JPH09171006A - Device or evaluating ultrasonic flow detection data - Google Patents

Abstract

PROBLEM TO BE SOLVED: To obtain more accurate discriminated results while the setting of a time gate is facilitated. SOLUTION: In the main body 30 of a device for evaluating ultrasonic flaw detection data, a data input section 34 inputs ultrasonic flaw detection data 29 obtained from an object 24 to be inspected and a time gate setting section 36 extracts a plurality of extraction data 37-39 by multiplying the data 29 by a time gate. Then a data analyzing and processing section 40 analyzes and processes the data 37-39 extracted by the setting section 36 and a discriminating section 44 using a neural network discriminates the presence/absence of a defect based on analyzed and processed data 41-43 from the analyzing and processing section 40.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an ultrasonic inspection data evaluation apparatus.

[0002]

2. Description of the Related Art In various plants, ultrasonic flaw detection is widely used as a means for nondestructive inspection of structures and welds.

In this case, it is a tester who has specialized knowledge to evaluate the ultrasonic flaw detection data obtained by the ultrasonic flaw detection inspection to determine whether or not there is a defect.

However, an examiner who has specialized knowledge requires a considerable amount of skill because the examiner makes the determination based on his or her experience, and there is a possibility that the determination result may vary among the examiners. Further, it is a very difficult work to make a judgment by looking at all of the tens and hundreds of ultrasonic flaw detection data obtained by the inspection.

[0005] Therefore, research and development for automatically judging ultrasonic flaw detection data are being advanced.

An ultrasonic flaw detection data evaluation apparatus currently under development is as shown in FIG.

In the figure, 1 is a tube as an example of a non-destructive inspection object (inspection object), 2 is a welded portion of the tube 1, 3 is an ultrasonic flaw detector, and 4 is ultrasonic waves of the ultrasonic flaw detector 3. Transmitter / receiver, 5
Is an ultrasonic probe of the ultrasonic flaw detector 3.

Then, the ultrasonic flaw detection data evaluation device main body 7 is provided by inputting the ultrasonic flaw detection data 6 obtained by the ultrasonic transmission / reception section 4 to automatically evaluate and judge the ultrasonic flaw detection data 6. An input device 8 such as a keyboard, a pointing device 9 such as a mouse or a tablet, and a display device 10 such as a display are connected to the evaluation device body 7.

The ultrasonic testing data evaluation device body 7 is
As shown in FIG. 5, a part of the ultrasonic flaw detection data 6 is recorded by a data input unit 11 that receives an input of the ultrasonic flaw detection data 6 from the ultrasonic transmission / reception unit 4 and a position instruction input 12 from the pointing device 9. Based on the time gate setting unit 13 to be extracted, the data analysis processing unit 15 that analyzes the extracted data 14 extracted by the time gate setting unit 13 by Fourier transform, and the analysis data 16 that is analyzed by the data analysis processing unit 15. The determination unit 17 that uses a neural network or the like for making the determination (hereinafter,
Neural network 17)).

In the figure, reference numeral 18 is teaching data used for causing the neural network 17 to perform learning.

Further, in FIG. 10, 19 is a neuron which constitutes the neural network 17, 20 is an input layer of the neural network 17, 21 is an intermediate layer of the neural network 17, 22 is an output layer of the neural network 17, Reference numeral 23 is a grid point set on the coordinate formed by the frequency in the analysis data 16 and each position a, b, c, d, e.

When performing a non-destructive inspection of the welded portion 2 of the pipe 1, the ultrasonic probe 5 of the ultrasonic flaw detector 3 is provided in the vicinity of the welded portion 2 of the pipe 1 as shown in FIGS. The ultrasonic wave transmitted from the ultrasonic wave transmitting / receiving unit 4 is arranged from the ultrasonic probe 5 to the tube 1
The ultrasonic wave that has been made incident on the ultrasonic wave and propagated inside the tube 1 and reflected by the ultrasonic wave is transmitted as ultrasonic flaw detection data 6 to the ultrasonic wave transmitting / receiving unit 4
To receive. Then, the above work is performed at a plurality of positions (five positions a, b, c, d, and e in the figure) while the ultrasonic probe 5 is gradually moved in the axial direction a of the tube 1. As described above, a plurality (see FIG. 7) of ultrasonic flaw detection data 6 for different positions in the circumferential direction b of the welded portion 2 can be obtained. Further, while the ultrasonic probe 5 is gradually moved in the circumferential direction b of the pipe 1 and the above work is repeated, the ultrasonic flaw detection data 6 is collected over the entire circumferential direction b of the welded portion 2.

In this way, when the ultrasonic flaw detection data 6 is collected by the ultrasonic flaw detection device 3, the ultrasonic flaw detection data 6 is input to the data input section 11 of the ultrasonic flaw detection data evaluation device body 7. Ultrasonic flaw detection data evaluation device body 7
The ultrasonic flaw detection data 6 is input to the ultrasonic transmission / reception unit 4 and the ultrasonic flaw detection data evaluation apparatus main body 7 via a cable or a network for electric transmission, or when both have infrared ports. Transfer by infrared communication,
Data may be input via a removable medium such as a magnetic tape, a magnetic disk, or an optical disk.

When the ultrasonic flaw detection data 6 is input, the time gate setting section 13 of the ultrasonic flaw detection data evaluation apparatus main body 7 is inputted.
Causes the display device 10 such as a display to display the ultrasonic flaw detection data 6, and the operator uses the pointing device 9 such as a mouse or a tablet to display a part of the ultrasonic flaw detection data 6 as shown in FIG. Is extracted (multiplied by the time gate T).

As a concrete method of setting the time gate T by the operator, the vicinity of the peak value of the ultrasonic flaw detection data 6 is designated as the central position T ₀ , and the range before and after the central position T ₀ is designated with an appropriate width. (The range is symmetrical with respect to the center position, so it is sufficient to specify either the front or the rear).

After setting the time gate T, the data analysis processing section 15 of the ultrasonic flaw detection data evaluation apparatus main body 7
The portion of the extracted data 14 of the ultrasonic flaw detection data 6 is analyzed.

As a concrete method of the analysis processing, the extracted data 14 is subjected to frequency analysis by an integral conversion method using a trigonometric function called a fast Fourier transform, and the extracted data 1
Two-dimensional data indicating the energy intensity for each frequency of 4 is obtained. At this time, since the entire area of the extracted data 14 is subjected to frequency analysis, the concept of time disappears from the two-dimensional data. The two-dimensional data are a, b,
The positions c, d, and e are superimposed on each other to form pseudo three-dimensional data as shown in FIGS. By the way, FIG. 8 shows typical analysis data 16 when stress corrosion cracking is present, and FIG. 9 is typical analysis data 16 when stress corrosion cracking is not present. It should be noted that the two waveforms are perceived to be distinctly different to the human eye, but it is quite difficult to make similar engineering engineering.

Further, the data analysis processing unit 15 performs normalization so that the energy intensity in the analysis data 16 is represented by a value between 0 and 1 for the convenience of the subsequent processing.

When the analysis data 16 is obtained in this way, the ultrasonic flaw detection data evaluation apparatus main body 7 is
Is determined by the determination unit 17 such as a neural network.

Here, the neural network 17 was developed in order to realize the excellent information processing capability of the human brain in an engineering manner.
9 are constructed.

As shown in FIG. 10, the neuron 19 is an input Si (0≤Si≤1, i = 1 to n) and a weighting factor Wi (excitability when Wi≥0, and Wi <0). The internal state u is determined by u = ΣWi · Si−θ by i = 1 to n) indicating the suppression property and the threshold value θ, and this internal state u is output function f (x) = 1 / { 1 + exp (-x /
t) By substituting into｝, the following output is obtained.

[0022]

F (u) = 1 / {1 + exp (-u / t)}

Note that t is a positive constant (usually 1.0) called the temperature of the neuron 19.

Further, the output function f (x) is called a sigmoid function, and as shown in FIG. 11, while the value of x changes from − to +, it nonlinearly changes from 0 to 1. It is a changing function (0 ≦ f (x) ≦ 1).

Then, the neural network 17 is constructed by combining a plurality of the neurons 19. The neural network 17 includes various types such as a mutual type and a hierarchical type. In this case, the hierarchical neural network 17 is used. As shown in FIG. 12, the hierarchical neural network 17 is formed by connecting neurons 19 to have layers such as an input layer 20, an intermediate layer 21, and an output layer 22, and each layer has one or more layers. It is composed of neurons 19, and neurons 19 in the same layer are not connected to each other, and each neuron 19 in the lower layer is connected to all neurons 19 in the upper layer. There is.

The input layer 20 is composed of the same number of neurons 19 as the grid points 23 set on the coordinates formed by the frequencies in the analysis data 16 and the respective positions a, b, c, d, e, and the intermediate number. The layer 21 is composed of one or more layers of neurons 19 (one layer in the figure), and the output layer 22 is composed of two neurons 19a and 19b.

Further, the neural network 17 is learned by setting parameters such as the weighting factor Wi and the threshold value θ for each neuron 19 in advance.

As a learning method, first, each parameter such as the weighting factor Wi and the threshold value θ is randomly set using the input device 8 such as a keyboard to initialize the neural network 17, and the teaching data 18 is stored therein. Input and generate an output, calculate an error between the output from the neural network 17 and the actual result of the teaching data 18, and output the error from the output layer 22 to the intermediate layer 21 and from the intermediate layer 21 to the input layer 20. The error backpropagation learning method in which the parameters are adjusted / changed for each layer while propagating in the opposite direction is used to repeat the operation for a large number of teaching data 18.

At this time, the two neurons 1 in the output layer 22
If the outputs of 9a and 19b are defective, (1.0 to 0.7,
0.0-0.3), if unknown (0.7-0.3, 0.
3 to 0.7), if it is not a defect (0.3 to 0.0, 1..
0 to 0.7).

In the neural network 17 which has been sufficiently learned in this way, the output of each neuron 19 can be obtained only by inputting the energy intensity at the corresponding grid point 23 to each neuron 19 constituting the input layer 20. It is calculated one after another and the correct judgment result is automatically derived.

In this way, the neural network 17
By using, unlike fuzzy and AI,
It becomes possible to make a correct decision even from a waveform pattern that is difficult to rule.

Since the learning contents are distributed and stored in each parameter, the neural network 17 itself is made into a black box, but more learning is expected, and a more accurate judgment result is expected. become able to.

The determination result thus obtained is also learned by the neural network 17.

The determination result is displayed on the input device 8.
Further, it may be stored in an external storage device (not shown) or the like, if necessary.

[0035]

However, the conventional ultrasonic flaw detection data evaluation apparatus described above has the following problems.

That is, the ultrasonic testing data evaluation apparatus main body 7
In the time gate setting section 13, the operator uses the pointing device 9 such as a mouse or a tablet to extract a part of the ultrasonic flaw detection data 6 as shown in FIG. 7 (multiplies the time gate T). I try to let you
Setting time gate T is the center position T ₀ near the peak value of the ultrasonic flaw detection data 6, so that to the range specified before and after the center position T ₀ with a suitable width, the optimum time gate T once Was difficult to set in.

Therefore, the set width of the time gate T becomes too wide and the extracted data 14 contains noise, or the set width of the time gate T becomes too narrow and necessary information is missing from the extracted data 14. In order to avoid this, it is necessary to repeatedly set and determine the time gate T and make adjustments, and it takes time and effort to obtain the optimum time gate T.

In view of the above situation, it is an object of the present invention to provide an ultrasonic flaw detection data evaluation apparatus which makes it possible to obtain a more accurate determination result while facilitating the setting of the time gate.

[0039]

SUMMARY OF THE INVENTION According to the present invention, a data input section for receiving input of ultrasonic flaw detection data obtained from an object to be inspected, and a plurality of extracted data by multiplying the input ultrasonic flaw detection data by a time gate. A time gate setting unit to be extracted, a data analysis processing unit that analyzes each of the plurality of extracted data extracted by the time gate setting unit by Fourier transform, and a defect analysis based on each analysis data analyzed by the data analysis processing unit. The present invention relates to an ultrasonic flaw detection data evaluation apparatus characterized in that an ultrasonic flaw detection data evaluation apparatus main body is configured with a determination unit that uses a neural network for determining whether or not there is.

In this case, the time gate setting unit spreads the extracted data of three large, medium and small, which are spread forward and backward by the same width with the vicinity of the peak value of the ultrasonic flaw detection data as the center position and overlap each other without crossing each other. A large gate setting unit for extracting, a medium gate setting unit, and a small gate setting unit may be provided.

Further, an ultrasonic flaw detector for collecting ultrasonic flaw detection data from an object to be inspected may be integrated with the main body of the ultrasonic flaw detection data evaluation device.

According to the above means, the following effects can be obtained.

In the main body of the ultrasonic flaw detection data evaluation apparatus, the data input section inputs the ultrasonic flaw detection data obtained from the object to be inspected, and the time gate setting section applies the time gate to the input ultrasonic flaw detection data. A plurality of extracted data are multiplied by each other, the data analysis processing unit analyzes the plurality of extracted data extracted by the time gate setting unit by Fourier transform, and the determination unit using the neural network operates the data analysis processing unit. It is determined whether or not there is a defect on the basis of each analysis data subjected to the analysis processing in.

In this case, the time gate setting unit includes a large gate setting unit, a middle gate setting unit, and a small gate setting unit, and moves forward and backward with the vicinity of the peak value of ultrasonic flaw detection data as the central position. Three large, medium and small extracted data are extracted so that they are spread by equal width and do not intersect each other.

As described above, the large, medium, and small three extracted data are extracted in advance, and the determination is made based on the large, medium, and small three extracted data, so that an accurate determination can be made without extracting the optimum time gate. You will be able to produce results.

Further, by integrating an ultrasonic flaw detector for collecting ultrasonic flaw detection data from the object to be inspected with the main body of the ultrasonic flaw detection data evaluation device, the ultrasonic flaw detection data is collected and processed internally and continuously. Will be done in.

[0047]

Embodiments of the present invention will be described below with reference to the drawings.

1 to 3 show an example of the embodiment of the present invention.

In the figure, 24 is a tube as an example of a non-destructive inspection object (inspection object), 25 is a welded portion of the pipe 24, 26 is an ultrasonic flaw detector, and 27 is an ultrasonic wave of the ultrasonic flaw detector 26. The transceiver unit 28 is an ultrasonic probe of the ultrasonic flaw detector 26.

Then, the ultrasonic flaw detection data evaluation apparatus main body 3 is inputted by inputting the ultrasonic flaw detection data 29 obtained by the ultrasonic transmission / reception section 27.
0 is provided, and an input device 31 such as a keyboard, a pointing device 32 such as a mouse or a tablet, and a display device 33 such as a display are connected to the ultrasonic flaw detection data evaluation device main body 30. The ultrasonic flaw detection data evaluation apparatus main body 30 may be integrated with the ultrasonic flaw detection equipment 26.

The ultrasonic flaw detection data evaluation apparatus main body 30
The data input unit 34 that receives the input of the ultrasonic flaw detection data 29 from the ultrasonic transmission / reception unit 27, and the position indication input 35 from the pointing device 32 provide the ultrasonic flaw detection data 29 with time gates T _{1 to} T ₃ . Multiply (three in this embodiment) extracted data 37 to 39
The time gate setting unit 36 for extracting the data, the data analysis processing unit 40 for analyzing the plurality of extracted data 37 to 39 extracted by the time gate setting unit 36 by Fourier transform, and the data analysis processing unit 40 for the analysis processing. The determination unit 44 (hereinafter, referred to as a neural network 44) that uses a neural network or the like to make a determination based on the analyzed data 41 to 43.

In the present invention, the time gate setting section 36 is used.
Is the center position T ₀ around the peak value of the ultrasonic flaw detection data 29 and spreads by two equal widths to the front and the rear, for example, to extract three large, medium and small extraction data 37 to 39. And the middle gate setting unit 46
And a small gate setting unit 47. The three large, medium and small extracted data 37 to 39 thus extracted are overlapped with each other so as not to intersect each other.

At this time, even if the largest extracted data 37 is set so that it can be divided by the width D to automatically set the small and medium extracted data 38 and 39, on the contrary, the largest extracted data 39 It is also possible to set this by a width d to automatically set the large and medium extraction data 37, 38. The width d may be variable.

Further, the neural network 44 uses the analysis data 41 to 31 based on the three large, medium and small extracted data 37 to 39.
As a result of handling 43, the number of neurons 49 forming the input layer 48 is plural (three times) that in the case of FIG.

In the figure, reference numeral 50 is teaching data used for causing the neural network 44 to perform learning.

Further, in the figure, 51 is an intermediate layer of the neural network 44, 52 is an output layer of the neural network 44, and 53 is a frequency in the analysis data 41 to 43 and each position a, b, c, d, e. It is a grid point set on the coordinates.

Next, the operation will be described.

When performing a nondestructive inspection of the welded portion 25 of the pipe 24, the ultrasonic flaw detector 2 is installed near the welded portion 25 of the pipe 24.
The ultrasonic probe 28 of No. 6 is arranged, and the ultrasonic waves transmitted from the ultrasonic transmitting / receiving unit 27 are made incident from the ultrasonic probe 28 toward the tube 24, propagated inside the tube 24, and are reflected. The ultrasonic wave is used as ultrasonic flaw detection data 29, and the ultrasonic wave transmitting / receiving unit 27 is used.
To receive. Then, the above work is performed at a plurality of positions (five positions a, b, c, d, and e in the figure) while the ultrasonic probe 28 is gradually moved in the axial direction c of the tube 24. As described above, a plurality (see FIG. 2) of ultrasonic flaw detection data 29 for one position in the circumferential direction b of the welded portion 25 is obtained at different positions. Further, the ultrasonic probe 28 is moved little by little in the circumferential direction of the pipe 24 to repeat the above work, and
The ultrasonic flaw detection data 29 is collected over the entire circumferential direction b.

In this way, when the ultrasonic flaw detection data 29 has been collected by the ultrasonic flaw detection device 26, the ultrasonic flaw detection data 29 is input to the data input section 34 of the ultrasonic flaw detection data evaluation device main body 30. The input of the ultrasonic flaw detection data 29 to the ultrasonic flaw detection data evaluation apparatus main body 30 is performed by connecting the ultrasonic transmission / reception unit 27 and the ultrasonic flaw detection data evaluation apparatus main body 30 via a cable or a network and transmitting them. If there is an infrared port, the data may be transferred by infrared communication, or data may be input via a removable medium such as a magnetic tape, a magnetic disk, or an optical disk. When the ultrasonic flaw detector 26 is integrated with the ultrasonic flaw detector data evaluation apparatus main body 30, the ultrasonic flaw detection data 29 is input internally, and further automation is achieved. be able to.

When the ultrasonic flaw detection data 29 is input, the time gate setting unit 36 of the ultrasonic flaw detection data evaluation apparatus main body 30 displays the ultrasonic flaw detection data 29 on the display device 33 such as a display, and the operator is prompted to move the mouse. As shown in FIG. 2, a part of the ultrasonic flaw detection data 29 is extracted (multiplied by time gates T _{1 to} T ₃ ) using a pointing device 32 such as a tablet or a tablet.

Specific time gate T ₁ by the operator
How of T ₃ setting, specifies the vicinity of the peak value of the ultrasonic inspection data 29 as the center position T _0, (range is performed by specifying a range before and after a suitable width of the central position T _0, the center Since it is a target with respect to the position, you can specify either the front or the rear).

Moreover, in the present invention, the time gate setting section 36 includes the large gate setting section 45 and the middle gate setting section 4.
6 and a small gate setting section 47, and spreads by equal widths D to the front and the rear with the vicinity of the peak value of the ultrasonic flaw detection data 29 as the center position T ₀ , for example, three large, medium and small extracted data 37 to 39. Let it be extracted. In particular, the middle extracted data 38 should be kept close to the optimum range, and the largest extracted data 37 may contain some noise as long as all the necessary information is completely included. The small extracted data 39 is
It does not matter if the necessary information is missing.
In addition, the large, medium and small three extracted data 37-
39 are overlapped so as not to intersect each other.

At this time, even if the largest extracted data 37 is set so that it can be divided by the width D to automatically set the small and medium extracted data 38 and 39, on the contrary, the smallest extracted data By setting 39,
This may be multiplied by a width d to automatically set the large and medium extraction data 37, 38. The width d may be variable.

After setting the time gates T _{1 to} T ₃ ,
The data analysis processing unit 40 of the ultrasonic testing data evaluation apparatus main body 30 extracts the extracted data 37 to 39 of the ultrasonic testing data 29.
The parts of are analyzed in order.

As a concrete method of the analysis processing, the extracted data 37 to 39 are frequency-analyzed by an integral transform method using a trigonometric function called a fast Fourier transform, and the energy intensity of each frequency of the extracted data 37 to 39 is analyzed. To obtain the two-dimensional data. On this occasion,
Since the frequency analysis is performed on the entire extracted data 37 to 39, the concept of time disappears from the two-dimensional data. The two-dimensional data is extracted data 37 to 3
For each 9, the above a, b, c, d, and e positions are superposed to form three pseudo three-dimensional data.

Further, in the data analysis processing unit 40, for convenience of the processing in the subsequent stage, the data analysis processing unit 40 performs normalization so that the energy intensity in the analysis data 41 to 43 is represented by a value between 0 and 1.

When a plurality of pieces of analysis data 41 to 43 are obtained in this way, the ultrasonic flaw detection data evaluation apparatus main body 30 determines the analysis data 41 to 43 by the determination unit 44 such as a neural network.

Here, the neural network 44 was developed in order to realize the excellent information processing capability of the human brain in an engineering manner.
9 are constructed.

The neuron 49 is an input Si (0 ≦ S
i ≦ 1, i = 1 to n) and a weighting factor Wi (excitability when Wi ≧ 0, inhibitory property when Wi <0, i = 1 to n)
And the threshold value θ, the internal state u is u = ΣWi ·
It is defined by Si-θ, and this internal state u is output function f
By substituting (x) = 1 / {1 + exp (-x / t)}, the following output can be obtained (see FIG. 10).

[0070]

## EQU00002 ## f (u) = 1 / {1 + exp (-u / t)}

Note that t is a positive constant (normally 1.0) called the temperature of the neuron 49.

The output function f (x) is called a sigmoid function, and is a function whose value changes non-linearly from 0 to 1 while the value of x changes from − to + (0 ≤ f
(X) ≦ 1, see FIG. 11.).

Then, the neural network 44 is constructed by combining a plurality of the neurons 49. There are various types of neural networks 44 such as a mutual type and a hierarchical type. In this case, the hierarchical neural network 44 is used. As shown in FIG. 3, the hierarchical neural network 44 is formed by connecting neurons 49 to have layers such as an input layer 48, an intermediate layer 51, and an output layer 52, and each layer has one or more layers. Neurons 49 are composed of neurons 49, and neurons 49 in the same layer are not connected to each other, and
Each neuron 49 in the lower layer is connected to all neurons 49 in the upper layer.

Further, the input layer 48 has the frequencies and the positions a, b, c, d, e in the plurality of analysis data 41 to 43.
Lattice points 53 set on a plurality (three) coordinates of and
Is composed of the same number of neurons 49 as the
Is composed of one or more layers of neurons 49 (one layer in the figure), and the output layer 52 is composed of two neurons 49a and 49b.

Furthermore, the neural network 44 is learned in advance by setting parameters such as the weighting coefficient Wi and the threshold value θ for each neuron 49.

As the learning method, first, each parameter such as the weighting factor Wi and the threshold value θ is randomly set using the input device 31 such as a keyboard to initialize the neural network 44, and the teaching data 50 is stored therein. Input and generate an output, calculate an error between the output from the neural network 44 and the actual result of the teaching data 50,
Using the error backpropagation learning method in which the parameters are adjusted / changed for each layer while propagating the error from the output layer 52 to the intermediate layer 51 and from the intermediate layer 51 to the input layer 48, a large number of teachings are given for the work. Repeat for data 50.

At this time, the two neurons 4 in the output layer 52
If the outputs of 9a and 49b are defective (1.0 to 0.7,
0.0-0.3), if unknown (0.7-0.3, 0.
3 to 0.7), if it is not a defect (0.3 to 0.0, 1..
0 to 0.7).

In the fully learned neural network 44, the output of each neuron 49 can be obtained only by inputting the energy intensity at the corresponding grid point 53 to each neuron 49 constituting the input layer 48. It is calculated one after another and the correct judgment result is automatically derived.

In this way, the neural network 44
By using, unlike fuzzy and AI,
It becomes possible to make a correct decision even from a waveform pattern that is difficult to rule.

Since the learning content is distributed and stored in each parameter, the neural network 44 itself is made into a black box, but a more accurate determination result is expected by performing more learning. become able to.

Further, the judgment result thus obtained is also learned by the neural network 44.

The determination result is displayed on the display device 33.
Further, it may be stored in an external storage device (not shown) or the like, if necessary.

As described above, according to the present invention, the ultrasonic flaw detection data evaluation apparatus main body 30 includes the time gate setting section 36, the large gate setting section 45, the middle gate setting section 46, and
The small gate setting unit 47 is provided, and the operator uses the pointing device 32 such as a mouse or a tablet to set the vicinity of the peak value of the ultrasonic flaw detection data 29 as the center position T ₀ as shown in FIG. Expanded backward by equal width d, for example, three large, medium and small extracted data 37-
Since 39 are extracted, these extracted data 37 to 39 can be extracted without setting an optimum time gate.
Therefore, it becomes possible to obtain a highly accurate determination result using the neural network 44.

The present invention is not limited to the above-mentioned embodiment, and the object to be inspected is not limited to the pipe.
It is possible to apply three or more time gates for the same ultrasonic flaw detection data, but if too many time gates are applied, the calculation speed will decrease, but the accuracy will not improve. Needless to say, various changes can be made without departing from the scope of the present invention.

[0085]

As described above, according to the ultrasonic flaw detection data evaluation apparatus of the present invention, it is possible to obtain an excellent effect that a more accurate determination result can be obtained while facilitating the setting of the time gate. .

[Brief description of the drawings]

FIG. 1 is a schematic system diagram inside an ultrasonic testing data evaluation apparatus main body according to an example of an embodiment of the present invention.

FIG. 2 is a graph showing ultrasonic flaw detection data to be determined.

FIG. 3 is a system diagram showing a neural network part.

FIG. 4 is a schematic system diagram of an ultrasonic testing data evaluation apparatus main body under development.

FIG. 5 is a schematic system diagram inside the ultrasonic testing data evaluation apparatus main body.

FIG. 6 is a partial lateral cross-sectional view showing a method of ultrasonic inspection of a tube.

FIG. 7 is a graph showing ultrasonic flaw detection data to be determined.

FIG. 8 is a diagram showing typical analysis data when there is stress corrosion cracking.

FIG. 9 is a diagram showing typical analysis data when there is no stress corrosion cracking.

FIG. 10 is a diagram showing a model of a neuron.

FIG. 11 is a graph showing a sigmoid function.

FIG. 12 is a system diagram showing a neural network part.

[Explanation of symbols]

24 Inspection Object (Pipe) 25 Welding Part 26 Ultrasonic Testing Device 29 Ultrasonic Testing Data 30 Ultrasonic Testing Data Evaluation Device Main Body 34 Data Input Section 36 Time Gate Setting Section 37-39 Extraction Data 40 Data Analysis Processing Section 41-43 Analysis data 44 Judgment unit (neural network) 45 Large gate setting unit 46 Medium gate setting unit 47 Small gate setting unit T _{1 to} T ₃ Time gate T ₀ Center position width

Claims (3)

[Claims] 1. A data input unit for receiving input of ultrasonic flaw detection data obtained from an object to be inspected, and a time gate setting unit for applying a time gate to the input ultrasonic flaw detection data to extract a plurality of extracted data. A data analysis processing unit that analyzes a plurality of extracted data extracted by the time gate setting unit by Fourier transform, and a neural network that determines whether there is a defect based on each analysis data analyzed by the data analysis processing unit. An ultrasonic flaw detection data evaluation apparatus, comprising an ultrasonic flaw detection data evaluation apparatus main body including a determination unit using a network. 2. The time gate setting unit extracts three large, medium, and small extracted data that are spread by equal widths in the front and rear with the vicinity of the peak value of the ultrasonic flaw detection data as a center position and do not intersect each other. The ultrasonic flaw detection data evaluation apparatus according to claim 1, further comprising a large gate setting unit, a medium gate setting unit, and a small gate setting unit. 3. The ultrasonic flaw detection data evaluation apparatus according to claim 1, wherein the ultrasonic flaw detection data evaluation apparatus main body is integrated with an ultrasonic flaw detection apparatus for collecting ultrasonic flaw detection data from an object to be inspected.