CN114878689A - Portable on-line measuring system for measuring material parameters and control method thereof - Google Patents
Portable on-line measuring system for measuring material parameters and control method thereof Download PDFInfo
- Publication number
- CN114878689A CN114878689A CN202210791451.6A CN202210791451A CN114878689A CN 114878689 A CN114878689 A CN 114878689A CN 202210791451 A CN202210791451 A CN 202210791451A CN 114878689 A CN114878689 A CN 114878689A
- Authority
- CN
- China
- Prior art keywords
- layer
- echo
- module
- neuron
- portable
- 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
- 239000000463 material Substances 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims description 20
- 238000005259 measurement Methods 0.000 claims abstract description 17
- 210000002569 neuron Anatomy 0.000 claims description 71
- 238000006243 chemical reaction Methods 0.000 claims description 34
- 239000011159 matrix material Substances 0.000 claims description 26
- 230000005284 excitation Effects 0.000 claims description 22
- 238000001914 filtration Methods 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000002592 echocardiography Methods 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 28
- 230000003321 amplification Effects 0.000 description 8
- 238000003199 nucleic acid amplification method Methods 0.000 description 8
- 238000011161 development Methods 0.000 description 6
- 239000000523 sample Substances 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 125000004432 carbon atom Chemical group C* 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000002366 time-of-flight method Methods 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4481—Neural networks
Landscapes
- Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- General Physics & Mathematics (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biochemistry (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Acoustics & Sound (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The present application provides a portable on-line measurement system for measuring material parameters, comprising: the ultrasonic wave transmitting module is used for transmitting ultrasonic waves to a material to be detected; the echo receiving module is used for receiving echoes from the bottom surface of the material to be detected; a control device, the control device comprising: the first acquisition module is electrically connected with the echo receiving module and is configured to acquire the echo; the first operation module is electrically connected with the first acquisition module, the first operation module comprises an identification function, the identification function is configured to identify the echo and obtain the relevant parameters of the material to be detected corresponding to the echo, the occupied space of the identification function is extremely small, the required computing resources are few, the identification is quick and convenient, and the problem of large computing quantity is avoided.
Description
Technical Field
The application relates to the technical field of embedded development and ultrasonic wave, in particular to a portable online measuring system for measuring material parameters and a control method thereof.
Background
In actual engineering, accurate material parameters and structure dimensions are important indexes to be considered by engineering technicians when designing mechanical parts and evaluating mechanical properties. In many cases, one directly uses the material parameters of the standard sample at the time of shipment of the raw material. They often neglect that when these raw materials are made into parts, unknown variations in nominal material parameters and geometries will occur due to machining distortions. In addition, some critical components of mechanical equipment may degrade in mechanical performance after years of service. It is impractical to extract samples from these formed or in-use parts as measurement specimens using conventional destructive mechanical testing methods such as static tensile methods, beam bending methods, etc., so a rapid and nondestructive method for measuring actual engineering parts is urgently needed.
Ultrasound mainly acts in the high frequency, small stress range. The method can well reflect the mechanical property of the elastic stage in the ultrasonic wave propagation process, so that the method is more suitable for carrying out on-site real-time characterization on material parameters. The traditional ultrasonic material parameter control method is to inversely calculate the thickness or young modulus of the current material by measuring the wave velocity of ultrasonic waves by using a TOF method, and in addition, whether damage exists or not needs to be judged by analyzing waveform signals of the thickness or young modulus. This approach is computationally expensive and relatively slow to budget.
Disclosure of Invention
In view of the above-mentioned drawbacks and deficiencies of the prior art, the present application is directed to a portable online measurement system for measuring material parameters and a control method thereof.
In a first aspect, the present application provides a portable online measurement system for measuring a material parameter, comprising:
the ultrasonic wave transmitting module is used for transmitting ultrasonic waves to a material to be detected;
the echo receiving module is used for receiving echoes from the bottom surface of the material to be detected;
a control device, the control device comprising:
the first acquisition module is electrically connected with the echo receiving module and is configured to acquire the echo;
the first operation module is electrically connected with the first acquisition module, the first operation module comprises an identification function, and the identification function is configured to identify the echo and obtain the relevant parameters of the material to be detected corresponding to the echo.
According to the technical scheme provided by the embodiment of the application, the control device comprises a PS end and a PL end, wherein the PS end comprises an ARM chip, and the ARM chip comprises the first operation module; the PL end comprises an FPGA chip, and the FPGA chip comprises the first acquisition module.
According to the technical scheme provided by the embodiment of the application, the FPGA chip further comprises: the input end of the first data conversion module is electrically connected with the output end of the first acquisition module, and the first data conversion module is configured to convert the acquired analog quantity echo signal into a digital quantity echo signal.
According to the technical scheme provided by the embodiment of the application, the ARM chip further comprises: the input end of the filtering module is electrically connected with the output end of the first data conversion module, the output end of the filtering module is electrically connected with the first operation module, and the filtering module is configured to filter and intercept the echo signal of the digital quantity.
According to the technical scheme provided by the embodiment of the application, the FPGA chip further comprises:
the second acquisition module is configured to acquire an excitation signal of a digital quantity;
the input end of the second data conversion module is electrically connected with the output end of the second acquisition module, the second data conversion module is configured to convert the excitation signal of digital quantity into an analog quantity excitation signal, and the analog quantity excitation signal is used for driving the ultrasonic wave emission module to emit ultrasonic waves.
According to the technical scheme provided by the embodiment of the application, the FPGA chip further comprises a third data conversion module, and the third data conversion module is configured to convert the related parameters of the material to be tested in digital quantity into the related parameters in analog quantity.
According to the technical scheme provided by the embodiment of the application, the system further comprises a display terminal, wherein the input end of the display terminal is electrically connected with the third data conversion module, and the display terminal is used for displaying the numerical values of the relevant parameters.
In a second aspect, the present application provides a control method for a portable online measurement system for measuring a material parameter, comprising the steps of:
generating an excitation signal;
responding to the excitation signal and driving the ultrasonic wave transmitting module to transmit ultrasonic waves to the material to be detected;
collecting an echo from the bottom surface of the material to be detected, and setting the echo as a first echo;
intercepting the first echo to obtain a second echo;
setting an acquisition interval period;
obtaining a set of amplitudes of the second echo, the set of amplitudes being amplitudes of the second echo acquired periodically at the acquisition interval;
and inputting the amplitude set to the identification function to obtain the relevant parameter value of the material to be detected.
According to the technical scheme provided by the embodiment of the application, the identification function is composed of a neural network, the neural network sequentially comprises an input layer, a plurality of hidden layers and an output layer, the input layer comprises the amplitude set, and the output layer comprises a plurality of parameter values of the material to be detected;
the recognition function is:
wherein,
represents the firstlLayer of the first hidden layeriThe number of the nerve cells is one,
in the form of a function of the hyperbolic tangent,lis the number of layers of the hidden layer,iis as followslFirst of a layeriThe number of the nerve cells is one,jis as followsl-1 layer ofjThe number of the nerve cells is one,
is as followslLayer of the first hidden layeriThe nerve cell and the firstl-1 of said hidden layersjA weight matrix for each neuron;
is as followslLayer of the first hidden layeriA bias matrix for each neuron;sis as followsl-1 number of neurons of said hidden layer;
represents the firstl-1 a second of said hidden layersjA plurality of neurons;
let the value set be X = [ = ]x 1 ，x 2 …x m ] T ，mThe number of elements in the amplitude value set is used;
then:
（2）
wherein,x d being said input layerdOne neuron, the second in the set of amplitudesjA value of an element;
for the layer 1 and the hidden layerx d To a corresponding firstcThe number of the nerve cells is one,
for layer 1 of the hidden layercA neuron and the second of the input layerdA weight matrix for each neuron;
for layer 1 of the hidden layercA bias matrix for each neuron;
then:
（3）
wherein,lthe +1 represents the output layer or layers,pis as followslThe number of neurons in the hidden layer,
is the second of the output layernThe value of the individual neuron or neurons is,
represents the firstnThe value of a parameter of the respective material (500) to be measured,
is the second of the output layernThe nerve cell and the firstlLayer of the first hidden layeriA weight matrix for each neuron;
is the second of the output layernA bias matrix for each neuron;
the material parameter set is then: y = [ alpha ], [ beta ], [ alpha ], [ beta ], [ alpha ], [ beta ]y 1 ，y 2 …y n ] T WhereinnIs the number of parameters of the material (500) to be measured.
In summary, the present application provides a portable online measurement system for measuring material parameters, which transmits ultrasonic waves to a material to be measured through an ultrasonic transmitting module, receives echoes from the bottom surface of the material to be measured through an ultrasonic receiving module, acquires the echoes and transmits the echoes to a first operation module through a first acquisition module, and calculates relevant parameters of the material to be measured through an identification function of the first operation module.
In addition, the FPGA chip and the ARM chip are combined, so that the software programmability and the powerful control ability of the ARM processor are perfectly combined with the hardware programmability of the FPGA.
Drawings
Fig. 1 is a schematic structural diagram of a portable online measurement system for measuring a material parameter according to an embodiment of the present application;
fig. 2 is a schematic diagram of a Zynq embedded platform provided in the embodiment of the present application;
FIG. 3 is a schematic diagram of an echo provided by an embodiment of the present application;
FIG. 4 is a schematic diagram of an intercepted echo provided by an embodiment of the present application;
fig. 5 is a flowchart of a control method of a portable online measurement system for measuring a material parameter according to an embodiment of the present application.
The text labels in the figures are represented as:
100. an ARM chip; 200. an AXI4 interface; 301. a first data conversion module; 302. a first data transmission module; 303. a second data conversion module; 304. a second data transmission module; 305. a power amplification module; 306. a third data conversion module; 400. zynq development board; 401. pressing a key; 500. a material to be tested; 600. an ultrasonic transducer; 700. and displaying the terminal.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Example 1
As mentioned in the background, the present application proposes, in view of the problems of the prior art, a portable online measurement system for measuring material parameters, as shown in fig. 1, comprising:
the ultrasonic wave transmitting module is used for transmitting ultrasonic waves to the material 500 to be detected;
an echo receiving module, configured to receive an echo from a bottom surface of the material 500 to be tested; optionally, an ultrasonic transducer 600 with a twin-crystal probe is adopted to transmit ultrasonic waves and receive echoes, the probe of the ultrasonic transducer 600 has dual functions of the ultrasonic transmitting module and the echo receiving module, the model of the ultrasonic transducer 600 is yufeng 1P20FG10, when in use, the probe is vertically placed on the material 500 to be measured, the center frequency of the probe is 1Mhz, when a sound wave hits the bottom surface of the material 500 to be measured, the sound wave is reflected and then received by the probe of the ultrasonic transducer 600 to generate a voltage signal, and further, an echo is formed; the ultrasonic transducer 600 is adopted to integrate the ultrasonic transmitting module and the echo receiving module, so that the simplicity of the device is improved;
a control device, the control device comprising:
the first acquisition module is electrically connected with the echo receiving module and is configured to acquire the echo;
the first operation module is electrically connected with the first acquisition module, the first operation module comprises an identification function, and the identification function is configured to identify the echo and obtain a relevant parameter of the material to be detected 500 corresponding to the echo; the relevant parameters comprise parameters such as Young modulus, Poisson ratio, density and the like of the material 500 to be tested; the neural network function trained by the scheme has the advantages of extremely small occupied space, less required computing resources, quick and convenient identification and capability of avoiding the problem of large calculated amount.
Further, as shown in fig. 2, the control device includes a PS terminal and a PL terminal, the PS terminal includes an ARM chip 100, and the ARM chip 100 includes the first operation module; the PL end comprises an FPGA chip, and the FPGA chip comprises the first acquisition module; the System adopts a Zynq embedded platform and comprises a Zynq development board, wherein the Zynq development board is provided with a PS (Processing System) Processing System and a PL (Progarmmable Logic) programmable Logic, the PS comprises an ARM chip 100, an internal memory, an external memory interface and peripheral equipment, the PL comprises the FPGA chip and various interfaces, and the FPGA chip and the ARM chip have rich expansion capability; the FPGA chip and the ARM chip 100 realize communication and data interaction between the FPGA chip and the ARM chip through the AXI4 interface 200; optionally, the model of Zynq is ALINXAX7010, the kernel is a dual-core ARM Cortex-A9 chip, and the dominant frequency is 666 Mhz; and the program for burning the identification function in the first operation module is used for identifying and processing the echo.
Further, the FPGA chip further includes: a first data conversion module 301, an input end of the first data conversion module 301 is electrically connected to an output end of the first acquisition module, and the first data conversion module 301 is configured to convert the acquired analog echo signal into a digital echo signal; as shown in fig. 3, the waveform of the echo is shown, the abscissa represents time in μ s, the ordinate represents amplitude in V, the echo is analog, and the program in the ARM chip 100 cannot recognize the analog, so that the analog signal is converted into digital, and optionally, the first data conversion module is an AD9238 module.
Further, the ARM chip 100 further includes: the input end of the filtering module is electrically connected with the output end of the first data conversion module 301, the output end of the filtering module is electrically connected with the first operation module, and the filtering module is configured to filter and intercept an echo signal of a digital quantity; the composition of echo signals is complex, and the echo signals consist of longitudinal echo signals, surface echo signals and echo signals reflected by a transverse boundary; the echo signal converted into the digital quantity is transmitted to the filtering module through the first data transmission module 302;
the filtering module comprises a filtering algorithm, optionally, the filtering algorithm is a band-pass filtering algorithm, the band-pass frequency range is 0.5Mhz-1.5Mhz, and the adopted window function is as follows:
wherein, T 1 To intercept the starting point, T 2 To intercept an endpoint, optionally, T 1 Setting the interception time to be 3 mus for the time of reaching the peak for the first time in the echo wave group, and then T 2 =T 1 +3 μ s; as shown in FIG. 3, T 1 Is 14 mus, T 2 The intercepted part of the simulated echo waveform is shown in fig. 4, wherein the abscissa represents time in mus, and the ordinate represents amplitude in V; the peak valley is taken as the characteristic point, if the characteristic point is too few, the number of the characteristic points in the waveform cannot meet the identification requirement, if the sampling characteristic point is too many, the waveform may be interfered by the subsequent noise to cause the false identification, therefore, after the integration, the interval time is set, and the echo signal waveform in the interval time contains four peak valleys to meet the requirement as the input response.
Further, the FPGA chip further includes:
the second acquisition module is configured to acquire an excitation signal of a digital quantity;
the input end of the second data conversion module 303 is electrically connected with the output end of the second acquisition module, the second data conversion module 303 is configured to convert the excitation signal of digital quantity into an analog quantity excitation signal, and the analog quantity excitation signal is used to drive the ultrasonic wave emission module to emit ultrasonic waves; the Zynq development board 400 is provided with a key 401, a program of the key 401 on the ARM chip 100 is triggered to generate a periodic sinusoidal signal digital pulse signal, the signal is transmitted from a memory at the PS end to the second data conversion module 303 at the PL end through the AXI4 bus 200 and the second data transmission module 304, the module converts the digital signal into AN analog signal, the central frequency of the generated signal is 1Mhz, the voltage range is-5V, and optionally, the signal of the second data conversion module is AN 9767; the output end of the second data conversion module 303 is further connected to a power amplification module 305, and the power amplification module 305 amplifies an analog quantity excitation signal to about hundred volts through a gain amplification model so as to meet the condition of driving the ultrasonic transmission module; the model of the power amplification module 305 is an AD603 module, and the power amplification module can amplify power to-100V-100V; the power amplification module 305 transmits the amplified excitation signal to the ultrasonic wave emission module through a coaxial cable, so as to drive the ultrasonic wave emission module to emit ultrasonic waves.
Further, the FPGA chip further includes a third data conversion module 306, where the third data conversion module 306 is configured to convert the relevant parameters of the material 500 to be tested in digital quantity into the relevant parameters in analog quantity; the echo signal is processed by the filtering module and then transmitted to the first operation module, the echo signal is identified and processed by the identification function in the first operation module, all functions and processing processes are burned in a chip in a program mode, data obtained after the program processing is digital quantity, the data cannot be visually displayed and needs to be converted into analog quantity, and optionally, the third data conversion module 306 is a VADM module developed by Xilinx corporation and specially used for video input and output.
Further, the measuring system further comprises a display terminal 700, an input end of the display terminal 700 is electrically connected with the third data conversion module 306, and the display terminal 700 is configured to display the numerical value of the relevant parameter; optionally, the display terminal 700 is a 7-inch LCD screen, and the relevant parameters of the material 500 to be tested are visually displayed on the display terminal 700.
Example 2
On the basis of embodiment 1, the present application further provides a control method for a portable online measurement system for measuring material parameters, as shown in fig. 5, including the following steps:
s01, generating an excitation signal; wherein, the excitation signal is triggered by a key 401 on the Zynq development board 400 and is sent out by the PS terminal;
s02, responding to the excitation signal and driving the ultrasonic wave emitting module to send ultrasonic waves to the material to be tested 500; the excitation signal passes through the second data conversion module 303 and the power amplification module 305, converts a digital quantity signal into an analog quantity signal, and amplifies the analog quantity signal to about hundred volts to drive the ultrasonic transducer 600 to emit ultrasonic waves;
s03, collecting an echo from the bottom surface of the material 500 to be detected, and setting the echo as a first echo; when the ultrasonic wave hits the bottom surface of the material 500 to be measured, the ultrasonic wave is reflected and then received by the echo receiving module of the ultrasonic transducer 600 to generate a voltage signal, so that an echo is formed;
s04, intercepting the first echo to obtain a second echo; wherein a clipping start point and a clipping end point are set, as shown in fig. 3 and 4, fig. 3 is the first echo waveform diagram, and the clipping start point is set as T 1 ，T 2 The interval time is 3 mus for intercepting the end point;
s05, setting an acquisition interval period; in the embodiment, the acquisition interval period is set to be 5 ns;
s06, obtaining an amplitude set of the second echo, wherein the amplitude set is the amplitude of the second echo acquired periodically at the acquisition interval; in the implementation, the acquisition interval period is 5ns, and the interval time is 3 mus, so that 601 acquisition points are included in the interval time;
s07, inputting the amplitude set to the recognition function to obtain a relevant parameter value of the material 500 to be detected; in embodiment 1, it is known that, first, the first echo is converted into a digital signal, and then the second echo is obtained by interception, so that 601 acquisition points are input to the first operation module in a digital form, and are identified and calculated through the identification function in the first operation module, so as to obtain the relevant parameters of the material 500 to be measured.
Further, the identification function is composed of a neural network, the neural network sequentially comprises an input layer, a plurality of hidden layers and an output layer, the input layer comprises the amplitude set, and the output layer comprises a plurality of parameter values of the material to be detected; optionally, the neural network is a back-propagation (BP) neural network, and the input signal is input into the model through an input layer, processed by a hidden layer, and output through an output layer. Typically, the hidden layer is a multi-layer structure, each layer having neurons, wherein each neuron has an activation function responsible for converting an input signal into a non-linear output. Each layer of neurons is connected with all neurons in the previous layer, namely a full-connection structure;
the recognition function is:
wherein,
represents the firstlLayer of the first hidden layeriThe number of the nerve cells is one,
is a function of the hyperbolic tangent,lis the number of layers of the hidden layer,iis as followslFirst of a layeriThe number of the nerve cells is one,jis as followsl-1 layer ofjThe number of the nerve cells is one,
is as followslLayer of the first hidden layeriThe nerve cell and the firstl-1 of said hidden layersjA weight matrix for each neuron;
is as followslLayer of the first hidden layeriA bias matrix for each neuron;sis as followsl-1 number of neurons of said hidden layer;
represents the firstl-1 a second of said hidden layersjA plurality of neurons;
before the identification function is used for identification processing, the identification function needs to be optimized, namely, the identification function training and learning process needs a large amount of data sets, so that a proxy model is established by a finite element simulation method, relevant parameters of a plurality of different materials are used as the input of the proxy model according to a set sequence, the relevant parameters input into the proxy model comprise Young modulus, Poisson ratio, density and the like, and the output of the proxy model is echo signals corresponding to the different materials, namely, the data sets needed by the identification function training and learning;
inputting the obtained echo signals corresponding to different materials into the identification function, outputting the echo signals as related parameters of the different materials, and optimizing a weight matrix and a bias matrix through inversion so that the relative error between the predicted value of the related parameters of the materials output by the identification function and the actual value of the related parameters of the materials meets the requirement of precision, thereby obtaining the value of the weight matrix and the bias matrix and finally obtaining the optimized identification function;
let the value set be X = [ = ]x 1 ，x 2 …x m ] T M is the number of elements in the amplitude set;
then:
（2）
wherein,x d being said input layerdOne neuron, the second in the set of amplitudesjA value of an element;
for the layer 1 and the hidden layerx d To a corresponding firstcThe number of the nerve cells is one,
for layer 1 of the hidden layercA neuron and the second of the input layerdA weight matrix for each neuron;
for layer 1 of the hidden layercA bias matrix for each neuron; in this embodiment, the period of the acquisition interval is 5ns, and the interval time is 3 μ s, so that 601 acquisition points are included in the interval time, and thenmIs 601;
then:
（3）
wherein,lthe +1 represents the output layer or layers,pis as followslThe number of neurons in the hidden layer,
is the second of the output layernThe value of the individual neuron or neurons is,
represents the firstnThe value of a parameter of the respective material (500) to be measured,
is the second of the output layernThe nerve cell and the firstlLayer of the first hidden layeriA weight matrix for each neuron;
is the first of the output layernA bias matrix for each neuron;
the material parameter set is then: y = [ alpha ], [ beta ], [ alpha ], [ beta ], [ alpha ], [ beta ]y 1 ，y 2 …y n ] T In whichnThe number of parameters of the material 500 to be measured;
taking the hidden layer as 2 layers and the number of neurons in each layer as 50 as an example, the output vector of the hidden layer in layer 1 is:
the output values of each neuron in the layer 2 hidden layer are as follows:
wherein,
representing a layer 2 hidden layerkThe output value of each of the neurons is,
representing a layer 2 hidden layerkThe first layer of neuron and the 1 st layer of hidden layercThe weight matrix of the individual neurons is determined,
a bias matrix representing a kth neuron of a layer 2 hidden layer;
the output vector of the layer 2 hidden layer is:
the output value of each neuron of the output layer is as follows:
wherein,
represents the output ofnThe value of the relevant parameter(s) is,
representing the output layernOne neuronWith a 2 nd hidden layerkThe weight matrix of the individual neurons is determined,
represents the output layernA bias matrix for each neuron;
the output vector of the output layer is: y = [ alpha ], [ beta ], [ alpha ], [ beta ], [ alpha ], [ beta ]y 1 ，y 2 …y n ] T ；
Optionally, the relevant parameters of the material to be tested include three: young's modulus, Poisson's ratio and density, thennIs the number of 3, and the number of the carbon atoms is 3,y 1 、y 2 、y 3 values for Young's modulus, Poisson's ratio, and density, respectively.
The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. The foregoing is only a preferred embodiment of the present application, and it should be noted that there are no specific structures which are objectively limitless due to the limited character expressions, and it will be apparent to those skilled in the art that a plurality of modifications, decorations or changes can be made without departing from the principle of the present invention, and the technical features mentioned above can be combined in a suitable manner; such modifications, variations, combinations, or adaptations of the invention in other instances, which may or may not be practiced, are intended to be within the scope of the present application.
Claims (9)
1. A portable on-line measurement system for measuring material parameters, comprising:
an ultrasonic wave emitting module for emitting ultrasonic waves to a material (500) to be measured;
an echo receiving module for receiving an echo from a bottom surface of the material (500) to be tested;
a control device, the control device comprising:
the first acquisition module is electrically connected with the echo receiving module and is configured to acquire the echo;
the first operation module is electrically connected with the first acquisition module, the first operation module comprises an identification function, and the identification function is configured to identify the echo and obtain the relevant parameters of the material (500) to be detected corresponding to the echo.
2. The portable on-line measurement system for measuring material parameters of claim 1, characterized in that: the control device comprises a PS end and a PL end, wherein the PS end comprises an ARM chip (100), and the ARM chip (100) comprises the first operation module; the PL end comprises an FPGA chip, and the FPGA chip comprises the first acquisition module.
3. The portable on-line measurement system for measuring material parameters of claim 2, characterized in that: the FPGA chip further comprises: the input end of the first data conversion module (301) is electrically connected with the output end of the first acquisition module, and the first data conversion module (301) is configured to convert the acquired analog echo signals into digital echo signals.
4. A portable on-line measurement system for measuring material parameters according to claim 3, characterized in that: the ARM chip (100) further comprises: the input end of the filtering module is electrically connected with the output end of the first data conversion module (301), the output end of the filtering module is electrically connected with the first operation module, and the filtering module is configured to filter and intercept the echo signal of the digital quantity.
5. The portable on-line measurement system for measuring material parameters of claim 4, wherein the FPGA chip further comprises:
the second acquisition module is configured to acquire an excitation signal of a digital quantity;
the input end of the second data conversion module (303) is electrically connected with the output end of the second acquisition module, the second data conversion module (303) is configured to convert the excitation signal of digital quantity into an analog quantity excitation signal, and the analog quantity excitation signal is used for driving the ultrasonic wave emission module to emit ultrasonic waves.
6. The portable on-line measurement system for measuring material parameters of claim 5, characterized in that: the FPGA chip further comprises a third data conversion module (306), wherein the third data conversion module (306) is configured to convert the relevant parameters of the material to be tested (500) in digital quantity into the relevant parameters in analog quantity.
7. The portable on-line measurement system for measuring material parameters of claim 6, characterized in that: the measuring system further comprises a display terminal (700), wherein the input end of the display terminal (700) is electrically connected with the third data conversion module (306), and the display terminal is used for displaying the numerical value of the relevant parameter.
8. A control method of a portable on-line measuring system for measuring material parameters according to any of claims 1-7, characterized by comprising the steps of:
generating an excitation signal;
responding to the excitation signal and driving the ultrasonic wave transmitting module to transmit ultrasonic waves to the material (500) to be detected;
collecting an echo from the bottom surface of the material (500) to be detected, and setting the echo as a first echo;
intercepting the first echo to obtain a second echo
Setting an acquisition interval period;
obtaining a set of amplitudes of the second echo, the set of amplitudes being amplitudes of the second echo acquired periodically at the acquisition interval;
and inputting the amplitude set into the identification function to obtain the relevant parameter value of the material (500) to be detected.
9. The control method of a portable on-line measuring system for measuring material parameters according to claim 8, characterized in that: the identification function is composed of a neural network, the neural network sequentially comprises an input layer, a plurality of hidden layers and an output layer, the input layer comprises the amplitude set, and the output layer comprises a plurality of parameter values of the material to be detected;
the recognition function is:
wherein,
represents the firstlLayer of the first hidden layeriThe number of the nerve cells is one,
in the form of a function of the hyperbolic tangent,lis the number of layers of the hidden layer,iis as followslFirst of a layeriThe number of the nerve cells is one,jis a firstl1 layer ofjThe number of the nerve cells is increased by the number of the nerve cells,
is as followslLayer of the first hidden layeriThe single neuron and the firstl-1 of said hidden layersjA weight matrix for each neuron;
is as followslLayer of the first hidden layeriA bias matrix for each neuron;sis as followsl-1 number of neurons of said hidden layer;
represents the firstl-1 a second of said hidden layersjA plurality of neurons;
let the value set be X = [ = ]x 1 ，x 2 …x m ] T ，mThe number of elements in the amplitude value set is used;
then:
（2）
wherein,x d being said input layerdOne neuron, the second in the set of amplitudesjA value of an element;
for the layer 1 and the hidden layerx d To a corresponding firstcThe number of the nerve cells is one,
for layer 1 of the hidden layercA neuron and the second of the input layerdA weight matrix for each neuron;
for layer 1 of the hidden layercA bias matrix for each neuron;
then:
（3）
wherein,lthe +1 represents the output layer or layers,pis as followslThe number of neurons in the hidden layer,
is the second of the output layernThe value of the individual neuron or neurons is,
represents the firstnThe value of a parameter of the respective material (500) to be measured,
is the second of the output layernThe nerve cell and the firstlLayer of the first hidden layeriA weight matrix for each neuron;
is the second of the output layernA bias matrix for each neuron;
the material parameter set is then: y = [ alpha ], [ beta ], [ alpha ], [ beta ], [ alpha ], [ beta ]y 1 ，y 2 …y n ] T WhereinnIs the number of parameters of the material (500) to be measured.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210791451.6A CN114878689B (en) | 2022-07-07 | 2022-07-07 | Portable on-line measuring system for measuring material parameters and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210791451.6A CN114878689B (en) | 2022-07-07 | 2022-07-07 | Portable on-line measuring system for measuring material parameters and control method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114878689A true CN114878689A (en) | 2022-08-09 |
| CN114878689B CN114878689B (en) | 2022-11-01 |
Family
ID=82683138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210791451.6A Active CN114878689B (en) | 2022-07-07 | 2022-07-07 | Portable on-line measuring system for measuring material parameters and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114878689B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004177313A (en) * | 2002-11-28 | 2004-06-24 | Mitsubishi Heavy Ind Ltd | Ultrasonic inspection apparatus |
| CN104792655A (en) * | 2015-03-31 | 2015-07-22 | 安徽江南化工股份有限公司 | Density detection system |
| CN105534546A (en) * | 2015-12-30 | 2016-05-04 | 哈尔滨工业大学 | Ultrasonic imaging method based on ZYNQ FPGAs |
| CN108956787A (en) * | 2018-06-13 | 2018-12-07 | 西安理工大学 | A kind of rail failure detection method neural network based |
| CN110646516A (en) * | 2019-10-29 | 2020-01-03 | 杭州欧贲科技有限公司 | Palm type ultrasonic flaw detector with extremely simple framework |
-
2022
- 2022-07-07 CN CN202210791451.6A patent/CN114878689B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004177313A (en) * | 2002-11-28 | 2004-06-24 | Mitsubishi Heavy Ind Ltd | Ultrasonic inspection apparatus |
| CN104792655A (en) * | 2015-03-31 | 2015-07-22 | 安徽江南化工股份有限公司 | Density detection system |
| CN105534546A (en) * | 2015-12-30 | 2016-05-04 | 哈尔滨工业大学 | Ultrasonic imaging method based on ZYNQ FPGAs |
| CN108956787A (en) * | 2018-06-13 | 2018-12-07 | 西安理工大学 | A kind of rail failure detection method neural network based |
| CN110646516A (en) * | 2019-10-29 | 2020-01-03 | 杭州欧贲科技有限公司 | Palm type ultrasonic flaw detector with extremely simple framework |
Non-Patent Citations (2)
| Title |
|---|
| JIAJUN LIU等: "Design of Multi-channel CMUT Phase-controlled Transmission System Based on ZYNQ-7010", 《2019 IEEE 5 TH INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATIONS》 * |
| 吕瑞宏等: "基于材料参数的管道防腐层粘接状态识别研究", 《仪器仪表学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114878689B (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6810743B2 (en) | Non-destructive evaluation of wire insulation and coatings | |
| CN1975370B (en) | Method for ultrasonic elastic modulus calculation and imaging | |
| CN1975410B (en) | Digital log amplifier for ultrasonic testing | |
| Ricci et al. | Pulse-compression ultrasonic technique for the inspection of forged steel with high attenuation | |
| CN108169330A (en) | The device and method of concrete component axial stress non-destructive testing based on non-linear ultrasonic Harmonic Method | |
| EP2888583A1 (en) | Integrated active ultrasonic probe | |
| Zgonc et al. | A neural network for crack sizing trained by finite element calculations | |
| US5408880A (en) | Ultrasonic differential measurement | |
| CN102109497B (en) | Sequentially fired high dynamic range NDT/NDI inspection device | |
| US5589209A (en) | Method for a non-destructive determination of quality parameters in fresh produce | |
| CN109871824B (en) | Ultrasonic guided wave multi-mode separation method and system based on sparse Bayesian learning | |
| Etxaniz et al. | Ultrasound-based structural health monitoring methodology employing active and passive techniques | |
| EP0625278B1 (en) | Audible techniques for the perception of non-destructive evaluation information | |
| CN110412132B (en) | Nonlinear imaging method based on multi-mode ultrasonic phased array detection system | |
| CN114878689B (en) | Portable on-line measuring system for measuring material parameters and control method thereof | |
| CN115540790A (en) | High-precision ultrasonic thickness measurement method and device | |
| Khlybov et al. | Assessment of the degree of damage in structural materials using the parameters of structural acoustic noise | |
| Bloxham et al. | Establishing the limits of validity of the superposition of experimental and analytical ultrasonic responses for simulating imaging data | |
| JP2005221321A (en) | Method and device for detecting ultrasonic signal | |
| Baglio et al. | " Fuzzy tap-testing" sensors for material health-state characterization | |
| Akundi et al. | Non-destructive testing (NDT) and evaluation using ultrasonic testing equipment to enhance workforce skillset for modern manufacturing | |
| Mestre et al. | Low-cost ultrasonic probe to assess wood defects and parameters | |
| Legendre et al. | Ultrasonic aluminum weld testing method based on the wavelet transform and a neural classifier | |
| Ono | Receiving Sensitivities of Acoustic Emission Sensors: A data compilation. | |
| Farin et al. | Localization of unbounded contacts on vibrating elastic plates |
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 |