a three-dimensional structure visualization model of the brake system, dynamically rendering the overall appearance of the brake system, receiving preprocessed data through a data driving module, and interactively mapping a twin real-time model. The realization method comprises the following steps: firstly, after a physical entity of a braking system receives a data request of a data acquisition module, sending various original parameters of the physical entity to a data preprocessing module for data preprocessing, and storing preprocessed data into a database; secondly, transmitting the preprocessed data to a digital twin module to realize interactive mapping of a physical entity and a digital twin, and interactively transmitting a digital twin three-dimensional model and the data to form a real-time mapping relation of the digital twin.
S 4 Because the value ranges of the system parameters are greatly different, the parameters need to be normalized, and the method adopts a min-max method to perform normalization processing to output the digital twin operation parameter x i ＝{x 1 ,x 2 ,...,x n Performing normalization processing, as shown in a formula:
wherein
Is normalized data, ranging between 0,1]；min(x i ) And max (x) i ) Is x i N is the length of the signal parameter;
S 5 inputting the parameter data of the digital twin module of the brake system into a residual service life prediction module for prediction;
said S 5 As shown in fig. 3, the specific steps include the following steps:
S 51 establishing a mapping relation between the residual service life and the brake system parameter data, wherein the formula is as follows:
RUL＝f(x t ),
wherein x t Is real-time data during operation of a digital twin model of the brake system, f is a mapping function, RUL is the real-time remaining useful life predicted by f, n is the length of a signal parameter,
S 52 the features of the parametric signal are extracted using a deep convolutional neural network. Firstly, transforming an original current signal of a digital twin module of a brake system by adopting ensemble empirical mode decomposition to obtain frequency domain energy, obtaining 8 different IMF components by the ensemble empirical mode decomposition, solving the energy entropy of the 8 IMF components, and segmenting the energy entropy and other parameter signal data, wherein the segmented parameter sequence of the brake system is x i ＝{x 1 ,x 2 ,...,x n Where n is the length of the signal parameter. The convolution operation for each sequence is defined as follows:
fea i ＝g(cx i +b)
where b and g represent the bias term and the nonlinear activation function, respectively. Convolutional layer output fea i Is derived from x by a convolution kernel c i Is obtained by sliding the convolution kernel over the corresponding sequence x i The above learned features.
Applying a pooling layer to output features generated by the convolutional layer, pooling extracting the most important local information in each feature map, and reducing feature dimensionality, wherein a maximum pooling function is used in the invention, and the pooling operation of each sequence is expressed as follows:
where r is the length of the pooling window, fo i Representing the output of the ith sequence characteristic after the pooling operation, and s represents the dimension;
S 53 in order to make the model obtain useful information from the multi-element parameter sequence as much as possible, the invention adopts a sliding window of 50 sizes to do fo to the data i Performing segmentation pretreatment, wherein the sliding step length is 1;
S 54 the prediction of the residual service life is realized by adopting a bidirectional long-short term memory network, the bidirectional long-short term memory network is an improvement on the long-short term memory network and can capture more valuable information, and a specific calculation formula is as follows:
f t ＝v(W f x t +K f y t-1 +b f )
i t ＝σ(W i x t +K i y t-1 +b i )
o t ＝σ(W o x t +K o y t-1 +b o )
wherein W f ，W i ，W o And W e Representing the weights between the three gates and the cell; k f 、K i 、K o And K c Representing the weight of the loop connection; b f 、b i 、b o And b c Represents a bias vector; y is the state of the hidden layer; c t And C t-1 Respectively representing the output states of the current and last units;
representing a cell input state;
multiplication of the representative elements; tanh is the hyperbolic tangent function and σ is the sigmoid activation function.
The core structure of the bidirectional long-short term memory network is that two opposite long-short term memory network layers are combined to process a time sequence, the output is calculated by connecting the forward long-short term memory network output and the backward long-short term memory network output, and the long-term dependency relationship of the current state of the time sequence is captured. The hidden state calculation method of the forward layer and the backward layer comprises the following steps:
S 55 In order to prevent overfitting, dropout is used for improving the generalization capability of the model; and updating the model parameters using Adam optimization algorithm. In the present invention, dropout is 0.5, learning rate is 0.001, batch-size is 512, and the maximum training period is set to 200. And (4) passing the processed characteristic data through the bidirectional long-short term memory network to obtain the output RUL with the residual service life.
S 56 The invention adopts the Score index to verify the effectiveness of the method, and the definition is as follows:
where n is the number of test samples, RUL' i Is a predicted RUL, RUL i Is the true RUL for the ith sample. For the Score index, the lower the value, the higher the prediction accuracy.
S 57 Comparing the Score values of the model, and repeating S if the Score values do not meet the preset Score value 54 ；
S 58 And residual service life prediction data meeting the system requirements are structured and updated into a digital twin module of the brake system, so that the physical entity and the digital twin are kept consistent in real time.
S 6 The maintenance decision suggestion module gives out a maintenance decision suggestion according to the residual service life value output by the residual service life prediction module and the component and system state output by the digital twin module;
S 7 the data visualization module provides a human-computer interaction interface for displaying relevant information of the whole life cycle of the brake system, displaying maintenance decision information and running state information through a user interface, and providing further maintenance decision operation options and human-computer operation interaction.
Claims (9)
1. A digital twin-based braking system residual service life prediction system is characterized by comprising a data acquisition module, a data preprocessing module, a braking system digital twin module, a residual service life prediction module, a maintenance decision suggestion module and a data visualization module;
the data acquisition module is used for acquiring monitoring data of the bottom sensor from a physical entity of the brake system and transmitting the monitoring data to the data preprocessing module;
the data preprocessing module is used for receiving and processing the physical entity monitoring data and storing the processed data;
the digital twin module of the braking system can accurately reflect the actual physical characteristics of the equipment, is used for multi-dimensional dynamic modeling of the equipment, and interactively updates the model of the system;
the residual service life prediction module performs feature extraction and feature learning calculation on real-time data of the digital twin model by using a deep learning method, and predicts the residual service life of the braking system;
the maintenance decision suggestion module fuses the residual service life predicted value and the data of the digital twin module of the brake system and outputs a maintenance decision suggestion;
and the data visualization module calls the maintenance decision suggestion and the system state related information for visualization display, provides further maintenance decision and interactive operation, and feeds back the current system state to guide the physical entity to perform maintenance updating.
2. The system as claimed in claim 1, wherein the physical parameters of the braking system of the data collection module include feedback type, command type, and control type, and the feedback type parameters include: the method comprises the following steps of (1) averaging a cylinder target pressure value Pe, a brake cylinder target pressure value Pb, a total wind pressure value Pta, a train pipe pressure value Ptp, a total wind flow value Fta, a BCU current value Ib and a BCU voltage value Vb; the command class arguments include: emergency brake command Ceb, penalty brake command Cpb, system self-test command Cst, sensor calibration command Csc; the control class parameters include: a high speed solenoid valve set Cve to control cylinder equalization pressure, a high speed solenoid valve set Cvb to control brake cylinder pressure, and a control brake valve cut Cvr.
3. The system for predicting the remaining service life of a digital twin-based brake system as claimed in claim 1, wherein said digital twin module of the brake system comprises a data driving module, a super-realistic simulation environment module, and a real-time twin model;
the data driving module is used for analyzing data of each monitoring module, states of input and output channels, positions of brake handles, balance and brake cylinder target pressure values, and performing data preprocessing, feature extraction, data tagging and structuring on the data; the super-realistic simulation environment module is used for operating a multi-physical field simulation model of the brake system and analyzing the fault type and the fault mechanism of the monitored data conversion; the real-time twin model utilizes the data processed by the data driving module and the simulation model of the super-realistic simulation environment module to carry out real-time comparison verification, so that interactive comparison data flow between the twin model and the physical entity is formed, the running state of the physical entity is continuously approached, and the real-time correction of the twin model is realized.
4. The system for predicting the residual service life of the digital twin-based braking system according to claim 1, wherein the digital twin module of the braking system establishes a three-dimensional structure simulation visualization model corresponding to the braking system according to various structural parameters, circuit air path attribute parameters and multi-working-condition parameters of a braking controller in a brake control unit, a valve, a cylinder, a sensor, an integrated air path pipeline board and a cab of the braking system, and combines with an electrical action relationship of the braking control unit, and receives real-time processed state data parameters to keep the digital twin simulation model consistent with a physical entity state.
5. A method for predicting the residual service life of a braking system based on digital twinning comprises the following steps:
S 1 according to the data collected by the data collection module, original data are transmitted to the data preprocessing module for processing by using the transmission technology of the Internet of things;
S 2 constructing a corresponding digital twin module of the braking system according to the physical entity; the digital twin module of the brake system comprises a data driving module and a super-realistic moduleA simulation environment module and a real-time twin model;
S 3 the method comprises the following steps of constructing a three-dimensional structure visualization model of the brake system by using CAD (computer-aided design), AMESIM (automatic learning and knowledge information system) or ANSYS (ANSYS) software, dynamically rendering the overall appearance of the brake system, receiving preprocessed data through a data driving module, and interactively mapping a twin real-time model;
S 4 normalizing each value of the system parameter by a min-max method;
S 5 and inputting various parameter data of the digital twin module of the brake system into the residual service life prediction module for prediction.
6. The method for predicting the residual service life of a digital twin-based brake system as claimed in claim 5, wherein S is 2 The method comprises the following steps:
S 21 establishing a model of a brake cylinder pressure control subsystem;
S 22 establishing connection between data accessed by the data driving module and the mathematical model, and fitting parameters G which are difficult to measure directly on line by using preprocessed data 1 And G 2 Estimating parameters on line by adopting a least square method;
S 23 building simulation modules of all parts of the brake system in a simulation environment;
S 24 simulating the influence of different fault degrees on a gas circuit, a component and a system by adjusting corresponding parameters, acquiring a large number of simulation data sets, carrying out sample training with a real-time data set, and continuously supplementing a digital twin sample set;
S 25 searching a corresponding real-time twin module according to the brake fault position, the fault type and the fault type simulation model information of the super-realistic simulation environment module, supplementing a digital twin data sample, and interacting a digital twin model of the synchronous brake system;
S 26 according to various physical structure parameters, circuit and air path attribute parameters of a brake control unit, a valve, a cylinder, a sensor, an integrated air path pipeline plate and a brake controller in a cab of the brake system,and the multi-working-condition parameters of the braking system are combined with the electrical action relation of the braking control unit to establish a three-dimensional structure simulation visual model corresponding to the braking system, and real-time state data is received to keep the digital twin simulation model consistent with the physical entity.
7. The method for predicting the remaining service life of a digital twin-based brake system as claimed in claim 5, wherein S is 5 The method comprises the following steps:
S 51 establishing a mapping relation between the residual service life and the parameter data of the brake system;
S 52 extracting the characteristics of the parameter signal by using a deep convolution neural network;
S 53 adopting a sliding window to carry out segmentation pretreatment on the data;
S 54 the residual service life is predicted by adopting a bidirectional long-short term memory network;
S 55 the generalization capability of the model is improved by using dropout; updating model parameters by using an Adam optimization algorithm;
S 56 verifying the effectiveness of the method by adopting a Score index;
S 57 comparing the model Score value, and repeating S if the model Score value does not meet the preset Score value 54 ；
S 58 And residual service life prediction data meeting the system requirements are structured and updated into a digital twin module of the brake system, so that the physical entity and the digital twin are ensured to be consistent in real time.
8. The method for predicting the remaining service life of a digital twin-based brake system according to claim 5, further comprising step S6, wherein the maintenance decision suggestion module outputs the maintenance decision suggestion according to the remaining service life value output by the remaining service life prediction module and according to the component and system state output by the digital twin module of the brake system.
9. The system and method for predicting the remaining service life of a digital twin-based brake system as claimed in claim 5, further comprising step S7, wherein the data visualization module provides a human-computer interaction interface for displaying the information related to the whole life cycle of the brake system, displaying the diagnosis information and the operation status information of the current brake system through the user interface, and providing further diagnosis decision operation options and human-computer interaction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210782812.0A CN114919559B (en) | 2022-07-05 | 2022-07-05 | System and method for predicting residual service life of brake system based on digital twin |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210782812.0A CN114919559B (en) | 2022-07-05 | 2022-07-05 | System and method for predicting residual service life of brake system based on digital twin |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114919559A true CN114919559A (en) | 2022-08-19 |
| CN114919559B CN114919559B (en) | 2023-05-12 |
Family
ID=82816057
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210782812.0A Active CN114919559B (en) | 2022-07-05 | 2022-07-05 | System and method for predicting residual service life of brake system based on digital twin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114919559B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116050190A (en) * | 2023-03-31 | 2023-05-02 | 中国海洋大学 | Product performance and degradation state analysis method based on digital twinning |
| CN116127821A (en) * | 2023-04-14 | 2023-05-16 | 浪潮软件科技有限公司 | Three-dimensional visual presentation method and platform for operation and maintenance data |
| CN117952323A (en) * | 2024-03-26 | 2024-04-30 | 大连豪森软件有限公司 | Product creation system, method, equipment and medium based on digital twin |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111399474A (en) * | 2020-02-29 | 2020-07-10 | 中南大学 | Health index-based life prediction method and device for balance control module |
| CN112904220A (en) * | 2020-12-30 | 2021-06-04 | 厦门大学 | UPS (uninterrupted Power supply) health prediction method and system based on digital twinning and machine learning, electronic equipment and storable medium |
| CN113119937A (en) * | 2021-03-31 | 2021-07-16 | 南京航空航天大学 | Intelligent brake-by-wire system based on digital twins and prediction control method thereof |
| CN113567858A (en) * | 2021-07-30 | 2021-10-29 | 北京航空航天大学 | Control moment gyro residual life prediction system |
| WO2022105072A1 (en) * | 2020-11-19 | 2022-05-27 | 中国矿业大学 | Intelligent reliability evaluation and service life prediction method for kilometer deep well hoist brake |
-
2022
- 2022-07-05 CN CN202210782812.0A patent/CN114919559B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111399474A (en) * | 2020-02-29 | 2020-07-10 | 中南大学 | Health index-based life prediction method and device for balance control module |
| WO2022105072A1 (en) * | 2020-11-19 | 2022-05-27 | 中国矿业大学 | Intelligent reliability evaluation and service life prediction method for kilometer deep well hoist brake |
| CN112904220A (en) * | 2020-12-30 | 2021-06-04 | 厦门大学 | UPS (uninterrupted Power supply) health prediction method and system based on digital twinning and machine learning, electronic equipment and storable medium |
| CN113119937A (en) * | 2021-03-31 | 2021-07-16 | 南京航空航天大学 | Intelligent brake-by-wire system based on digital twins and prediction control method thereof |
| CN113567858A (en) * | 2021-07-30 | 2021-10-29 | 北京航空航天大学 | Control moment gyro residual life prediction system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116050190A (en) * | 2023-03-31 | 2023-05-02 | 中国海洋大学 | Product performance and degradation state analysis method based on digital twinning |
| CN116127821A (en) * | 2023-04-14 | 2023-05-16 | 浪潮软件科技有限公司 | Three-dimensional visual presentation method and platform for operation and maintenance data |
| CN117952323A (en) * | 2024-03-26 | 2024-04-30 | 大连豪森软件有限公司 | Product creation system, method, equipment and medium based on digital twin |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114919559B (en) | 2023-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114919559B (en) | System and method for predicting residual service life of brake system based on digital twin | |
| CN112131760A (en) | CBAM model-based prediction method for residual life of aircraft engine | |
| Chen et al. | Application of generalized frequency response functions and improved convolutional neural network to fault diagnosis of heavy-duty industrial robot | |
| CN113469470B (en) | Energy consumption data and carbon emission correlation analysis method based on electric brain center | |
| CN112132430B (en) | Reliability evaluation method and system for distributed state sensor of power distribution main equipment | |
| CN105825271A (en) | Satellite fault diagnosis and prediction method based on evidential reasoning (ER) | |
| CN116150897A (en) | Machine tool spindle performance evaluation method and system based on digital twin | |
| CN111273125A (en) | RST-CNN-based power cable channel fault diagnosis method | |
| CN110991776A (en) | Method and system for realizing water level prediction based on GRU network | |
| CN115964907B (en) | Complex system health trend prediction method, system, electronic equipment and storage medium | |
| CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
| CN110516813A (en) | A method of batteries of electric automobile RDR prediction is carried out based on big data machine learning | |
| CN114266201B (en) | Self-attention elevator trapping prediction method based on deep learning | |
| CN115932592A (en) | Electric vehicle battery fault diagnosis method based on digital twin model | |
| CN113743019A (en) | Digital twin enhanced complex equipment health monitoring method | |
| CN114819054A (en) | Power electronic system state monitoring method based on physical information neural network | |
| CN116822652A (en) | Subway fault prediction method, subway fault prediction device, electronic equipment, subway fault prediction system and storage medium | |
| CN117371207A (en) | Extra-high voltage converter valve state evaluation method, medium and system | |
| CN115205782A (en) | Rice feeding robot cluster monitoring and management method based on digital twin technology | |
| CN117252051A (en) | Cable tunnel monitoring and early warning method and system based on digital twinning | |
| CN113536671B (en) | Lithium battery life prediction method based on LSTM | |
| Bourgani et al. | A study on fuzzy cognitive map structures for medical decision support systems | |
| Li et al. | A LSTM-based method for comprehension and evaluation of network security situation | |
| CN114720129B (en) | Rolling bearing residual life prediction method and system based on bidirectional GRU | |
| CN113468720B (en) | Service life prediction method for digital-analog linked random degradation equipment |
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 |