KR102230463B1 - Diagnosis system and method of defect of equipment component - Google Patents

Abstract

The present invention relates to a diagnosis system for a defect of an equipment component, comprising: a plurality of sensors; a conversion unit which converts signals sensed by the plurality of sensors into a spectrum; a normalization unit which normalizes the spectrum; a division unit which divides the normalized spectrum into grids; a binary pattern generation unit which generates a binary pattern based on the height of the spectrum substance included into each section divided; a calculation unit which calculates a similarity between the binary pattern and a pre-provided defect binary pattern; and a determination unit which, when the similarity is equal to or higher than a reference value, determines that it is a defect. The present invention is able to use a binary pattern and to thereby precisely, simply diagnose the presence or absence and the type of a defect of the equipment component.

Description

Equipment component defect diagnosis system and its method {DIAGNOSIS SYSTEM AND METHOD OF DEFECT OF EQUIPMENT COMPONENT}

The present invention relates to a system and method for diagnosing defects of equipment parts. Specifically, the present invention relates to a system that generates a binary pattern with signals sensed from a plurality of sensors disposed on a facility part and compares it with a previously provided defective binary pattern to determine the presence or absence of a defect in the facility part.

In general, rolling element bearings are basic parts necessary for the operation of various mechanical devices, and may cause serious failures in mechanical devices even by small defects on the surface due to high pressure during operation. These bearings are used as essential elements in various industrial machines, and when a mechanical device is operated in an abnormal state, an abnormal phenomenon appears first. Therefore, continuous monitoring of the bearing condition is required for stable operation of the mechanical device, and a recent condition monitoring system essentially includes a function for monitoring and diagnosing defects in the bearing.

Causes of bearing failure include insufficient lubrication, improper use of lubricants, incorrect installation of bearings, and excessive deformation of the shaft system. In the past, such problems were diagnosed by skilled technicians and determined whether or not there was a failure, but most of them have the disadvantages that the diagnosis time is long, subjective, and in some cases, the operation of the device system must be stopped. In recent years, as a system capable of diagnosing a failure of a bearing while maintaining the operation of a device system is required, it has been developed into a type of technology that can detect an abnormality in advance by continuously diagnosing the bearing operation state.

In the detection of bearing defects, in actual industrial sites, the characteristics of noise and vibration are used for non-destructive inspection, which greatly aids in maintenance and maintenance such as extending the water surface of the bearing. The most commonly used methods for diagnosing bearing defects are the envelope spectrum method and the trend monitoring method.

The trend monitoring method monitors the degree to which the magnitude of the measured vibration signal changes over time to determine the presence or absence of a defect, and is based on vibration data accumulated through continuous monitoring. That is, the size of the vibration data in the normal state of the bearing and the newly measured vibration data are compared, and if the difference is greater than a certain size, it is determined that a defect exists in the bearing. Bearing defect monitoring by this method is applicable only when vibration data accumulated for a certain period of time exists, and if the same equipment is installed in different locations, vibration characteristics are different, so vibration data is accumulated and compared individually for each equipment. There is a drawback that must be done. As a result, the above method has a problem that increases the overall cost related to the maintenance of the facility, since it is necessary to individually manage the vibration monitoring standard customized for each facility.

Meanwhile, in the envelope spectrum method, an envelope is obtained from a vibration signal of a bearing and a frequency is analyzed through a Fast Fourier Transform (FFT). This method is highly reliable because it can be compared with the fault frequency determined by the bearing specifications, and it also derives a new method by combining it with other signal processing methods.

There is a need for a simpler and more accurate method of diagnosing defects using this envelope spectrum method.

Korean Patent Application Publication No. KR 10-2017-0093613

The present application relates to a system for diagnosing defects of equipment parts for solving the problems of the prior art described above, by generating a binary pattern with signals sensed from a plurality of sensors disposed on the equipment parts and comparing it with a previously provided defective binary pattern. It is to provide a system to determine the presence or absence of defects in equipment parts.

In addition, it is to provide a method of diagnosing a defect of a facility part by using the defect diagnosis system of the facility part.

The system for diagnosing defects of equipment parts according to the present invention for achieving the above technical problem includes a plurality of sensors; A converter configured to convert the signals sensed by the plurality of sensors into a spectrum; A normalization unit normalizing the spectrum; A division unit for dividing the normalized spectrum into a grid; A binary pattern generator for generating a binary pattern based on the height of the spectral component included in each of the divided cells; A calculation unit that calculates a similarity between the binary pattern and a previously provided defective binary pattern; And a determination unit that determines that the similarity is greater than or equal to the reference value as a defect.

The division unit may divide the spectrum into 50 to 10,000 cells, but is not limited thereto.

The binary pattern generator may display 1 if the height of the spectral component included in each of the divided cells is more than half the height of one cell, and 0 if it is less than, but is not limited thereto.

The calculation unit may calculate the similarity using Equations 1 and 2 below, but is not limited thereto.

[Equation 1]

[Equation 2]

In Equations 1 and 2, a is the number of rows of the grid, b is the number of columns of the grid, M is the value of the binary pattern, and M _f is the value of the previously provided defective binary pattern. However, it is not limited thereto.

The reference value may be 0.3 to 0.7, but is not limited thereto.

A method for diagnosing a defect of a facility component includes: converting, by a system for diagnosing a defect of a facility component, into a spectrum of signals sensed by a plurality of sensors disposed on the facility component; Normalizing the spectrum; Dividing the normalized spectrum into a grid; Generating a binary pattern by displaying 1 if the height of the spectral component included in each of the divided cells is greater than or equal to half the height of one cell, and as 0 if it is less than the height of one cell; Calculating a similarity between the binary pattern and the previously provided defective binary pattern; And determining that the similarity is greater than or equal to the reference value as a defect.

The normalizing step may be normalized using Equation 3 below, but is not limited thereto.

[Equation 3]

는 정규화된 스펙트럼의 함수, 상기 f(i)는 스펙트럼의 함수, 상기 min(f)는 상기 스펙트럼의 최소값, 상기 max(f)는 상기 스펙트럼의 최대값인 것 일 수 있으나, 이에 제한되는 것은 아니다. In Equation 3,

Is a function of a normalized spectrum, f(i) is a function of a spectrum, min(f) is a minimum value of the spectrum, and max(f) is a maximum value of the spectrum, but is not limited thereto. .

The division may be to divide the spectrum into 50 to 10,000 cells, but is not limited thereto.

The similarity may be calculated using Equations 1 and 2 below, but is not limited thereto.

[Equation 1]

[Equation 2]

In Equations 1 and 2, a is the number of rows of the grid, b is the number of columns of the grid, M is the value of the binary pattern, and M _f is the value of the previously provided defective binary pattern. However, it is not limited thereto.

The reference value may be 0.3 to 0.7, but is not limited thereto.

The above-described problem solving means are merely exemplary and should not be construed as limiting the present application. In addition to the above-described exemplary embodiments, additional embodiments may exist in the drawings and detailed description of the invention.

The disclosed technology can have the following effects. However, since it does not mean that a specific embodiment should include all of the following effects or only the following effects, it should not be understood that the scope of the rights of the disclosed technology is limited thereby.

According to the above-described problem solving means of the present application, the defect diagnosis system of a facility part according to the present application generates a binary pattern with a signal sensed from a sensor attached to the facility or facility part, and compares it with a previously provided defect binary pattern to be simple and accurate. It is possible to determine the presence and type of defects in equipment parts.

In addition, it is possible to control the accuracy and processing speed of the analysis of the defect diagnosis system of equipment parts by adjusting and dividing the number of spectral grids.

Furthermore, by adjusting the reference value according to the user or equipment conditions, defects of the equipment parts can be determined according to the situation.

1 is a diagram of a system for diagnosing defects of equipment parts according to an exemplary embodiment of the present disclosure.
2 is a flowchart of a method for diagnosing defects of equipment parts according to an exemplary embodiment of the present disclosure.
3 is a spectrum of a signal sensed by a sensor according to an exemplary embodiment of the present disclosure.
4 is a spectrum of a normalized defect frequency according to an embodiment of the present disclosure.
5 is a spectrum in which cells are divided according to an embodiment of the present disclosure.
6A to 6C are diagrams showing a reference for generating a binary pattern according to an exemplary embodiment of the present disclosure.
7 is a diagram of a binary pattern according to an embodiment of the present application.
8A to 8C illustrate a defect spectrum and a defect binary pattern according to an exemplary embodiment of the present disclosure.
9 is a diagram illustrating a difference between a binary pattern and a defective binary pattern according to an exemplary embodiment of the present disclosure.

Since the present invention can make various changes and have various embodiments, specific embodiments are illustrated in the drawings and will be described in detail in the detailed description. However, this is not intended to limit the present invention to a specific embodiment, it should be understood to include all changes, equivalents, or substitutes included in the spirit and scope of the present invention.

In describing each drawing, similar reference numerals are used for similar elements. Terms such as first and second may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another component.

For example, without departing from the scope of the present invention, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. The term “and/or” includes a combination of a plurality of related stated items or any of a plurality of related stated items.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs.

Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning of the related technology, and should not be interpreted as an ideal or excessively formal meaning unless explicitly defined in the present application. Shouldn't.

Throughout the present specification, when a member is positioned "on", "upper", "upper", "under", "lower", and "lower" of another member, this means that a member is located on another member. This includes not only the case where they are in contact but also the case where another member exists between the two members.

In the entire specification of the present application, when a certain part "includes" a certain component, it means that other components may be further included, rather than excluding other components unless specifically stated to the contrary.

As used herein, the terms "about", "substantially" and the like are used at or close to the numerical value when manufacturing and material tolerances specific to the stated meaning are presented, and to aid understanding of the present application. In order to avoid unreasonable use by unscrupulous infringers of the stated disclosures, either exact or absolute figures are used. In addition, throughout the specification of the present application, "step to" or "step of" does not mean "step for".

In the entire specification of the present application, the term "combination of these" included in the expression of the Makushi format refers to one or more mixtures or combinations selected from the group consisting of components described in the expression of the Makushi format, and the constituent elements It means to include one or more selected from the group consisting of.

Hereinafter, a system for diagnosing defects of equipment parts of the present application and a method thereof will be described in detail with reference to embodiments, examples, and drawings. However, the present application is not limited to these embodiments and examples and drawings.

The present application, a plurality of sensors; A converter configured to convert the signals sensed by the plurality of sensors into a spectrum; A normalization unit normalizing the spectrum; A division unit for dividing the normalized spectrum into a grid; A binary pattern generator for generating a binary pattern based on the height of the spectral component included in each of the divided cells; A calculation unit that calculates a similarity between the binary pattern and a previously provided defective binary pattern; And a determination unit determining a defect if the similarity is greater than or equal to a reference value.

1 is a diagram of a system for diagnosing defects of equipment parts according to an exemplary embodiment of the present disclosure.

The sensor 110 may include a sensor selected from the group consisting of an acoustic sensor, an acoustic emission sensor, a vibration sensor, and combinations thereof, but is not limited thereto.

The sensor 110 may be disposed on a facility part.

There may be one or more sensors, and the number of sensors may be adjusted according to the number of equipment parts.

The equipment component may be a bearing of a rotating machine, but is not limited thereto.

The sensor 110 may be disposed on the facility part or the facility itself. Thereafter, a signal generated from the equipment component may be sensed at predetermined time intervals and transmitted to the conversion unit 120.

The system for diagnosing defects of the equipment parts may be operated for 1 to 10 seconds. In addition, by measuring for 1 second to 10 seconds and then continuously measuring for 1 second to 10 seconds, it is possible to accurately grasp the presence or absence of defects in equipment parts and the type of defects in real time.

The conversion unit 120 converts the signal sensed by the sensor 110 into a spectrum. In this case, a Fast Fourier Transform (FFT) may be used, but is not limited thereto.

The conversion unit 120 may receive a signal from the sensor 110 and recognize a signal generated according to a defect in a corresponding facility component. The conversion unit 120 may be individually connected to the plurality of sensors 110 so that the number of the conversion units 120 and the number of the sensors 110 may be the same. Alternatively, the conversion unit 120 may simultaneously receive signals from the plurality of sensors 110. That is, one conversion unit 120 may receive signals from the plurality of sensors 110.

The conversion unit 120 may receive a signal wirelessly from the sensor 110.

The system for diagnosing defects of the equipment parts may further include an extraction unit (not shown) for extracting a defect frequency band from the spectrum converted by the conversion unit 120.

The extraction unit extracts a frequency band between a minimum value and a maximum value from the spectrum as a defective frequency band. The defect frequency band may vary depending on the type of defect.

The normalization unit 130 normalizes the spectrum converted by the conversion unit 120.

The normalization unit 130 may normalize the spectrum to a value of 0 to 1.

The normalization unit 130 may normalize using Equation 3 below, but is not limited thereto.

는 정규화된 스펙트럼의 함수, 상기 f(i)는 스펙트럼의 함수, 상기 min(f)는 상기 스펙트럼의 최소값, 상기 max(f)는 상기 스펙트럼의 최대값인 것 일 수 있으나, 이에 제한되는 것은 아니다.In Equation 3,

Is a function of a normalized spectrum, f(i) is a function of a spectrum, min(f) is a minimum value of the spectrum, and max(f) is a maximum value of the spectrum, but is not limited thereto. .

The normalization unit 130 may normalize only the spectrum of the defect frequency band extracted by the extraction unit.

The normalization unit 130 may normalize the normalized spectrum into a two-dimensional graph in which an x-axis is a frequency and a y-axis is an amplitude.

The division unit 140 divides the normalized spectrum into a grid.

The dividing unit 140 may divide the spectrum into 50 to 10,000 cells, but is not limited thereto.

The dividing unit 140 may divide the spectrum into squares such as 100 horizontally and 100 vertically, and divided into a rectangle such as 10 horizontally and 20 vertically.

When the dividing unit 140 divides the spectra into less than 50 spectra, accuracy may be degraded when analyzing defects in the equipment parts. In addition, when the spectrum is divided into more than 10,000, the accuracy may be improved when analyzing defects of the equipment parts, but there is a problem in that the operation processing speed is reduced.

The binary pattern generator 150 may generate a binary pattern based on a height of a spectral component included in each of the divided cells.

The binary pattern generator 150 may display 1 if the height of the spectral component included in each of the divided cells is more than half of the height of one cell, and 0 if it is less than, but is not limited thereto.

Alternatively, the binary pattern generator 150 may display various colors such as black if the height of the spectral component included in each of the divided cells is more than half of the height of one cell, and white if the height of the spectral component is less than one cell, but is limited thereto. no.

The calculation unit 160 may calculate a similarity between the binary pattern and a previously provided defective binary pattern.

The defect binary pattern is obtained by converting a spectrum of a measured or theoretical value into a binary pattern according to a defect of an equipment component in advance. The defect may include, for example, a defect selected from the group consisting of an outer ring defect of a bearing, an inner ring defect of a bearing, a roller defect of a bearing, and combinations thereof, but is not limited thereto.

The calculation unit 160 may calculate the similarity by using Equations 1 and 2 below, but is not limited thereto.

In Equations 1 and 2, a is the number of rows of the grid, b is the number of columns of the grid, M is the value of the binary pattern, and M _f is the value of the previously provided defective binary pattern. However, it is not limited thereto.

The determination unit 170 may determine that the similarity is greater than or equal to a reference value as a defect.

The reference value may be 0.3 to 0.7, but is not limited thereto.

The reference value may be set according to a user or equipment conditions. Specifically, in the case of a facility capable of producing a large error even with a slight defect, the reference value may be set to about 0.3, and in the case of a facility that does not produce a large error even with a certain degree of defect, the reference value may be set to about 0.7.

If the reference value is less than 0.3, it is mostly judged as a defect, and even a simple malfunction can be judged as a defect. In addition, when the reference value exceeds 0.7, even when a defect occurs in a facility part, it may not be determined as a defect.

The determination unit 170 may determine according to each type of defect of the equipment component. For example, when comparing the similarity with the binary pattern for the bearing outer ring defect, it is possible to determine the presence or absence of the bearing outer ring defect of the equipment component. Alternatively, when comparing the similarity with the binary pattern for the bearing inner ring defect, it is possible to determine the presence or absence of the bearing inner ring defect of the equipment component. Alternatively, when comparing the similarity with the binary pattern for the bearing roller defect, it is possible to determine the presence or absence of the bearing roller defect of the equipment component. That is, the system for diagnosing defects of equipment parts according to the present application can recognize not only the presence or absence of defects of the equipment parts, but also the types of defects.

When diagnosing a defect in a facility component, the determination unit 170 may transmit a defect in the facility component and a type of the defect as a signal to the central management device.

The system for diagnosing defects of the equipment parts may further include a display (not shown).

The display may visually indicate the location of the defect, the presence or absence of the defect, and the type of the defect in the equipment part.

The system for diagnosing defects of the equipment parts 100 may further include a wireless transmission device (not shown).

By using the wireless reception device, a signal may be transmitted to a central management device that monitors whether or not a component of the facility is defective and the type of defect.

The system for diagnosing defects of the equipment parts 100 may further include a warning system (not shown).

The warning system may be a notification by a warning sound, a visual warning signal, etc., when the defect diagnosis system of the equipment part determines the defect of the equipment part.

By listening to the warning sound of the warning system and accurately grasping the location and type of defects of the equipment parts displayed on the display in real time, it is possible to respond to them.

The present application includes the steps of converting a signal sensed by a plurality of sensors disposed on a facility part into a spectrum, by a system for diagnosing a defect of a facility part; Normalizing the spectrum; Dividing the normalized spectrum into a grid; Generating a binary pattern by displaying 1 if the height of the spectral component included in each of the divided cells is greater than or equal to half the height of one cell, and as 0 if it is less than the height of one cell; Calculating a similarity between the binary pattern and the previously provided defective binary pattern; And determining that the similarity is greater than or equal to a reference value as a defect.

2 is a flowchart of a method for diagnosing defects of equipment parts according to an exemplary embodiment of the present disclosure.

Referring to FIG. 2, first, a signal sensed by a plurality of sensors disposed on a facility part is converted into a spectrum (S100).

The transforming step may be transforming the signal sensed by the sensor into a Fast Fourier Transform (FFT).

3 is a spectrum of a signal sensed by a sensor according to an exemplary embodiment of the present disclosure.

Specifically, in FIG. 3, the x-axis may represent frequency and the y-axis may represent amplitude. In addition, in FIG. 3, the defect frequency band is indicated by a red square box. The defect frequency band is obtained by extracting a frequency band between a minimum value and a maximum value in the spectrum as a defect frequency band, and the defect frequency band may vary according to the type of defect.

Then, the spectrum is normalized (S200).

The normalizing may be normalized using Equation 3, but is not limited thereto.

The normalization may be to normalize the spectrum to a value of 0 to 1. In addition, it may be to normalize only the defective frequency band portion indicated by the red square box in FIG. 3.

4 is a spectrum of a normalized defect frequency according to an embodiment of the present disclosure.

Subsequently, the normalized spectrum is divided into a grid (S300).

The division may be to divide the spectrum into 50 to 10,000 cells, but is not limited thereto.

5 is a spectrum in which cells are divided according to an embodiment of the present disclosure.

Specifically, FIG. 5 shows the spectrum of the normalized defect frequency of FIG. 4 divided into 21 horizontal spaces, 13 vertical spaces, and a total of 273 spaces.

Subsequently, if the height of the spectral component included in each of the divided cells is greater than or equal to half the height of one cell, it is expressed as 1, and if it is less than the height, it is expressed as 0 to generate a binary pattern (S400).

Alternatively, if the height of the spectral component included in each of the divided cells is more than half of the height of one cell, it may be displayed in various colors, such as black, and if it is less than the height of one cell, white, etc., but is not limited thereto.

6A to 6C are diagrams showing a reference for generating a binary pattern according to an exemplary embodiment of the present disclosure.

Referring to FIG. 6A, it can be seen that the height of the spectral component included in the divided cells is more than half of the height of one cell. Therefore, it can be expressed as 1. Referring to FIGS. 6B and 6C, it can be seen that the height of the spectral component included in the divided cells is less than half of the height of one cell. Therefore, it can be marked as 0.

7 is a diagram of a binary pattern according to an embodiment of the present application.

Referring to FIG. 7, when the height of the spectral component included in the divided cells is more than half of the height of one cell, those that are less than half the height are indicated in red, and those that are less than that are indicated in white. In addition, the red column means 1, and the white column means 0.

Subsequently, the similarity between the binary pattern and the previously provided defective binary pattern is calculated (S500).

8A to 8C illustrate a defect spectrum and a defect binary pattern according to an exemplary embodiment of the present disclosure.

Specifically, FIG. 8A is a spectrum and a binary pattern when a defect occurs in the outer ring of the bearing, using the equation of Equation 4 below, and FIG. 8B is a spectrum and a binary pattern when a defect occurs in the inner ring of the bearing. Equation 5 is used, and Fig. 8C is a spectrum and a binary pattern when a defect occurs in the roller of the bearing, using Equation 6 below.

In Equations 4 to 6, BPFO (Ball Pass Frequency of Outer Ring) is the outer ring passing frequency of the rolling bearing, BPFI (Ball Pass Frequency of Inner ring) is the inner ring passing frequency of the rolling bearing, and BSF (Ball Spin Frequency) is rolling. Ball passing frequency of the bearing, RPM (Revolutions Per Minute) is the number of revolutions per minute, N _B is the number of bearings, B _D is the diameter of the bearing, P _D is the diameter of the pitch, and β is the contact angle. It may be, but is not limited thereto.

The similarity may be calculated using Equations 1 and 2, but is not limited thereto.

9 is a diagram illustrating a difference between a binary pattern and a defective binary pattern according to an exemplary embodiment of the present disclosure.

_{Specifically, FIG. 9 shows the difference (M d} ) of the binary pattern excluding the _{outer ring defect binary pattern (M f} ) of FIG. 8A from the generated binary pattern (M) of FIG. 7. In FIG. 9 _{, it can be seen that M d} is 0.2673 (=73/273) and the similarity is 0.7327.

Subsequently, if the degree of similarity is greater than or equal to the reference value, it is determined as a defect (S600).

The reference value may be 0.3 to 0.7, but is not limited thereto.

For example, when the reference value is 0.5, the binary pattern M generated in FIG. 9 may have an outer ring defect because the similarity to the outer ring defect binary pattern is 0.7327, which is greater than the reference value of 0.5. _{In addition, M d} of the binary pattern generated in FIG. 7 with the inner ring defect binary pattern of FIG. 8B is 0.341 (=93/273), and the similarity is 0.659, which is greater than the reference value of 0.5, so it can be determined that there is an inner ring defect. In addition, it can be determined that there is a defect due to the roller 7 is also generated by the M _d of the roller defect in Figure 8c the binary pattern binary pattern is 0.19 (52/273), the degree of similarity is larger than the reference value as 0.81 to 0.5.

The system for diagnosing defects of facility parts according to the present application and its method are to generate a binary pattern with a signal sensed from a sensor attached to the facility or facility and compare it with a previously provided defect binary pattern, and the existence and type of defects of the facility part simply and accurately. Can grasp.

In addition, by controlling the number of grids of the spectrum and dividing it, the accuracy and processing speed of the analysis of the defect diagnosis system of equipment parts can be controlled.

Furthermore, by adjusting the reference value according to the user or equipment conditions, defects of the equipment parts can be determined according to the situation.

The foregoing description of the present application is for illustrative purposes only, and those of ordinary skill in the art to which the present application pertains will be able to understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present application. Therefore, it should be understood that the embodiments described above are illustrative and non-limiting in all respects. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present application is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present application.

100: equipment component defect diagnosis system
110: sensor
120: conversion unit
130: normalization unit
140: division
150: binary pattern generator
160: calculation unit
170: judgment unit

Claims (10)

A plurality of sensors;
A converter configured to convert the signals sensed by the plurality of sensors into a spectrum;
A normalization unit normalizing the spectrum;
A division unit for dividing the normalized spectrum into a grid;
A binary pattern generator for generating a binary pattern based on the height of the spectral component included in each of the divided cells;
A calculation unit that calculates a similarity between the binary pattern and a previously provided defective binary pattern; And
If the similarity is greater than or equal to a reference value, a determination unit that determines it as a defect; and a defect diagnosis system for equipment parts.
The method of claim 1,
The division unit is to divide the spectrum into 50 to 10,000 cells, the defect diagnosis system for equipment parts.
The method of claim 1,
If the height of the spectral component included in each of the divided cells is equal to or greater than half of the height of one cell, the binary pattern generation unit displays 1, and if the height of the spectral component is less than one cell, 0 is displayed.
The method of claim 1,
The calculation unit is to calculate the similarity by using the following equations 1 and 2, the defect diagnosis system of the equipment parts:
[Equation 1]

[Equation 2]

(In Equations 1 and 2,
Where a is the number of rows of the grid,
B is the number of rows of the lattice,
M is the value of the binary pattern,
The M _f is the value of the previously provided defective binary pattern).
The method of claim 1,
The reference value is from 0.3 to 0.7, the system for diagnosing defects of equipment parts.
Converting a signal sensed by a plurality of sensors disposed on the equipment component into a spectrum;
Normalizing the spectrum;
Dividing the normalized spectrum into a grid;
Generating a binary pattern by indicating 1 if the height of the spectral component included in each of the divided cells is greater than or equal to half the height of one cell, and as 0 if it is less than the height of one cell;
Calculating a similarity between the binary pattern and the previously provided defective binary pattern; And
If the similarity is greater than or equal to a reference value, determining as a defect.
The method of claim 6,
The normalizing step is to normalize using Equation 3 below:
[Equation 3]

(In Equation 3,
remind

Is a function of the normalized spectrum,
F(i) is a function of the spectrum,
The min(f) is the minimum value of the spectrum,
The max(f) is the maximum value of the spectrum).
The method of claim 6,
The division is to divide the spectrum into 50 to 10,000 cells, the method for diagnosing defects in equipment parts.
The method of claim 6,
The similarity is calculated using the following equations 1 and 2, a method for diagnosing defects of equipment parts:
[Equation 1]

[Equation 2]

(In Equations 1 and 2,
Where a is the number of rows of the grid,
B is the number of rows of the lattice,
M is the value of the binary pattern,
The M _f is the value of the previously provided defective binary pattern).
The method of claim 6,
The reference value is from 0.3 to 0.7, the method for diagnosing defects in equipment parts.

Images