JP2837003B2 - Laser work monitoring device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a monitoring apparatus used for diagnosing a laser operation such as welding of a laser welding machine and cutting of a laser cutting machine.

[0002]

2. Description of the Related Art Conventionally, in order to monitor the state of circumferential laser welding, for example, in which a sleeve is inserted into the inner peripheral surface of a heat transfer tube of a steam generator for repair, the welding state is monitored by six monitor signals. The monitoring is performed, each monitor signal is separately processed and displayed, and the operator monitors and determines whether welding is good or not.

FIG. 16 is a functional block diagram showing the above-described conventional apparatus.
For example, a sleeve of a heat transfer tube of a steam generator is repaired by welding, a laser welding portion 100 to be welded is monitored, and a YAG (Yttrium Aluminum Garnet) laser is provided to each channel of the monitor signal input means 300. Oscillator laser output signal, green laser signal representing the emission intensity of 0.8 μm wavelength emitted from the weld, blue laser signal representing the emission intensity of 0.94 μm wavelength emitted from the weld, reflected light of the YAG laser , A purple laser signal representing the intensity of the 1.06 μm wavelength, a welding speed signal, and a load ratio signal of the welding feed motor. When the monitor signal input means 300 converts these monitor signals to be monitored into digital signals and sends them to the monitor signal processing means 400, the monitor signal processing means 400 outputs all the signals sampled in one laser welding operation. A process of converting each monitor signal into a deviation value when the average value is 50, that is, a normalization process is performed to obtain monitor data. This monitor data is displayed on the display means 500 and, if desired, the printing means 600.
Is printed.

[0004] The operator operates display means 50 such as a cathode ray tube.
Looking at the screen 0 or the output tape of the printing means 600, the monitoring / judgment of the normal / abnormal state of the welded portion is performed based on the change of the monitor signal such as the laser output described above.

[0005]

As is well known, spatter adheres to a nozzle that blows out a blocking gas for protecting a welding tool from spatter generated from the welding part, and the blocking gas is disturbed when the welding part is abnormal. Abnormalities (sputter adhesion abnormalities), abnormalities caused by the laser output being greatly attenuated in the middle of the oscillator or optical system (laser output attenuation abnormalities), and uniformity due to the eccentric rotation of the welding tool axis. Welding failure (tool eccentricity failure), welding tool position detector or motor failure and uneven welding speed (welding speed fluctuation error), welding tool optical system lens, There are abnormalities (damage of optical system) due to damage of the mirror and the like and interruption of the laser beam, and abnormalities (mirror abnormality) due to mirror displacement of the optical system. The operator is required to appropriately judge these abnormalities and their types or causes.However, since the judgment requires skill, it takes a long time to identify the abnormalities, and the welding work efficiency is not improved. Rather, it required a considerable amount of training time for skill, and improvements were desired.

[0006] In particular, laser welding is applied to high-precision welding because a thin plate structure can be joined with high accuracy by adjusting the focal position of a laser beam without giving deformation such as welding distortion. In the case of laser welding, since the difference in characteristics including the habit of the welding tool affects the quality of welding,
Human judgment was even more difficult.

Accordingly, it is an object of the present invention to allow an unskilled person to easily judge an abnormality in a laser working condition, and to make a normal / abnormal judgment with certainty and to easily identify the type of abnormality. It is an object of the present invention to provide a monitoring device for laser operation.

[0008]

In order to achieve the above object, a laser operation monitoring apparatus according to the present invention comprises a monitor data storage means for storing monitor data for monitoring, and a monitor data from the monitor data storage means. The first normal / normal condition for discriminating between normal and abnormal work conditions with a relatively low verification rate
Abnormality determination means; and second normal / abnormality determination means for further determining the work state at a relatively high verification rate when the work state is determined to be abnormal by the first normal / abnormality determination means. An abnormality identification unit for identifying the type of abnormality when the result of the determination by the second normal / abnormality identification unit is a work condition abnormality; and monitor data of a normal operation that has been tried in advance and is connected to the monitor data storage unit. It is characterized in that it comprises a normal norm learning means for learning normal norm data, and an abnormal norm learning means connected to the monitor data storage means and learning the abnormal norm data from monitor data of a previously performed abnormal work.

[0009]

In the present invention, the operator uses the normal or abnormal monitor data of the laser operation stored in the monitor data storage means to set the normal or abnormal norm by the normal norm learning means or the abnormal norm learning means. Train the device. Also,
Whether the monitor signal to be newly determined is normal or abnormal is determined by the first normal / abnormal determining means having a relatively low verification rate, and if abnormal, the abnormality is determined by the second normal / abnormal determining means. The information between the distinct abnormality and the distinct normal is taken out, and the type of the abnormality is identified by the abnormality identification means. in this way,
By providing the welding status monitoring device with a learning function of normal and abnormal and two discriminating functions based thereon, the operator can reliably determine the abnormality without any skill and in a short time, and determine the type of abnormality. Know exactly and easily.

[0010]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Next, the related art will be described first so that the present invention can be easily understood, and then a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings.
In the drawings, the same reference numerals indicate the same or corresponding parts.
The present invention is described as being applied to diagnosis of laser welding, but is not limited to this, as will be apparent to those skilled in the art.

FIGS. 6 to 15 show a welding condition monitoring device according to the related art of the present invention.
"Welding condition monitoring device" on the same day by the same applicant as the present application
As a patent application. The welding status monitor is shown in FIG.
A monitor data storage unit 81 for storing monitor data and learning data surrounded by a chain line 800 between the monitor signal processing unit 400 and the display unit 500 of the related art shown in FIG.
0, comparing the data to be determined with the normal reference data,
Normal / abnormality determining means 710 for determining whether the state is normal or abnormal;
Further, an abnormality identification unit 730 for identifying the type of abnormality, a normal norm learning unit 84 for learning a normal norm from stored monitor data of 80 cycles (80 laser welding operations).
0, an abnormal norm learning means 850 for learning an abnormal norm artificially or from stored monitor data, and an operating means 860 as an interface when an operator uses the welding condition monitoring apparatus. This welding condition monitoring device is required to properly judge the welding abnormality and its type or cause, but the judgment requires skill, so it takes a long time to identify the abnormality and the welding work efficiency is increased. In addition, it eliminates the disadvantages of the prior art device of FIG. 16, which required a considerable amount of training time for skill.

The welding condition monitoring apparatus shown in FIGS. 6 to 15 will be described in more detail.
And 600 are a welding target, a welding tool or device, a monitor signal input unit, a display unit, and a printing unit, respectively, similar to the conventional example. Accordingly, the welding device 200 performs, for example, repair of the sleeve of the heat transfer tube of the steam generator by welding, and also monitors the laser welded portion 100 to be welded, and monitors each channel of the monitor signal input means 300 (No. 0, No. 1, No. 3,..., No. 5 channels), a laser output signal of a YAG (Yttrium Aluminum Garnet) laser oscillator, and a 0.8 μm wavelength light emission intensity emitted from the welded portion. Green laser signal indicating the emission intensity of the 0.94 μm wavelength emitted from the weld, and 1.06 of the reflected light of the YAG laser.
A purple laser signal, a welding speed signal, and a motor load ratio signal representing the intensity of a μm wavelength are input. Then, the monitor signal input means 300 converts these monitor signals into digital signals and sends them to the monitor signal processing means 400.

The reference numeral 400 indicates, in addition to the normalization of the monitor signal,
A description will be given of the welding speed signal from the monitor signal input means 300, which is a monitor signal processing means for performing average value processing. For example, the arithmetic average value of the welding speed signal sampled within a certain time such as 0.5 second is described. And a normalization process of converting monitor signals of all welding speeds sampled during one laser welding operation into a deviation value when the average value is set to 50. Specifically, in the embodiment, the monitor signal processing means 400 has a capacity of 20 times for one cycle (one laser welding operation).
0 sampling (2 data during one laser welding operation)
(Collected 00 times), 200 points of data are averaged for every 5 or 6 data points, and averaged to 38 samplings per cycle. The monitor signal processing means 4
00 is input to the monitor data storage unit 810 to store the date, time, and welding tool name collected together with the processed data.

This welding condition monitoring apparatus has the following five modes: AMOD mode (normal / abnormality discriminating mode) BMOD mode (abnormality discriminating mode) CMOD mode (normal norm learning mode) DMOD mode (abnormality standard learning mode) Although the printer operates in the EMOD mode (print mode), the operation unit 860 and the monitor data storage unit 810 will be described before describing each operation.

By operating the operation unit 860, a screen shown in FIG. 7 appears on the display unit 500 including a display (not shown). As can be seen from this figure, the operating means 860 includes a welding tool name selecting means 821, an AMOD mode selecting means 8
22, a CMOD mode selection unit 823, a DMOD mode selection unit 824, and an EMOD mode selection unit 825. In the screen of the display unit, "Please select a tool name." Is displayed. AMOD mode selection means 82 in the figure
The fact that the inside of a block is filled with a plurality of “•” like the block 2 indicates that the AMOD mode has been selected.

FIGS. 8 and 9 show the monitor data from the monitor signal processing means 400 and the normal norm learning means 840.
Monitor data storage means 8 for storing learning data from
10, the monitor data storage means 810 includes:
The determination data 831 to be newly determined, the learning data 832 for 80 cycles for creating a normal norm, and the normal norm data 833 used for normality / abnormality determination are provided. In order to create a normal norm, an observation value or measured value is obtained by performing welding, and an observation value when the operator judges the result is normal by observing the result of the trial welding is used as learning data. Created. In FIG.
Reference numeral 841 denotes the reference data of the abnormality A, that is, an abnormality pattern including 26 elements or identification sections.
6 represents patterns of abnormalities B to F, respectively. The identification section filled with a plurality of “·” indicates a section determined to be abnormal. The abnormality norm is created by the operator based on the processing result obtained from the monitor data at the time of the past abnormality, and is made to be learned by the machine. In the embodiment, the abnormal norm data is stored in the abnormal norm learning means 8.
50 to the monitor data storage unit 810.
The abnormalities A to F indicate the spatter adhesion abnormality, laser output attenuation abnormality, tool eccentricity abnormality, welding speed fluctuation abnormality, optical system damage abnormality, mirror abnormality, and the like, respectively.

First, the AMOD mode, that is, the normal / abnormal discrimination mode of welding just completed will be described. Normal / normal in the AMOD mode selection means 822 of the operation means 860
When the abnormality determination mode is selected (FIG. 7), the monitor signal input means 300 samples the monitor signal 200 times during one laser welding operation, for example, for about 18 seconds, and the channel Nos. Is read for each 200 samplings. These monitor signals are normalized and averaged by the monitor signal processing means 400 and stored in the monitor data storage means 810 as monitor data. On the other hand, the normal / abnormal discriminating means 710 (FIG. 6) fetches, from the monitor data storage means 810, one by one the observed value of the welding to be discriminated between normal and abnormal, that is, a sample of the discriminated data.

Here, the discriminated data is represented as Y ^j ₁ , _i . Here, j is the number of samplings per cycle and j = 1
38 (time order), i is a channel number and i = 0-5 (section s = 1-6). What is a section?
This means 8 × 6 data sections, and normal / abnormal is determined for each section. That is, in each section, whether the data is normal or abnormal is determined by Mahalanobis' generalized distance comparing the degree of similarity of data variation, or reference value comparison determining comparing the magnitude of the absolute value of data. When the distribution of the normal norm is normally distributed, the former discrimination method is used, and when the normal norm is not normally distributed, the latter discrimination method is used.

The Maharanobis's gen
The determination by eralized distance), in a section, ^{_{"if D 2 j, s> 31.4}} , then the section is abnormal, the else the section is normal." It is an. Here, Mahalanobis' generalized distance D ² _j , _s is represented by the following equation, where Y ^j ₁ , _i is a sample (Y ₁ , ₁ ... Y ₁ , _p ) ^T , p = i.

[0020]

D ² _j , _s = (Y ^j ₁ , _i −μ ^j _i ) ^T Σ ⁻¹ (Y ^j ₁ , _i −μ ^j _i )

The reference value comparison discrimination means that in a certain section, “if all (sL−α) <Y _p <(sL + α),
then the section is normal, else the section is abnormal. "

If it is determined that even one section is abnormal, the welding is determined to be abnormal. If all sections are determined to be normal, the welding is determined to be normal.

When the operation means 860 is operated so as to make the above-mentioned normal / abnormal discrimination, various displays shown in FIG. 10 appear on the display means. In FIG. 10, reference numeral 851 denotes a data / result display for displaying data to be discriminated or a discrimination result, reference numeral 852 denotes a discrimination display indicating that discrimination processing is being performed, and reference numeral 853 indicates that the discrimination result is normal. This is a normal display, 854 is an abnormal display indicating that the result of the determination is abnormal, 855 is a confirmation button used to confirm the determination result and identify the type of abnormality, and 856 performs identification. 857 is 8
Reference numeral 51 denotes a raw data display that indicates that the data being displayed is data to be determined, and reference numeral 858 denotes a determination pattern display that indicates that the data displayed by 851 is the result of the determination. In addition, a message such as "the result of the determination is abnormal" and "the result of the determination is displayed" are displayed on the display means.

When the operation means 860 determines that an abnormality has occurred in the AMOD mode, it operates in the BMOD mode (abnormality identification mode).
Is automatically selected, and a screen shown in FIG. 11 is displayed on the display means. Abnormality identification means 73 in FIG.
A value of 0 converts 6 × 38 sections of data determined to be abnormal into 26 sections by regarding a section group consisting of 3 × 4 sections as a new section. This pattern is distinguished from the above-mentioned reference patterns of the abnormalities A to F.

FIG. 11 shows an operation used when learning the abnormal norm data. Reference numeral 861 denotes an abnormal norm data display showing a pattern to be identified as the abnormal norm.
Reference numeral 62 denotes an abnormality identification display indicating the identification result, 863 denotes an identification impossible display indicating that identification is impossible, and 864.
Is a confirmation button for confirming the abnormality identification result, 865 is an identification display indicating that identification is being executed, and 86
Reference numeral 6 denotes a NEXT button used to select the type of the first abnormal norm to be displayed, and reference numeral 868 denotes a discrimination pattern display indicating that the data displayed in 861 is a pattern used for discrimination.

As a method for identifying an abnormality, a method of comparing a reference abnormal pattern created artificially or from stored data with an abnormal pattern of data to be determined by using a neural network model shown in FIG. It is preferred to use. In FIG. 12, reference numeral 871 denotes an input layer corresponding to 26 sections; 872, an intermediate layer; and 873, an output layer corresponding to the number of abnormal types (6) and the number of normal types.

Next, in FIG. 7, when the normal norm learning mode selecting means 823 is selected, the abnormal data is smaller than the normal data group in the degree of similarity in the variation of the data or is smaller than the normal data group. The normal reference learning means 840 first determines whether the comparison is based on the similarity of the variation in data (Maharanobis general distance) or the magnitude of the absolute value of the data (reference value comparison). In order to select a method for determination, the cycle synchronization of data for 80 cycles stored in the monitor data storage unit 810 is confirmed. That is, in order to confirm that ^{_{X j a, i (j =}} 1~38, i = 0~5) does not change greatly different cycles a even (a = 1 to 80), taken out X ^j _{a, i,} Mother Examine the normal distribution (reproducibility) of the population. Specifically, a certain j, a certain i
Of X ^j _{a, i} is, to examine whether distribution by cycle a is a normal distribution, performing x2 square test (chi-square test).
In a certain section (s, j), if the channel i of the section is a normal distribution, the section is determined to be an M section that performs “discrimination based on Mahalanobis' generalized distance”. The determination method is a K section for performing “reference value comparison determination”.

Further, in order to speed up the discrimination process after welding, a pre-calculation of the Mahalanobis general distance is performed. That is, μ
The ^j _i X ^j _a, the average of the _{i = (μ 1 ·· μ p} ) T, p = 1, Σ
^-1 X ^j _a, when the variance-covariance matrix of _i, sigma is expressed by the following matrix expression (2).

[0029]

(Equation 2) Here, σ _uv is given by the following equation (3).

(Equation 3) For example, σ ₁₁ is represented by Expression (4).

(Equation 4)

Further, in order to calculate the reference value used for reference value comparison determination, at each section, using the Chebyshev, normal known data X ^j _a, the reference value in one of _i a (sL ± alpha) The value at which the probability of exceeding is 5% is set as a reference value.

FIG. 13 shows operations and display means used for learning the normal norm data described above.
Is a normal norm data display indicating the number of data called as the normal norm and the contents thereof, 882 is a normal norm data number display indicating the number of data of the normal norms selected so far, and 883 is a normal norm data as further normal norm data. A selectable display indicating that selection is possible, 884 is a NEXT button used to select another normal normative data, and 885 is 8
A registration enabled display 886 indicating that the data displayed at 81 can be registered as normal norm data.
Is a registration button used for execution of registration, 887 is an end display indicating whether the data to be selected has been completed or the data to be registered has been completed, and 888 is the end of registration and selection, and enters learning. An end button 889 used occasionally is a learning lamp indicating that learning is being performed.

In FIG. 7, when the abnormal norm learning mode is selected, the abnormal norm learning means 850 first creates each pattern of the abnormal states A to F based on past abnormal data, experience, and knowledge, and generates an abnormal normal pattern. Register By learning
Create accurate abnormal patterns in neural networks. Learning means that when the operator inputs learning data and teacher data to the welding status monitoring device, the welding status monitoring device learns the relationship between the data by itself and then the operator inputs the learning data and unlearned data. Is to output data corresponding to teacher data. For example, a pattern of "black and white, black and white, black and white" is given as learning data, and "abnormal A" data is given as teacher data, and many such sets are given in pairs. Then, when a pattern of “black and white, black and white, black and white...

FIG. 14 shows the registration of the abnormal A3 pattern.
The operation means and the display means at the time of learning are shown. FIG.
In 89, 891 is the registered abnormality A1, A2, B
An abnormal norm pattern display showing patterns of 1, B2, B3 and an abnormal A3 to be registered from now on, 892 is a registered display showing which abnormalities have been registered, and 893 is an abnormal norm showing the number of already registered abnormal patterns. Registration number display, 8
94 is A3 as a reference pattern for abnormalities to be registered from now on.
Is a registration status display indicating that is selected, 895 is a NEXT button used for selecting another abnormal pattern,
Reference numeral 896 denotes a registration button used when performing registration, 89
7 is a learning lamp indicating that learning is being performed, 89
Reference numeral 8 denotes an execution button used for executing learning, and 899 denotes an end lamp indicating that learning of the abnormal norm has been completed.

Finally, when the print mode is selected in FIG. 6, the printing means 825 prints the data list and the contents of the display screen stored in the monitor data storage means 810 at the request of the operator. FIG. 15 shows a printing unit 825.
Here is an example of the output. In FIG. 15, for example, the cycle data numbers 123-234-345LKZD indicate that the data determined to be abnormal and the data identified as abnormal A1 are being used as abnormal reference data.

In the invention of the above-mentioned prior application, it is possible to reliably determine whether the welding is normal or abnormal by making the test rate of the abnormality determination of the normal / abnormal determination means 710 relatively small. However, according to the knowledge of the present inventor, it has been found that by making the test rate of the abnormality determination small, it becomes difficult for the abnormality identification means 730 to identify the abnormality.

The present invention, whose embodiments are shown in FIGS. 1 to 5, has been made in order to improve the invention of the above-mentioned prior application.
By providing the normal / abnormal discriminating means, the disadvantage of the prior application is eliminated.

Next, an embodiment of the present invention will be described with reference to FIGS. 1 to 5. However, omitting the description of the same parts as the welding status monitoring device of the prior application will not hinder the understanding of the present invention. The explanation of the part is omitted or simplified,
See the above description of the prior application as necessary.

In FIG. 1, reference numeral 720 denotes a second normal / abnormality judging means provided according to the present invention, and a first normal / abnormality judging means 710 which is also provided in the prior application.
If the result of the determination (which has a relatively small verification rate to ensure the determination of whether the weld is normal or abnormal) is "abnormal," then the second normal / relatively high verification rate
The abnormality discriminating means 720 discriminates between abnormal and normal, and easily obtains information indicating the characteristics of the abnormality.

In the laser operation monitoring device of FIG. 1, each time one laser welding operation is completed, monitor signal input means 3
00 reads the monitor signals of channels 0 to 5 for each 200 samplings. These monitor signals are normalized and averaged by the monitor signal processing means 400 and stored in the monitor data storage means 810 as monitor data.

FIG. 2 shows first and second normal / abnormality determining means 71.
7 shows the configurations of the 0, 720 and abnormality identification means 730 and the relationship between them. In FIG. 2, a sample of the discriminated data from the monitor data storage unit 810 is taken into the discriminated data input unit 711. The discriminated data is represented as Y ^j ₁ , _i . Here, j is the number of samplings per cycle, j = 1 to 38 (time order), and i is the channel number, i = 0 to 5 (sections s = 1 to 6). Also,
The discrimination section means each of 38 × 6 data sections.

Each discrimination section discriminates whether the discrimination section 712 is normal or abnormal by the above-mentioned “Maharanobis general distance”. Reference numeral 713 denotes a determination unit based on a reference value, and performs the “reference value comparison determination” described above for each determination section. The generalized distance determination of Mahalanobis, in certain sections, ^{_{"if D 2 j, s> SH}} (D 2), then the section is abnormal, the else the section is normal."
It is assumed that. However, 0.02% of the value of SH (D ²⁾ is X2 square test (chi-square test), generalized distance D ² _{j, s} Mahalanobis is the Y ^j _{1, i} samples (Y _{1, 1} ·・ Y ₁ , _p ) ^T , p
If = 1, it is expressed by the following equation.

[0042]

D ² _j , _s = (Y ^j ₁ , _i −μ ^j _i ) ^T Σ ⁻¹ (Y ^j ₁ , _i −μ ^j _i )

The reference value comparison discrimination means that in a certain section, “if all (sL−α) <Y _p <(sL + α),
then the section is normal, else the section is abnormal. " However, the reference value in each determination section, with Chebyshev, the probability that more than one, even the reference values of normal known data ^{_{X j a, i (a =}} 1~80) (sL ± α) 0. 02%.

The results of the discriminating means 712 and 713 are sent to the normal / abnormal discriminating means 714 in all sections.
If it is determined that the welding is abnormal also in one of the determination sections, the welding is determined to be abnormal, and if it is determined that all the welding sections are normal, the welding is determined to be normal. FIG.
Is an explanatory diagram of the first normal / abnormality determining unit 710, and reference numeral 741 denotes a group of determination sections obtained from the normality / abnormality determining unit 710. X in the figure is a discrimination section in which an abnormality is discriminated at a relatively small test rate.

In FIG. 2, when the welding is judged to be abnormal by the first normal / abnormal judging means 710, the signal is sent to the discriminated data input means 72 of the second normal / abnormal judging means 720.
1 and then input to the discriminating means 722 and 733, and it is discriminated whether it is normal or abnormal by the above-mentioned "discrimination based on Mahalanobis' general distance" and "reference value comparison determination", respectively. However, in Mahalanobis' generalized distance discrimination, SH (D
² ) is a value of 10% of the chi-square test. In the reference value comparison judgment, the probability that the reference value exceeds (sL ± α) is 10%.
The value is 724 indicates that all sections are normal /
It is an abnormality determination unit. FIG. 4 is an explanatory diagram of the second normal / abnormality judging means 720, and reference numeral 746 denotes a group of judgment sections obtained from the normal / abnormality judging means 720. X in the figure is a discrimination section in which an abnormality is discriminated at a relatively large test rate.

Returning to FIG. 2 again, reference numeral 760 designates a discrimination section group consisting of 3 × 4 discrimination sections of 6 × 38 discrimination sections of data determined to be abnormal, and 26 discrimination sections as new sections. This is a conversion means for converting into sections and creating abnormal patterns. The identification unit 770 of the abnormality identification unit 730 identifies the patterns of the 26 identification sections and the above-described reference patterns of the abnormalities A to F using the neural network shown in FIG. FIG. 5 is an explanatory diagram of the abnormality identification means 730, where 751 is an abnormal pattern to be identified, 752 is a reference pattern of abnormality A, 753 is a reference pattern of abnormality B, 754 is a reference pattern of abnormality C, 7
Reference numeral 55 denotes a reference pattern of the abnormality D, and reference numeral 756 denotes a reference pattern of the abnormality E.

The data used by the first and second normal / abnormal discriminating means 710 and 720 are shown in FIG.
When the normal norm learning mode selecting means 823 is selected, the cycle synchronism of data for 80 cycles is confirmed by the normal norm learning means 840 as in the above-mentioned prior application. Also,
The pre-calculation of the Mahalanobis general distance used for discrimination of normal / abnormal is performed in the same manner as in the prior application.

The abnormal norm learning means 850 creates patterns of abnormal states A to F based on past abnormal data, experience, and knowledge, and registers the abnormal norm pattern in the same manner as in the prior application. By learning, we will create a proper norm for abnormal patterns in a neural network.

[0049]

According to the present invention, the operator can use the normal or abnormal monitor data stored in the monitor data storage means by trial laser work (welding) to learn the normal norm learning means or abnormal norm learning. Means for learning a normal norm or abnormal norm by means of the apparatus, and a new monitor signal to be discriminated is discriminated as normal or abnormal by first normal / abnormal discriminating means having a relatively low verification rate, and if abnormal, a comparison is made. Since the second normal / abnormality determining means having a relatively high verification rate forms a determination section for abnormality identification and is configured to identify the type of abnormality by the abnormality identifying means, the laser operation monitoring apparatus can operate normally and abnormally. , And two discriminating functions based on the learning function, so that normal / abnormal discrimination is assured and the type of abnormality can be easily identified. In addition, because of the above-mentioned function, even if the user is not a skilled person, it is possible to cope with the variation in the characteristics of the laser power tool, so that a relatively long training time is not required for the skill. Further, the efficiency of the entire laser operation can be improved because it is not necessary to spend much time monitoring during the laser operation.

[Brief description of the drawings]

FIG. 1 is a block diagram of a laser operation monitoring device according to the present invention.

FIG. 2 is a block diagram for explaining first and second normal / abnormal discriminating means and abnormal discriminating means of the laser operation monitoring device of FIG. 1;

FIG. 3 is an explanatory diagram of an abnormal judgment section of a first normal / abnormal judging means of the laser operation monitoring device of FIG. 1;

FIG. 4 is an explanatory diagram of a discrimination section of a second normal / abnormal discriminating means of the laser operation monitoring device of FIG. 1;

FIG. 5 is an explanatory diagram of an abnormality identification unit of the laser operation monitoring device of FIG. 1;

FIG. 6 is a block diagram of a welding status monitoring device of a prior application related to the present invention.

FIG. 7 is an explanatory diagram of operation means used in the welding situation monitoring device of FIG. 6;

FIG. 8 is an explanatory diagram of monitor signal storage means used in the welding situation monitoring device of FIG. 6;

FIG. 9 is an explanatory diagram showing an example of an abnormal pattern stored in the monitor signal storage means of FIG.

FIG. 10 is an explanatory diagram showing a screen appearing on a display unit when a normal / abnormal discrimination mode is selected by an operation unit of the welding situation monitoring device of FIG. 6;

FIG. 11 is an explanatory view showing a screen displayed on a display unit when an abnormality identification mode is selected by an operation unit of the welding situation monitoring device of FIG. 6;

FIG. 12 is an explanatory diagram of a neural network model used for abnormality identification by an abnormality identification unit when an abnormality identification mode is selected.

FIG. 13 is an explanatory view showing a screen appearing on a display unit when the normal norm learning mode is selected by the operation unit of the welding situation monitoring device of FIG. 6;

FIG. 14 is an explanatory view showing a screen appearing on a display unit when an abnormal norm learning mode is selected by an operation unit of the welding situation monitoring device of FIG. 6;

FIG. 15 is an explanatory diagram showing a screen appearing on a display unit when a print mode is selected by the operation unit of the welding situation monitoring device of FIG. 6;

FIG. 16 is a block diagram showing a conventional welding status monitoring device.

[Explanation of symbols]

 Reference Signs List 200 welding tool or apparatus 300 monitor signal input means 400 monitor signal processing means 710 first normal / abnormal discriminating means 720 second normal / abnormal discriminating means 730 abnormality discriminating means 810 monitor data storage means 840 normal norm learning means 850 abnormal norm Learning means

──────────────────────────────────────────────────続 き Continuation of the front page (72) Inventor Nagashima, 1-1 1-1 Wadazakicho, Hyogo-ku, Kobe City, Hyogo Prefecture Inside Mitsubishi Heavy Industries, Ltd. Kobe Shipyard (56) References A) JP-A-63-269588 (JP, A) JP-A 1-273685 (JP, A) JP-A 5-66202 (JP, A) JP-A 5-309485 (JP, A) -28454 (JP, U) (58) Fields investigated (Int. Cl. ⁶ , DB name) B23K 26/00-26/18

Claims (1)

(57) [Claims] 1. A monitor for monitoring the status of a laser operation using a monitor signal, wherein monitor data storage means for storing monitor data for monitoring, and whether the operation status is normal or abnormal based on the monitor data from the monitor data storage means. A first normal / abnormality discriminating means for discriminating at a relatively low verification rate, and a relatively high verification of the work status when the first normal / abnormality discriminating means determines that the work status is abnormal. Second normal / abnormality discriminating means for further discriminating by a rate, abnormality discriminating means for identifying the type of abnormality when the result of the discrimination by the second normal / abnormality discriminating means is a work situation abnormality, and the monitor data storage means A normal norm learning means for learning normal norm data from monitor data of a previously tried normal operation, and a monitor of a previously attempted abnormal work connected to the monitor data storage means. A laser work monitoring device, comprising: an abnormal norm learning means for learning abnormal norm data from the data.