JPH0980034A - Discrimination apparatus for underground buried object - Google Patents

Abstract

PROBLEM TO BE SOLVED: To obtain a discrimination apparatus by which the kind of an underground buried object is discriminated stably, with high accuracy and at high speed. SOLUTION: A probe 28, for vibration application, of an oscillating device 21 and a probe 32, for vibration reception, of a vibration receiving device 22 are inserted into the ground 34 until they come into contact with a buried object 35. A shock is given to the probe 28 for vibration application. A vibration is given to the buried object 35. Elastic waves which are generated at the buried object 35 are received by the probe 32 for vibration reception. In a signal processing circuit 23, a split response signal as a discrimination signal which is used to discriminate the kind of the underground buried object is created from an elastic-wave signal based on the received elastic waves. In a discrimination circuit 24, the kind of the underground buried object expressed by the split response signal is discriminated on the signal. A discriminated result is displayed on a display device 26.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a device for identifying an underground buried object, which is capable of identifying the type of the underground buried object with stable and high accuracy by utilizing elastic waves peculiar to a substance.

[0002]

2. Description of the Related Art Conventionally, as a method for detecting an underground buried object,
A method using electromagnetic waves, ultrasonic waves, etc. is adopted. These methods send electromagnetic waves from the ground surface into the ground and detect reflected waves or refracted waves at the underground buried object.The buried position and size of the underground buried object are detected. You can get information. However, these methods cannot obtain information such as the material for identifying the type of the underground buried object.

Although it is possible to detect an underground buried object by a metal detector using magnetism or the like,
In this case, the underground buried objects that can be detected are only those made of metal, and those made of, for example, plastic or glass cannot be detected.

Further, as a conventional technique for identifying the type of the buried object, the operator himself / herself depends on the feel of the probe when it penetrates into the ground and the vibration of the probe and the sliding condition of the probe. There is a way to identify. However, in this case
Since the identification accuracy is determined by the subjectivity of the operator, it is difficult to stably identify the type of buried object. In addition, since the judgment is performed by a person, it takes time and hinders labor saving and labor saving of the identification work. In order to eliminate such inconvenience, objective identification using a recognition device as shown below can be considered.

FIG. 10 is a block diagram showing the structure of a pattern recognition apparatus 71 which is a typical conventional example. Input patterns such as images and sounds are given to the feature extraction means 72. The feature extraction unit 72 extracts a feature amount that characterizes the input pattern from the input pattern. The feature amount is, for example, in the case of an image, the essential information used to identify the image pattern more simply and to be described later. The feature vector having the extracted feature amount as an element is given to the identifying unit 73.

The discriminating means 73 calculates and outputs a category vector expressing which category of the plurality of predetermined categories the input pattern belongs to, based on the inputted feature vector. The identification unit 73 is realized by a neural network in which the relationship between the feature vector and the category vector has been learned in advance. The calculated category vector is given to the identification result determination means 74.
The discrimination result determining means 74 determines the category to which the input pattern belongs, based on the given category vector,
Output as the identification result. The identification result is given to the output means 75. The output means 75 is realized by a display device such as a CRT (cathode ray tube) and outputs (notifies) the identification result to the outside (operator).

The neural network used for the identifying means 73 is, for example, a back propagation neural network (hereinafter
(Abbreviated as "BPNN") is used. This BPNN
For more information, see `` NATURE vol.323 9 p536-553 (Oct 1986).
Learning Representations by backpropagationerror
s ".

The BPNN consists of an input layer, an output layer, and one or more intermediate layers, each of which is composed of a plurality of node groups. In the identification by the neural network, for example, in the case of a general configuration in which each node in the output layer of the neural network is in a one-to-one correspondence with the category to be identified, the maximum value is output among the plurality of nodes forming the output layer. The category corresponding to the active node is used as the identification result.

[0009]

The conventional technique for detecting a reflected wave or a refracted wave using electromagnetic waves or the like has a problem that it is impossible to specify the type of the underground buried object. Further, in the case of identification by the feel when the probe penetrating into the ground is shaken or the sliding condition of the probe, the operator determines the type of the buried object 14 as described above. If they are different, the identification accuracy will be different, and it will be difficult to perform stable identification. In addition, since the judgment is performed by a person, it takes time and hinders labor saving and labor saving of the identification work.

Further, in the case of the identification using the pattern recognition device 71, although the inconvenience of the above-mentioned operator identification is eliminated, what kind of data should be input as the input pattern is optimum. It is not clear what the specific method will be.

An object of the present invention is to provide a device for identifying an underground buried object, which can identify the type of a buried object with stable high accuracy and at high speed.

[0012]

SUMMARY OF THE INVENTION The present invention has an oscillating means having a vibrating probe that is inserted into the ground until it comes into contact with the ground buried object, and vibrates the ground buried object. A vibration-reception probe having a vibration-receiving probe that is inserted into the ground until it comes into contact with a buried object, and receives an elastic wave generated by the oscillation means vibrating the buried object and outputs it as an elastic-wave signal. Means, signal processing means for creating an identification signal for identifying the type of the underground buried object from the elastic wave signal output by the vibration receiving means, and the underground buried object represented by the identification signal based on the identification signal The input layer having a plurality of input parts, the output layer having the number of output parts corresponding to the type of the underground buried object, the input layer and the output. A neuron consisting of one or more intermediate layers interposed between the layers Includes a network, said signal processing means, as the identification signal, the acoustic wave signal analog /
A frequency response signal is created by performing a Fourier transform after digital conversion, and the divided response signal obtained by dividing the frequency response signal for each of a plurality of frequency bands is applied to each of the plurality of input units of the input layer of the neural network. This is a device for identifying underground buried objects. According to the present invention, the vibrating probe of the oscillating means and the vibrating probe of the vibrating means are inserted into the ground until they come into contact with the underground buried object, and the vibrating probe of the oscillating means is used. To give a vibration to the underground buried object, and to receive the elastic wave generated in the underground buried object through the vibration receiving probe of the vibration receiving means. An identification signal for identifying the type of the underground buried object is created from the elastic wave signal based on the received elastic wave, and the type of the underground buried object represented by the identification signal is identified based on the created identification signal. . The elastic wave generated in the underground buried object is
It is unique to the underground buried object, and thus it is possible to identify the type of the underground buried object as described above. The method of identifying an underground buried object as described above is performed using an apparatus for identifying an underground buried object that includes an oscillating means, a vibration receiving means, a signal processing means, and an identifying means. The signal processing means creates the identification signal, and the identification means identifies the type of the underground buried object represented by the identification signal based on the identification signal created by the signal processing means. The identification means includes an input layer having a plurality of input parts, an output layer having a number of output parts corresponding to the type of the underground buried object, and one or more interposed between the input layer and the output layer. And a neural network including an intermediate layer of the neural network, the signal processing means applies the following signals as the identification signals to a plurality of input sections of the input layer of the neural network. That is, the signal processing means is
The elastic wave signal is subjected to analog / digital conversion and then Fourier transform to create a frequency response signal, and the divided response signal obtained by dividing the frequency response signal into a plurality of frequency bands is applied to a plurality of input units. The divided response signal is an identification signal. Since the type of underground buried object is identified by the above-mentioned method using such an underground buried object identifying device, compared to identifying the type of underground buried object by hand as in the prior art, It enables stable and highly accurate identification. In addition, the time required for identification can be shortened, and labor and labor can be saved. Furthermore, by using a plurality of oscillation and vibration receiving means, it becomes possible to identify a large number of underground buried objects at one time, and the identification efficiency can be further improved. Further, by using the neural network, it is relatively easy to change the number of input data to the input layer and the number of output data from the output layer.

The identifying means of the present invention is a determining means for determining the type of underground buried object based on the output signal level output from the output section of the output layer of the neural network for each type of underground buried object. It is characterized by including. According to the invention, the identifying means includes a determining means, and determines the type of the underground buried object based on an output signal level output from the output unit of the output layer of the neural network for each type of the underground buried object. . Therefore, it is possible to further improve the identification accuracy.

Further, the present invention is characterized by including an output means for outputting the identification result of the identification means. According to the invention, the device for identifying an underground buried object includes an output means, and outputs an identification result of the identification means. Therefore, the operator
The identification result of the identification means can be known.

Further, the output means of the present invention is a display means for displaying the identification result of the identification means. According to the invention, the device for identifying an underground buried object includes an output means, and outputs an identification result of the identification means. The output means is realized by a display means, for example. Therefore,
The operator can know the identification result of the identification means.

The vibrating probe and the vibrating probe of the present invention are the same probe. According to the invention, the vibrating probe and the vibrating probe are realized by the same probe. Therefore, it is only necessary to insert one probe into the ground, and the work can be simplified.

Further, the present invention includes storage means for sequentially storing the elastic wave signals output by the vibration receiving means, and the identification means is stored in the storage means when the identification result by the identification means is incorrect. The elastic wave signal is read, and the neural network included in the identification means is learned using the read elastic wave signal. According to the invention, the identification device for the underground buried object includes a storage means for sequentially storing the elastic wave signals output by the vibration receiving means, and the identification means is provided when the identification result by the identification means is incorrect. The elastic wave signal stored in the storage means is read, and the neural network included in the identification means is learned by using the read elastic wave signal. Therefore, even if incorrect identification is performed, correct identification can be performed from the next time, and the identification performance is further improved.
In addition, the identification performance can be easily improved.

[0018]

1 is a block diagram showing an identification device 27 for an underground buried object according to an embodiment of the present invention. The identification device 27 includes an oscillation device 21, a vibration receiving device 22, a signal processing circuit 23, an identification circuit 24, a display processing circuit 25, a display device 26, and a database circuit 43.

The oscillating device 21 includes a vibrating probe 28, a hammer 29, a motor 30, and a spring 31. On the one end side of the vibration probe 28, the vibration probe 2 is provided by a spring 31.
A spring-biased hammer 29 is arranged in parallel with the longitudinal direction (vertical direction) of 8. When the hammer 29 is dropped downward after the motor 30 is driven by the hammer drive circuit 30a to pull up the hammer 29 upward, the hammer 29 gives an impact to the vibrating probe 28.

The other end of the vibrating probe 28 has a buried object 35.
The impact applied as described above by the hammer 29 becomes a damping vibration, propagates through the vibrating probe 28, and is transmitted to the buried object 35 until it comes into contact with the.
In the buried object 35 to which the vibration is transmitted, an elastic wave peculiar to the substance is generated. The vibrating probe 28 is inserted at an angle of, for example, 30 ° to 45 ° with respect to the ground surface, and is 0.1 kg.
Vibration is applied with a weight of ~ 0.3 kg.

The vibration receiving device 22 includes a vibration receiving probe 32 and a sensor 33. A sensor 33 is attached to one end of the vibration receiving probe 32. The other end of the vibration receiving probe 32 is inserted into the ground 34 until it abuts on the buried object 35. The elastic wave generated in the buried object 35 as described above is
The vibration is received by the vibration receiving probe 32, propagates through the vibration receiving probe 32, and is converted into an elastic wave signal by the sensor 33. The elastic wave signal is input to the signal amplifier 36 of the signal processing circuit 23, the database circuit 43, and the display processing circuit 25.

The signal processing circuit 23 includes a signal amplifier 36, A
/ D converter 37, waveform storage circuit 38, FFT operation circuit 3
9 and an input vector generation circuit 40. The signal processing circuit 23 creates an identification signal for identifying the underground buried object from the received elastic wave. That is, the elastic wave signal converted by the sensor 33 is input to the signal amplifier 36 and amplified. Further, if necessary, unnecessary signals are removed by using a filter included in the signal amplifier 36. The signal processed by the signal amplifier 36 is A /
The signal is input to the D (analog / digital) converter 37, converted into a digital signal, further input to the waveform storage circuit 38, and stored as a time axis response signal.

The time axis response signal stored in the waveform storage circuit 38 is Fourier transformed by an FFT (Fast Fourier Transform) calculation circuit 39 to create a frequency response signal. The generated frequency response signal is divided by the input vector generation circuit 40 into a plurality of frequency bands to generate divided response signals. For example, a signal in the frequency band of 20 Hz to 5 kHz is divided into a range of 10 to 100. For example, it is divided into 50. These divided signals are learned in advance, divided by the maximum value of each component in the data stored in the database circuit 43, and normalized to a value of 0 to 1. The divided response signal thus created is the identification signal.

The identification circuit 24 includes a neural network 41 and an output vector determination circuit 42. As the neural network 41, for example, B
PNN is used. The division response signal from the input vector generation circuit 40 is input to the neural network 41, an output signal for each type of underground buried object is created based on the division response signal, and is provided to the output vector determination circuit 42. The output vector determination circuit 42 determines the type of underground buried object based on the output signal level from the neural network 41.

The waveform storage circuit 38, the FFT operation circuit 39,
Input vector generation circuit 40, neural network 4
1 and the output signal from the output vector determination circuit 42 is
The image is processed by the display processing circuit 25 and displayed on the display device 26 realized by, for example, a liquid crystal display device.

FIG. 2 is a diagram showing a schematic configuration of the neural network 41 of the discrimination circuit 24. The neural network 41 is the BPNN, and the input layer 4
4, the intermediate layer 45 and the output layer 46. The input layer 44 is composed of a plurality of nodes NI1 to NIm. The intermediate layer 45 has a structure of one or a plurality of layers, and each layer is composed of a plurality of nodes NM. In this embodiment, the intermediate layer 45 is one layer, and the intermediate layer 45 includes a plurality of nodes NM.
1 to NMp. The output layer 46 is composed of a plurality of nodes NO1 to NOn.

The number of nodes constituting the input layer 44 and the output layer 46 is determined according to the number of input data and the number of data to be output. That is, the number of nodes NI that make up the input layer 44 corresponds to the number of divided response signals created by the input vector generation circuit 40. Further, the number of node NOs configuring the output layer 46 corresponds to the number of types of buried objects. For example, the number of nodes NI is 50
In addition, the number of nodes NO is selected to be 4, and the number of nodes NM forming the intermediate layer 45 is empirically selected to be 20.

For the learning of the neural network 41, the data of the elastic wave signal and the type of the underground buried object stored in the database circuit 43 in advance are used. The category vector corresponding to the type of underground buried object represents the type to be identified by the state of the node NO of the output layer 46 of the neural network 41. There is a one-to-one correspondence between the node NO of the output layer 46 and the category to be identified. For example, when learning the category corresponding to the node NOn of the output layer 46, the node NI of the input layer 44 is
1 to NIm are respectively given predetermined feature vectors, and category vectors of Ci (i = n) = 1 and Ci (i ≠ n) = 0 are given to the nodes NO1 to NOn of the output layer 46 as teacher signals.

FIG. 3 is a diagram for explaining a determination method in the output vector determination circuit 42 of the identification circuit 24. Description will be made assuming four types of embedded objects, A to D. Therefore, the output layer of the neural network 41 is composed of four nodes NO1 to NO4, and four output signals corresponding to the types A to D are output from the neural network 41 and input to the output vector determination circuit 42. . At this time, the one with the maximum output signal level is selected as the identification candidate. In the output vector determination circuit 42,
Two thresholds T1 and T2 (T1> T2) are set in advance.

As shown in FIG. 3 (1), the output signal level is the maximum, the signal level of B selected as an identification candidate is T1 or more, and the signal levels of A, C, and D are T.
If it is 2 or less, B as the identification candidate is adopted as the type of the buried object. As shown in FIG. 3 (2), when the signal level of B is T2 or more and T1 or less and the signal levels of A, C, D are T2 or less, or as shown in FIG. 3 (3). If the signal level of B is T1 or higher, A, C, D
In any of the above, for example, when A is T2 or more, B as an identification candidate is rejected.

The thresholds T1 and T2 are selected empirically. For example, when four output signal levels are close to each other, if T1 and T2 are set to values having a relatively small difference near the output signal level, the selected identification candidate can be adopted, and T1 and T2 can be set to the difference. When set to a large value, the selected identification candidates are rejected. T1 and T2 are set according to desired identification accuracy. For example, assuming that the maximum value of the output signal level is 1, T1 = 0.7 and T2 = 0.3 are set.

FIG. 4 is a diagram showing the configuration of the display screen 47 displayed on the display device 26. The display screen 47 includes a time waveform display area 48 and frequency spectrum display areas 49, 5
0, an input vector display area 51, a neural network configuration display area 52, an output vector display area 53, and an embedded object name display area 54.

In the time waveform display area 48, a waveform based on the time axis response signal from the waveform storage circuit 38 is displayed, for example, a waveform for 0 to 50 msec is displayed. A spectrum based on the frequency response signal from the FFT calculation circuit 39 is displayed in the frequency spectrum display areas 49 and 50. In one frequency spectrum display area 49, for example, a spectrum between 0 and 20 kHz is displayed, and in the other frequency spectrum display area 50, for example, 20H.
The spectrum between z and 5 kHz is displayed logarithmically.

In the input vector display area 51, a graph based on a plurality of divided response signals from the input vector generation circuit 40, that is, an input vector input to the neural network 41 is displayed. In the neural network configuration display area 52, the configuration of the neural network 41 described above is displayed. Output vector display area 53
, The output vector from the neural network 41 is displayed, for example, as a bar graph. In the embedded object name display area 54, a name indicating the type of embedded object determined by the output vector determination circuit 42 is displayed.

FIG. 5 is a flowchart showing a method of identifying and learning a buried object. FIG. 6 is a diagram showing an example of the display screen 47. In step a1, the elastic wave signal received by the vibration receiving device 22 is input to the signal amplifier 36 of the signal processing circuit 23, converted into a digital signal by the A / D converter 37, and is stored in the waveform storage circuit 38 as a time axis response signal. Remembered. In step a2, the waveform storage circuit 38
The time-axis response signal stored in the FFT calculation circuit 39 is Fourier-transformed to create a frequency response signal. Further, the input vector generation circuit 40 creates a plurality of divided response signals. In step a3, the received elastic wave signal is stored in the database circuit 43. By storing in the database circuit 43, it becomes possible to re-learn the neural network when an incorrect identification is made.

At step a4, it is judged whether or not the discrimination mode is set. If it is the identification mode, step a5
If it is not the identification mode but the learning mode, the process proceeds to step a9. In step a5, the divided response signal generated by the input vector generation circuit 40 is input to the neural network 41 and subjected to neural network identification processing. In step a6, the output signal from the neural network 41 is input to the output vector determination circuit 42 and subjected to the discrimination result determination processing. In step a7, the display screen 47 shown in FIG. 6, for example, is displayed on the display device 26.

At step a8, it is judged whether or not the processing is completed, and if not completed, the processing returns to step a1.

In step a9 when the learning mode is set in step a4, the elastic wave signal stored in the database circuit 43 in step a3 is read out and used for learning the neural network 41. .

In step a10, the neural network 41 learns the relationship between the read elastic wave signal and the type of the corresponding buried object. When the learning process ends, the process returns to step a8.

The learning mode can be executed before the discrimination is performed and also when the discrimination is performed and the result of the discrimination is erroneous. An error in the identification result is judged by the operator. By operating the learning mode in this way, the discrimination ability can be further improved.

7 and 8 are graphs showing an example of elastic waves for each type of buried object. 7 (1), (3),
(5), (7) and FIGS. 8 (1), (3), (5),
(7) is a graph showing the relationship between elastic wave intensity and time, and is shown in FIGS. 7 (2), (4), (6), (8) and FIG.
(2), (4), (6) and (8) are graphs showing the relationship between elastic wave intensity and frequency. (1) and (2) of FIGS. 7 and 8 show (3), when the buried object is a metal piece.
(4) is a piece of plastic, (5) and (6) are pieces of stone, and (7) and (8) are pieces of wood. FIG. 7 shows the case where the soil is dry loamy soil, and FIG. 8 shows the case where the soil is wet sand.

From the frequency spectra of FIGS. 7 and 8,
It can be seen that there are response characteristics peculiar to the substance. It can also be seen that the influence of the measurement conditions is small. Furthermore, it has been confirmed that the reproducibility is also excellent. from these things,
It can be seen that it is possible to stably and accurately identify the type of underground buried object using elastic waves.

FIG. 9 shows an oscillating device 21 and a vibration receiving device 22.
FIG. 11 is a block diagram showing an oscillation / vibration receiving device 55 which is another example of FIG. The oscillating / vibrating device 55 uses the vibrating probe 28 of the oscillating device 21 and the vibrating probe 32 of the vibrating device 22 as the same probe.
6, a motor 57, a spring 58, a sensor 59, and a vibrating / vibrating probe 60. The damped vibration generated by the impact applied to the probe 60 by the hammer 56 and the motor 57 in the same manner as the oscillation device 21 propagates through the excitation / vibration probe 60 and is transmitted to the buried object 35. The elastic wave generated in the embedded object 35 is received by the vibration / vibration probe 60, propagates through the vibration / vibration probe 60, and is converted into an elastic wave signal by the sensor 59. The elastic wave signal is input to the signal amplifier 36.

As described above, according to the present embodiment, it becomes possible to perform identification with stable and high accuracy as compared with the case where the operator identifies the type of the buried object as in the prior art.
In addition, the identification can be performed in a short time, and labor and labor can be saved.

Further, when the neural network 41 is used, the number of input data to the input layer 44 and the output layer 4
It is relatively easy to change the number of output data from 6. In addition to the divided response signal as input data to the input layer 44 of the neural network 41, geological conditions (for example, insertion force of the probe, soil density, etc.) and measurement conditions (for example, insertion angle of the probe, insertion depth, etc.) It is possible to further improve the identification accuracy by inputting the data representing (). Although the example of the BPNN has been described in the present embodiment, the same effect can be obtained by using, for example, a nonlinear function other than the sigmoid function or any neural network other than the BPNN.

Further, by making a decision based on the output signal level from the neural network 41 in the output vector decision circuit 42, it is possible to improve the identification accuracy. If the output vector determination circuit 42 is not provided, for example, the type of underground buried object is determined by the output signal from the neural network 41 having the maximum output signal level.

Further, since the identification status is displayed step by step on the display device 26, the operator can know the identification result and further know the process of the identification process. In addition to the display on the display device 26, an example of providing an informing means for emitting a buzzer sound when the identification result is a desired type of buried object, and an example of flashing (flashing) with a warning light are also included in the present invention. It belongs to the range.

Further, by using the oscillation / vibration receiving device 55, only one probe needs to be inserted into the ground, and the work can be simplified.

[0049]

As described above, according to the present invention, it is possible to identify the type of an underground buried object with stable and high accuracy in a short time, and to save labor and labor. It will be possible. Also, using a neural network
It is relatively easy to change the number of input data to the neural network and the number of output data from the neural network. Further, by providing the judging means, the identification accuracy is improved. Furthermore, the operator can know the identification result by outputting the identification result. further,
By making the vibration probe and the vibration probe the same probe, the work can be simplified. Further, even if incorrect identification is performed, by learning the neural network, correct identification can be performed from the next time, and the identification performance is further improved.

[Brief description of drawings]

FIG. 1 is a block diagram showing an identification device 27 of an underground buried object according to an embodiment of the present invention.

FIG. 2 is a diagram showing a schematic configuration of a neural network 41 of a discrimination circuit 24.

FIG. 3 is a diagram for explaining a determination method in an output vector determination circuit 42 of the identification circuit 24.

4 is a diagram showing a configuration of a display screen 47 displayed on the display device 26. FIG.

FIG. 5 is a flowchart showing a method for identifying and learning an underground buried object.

FIG. 6 is a diagram showing an example of a display screen 47.

FIG. 7 is a graph showing an example of elastic waves of a buried object.

FIG. 8 is a graph showing an example of elastic waves of a buried object.

9 is a block diagram showing an oscillating / vibrating device 55. FIG.

FIG. 10 is a typical prior art pattern recognition device 71.
FIG. 3 is a block diagram showing the configuration of FIG.

[Explanation of symbols]

 21 oscillator device 22 vibration receiving device 23 signal processing circuit 24 identification circuit 26 display device 27 identification device for underground buried object 28 vibration probe 29 hammer 32 vibration receiving probe 33 sensor 34 underground 35 buried object 36 signal amplifier 37 A / D (analog / digital) converter 38 Waveform memory circuit 39 FFT operation circuit 40 Input vector generation circuit 41 Neural network 42 Output vector determination circuit 43 Database circuit 44 Input layer 45 Intermediate layer 46 Output layer 55 Oscillation / vibration device 60 Excitation・ Vibration probe

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Nobuhiro Shimoi 3-23-4 Tsukushino, Machida City, Tokyo (72) Inventor Masahiko Kano 1-18-32 Fuchinobe Sagamihara City, Kanagawa Prefecture A-302 (72) Inventor Makino Tatsuo, 1 Kawasaki-cho, Kakamigahara-shi, Gifu Kawasaki Heavy Industries Ltd., Gifu factory (72) Inventor Masayoshi Uno, 1 Kawasaki-cho, Kakamigahara-shi, Gifu Prefecture Kawasaki Heavy Industries, Ltd. Gifu factory (72) Inventor, Kimura Chino Kagami 1 Kawasaki-cho, Ichi Kawasaki Heavy Industries Gifu factory

Claims (6)

[Claims] 1. An oscillating means having a vibrating probe that is inserted into the ground until it comes into contact with an underground buried object, and an oscillating means for vibrating the underground buried object, and a ground until coming into contact with the underground buried object. A vibrating means having a vibrating tip inserted therein, the vibrating means vibrating an elastic wave generated by vibrating the buried object and outputting as an elastic wave signal; and the vibrating means outputs Signal processing means for creating an identification signal for identifying the type of the underground buried object from the elastic wave signal, and identification means for identifying the type of the underground buried object represented by the identification signal based on the identification signal The identifying means is interposed between the input layer having a plurality of input parts, the output layer having a number of output parts corresponding to the type of the underground buried object, and the input layer and the output layer. Including a neural network consisting of one or more intermediate layers As the identification signal, the signal processing means performs analog / digital conversion of an elastic wave signal and then Fourier transforms the frequency response signal to create a frequency response signal. An apparatus for identifying an underground buried object, which is applied to each of a plurality of input sections of an input layer of a neural network. 2. The identifying means includes determining means for determining the type of the underground buried object based on the output signal level output from the output unit of the output layer of the neural network for each type of the underground buried object. The identification device for an underground buried object according to claim 1, characterized in that. 3. The apparatus for identifying an underground buried object according to claim 1, further comprising output means for outputting the identification result of the identification means. 4. The output means is a display means for displaying the identification result of the identification means.
The device for identifying underground buried objects. 5. The apparatus for identifying an underground buried object according to claim 1, wherein the vibration probe and the vibration probe are the same probe. 6. The elastic wave signal stored in the storage means is included when the identification means has an erroneous identification result. The apparatus for identifying an underground buried object according to claim 1, wherein a signal is read out and the neural network included in the identification means is learned by using the read elastic wave signal.