CN115728389B - Rail transit vehicle component quality detection device and method - Google Patents
Rail transit vehicle component quality detection device and method Download PDFInfo
- Publication number
- CN115728389B CN115728389B CN202310040803.9A CN202310040803A CN115728389B CN 115728389 B CN115728389 B CN 115728389B CN 202310040803 A CN202310040803 A CN 202310040803A CN 115728389 B CN115728389 B CN 115728389B
- Authority
- CN
- China
- Prior art keywords
- rail transit
- transit vehicle
- probe
- inspection robot
- ultrasonic detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The invention discloses a device and a method for detecting the quality of a rail transit vehicle component. The quality detection device comprises data processing equipment, a base, an upper support, a first inspection robot, a second inspection robot and a clamp; the first inspection robot is transversely movably arranged on the base; the first inspection robot and the second inspection robot comprise a robot body, and the first inspection robot is provided with an upper detection probe; a second inspection robot lower detection probe; the upper and lower detection probes comprise a connecting plate, a probe horizontal plane rotary driving motor, a probe vertical plane rotary driving motor, a mounting plate, an ultrasonic detection probe and a camera; the ultrasonic detection probe is connected with the signal generator; the data processing equipment comprises an ultrasonic detection risk factor calculation module, a prediction module and a risk point judgment module; therefore, the invention improves the sensitivity of detecting the defects of the rail transit vehicle components, and can effectively detect the defects, thereby improving the detection efficiency of products.
Description
Technical Field
The invention relates to a device and a method for detecting the quality of a rail transit vehicle component, and belongs to the technical field of detection.
Background
Rail traffic refers to a type of transportation means or transportation system in which an operating vehicle needs to travel on a specific track, and the most typical rail traffic is a railway system consisting of a traditional train and a standard railway, and along with the diversified development of train and railway technologies, the rail traffic is of more and more types, and is not only transported over long-distance lands, but also widely applied to medium-short-distance urban public transportation.
At present, the quality detection mode of the rail transit vehicle component has the advantages of large detection blind area, poor near-surface resolution, low signal-to-noise ratio and insufficient sensitivity, increases the difficulty of defect identification and resolution, is unfavorable for defect detection, influences defect judgment, and also influences detection efficiency on certain specifications of products.
Disclosure of Invention
The invention aims to provide a device and a method for detecting the quality of a rail transit vehicle component, which are used for improving the sensitivity of detecting the defects of the rail transit vehicle component, and effectively detecting the defects, so that the product detection efficiency is improved.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
the rail transit vehicle component quality detection device is used for detecting defects of a rail transit vehicle component to be detected and comprises data processing equipment, a base, an upper support, a first inspection robot, a second inspection robot and a clamp; wherein:
The upper support is arranged above the base through a supporting upright post;
the first inspection robot is transversely movably arranged on the base; the second inspection robot is transversely movably arranged on the upper support, and a clamp for clamping a rail transit vehicle component to be inspected is also arranged on the upper support;
the first inspection robot and the second inspection robot comprise robot bodies, and the robot bodies of the first inspection robot are provided with upper detection probes on the surfaces facing to the rail transit vehicle components to be inspected; the robot body of the second inspection robot is provided with a detection probe under the surface of the robot body facing the rail transit vehicle component to be inspected;
the upper detection probe and the lower detection probe comprise a connecting plate, a probe horizontal plane rotary driving motor, a probe vertical plane rotary driving motor, a mounting plate, an ultrasonic detection probe and a camera; the probe horizontal plane rotary driving motor is connected with the robot body through a connecting plate, the power output end of the probe horizontal plane rotary driving motor is connected with the fixed part of the probe vertical plane rotary driving motor, the power output end of the probe vertical plane rotary driving motor is connected with the mounting plate, and the ultrasonic detection probe and the camera are respectively mounted on the mounting plate;
The ultrasonic detection probe and the camera are respectively connected with the data processing equipment, and the ultrasonic detection probe is connected with the signal generator; the camera is used for photographing and detecting the rail transit vehicle component to be detected so as to obtain an image detection risk factor of the rail transit vehicle component to be detected, and synchronously uploading the image detection risk factor to the data processing equipment;
the data processing equipment comprises an ultrasonic detection risk factor calculation module, a prediction module and a risk point judgment module;
under the cooperative work of the probe horizontal plane rotary driving motor and the probe vertical plane rotary driving motor, the ultrasonic detection probe of the upper detection probe is contacted with the upper surface of the rail transit vehicle member to be detected, and the ultrasonic detection probe of the lower detection probe is contacted with the lower surface of the rail transit vehicle member to be detected;
during detection, under the control of the data processing equipment, a signal generator is started, and sends a first excitation wave signal to the upper surface of a rail transit vehicle component to be detected through an ultrasonic detection probe of an upper detection probe, and a corresponding first receiving wave signal is acquired through a second probe and fed back to an ultrasonic detection risk factor calculation module; the ultrasonic detection risk factor calculation module calculates a corresponding time domain mirror image signal according to the received first received wave signal; under the control of the data processing equipment, the time domain mirror image signal is used as a second excitation wave signal and is sent to a rail transit vehicle component to be detected through a second probe, and at the moment, a corresponding second receiving wave signal can be acquired through the first probe and fed back to an ultrasonic detection risk factor calculation module; the ultrasonic detection risk factor calculation module can obtain ultrasonic detection risk factors of the rail transit vehicle components to be detected by calculating correlation coefficients between the first excitation wave signals and the second received wave signals, and synchronously upload the ultrasonic detection risk factors to the prediction module;
The prediction module is constructed based on a neural network algorithm, can process the received ultrasonic detection risk factors and image detection risk factors to obtain fusion estimation risk factors and synchronously uploads the fusion estimation risk factors to the risk point judgment module;
a defect risk threshold value is preset in the risk point judging module; and comparing the fusion estimation risk factors with defect risk thresholds, so as to judge each defect risk point of the rail transit vehicle component to be detected.
Preferably, the base is provided with a first guide rail along a transverse direction, and the upper support is provided with a second guide rail along a transverse direction;
a first self-driven travelling wheel is arranged below the robot body of the first inspection robot, and can be assembled in a first guide rail;
the second self-driven travelling wheel is installed below the robot body of the second inspection robot and can be assembled in the second guide rail.
Preferably, the clamp comprises two clamping plates; the two clamping plates can clamp/loosen the rail transit vehicle components to be detected under the drive of the clamping driving mechanism;
the clamping driving mechanism comprises a clamping driving motor, a screw rod, a guide pillar and a gear transmission mechanism;
The fixed part of the clamping driving motor is arranged on the upper support; the screw rod and the guide post are arranged in parallel and are positioned and supported by the upper support, and the power output end of the clamping driving motor is connected with the screw rod through the gear transmission mechanism;
the two clamping plates are arranged in parallel; each clamping plate is in threaded fit connection with the screw rod; and each clamping plate is connected with the guide post in a guiding way.
Preferably, the prediction model comprises a component prediction model, an adaptive weight fusion prediction model and a fusion layer, wherein the component prediction model comprises an RNN network model and a first kalman filtering model; the self-adaptive weight fusion prediction model comprises an LSTM network model and a second kalman filtering model;
in the reverse propagation process of the RNN network model, performing first kalman filtering estimation on a predicted value obtained by prediction in the forward propagation process through a first kalman filtering model, and calculating the obtained first kalman filtering estimated value in the reverse propagation process of the RNN network model; the obtained first kalman filtering estimated value enters an LSTM network model and a fusion layer;
in the back propagation process of the LSTM network model, performing second kalman filtering estimation on a predicted value obtained by prediction in the forward propagation process through a second kalman filtering model, and calculating the obtained second kalman filtering estimated value in the back propagation process of the LSTM network model; the obtained second kalman filtering estimated value enters a fusion layer;
The risk factors and weights of the fusion layer are adaptively updated through the first kalman filtering estimated value and the second kalman filtering estimated value, and updated fusion estimated risk factors are obtained;
preferably, the RNN network model includes a first input layer, a first hidden layer, and a first output layer connected in sequence, where the first input layer is connected with a camera detection unit and an ultrasonic detection risk factor calculation module; the input end of the first kalman filtering model is connected with the first input layer and the first output layer respectively, and the output end of the first kalman filtering model is connected with the first hidden layer, the fusion layer and the self-adaptive weight fusion prediction model respectively.
Preferably, the LSTM network model includes a second input layer, a second fully-connected long-short-period memory network, and a second output layer that are sequentially connected, where the second input layer is connected with an output end of the first kalman filtering model; the input end of the second kalman filtering model is connected with the second input layer and the second output layer respectively; the output end of the second kalman filtering model is respectively connected with the second full-connection long-short-term memory network and the fusion layer.
Preferably, the second full-connection long-term memory network comprises a full-connection non-excitation function layer, a 3-hierarchy long-term memory network and a discarding layer which are connected in sequence.
Preferably, the loss value is calculated in the LSTM network model using a cross entropy loss function as the loss function; calculating a loss value in the RNN network model by using a Huber error loss function as a loss function; the RNN network model is activated by adopting a tanh activation function or a softmax activation function; and activating by adopting a sigmoid activating function or a tanh activating function in the LSTM network model.
Another technical object of the present invention is to provide a method for detecting the quality of a rail transit vehicle component, which is implemented based on the device for detecting the quality of a rail transit vehicle component, comprising the following steps:
step one, installing a workpiece
Mounting a rail transit vehicle component to be detected above the base and below the upper support through a clamp;
step two, starting the first inspection robot and the second inspection robot
Synchronously starting the first inspection robot and the second inspection robot, so that the detection probes of the first inspection robot and the detection probes of the second inspection robot are distributed on the upper side and the lower side of the rail transit vehicle component to be inspected and are opposite to each other;
step three, starting the probe horizontal plane rotation driving motor and the probe vertical plane rotation driving motor
Synchronously starting a probe horizontal plane rotary driving motor and a probe vertical plane rotary driving motor, so that an ultrasonic detection probe of a first inspection robot is contacted with the lower surface of a rail transit vehicle member to be inspected, an ultrasonic detection probe of a second inspection robot is contacted with the upper surface of the rail transit vehicle member to be inspected, and the ultrasonic detection probe of the first inspection robot is opposite to the ultrasonic detection probe of the second inspection robot;
Step four, acquiring and synchronously uploading ultrasonic detection risk factors
Starting a signal generator, transmitting a first excitation wave signal to a rail transit vehicle component to be detected through an ultrasonic detection probe of a first inspection robot, and acquiring a corresponding first receiving wave signal through an ultrasonic detection probe of a second inspection robot;
then calculating a time domain mirror image signal of the first received wave signal; then the time domain mirror image signal is used as a second excitation wave signal, the second excitation wave signal is sent to the rail transit vehicle component to be detected through the ultrasonic detection probe of the second inspection robot, and the corresponding second receiving wave signal can be acquired through the ultrasonic detection probe of the first inspection robot; the ultrasonic detection risk factors of the rail transit vehicle components to be detected can be obtained by calculating the correlation coefficients between the first excitation wave signals and the second received wave signals;
step five, image information acquisition and synchronous uploading
Photographing and detecting the rail transit vehicle component to be detected by adopting a camera, obtaining an image detection risk factor of the rail transit vehicle component to be detected, and synchronously transmitting the obtained image detection risk factor to data processing equipment;
step six, in the data processing equipment, a prediction model constructed based on a neural network algorithm is adopted to process the received ultrasonic detection risk factors and image detection risk factors, and fusion estimation risk factors are obtained; and comparing the obtained fusion estimation risk factors with a defect risk threshold preset in the data processing equipment, so as to judge each defect risk point of the rail transit vehicle component to be detected.
Preferably, in the sixth step, the prediction model includes a component prediction model, an adaptive weight fusion prediction model and a fusion layer, where the component prediction model includes an RNN network model and a first kalman filtering model; the self-adaptive weight fusion prediction model comprises an LSTM network model and a second kalman filtering model;
in the reverse propagation process of the RNN network model, performing first kalman filtering estimation on a predicted value obtained by prediction in the forward propagation process through a first kalman filtering model, and calculating the obtained first kalman filtering estimated value in the reverse propagation process of the RNN network model; the obtained first kalman filtering estimated value enters an LSTM network model and a fusion layer;
in the back propagation process of the LSTM network model, performing second kalman filtering estimation on a predicted value obtained by prediction in the forward propagation process through a second kalman filtering model, and calculating the obtained second kalman filtering estimated value in the back propagation process of the LSTM network model; the obtained second kalman filtering estimated value enters a fusion layer;
and adaptively updating the risk factors and weights of the fusion layer through the first kalman filter estimated value and the second kalman filter estimated value to obtain updated fusion estimated risk factors.
Based on the technical objects, compared with the prior art, the invention has the following advantages:
1. the invention provides a rail transit vehicle component quality detection device, in particular discloses a detection means for detecting risk factors by ultrasonic, and can further improve the sensitivity of ultrasonic flaw detection so as to further improve the quality of rail transit vehicle component quality detection.
2. In the reverse propagation process, the RNN network model carries out first kalman filtering estimation on a predicted value obtained by prediction in the forward propagation process, and the obtained first kalman filtering estimation value enters the reverse propagation process to be calculated. In the backward propagation process, the LSTM network model carries out second kalman filtering estimation on the predicted value obtained by prediction in the forward propagation process, and the obtained second kalman filtering estimation value enters the backward propagation process to be calculated. The fusion layer is adaptively updated through the first kalman filter estimated value and the second kalman filter estimated value, and the updated fusion estimation risk factor is obtained, so that the method is high in robustness and high in accuracy of obtaining the fusion estimation risk factor.
Drawings
FIG. 1 is a schematic view of a mass detection device for rail transit vehicle components according to the present invention;
FIG. 2 is a schematic diagram of the structure of the upper/lower inspection probe of FIG. 1;
FIG. 3 is a control flow diagram of a mass detection device for rail transit vehicle components according to the present invention;
in fig. 1 to 2: 1-a base; 2-a first guide rail; 3-a first inspection robot; 4-supporting columns; 5-upper support; 6-a second guide rail; 7-clamping plates; 8-a guide post; 9-a screw; 10-upper detection probe; 11-clamping a drive motor; 12-a second inspection robot; 13-lower detection probe; 14-a probe horizontal plane rotation driving motor; 15-a probe vertical surface rotary driving motor; 16-mounting plate; 17-an ultrasonic detection probe; 18-a camera; 19. and (5) connecting a plate.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention. The relative arrangement, expressions and numerical values of the components and steps set forth in these embodiments do not limit the scope of the present invention unless it is specifically stated otherwise. Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate. In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of the exemplary embodiments may have different values.
Spatially relative terms, such as "above … …," "above … …," "upper surface at … …," "above," and the like, may be used herein for ease of description to describe one device or feature's spatial location relative to another device or feature as illustrated in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations in use or operation in addition to the orientation depicted in the figures. For example, if the device in the figures is turned over, elements described as "above" or "over" other devices or structures would then be oriented "below" or "beneath" the other devices or structures. Thus, the exemplary term "above … …" may include both orientations of "above … …" and "below … …". The device may also be positioned in other different ways (rotated 90 degrees or at other orientations).
As shown in fig. 1 and 2, the device for detecting the quality of the rail transit vehicle component is used for detecting the defect of the rail transit vehicle component to be detected, and comprises data processing equipment, a base 1, an upper support 5, a first inspection robot 3, a second inspection robot 12 and a clamp; wherein:
The upper support 5 is arranged above the base 1 through a supporting upright post 4; in this embodiment, there are two support columns 4 symmetrically disposed above the base 1, and the upper support 5 is supported by the two support columns 4. In addition, the upper support 5 in the present embodiment has a rectangular frame structure, and the base 1 has a flat plate structure.
The first inspection robot 3 is transversely movably arranged on the base 1; the second inspection robot 12 is transversely movably arranged on the upper support 5, and a clamp for clamping a rail transit vehicle component to be inspected is also arranged on the upper support 5; specifically, in this embodiment, two first guide rails 2 parallel to each other are disposed on the base 1 along the transverse direction, and two second guide rails 6 parallel to each other are also disposed on the upper support 5 along the transverse direction. In addition, the clamp comprises two clamping plates 7; the two clamping plates 7 can clamp/unclamp the rail transit vehicle components to be detected under the drive of the clamping driving mechanism; the clamping driving mechanism comprises a clamping driving motor 11, a screw 9, a guide pillar 8 and a gear transmission mechanism; the fixed part of the clamping driving motor 11 is arranged on the upper support 5; the screw rod 9 and the guide post 8 are arranged in parallel and are positioned and supported by the upper support 5, and the power output end of the clamping driving motor 11 is connected with the screw rod 9 through a gear transmission mechanism; the two clamping plates 7 are arranged in parallel; each clamping plate 7 is in threaded fit connection with the screw 9; and each clamping plate 7 is connected with the guide post 8 in a guiding way.
The first inspection robot 12 and the second inspection robot 12 comprise robot bodies, and the robot bodies of the first inspection robot 3 are provided with upper detection probes 10 on the surfaces facing to the rail transit vehicle components to be inspected; the robot body of the second inspection robot 12 is provided with a lower detection probe 13 facing the surface of the rail transit vehicle component to be inspected; the lower part of the robot body of the first inspection robot 3 is provided with first self-driven travelling wheels which can be assembled in the first guide rail 2, and two first self-driven travelling wheels on each side, namely four first self-driven travelling wheels are arranged under the robot body of the first inspection robot 3; the second self-driven travelling wheels are installed below the robot body of the second inspection robot 12, the second self-driven travelling wheels can be assembled in the second guide rail 6, and two second self-driven travelling wheels on each side are arranged, namely four second self-driven travelling wheels are installed below the robot body of the second inspection robot 12.
The upper detection probe 10 and the lower detection probe 13 comprise a connecting plate 19, a probe horizontal plane rotary driving motor 14, a probe vertical plane rotary driving motor 15, a mounting plate 16, an ultrasonic detection probe 17 and a camera 18; the probe horizontal plane rotation driving motor 14 is connected with the robot body through a connecting plate 19, the power output end of the probe horizontal plane rotation driving motor 14 is connected with the fixed part of the probe vertical plane rotation driving motor 15, the power output end of the probe vertical plane rotation driving motor 15 is connected with the mounting plate 16, and the ultrasonic detection probe 17 and the camera 18 are respectively mounted on the mounting plate 16;
The ultrasonic detection probe 17 and the camera 18 are respectively connected with the data processing equipment, and the ultrasonic detection probe 17 is connected with the signal generator; the camera 18 is used for photographing and detecting the rail transit vehicle component to be detected to obtain an image detection risk factor of the rail transit vehicle component to be detected, and synchronously uploading the image detection risk factor to the data processing equipment;
the data processing equipment comprises an ultrasonic detection risk factor calculation module, a prediction module and a risk point judgment module;
under the cooperative work of the probe horizontal plane rotation driving motor 14 and the probe vertical plane rotation driving motor 15, the ultrasonic detection probe 17 of the upper detection probe 10 is contacted with the upper surface of the rail transit vehicle member to be detected, and the ultrasonic detection probe 17 of the lower detection probe 13 is contacted with the lower surface of the rail transit vehicle member to be detected;
during detection, under the control of the data processing equipment, a signal generator is started, and the signal generator sends a first excitation wave signal to the upper surface of a rail transit vehicle component to be detected through the ultrasonic detection probe 17 of the upper detection probe 10, acquires a corresponding first receiving wave signal through the second probe and feeds back the corresponding first receiving wave signal to the ultrasonic detection risk factor calculation module; the ultrasonic detection risk factor calculation module calculates a corresponding time domain mirror image signal according to the received first received wave signal; under the control of the data processing equipment, the time domain mirror image signal is used as a second excitation wave signal and is sent to a rail transit vehicle component to be detected through a second probe, and at the moment, a corresponding second receiving wave signal can be acquired through the first probe and fed back to an ultrasonic detection risk factor calculation module; the ultrasonic detection risk factor calculation module can obtain ultrasonic detection risk factors of the rail transit vehicle components to be detected by calculating correlation coefficients between the first excitation wave signals and the second received wave signals, and synchronously upload the ultrasonic detection risk factors to the prediction module;
The prediction module is constructed based on a neural network algorithm, can process the received ultrasonic detection risk factors and image detection risk factors to obtain fusion estimation risk factors and synchronously uploads the fusion estimation risk factors to the risk point judgment module;
a defect risk threshold value is preset in the risk point judging module; and comparing the fusion estimation risk factors with defect risk thresholds, so as to judge each defect risk point of the rail transit vehicle component to be detected.
Based on the device for detecting the quality of the rail transit vehicle component, the invention provides a method for detecting the quality of the rail transit vehicle component, which comprises the following steps:
step one, installing a workpiece
Mounting rail transit vehicle components to be detected above the base 1 and below the upper support 5 through a clamp;
step two, starting the first and second inspection robots 12
Synchronously starting the first inspection robot 12 and the second inspection robot 12, so that the detection probes of the first inspection robot 3 and the detection probes of the second inspection robot 12 are distributed on the upper side and the lower side of the rail transit vehicle component to be inspected and are opposite to each other;
step three, starting the probe horizontal plane rotation driving motor 14 and the probe vertical plane rotation driving motor 15
Synchronously starting a probe horizontal plane rotary driving motor 14 and a probe vertical plane rotary driving motor 15, so that an ultrasonic detection probe 17 of a first inspection robot 3 is contacted with the lower surface of a rail transit vehicle member to be inspected, an ultrasonic detection probe 17 of a second inspection robot 12 is contacted with the upper surface of the rail transit vehicle member to be inspected, and the ultrasonic detection probe 17 of the first inspection robot 3 is opposite to the ultrasonic detection probe 17 of the second inspection robot 12;
Step four, acquiring and synchronously uploading ultrasonic detection risk factors
Starting a signal generator, transmitting a first excitation wave signal to a rail transit vehicle component to be detected through an ultrasonic detection probe 17 of a first inspection robot 3, and acquiring a corresponding first receiving wave signal through an ultrasonic detection probe 17 of a second inspection robot 12;
then calculating a time domain mirror image signal of the first received wave signal; then the time domain mirror image signal is used as a second excitation wave signal and is sent to the rail transit vehicle component to be detected through the ultrasonic detection probe 17 of the second inspection robot 12, and at the moment, a corresponding second receiving wave signal can be acquired through the ultrasonic detection probe 17 of the first inspection robot 3; the ultrasonic detection risk factors of the rail transit vehicle components to be detected can be obtained by calculating the correlation coefficients between the first excitation wave signals and the second received wave signals;
step five, image information acquisition and synchronous uploading
Photographing and detecting the rail transit vehicle component to be detected by adopting the camera 18, obtaining an image detection risk factor of the rail transit vehicle component to be detected, and synchronously transmitting the obtained image detection risk factor to the data processing equipment;
Step six, in the data processing equipment, a prediction model constructed based on a neural network algorithm is adopted to process the received ultrasonic detection risk factors and image detection risk factors, and fusion estimation risk factors are obtained; and comparing the obtained fusion estimation risk factors with a defect risk threshold preset in the data processing equipment, so as to judge each defect risk point of the rail transit vehicle component to be detected.
In the invention, the prediction model comprises a component prediction model, an adaptive weight fusion prediction model and a fusion layer, wherein the component prediction model comprises an RNN network model and a first kalman filtering model. The adaptive weight fusion prediction model includes an LSTM network model and a second kalman filter model.
The RNN network model comprises a first input layer, a first hidden layer and a first output layer which are sequentially connected, wherein the first input layer is connected with a camera shooting detection unit, an ultrasonic flaw detection unit and an impact detection unit (optional). The input end of the first kalman filtering model is connected with the first input layer and the first output layer respectively, and the output end of the first kalman filtering model is connected with the first hidden layer, the fusion layer and the adaptive weight fusion prediction model respectively.
The neurons of the first hidden layer of the RNN network model are provided with a feedback mechanism, so that the front and back information transmission is realized, and the RNN has the capability of processing sequence data. After the RNN network model finishes training, predicting the output of the next moment.
RNN network model:
input layer:
hidden layer:
output layer:
wherein, the liquid crystal display device comprises a liquid crystal display device,
representing input of a first input layer
The data of the moment of time,
，
is shown in
Time of day (time)
The first track traffic detected by the detection units
The risk factors for the individual probe points,
，
the number of the detection units is represented,
，
the image sensing detection unit is shown as such,
an ultrasonic flaw detection unit is shown,
the impact detection unit is indicated as such,
，
the number of detection points of the rail transit is represented,
representing RNN networks
The hidden state of the moment of time,
represents an RNN network hidden layer activation function, wherein the RNN network hidden layer activation function selects a tanh activation function,
representing RNN network hidden layers
A weight matrix of the time-of-day input data,
representing RNN network hidden layers
A weight matrix of the time-of-day output data,
representing the RNN network hidden layer offset matrix,
representing RNN network output layer
The estimated value of the time-of-day output,
represents an RNN network output layer activation function, the RNN network output layer activation function selects a softmax activation function, 
Representing RNN network output layer
A weight matrix of the time-of-day input data,
representing the RNN network output layer offset matrix.
RNN network model in
In the forward propagation process of time, a layer of unidirectional circulating neural network is formed along the direction of a time axis; and then, in the network hierarchy direction, a deep cyclic neural network is formed by stacking one layer by taking a layer of cyclic neural network as a unit. In the backward propagation process, a first kalman filter estimation is carried out on a predicted value obtained in the forward propagation process, a first kalman filter estimation value is obtained, the obtained first kalman filter estimation value is subjected to loss calculation through a loss function, and then the maximum likelihood estimation of RNN network model parameters is obtained by adopting a gradient descent method, wherein the obtained maximum likelihood estimation is used as a hidden state in the forward propagation process at the next moment.
The neural network model adopts a gradient descent method to obtain maximum likelihood estimation of model parameters, and back propagation is a process of obtaining partial derivatives (i.e. parameter gradients) of the model parameters of a loss function and updating the model parameters by using the partial derivatives (i.e. parameter gradients).
kalman filtering:
consider a discrete system as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,
indicating the current time of day and,
the time of day is indicated as the last time,
for the state vector of the system at the current moment, 
For the state vector of the system at the previous time,
in the form of a system matrix,
in order to control the input of the device,
in order to input the matrix of the data,
in the event of a system noise,
for the system output at the current moment,
in order to output the matrix of the matrix,
noise is measured for the system.
wherein, the liquid crystal display device comprises a liquid crystal display device,
representing mathematical expectations.
The covariance matrix is defined as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,
the covariance operation is represented by the terms of a covariance,
representation of
Is used for the co-variance matrix of (a),
representation of
Covariance matrix of (2), superscript
Representing a matrix transposition operation.
Assume that at the current time, the following is satisfied:
wherein, the liquid crystal display device comprises a liquid crystal display device,
representing an estimated value of the current time of day,
a predicted value representing the current time of day,
the Kalman gain matrix is the Kalman gain matrix to be solved,
for the system output at the current moment,
is an output matrix.
The equations (1) and (4) are available simultaneously, and the following equation relationship is obtained:
wherein, the liquid crystal display device comprises a liquid crystal display device,
as a deviation between the true value and the estimated value,
is an identity matrix.
The covariance matrix is defined as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,
is that
Is a covariance matrix of (a).
The simultaneous (3), (5) and (6) are available:
wherein, the liquid crystal display device comprises a liquid crystal display device,
as a deviation between the true value and the estimated value,
，
as a deviation between the true value and the predicted value, 
，
As a covariance of the deviation between the true and predicted values,
。
for a pair of
Tracing, namely:
wherein, the liquid crystal display device comprises a liquid crystal display device,
the trace operation is represented.
Regarding (8)
Partial differentiation of (c) can be obtained:
wherein, the liquid crystal display device comprises a liquid crystal display device,
is partial differential operation.
According to the Kalman filtering criterion, let equation (9) be zero, it is possible to obtain:
wherein, superscript
Representing a matrix inversion operation.
Simultaneous (7) and (10) formulas, can be obtained:
since at the current time, the following is satisfied:
wherein, the liquid crystal display device comprises a liquid crystal display device,
is that
An estimate of time of day.
And (12) at the same time, the following can be obtained:
wherein, the liquid crystal display device comprises a liquid crystal display device,
。
then the first time period of the first time period,
wherein, the liquid crystal display device comprises a liquid crystal display device,
。
from the above derivation, the kalman estimation actually consists of two processes: prediction and correction, in the prediction phase, the filter uses the estimate of the last state to make a prediction of the current state. In the correction phase, the filter corrects the predicted value obtained in the prediction phase with the observed value for the current state to obtain a new estimated value that more closely matches the true value.
Predicted value equation at current time:
updating the equation of the prediction covariance matrix:
calculation equation of kalman gain matrix:
the optimal estimated value equation at the current moment:
updating the equation of the estimated covariance matrix:
from this, it can be seen that CallsThe Mannich filter algorithm only needs to give an initial state 
And initial estimation covariance matrix
Can be based on the measured value at the current time
Obtaining the optimal estimated value of the system state
. Firstly, based on the estimated value of the previous moment, a predicted value of the current moment is obtained, and the prediction accuracy is described through a prediction covariance matrix. At the same time, a Kalman gain matrix is calculated based on the matrix
. Then according to
And
and obtaining the optimal estimated value at the current moment. Finally, the estimated covariance matrix is updated by (19) and is used for the next moment #
) Is prepared for recursion of (c). The Kalman filtering adopts a recursive method, and continuously predicts and updates according to measured values at different moments, and obtains an optimal estimated value of the system state. In the invention, an RNN network model is adopted in the back propagation process, a first kalman filter estimation is carried out on a predicted value obtained in the forward propagation process through a first kalman filter model, and the obtained first kalman filter estimation value enters the back propagation process of the RNN network model to be calculated. The obtained first kalman filter estimation value enters the LSTM network model and the fusion layer.
Thus, the filtering process of the first kalman filter model is:
predicted value equation at current time:
Updating the equation of the prediction covariance matrix:
calculation equation of kalman gain matrix:
the optimal estimated value equation at the current moment:
updating the equation of the estimated covariance matrix:
wherein, the liquid crystal display device comprises a liquid crystal display device,
representing the first kalman filtered predictor,
，
is shown in
Time of day (time)
The first track traffic detected by the detection units
The first kalman filter predictor of the detected points,
，
the number of the detection units is represented,
，
the image sensing detection unit is shown as such,
an ultrasonic flaw detection unit is shown,
the impact detection unit is indicated as such,
，
the number of detection points of the rail transit is represented,
representing a first kalman filtered estimate,
system matrix for first kalman filtering， 
For the first kalman filtered input matrix,
for the first kalman filtered control input,
a prediction covariance matrix is filtered for the first kalman,
a covariance matrix is estimated for the first kalman filter,
a system noise covariance matrix for the first kalman filter,
a gain matrix for the first kalman filter,
for the first kalman filtered output matrix,
a measurement noise covariance matrix filtered for the first kalman,
is an identity matrix.
The LSTM network model comprises a second input layer, a second full-connection long-period memory network and a second output layer which are sequentially connected, wherein the second full-connection long-period memory network comprises a full-connection non-excitation function layer, a 3-level long-period memory network and a discarding layer which are sequentially connected. The second kalman filtering model is respectively connected with the first input layer, the second input layer and the second output layer.
The second full-connection long-term memory network comprises a forgetting gate, an input gate and an output gate, wherein:
forgetting the door:
an input door:
updating the cell state:
output door:
wherein, the liquid crystal display device comprises a liquid crystal display device,
indicating that the door is left to be forgotten,
for the input of the LSTM network,
，
in order to be in the hidden state,
in order to update the state of the cells,
is the output of the LSTM network.
the loss value is calculated in the LSTM network model using a cross entropy loss function as the loss function.
Wherein, the liquid crystal display device comprises a liquid crystal display device,
a label representing a sample, positive class 1, negative class 0,
for the sample
The probability of being predicted as a positive class,
representing the total number of samples.
LSTM network model in
In the forward propagation process of time, a layer of unidirectional circulating neural network is formed along the direction of a time axis; then, a deep cyclic neural network is formed by stacking one layer by one layer along the network layer direction by taking a layer of cyclic neural network as a unit; in the backward propagation process, performing second kalman filtering estimation on the predicted value obtained in the forward propagation process, performing loss calculation on the obtained second kalman filtering estimated value through a loss function, and obtaining the maximum likelihood estimation of the LSTM network model parameter by adopting a gradient descent method, wherein the obtained maximum likelihood estimation is used as a hidden state in the forward propagation process at the next moment.
As can be seen from formulas (15) - (19), the filtering process of the second kalman filtering model is:
predicted value equation at current time:
updating the equation of the prediction covariance matrix:
calculation equation of kalman gain matrix:
the optimal estimated value equation at the current moment:
updating the equation of the estimated covariance matrix:
wherein, the liquid crystal display device comprises a liquid crystal display device,
is shown in
Time of day (time)
The first track traffic detected by the detection units
The second kalman filter of the detection points predicts weights,
，
the number of the detection units is represented,
，
the image sensing detection unit is shown as such,
an ultrasonic flaw detection unit is shown,
the impact detection unit is indicated as such,
，
the number of detection points of the rail transit is represented,
is shown in
Time of day (time)
The first track traffic detected by the detection units
The second kalman filter of the detection points estimates weights,
system matrix for second kalman filtering， 
For the second kalman filtered input matrix,
for the second kalman filtered control input,
the prediction covariance matrix is filtered for a second kalman,
a covariance matrix is estimated for the second kalman filter,
a second kalman filtered system noise covariance matrix,
a gain matrix for the second kalman filter,
for the second kalman filtered output matrix,
a second kalman filtered measurement noise covariance matrix, 
Is an identity matrix.
In the invention, an LSTM network model is adopted in the back propagation process, a second kalman filter estimation is carried out on a predicted value obtained in the forward propagation process through a second kalman filter model, and the obtained second kalman filter estimation value enters the back propagation process of the LSTM network model to be calculated. The resulting second kalman filter estimate is entered into the fusion layer.
The fusion layer is respectively connected with the first kalman filtering model and the second kalman filtering model. And adaptively updating the risk factors and weights of the fusion layer through the first kalman filter estimated value and the second kalman filter estimated value to obtain updated fusion estimated risk factors.
Wherein, the liquid crystal display device comprises a liquid crystal display device,
is shown in
Time of track traffic
Fusion risk factors for the individual probe points,
is shown in
Time of day (time)
The first track traffic detected by the detection units
The first kalman filter predictor of the detected points,
is shown in
Time of day (time)
The first track traffic detected by the detection units
The second kalman filter of the detection points predicts weights,
indicating the number of detection units.
The risk point judging unit is used for judging the risk point according to the fusion estimation risk factor, if the fusion estimation risk factor is within the set risk point threshold range, the risk point of the rail transit vehicle component to be tested is judged to be safe, and the risk point safety signal is output through the output unit. If the fusion estimation risk factor is not in the set risk point threshold range, judging that the risk point of the rail transit vehicle component to be detected is at risk, and outputting a risk point alarm signal of the rail transit vehicle component to be detected through an output unit.
According to the invention, the RNN network model and the first kalman filter are used for carrying out cyclic network nerve calculation on the image detection risk factors, the ultrasonic detection risk factors and the impact detection risk factors (optional), so that the robustness of the system is improved, and the prediction precision of the image detection risk factors, the ultrasonic detection risk factors and the impact detection risk factors is improved. The fusion weight of the fusion layer is adaptively updated through the LSTM network model and the second kalman filter, and the fusion layer obtains updated fusion estimation risk factors according to the updated fusion weight and the first kalman filter estimation.
The foregoing is only a preferred embodiment of the invention, it being noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the invention.
Claims (10)
1. The device for detecting the quality of the rail transit vehicle component is used for detecting the defects of the rail transit vehicle component to be detected and is characterized by comprising data processing equipment, a base, an upper support, a first inspection robot, a second inspection robot and a clamp; wherein:
The upper support is arranged above the base through a supporting upright post;
the first inspection robot is transversely movably arranged on the base; the second inspection robot is transversely movably arranged on the upper support, and a clamp for clamping a rail transit vehicle component to be inspected is also arranged on the upper support;
the first inspection robot and the second inspection robot comprise robot bodies, and the robot bodies of the first inspection robot are provided with upper detection probes on the surfaces facing to the rail transit vehicle components to be inspected; the robot body of the second inspection robot is provided with a detection probe under the surface of the robot body facing the rail transit vehicle component to be inspected;
the upper detection probe and the lower detection probe comprise a connecting plate, a probe horizontal plane rotary driving motor, a probe vertical plane rotary driving motor, a mounting plate, an ultrasonic detection probe and a camera; the probe horizontal plane rotary driving motor is connected with the robot body through a connecting plate, the power output end of the probe horizontal plane rotary driving motor is connected with the fixed part of the probe vertical plane rotary driving motor, the power output end of the probe vertical plane rotary driving motor is connected with the mounting plate, and the ultrasonic detection probe and the camera are respectively mounted on the mounting plate;
The ultrasonic detection probe and the camera are respectively connected with the data processing equipment, and the ultrasonic detection probe is connected with the signal generator; the camera is used for photographing and detecting the rail transit vehicle component to be detected so as to obtain an image detection risk factor of the rail transit vehicle component to be detected, and synchronously uploading the image detection risk factor to the data processing equipment;
the data processing equipment comprises an ultrasonic detection risk factor calculation module, a prediction module and a risk point judgment module;
under the cooperative work of the probe horizontal plane rotary driving motor and the probe vertical plane rotary driving motor, the ultrasonic detection probe of the upper detection probe is contacted with the upper surface of the rail transit vehicle member to be detected, and the ultrasonic detection probe of the lower detection probe is contacted with the lower surface of the rail transit vehicle member to be detected;
during detection, under the control of the data processing equipment, starting a signal generator, sending a first excitation wave signal to the upper surface of a rail transit vehicle component to be detected through an ultrasonic detection probe of an upper detection probe, acquiring a corresponding first receiving wave signal through an ultrasonic detection probe of a lower detection probe, and feeding back to an ultrasonic detection risk factor calculation module; the ultrasonic detection risk factor calculation module calculates a corresponding time domain mirror image signal according to the received first received wave signal; under the control of the data processing equipment, the time domain mirror image signal is used as a second excitation wave signal, the second excitation wave signal is sent to a rail transit vehicle component to be detected through an ultrasonic detection probe of the lower detection probe, and at the moment, a corresponding second receiving wave signal can be acquired through the ultrasonic detection probe of the upper detection probe and fed back to the ultrasonic detection risk factor calculation module; the ultrasonic detection risk factor calculation module can obtain ultrasonic detection risk factors of the rail transit vehicle components to be detected by calculating correlation coefficients between the first excitation wave signals and the second received wave signals, and synchronously upload the ultrasonic detection risk factors to the prediction module;
The prediction module is constructed based on a neural network algorithm, can process the received ultrasonic detection risk factors and image detection risk factors to obtain fusion estimation risk factors and synchronously uploads the fusion estimation risk factors to the risk point judgment module;
a defect risk threshold value is preset in the risk point judging module; and comparing the fusion estimation risk factors with defect risk thresholds, so as to judge each defect risk point of the rail transit vehicle component to be detected.
2. The mass detection device of rail transit vehicle components of claim 1, wherein a first rail is disposed on the base in a lateral direction and a second rail is disposed on the upper support in a lateral direction;
a first self-driven travelling wheel is arranged below the robot body of the first inspection robot, and can be assembled in a first guide rail;
the second self-driven travelling wheel is installed below the robot body of the second inspection robot and can be assembled in the second guide rail.
3. The mass detection device of rail transit vehicle components of claim 1, wherein the clamp comprises two clamp plates; the two clamping plates can clamp/loosen the rail transit vehicle components to be detected under the drive of the clamping driving mechanism;
The clamping driving mechanism comprises a clamping driving motor, a screw rod, a guide pillar and a gear transmission mechanism;
the fixed part of the clamping driving motor is arranged on the upper support; the screw rod and the guide post are arranged in parallel and are positioned and supported by the upper support, and the power output end of the clamping driving motor is connected with the screw rod through the gear transmission mechanism;
the two clamping plates are arranged in parallel; each clamping plate is in threaded fit connection with the screw rod; and each clamping plate is connected with the guide post in a guiding way.
4. The mass detection device of rail transit vehicle components of claim 1, wherein the prediction model comprises a component prediction model, an adaptive weight fusion prediction model, and a fusion layer, the component prediction model comprising an RNN network model and a first kalman filter model; the self-adaptive weight fusion prediction model comprises an LSTM network model and a second kalman filtering model;
in the reverse propagation process of the RNN network model, performing first kalman filtering estimation on a predicted value obtained by prediction in the forward propagation process through a first kalman filtering model, and calculating the obtained first kalman filtering estimated value in the reverse propagation process of the RNN network model; the obtained first kalman filtering estimated value enters an LSTM network model and a fusion layer;
In the back propagation process of the LSTM network model, performing second kalman filtering estimation on a predicted value obtained by prediction in the forward propagation process through a second kalman filtering model, and calculating the obtained second kalman filtering estimated value in the back propagation process of the LSTM network model; the obtained second kalman filtering estimated value enters a fusion layer;
and adaptively updating the risk factors and weights of the fusion layer through the first kalman filter estimated value and the second kalman filter estimated value to obtain updated fusion estimated risk factors.
5. The rail transit vehicle component quality detection device according to claim 4, wherein the RNN network model comprises a first input layer, a first hidden layer and a first output layer which are sequentially connected, wherein the first input layer is connected with a camera detection unit and an ultrasonic detection risk factor calculation module; the input end of the first kalman filtering model is connected with the first input layer and the first output layer respectively, and the output end of the first kalman filtering model is connected with the first hidden layer, the fusion layer and the self-adaptive weight fusion prediction model respectively.
6. The mass detection device of rail transit vehicle components of claim 5, wherein the LSTM network model comprises a second input layer, a second fully-connected long-term memory network, and a second output layer connected in sequence, the second input layer being connected to an output of the first kalman filtering model; the input end of the second kalman filtering model is connected with the second input layer and the second output layer respectively; the output end of the second kalman filtering model is respectively connected with the second full-connection long-short-term memory network and the fusion layer.
7. The mass detection device of rail transit vehicle components of claim 6, wherein the second fully-connected long-term memory network comprises a fully-connected non-incentive function layer, a 3-hierarchy long-term memory network, and a discard layer connected in sequence.
8. The mass detection device of rail transit vehicle components of claim 7, wherein the LSTM network model uses a cross entropy loss function as a loss function to calculate a loss value; calculating a loss value in the RNN network model by using a Huber error loss function as a loss function; the RNN network model is activated by adopting a tanh activation function or a softmax activation function; and activating by adopting a sigmoid activating function or a tanh activating function in the LSTM network model.
9. A rail transit vehicle component quality detection method, implemented based on the rail transit vehicle component quality detection apparatus of claim 1, comprising the steps of:
step one, installing a workpiece
Mounting a rail transit vehicle component to be detected above the base and below the upper support through a clamp;
step two, starting the first inspection robot and the second inspection robot
Synchronously starting the first inspection robot and the second inspection robot, so that the detection probes of the first inspection robot and the detection probes of the second inspection robot are distributed on the upper side and the lower side of the rail transit vehicle component to be inspected and are opposite to each other;
Step three, starting the probe horizontal plane rotation driving motor and the probe vertical plane rotation driving motor
Synchronously starting a probe horizontal plane rotary driving motor and a probe vertical plane rotary driving motor, so that an ultrasonic detection probe of a first inspection robot is contacted with the lower surface of a rail transit vehicle member to be inspected, an ultrasonic detection probe of a second inspection robot is contacted with the upper surface of the rail transit vehicle member to be inspected, and the ultrasonic detection probe of the first inspection robot is opposite to the ultrasonic detection probe of the second inspection robot;
step four, acquiring and synchronously uploading ultrasonic detection risk factors
Starting a signal generator, transmitting a first excitation wave signal to a rail transit vehicle component to be detected through an ultrasonic detection probe of a first inspection robot, and acquiring a corresponding first receiving wave signal through an ultrasonic detection probe of a second inspection robot;
then calculating a time domain mirror image signal of the first received wave signal; then the time domain mirror image signal is used as a second excitation wave signal, the second excitation wave signal is sent to the rail transit vehicle component to be detected through the ultrasonic detection probe of the second inspection robot, and the corresponding second receiving wave signal can be acquired through the ultrasonic detection probe of the first inspection robot; the ultrasonic detection risk factors of the rail transit vehicle components to be detected can be obtained by calculating the correlation coefficients between the first excitation wave signals and the second received wave signals;
Step five, image information acquisition and synchronous uploading
Photographing and detecting the rail transit vehicle component to be detected by adopting a camera, obtaining an image detection risk factor of the rail transit vehicle component to be detected, and synchronously transmitting the obtained image detection risk factor to data processing equipment;
step six, in the data processing equipment, a prediction model constructed based on a neural network algorithm is adopted to process the received ultrasonic detection risk factors and image detection risk factors, and fusion estimation risk factors are obtained; and comparing the obtained fusion estimation risk factors with a defect risk threshold preset in the data processing equipment, so as to judge each defect risk point of the rail transit vehicle component to be detected.
10. The method for detecting the quality of a rail transit vehicle component according to claim 9, wherein in the sixth step, the prediction model includes a component prediction model, an adaptive weight fusion prediction model, and a fusion layer, and the component prediction model includes an RNN network model and a first kalman filtering model; the self-adaptive weight fusion prediction model comprises an LSTM network model and a second kalman filtering model;
in the reverse propagation process of the RNN network model, performing first kalman filtering estimation on a predicted value obtained by prediction in the forward propagation process through a first kalman filtering model, and calculating the obtained first kalman filtering estimated value in the reverse propagation process of the RNN network model; the obtained first kalman filtering estimated value enters an LSTM network model and a fusion layer;
In the back propagation process of the LSTM network model, performing second kalman filtering estimation on a predicted value obtained by prediction in the forward propagation process through a second kalman filtering model, and calculating the obtained second kalman filtering estimated value in the back propagation process of the LSTM network model; the obtained second kalman filtering estimated value enters a fusion layer;
and adaptively updating the risk factors and weights of the fusion layer through the first kalman filter estimated value and the second kalman filter estimated value to obtain updated fusion estimated risk factors.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310040803.9A CN115728389B (en) | 2023-01-12 | 2023-01-12 | Rail transit vehicle component quality detection device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310040803.9A CN115728389B (en) | 2023-01-12 | 2023-01-12 | Rail transit vehicle component quality detection device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115728389A CN115728389A (en) | 2023-03-03 |
| CN115728389B true CN115728389B (en) | 2023-05-16 |
Family
ID=85302051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310040803.9A Active CN115728389B (en) | 2023-01-12 | 2023-01-12 | Rail transit vehicle component quality detection device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115728389B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5042305A (en) * | 1988-07-30 | 1991-08-27 | Hitachi Construction Machinery Co., Ltd. | Ultrasonic flaw detecting system |
| JPH0510928A (en) * | 1991-06-28 | 1993-01-19 | Hitachi Constr Mach Co Ltd | Ultrasonic wave image inspection apparatus |
| CN104634866A (en) * | 2015-02-16 | 2015-05-20 | 爱德森（厦门）电子有限公司 | Device and method for evaluating directions and depths of metal cracks by using ultrasonic electromagnetic principle |
| JP2015206607A (en) * | 2014-04-17 | 2015-11-19 | 三菱電機株式会社 | Measuring apparatus |
| JP2017223510A (en) * | 2016-06-14 | 2017-12-21 | 日立Ｇｅニュークリア・エナジー株式会社 | Submerged visualization device and submerged visualization method |
| CN107735680A (en) * | 2016-04-25 | 2018-02-23 | 非破坏检查株式会社 | The stripping inspection method and stripping check device of layered product |
| CN108593767A (en) * | 2018-01-24 | 2018-09-28 | 天津大学 | A kind of method for building up of shoal buried pipes supersonic sounding echo model |
| CN111521679A (en) * | 2020-05-06 | 2020-08-11 | 京冶华诚(天津)钢结构有限公司 | Flaw detection method for steel structure |
| CN114715216A (en) * | 2022-03-26 | 2022-07-08 | 北京交通运输职业学院 | Intelligent maintenance system for rail transit and control method thereof |
| CN115540790A (en) * | 2022-10-30 | 2022-12-30 | 苏州爱思尔提科技有限公司 | High-precision ultrasonic thickness measurement method and device |
| CN115577860A (en) * | 2022-11-21 | 2023-01-06 | 南京地铁运营咨询科技发展有限公司 | Intelligent maintenance method and system for rail transit based on adaptive control |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101836110B (en) * | 2008-03-31 | 2013-05-01 | 日本克劳特克雷默尔株式会社 | Ultrasonic flaw detection method and device thereof |
-
2023
- 2023-01-12 CN CN202310040803.9A patent/CN115728389B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5042305A (en) * | 1988-07-30 | 1991-08-27 | Hitachi Construction Machinery Co., Ltd. | Ultrasonic flaw detecting system |
| JPH0510928A (en) * | 1991-06-28 | 1993-01-19 | Hitachi Constr Mach Co Ltd | Ultrasonic wave image inspection apparatus |
| JP2015206607A (en) * | 2014-04-17 | 2015-11-19 | 三菱電機株式会社 | Measuring apparatus |
| CN104634866A (en) * | 2015-02-16 | 2015-05-20 | 爱德森（厦门）电子有限公司 | Device and method for evaluating directions and depths of metal cracks by using ultrasonic electromagnetic principle |
| CN107735680A (en) * | 2016-04-25 | 2018-02-23 | 非破坏检查株式会社 | The stripping inspection method and stripping check device of layered product |
| JP2017223510A (en) * | 2016-06-14 | 2017-12-21 | 日立Ｇｅニュークリア・エナジー株式会社 | Submerged visualization device and submerged visualization method |
| CN108593767A (en) * | 2018-01-24 | 2018-09-28 | 天津大学 | A kind of method for building up of shoal buried pipes supersonic sounding echo model |
| CN111521679A (en) * | 2020-05-06 | 2020-08-11 | 京冶华诚(天津)钢结构有限公司 | Flaw detection method for steel structure |
| CN114715216A (en) * | 2022-03-26 | 2022-07-08 | 北京交通运输职业学院 | Intelligent maintenance system for rail transit and control method thereof |
| CN115540790A (en) * | 2022-10-30 | 2022-12-30 | 苏州爱思尔提科技有限公司 | High-precision ultrasonic thickness measurement method and device |
| CN115577860A (en) * | 2022-11-21 | 2023-01-06 | 南京地铁运营咨询科技发展有限公司 | Intelligent maintenance method and system for rail transit based on adaptive control |
Non-Patent Citations (1)
| Title |
|---|
| 采用超声导波阵列技术研究板类结构大面积检测;郑阳;何存富;吴斌;周进节;;声学学报(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115728389A (en) | 2023-03-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113358053B (en) | Track irregularity detection and evaluation system and method, electronic equipment and track vehicle | |
| CN105930787A (en) | Vehicle door opening early-warning method | |
| CN102700551A (en) | Method for estimating gradient of road surface in real time in vehicle running process | |
| US11780452B2 (en) | Method and system for fault diagnoses of intelligent vehicles | |
| CN108008099A (en) | A kind of pollution sources localization method | |
| CN114996654B (en) | Road surface flatness detection method and device, electronic equipment and medium | |
| CN112713881B (en) | Synchronous clock maintaining system and method based on edge calculation | |
| CN106597109A (en) | Battery AC impedance measurement circuit and method | |
| CN111862165A (en) | Target tracking method for updating Kalman filter based on deep reinforcement learning | |
| CN115728389B (en) | Rail transit vehicle component quality detection device and method | |
| CN115808324B (en) | Light safety management monitoring method and system for small and medium span bridges | |
| CN113203464A (en) | Sensor fault detection method of dynamic vehicle-mounted weighing system | |
| CN102306331B (en) | Intelligent counting method of interference fringes | |
| CN107831485A (en) | The method of the multiple water body optical signature parameters of the more visual field laser radar detections of boat-carrying | |
| Escoriza et al. | Data-driven Kalman-based velocity estimation for autonomous racing | |
| CN108982096A (en) | Industrial robot crank axle wear detecting method based on heuristic rule system | |
| Mangan et al. | Measurement of the road gradient using an inclinometer mounted on a moving vehicle | |
| CN115577860B (en) | Intelligent maintenance method and system for rail transit based on adaptive control | |
| CN114858221B (en) | Intelligent water bloom early warning system and method based on water area nutrition state prediction | |
| CN113252777B (en) | Detection device and detection method for cracks of underwater concrete panel of rock-fill dam | |
| CN111561929B (en) | Time delay and noise reduction method for vehicle-mounted MEMS inertial sensor | |
| CN115524086A (en) | Statistical moment-curvature beam type bridge damage identification method based on axle coupling vibration | |
| Al-Din | Calibration and pre-processing techniques for a smartphone-based driving events identification and classification system | |
| CN112860658A (en) | High-speed train electromagnetic emission prediction method based on data mining | |
| RU2411550C2 (en) | Method of detecting local magnetic anomaly |
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 |