KR102333457B1 - Machine Fault diagnostic device using vibration and noise signal and big data based smart sensor system using signals therefrom - Google Patents

Abstract

Vibration sensor 100 for detecting the vibration of the machine; Acoustic sensor 200 for detecting the noise of the machine; a time and frequency data forming unit 400 for forming time domain data 410 and frequency domain data 420 from the signals of the vibration sensor 100 and the acoustic sensor 200, respectively; a code value calculation unit 500 for calculating a vibration code value and a noise code value from the time domain data 410 and the frequency domain data 420, respectively; If there are stored vibration standards and noise standards, they are used. However, if the user sets the vibration standards and noise standards in order to measure and manage vibrations at any location on the machine, it is possible to measure and , a reference setting unit 800 for calculating the average value and standard deviation of the measured vibration signal and the noise signal, and performing a function of setting the vibration standard and the noise standard in each operating condition; Defect pattern setting unit 700 in which the defect pattern data of the machine is stored; Based on the defect pattern data of the machine read out from the defect pattern setting unit 700, the vibration standard and the noise standard of the reference setting unit 800 are combined with the vibration code value and the noise code value of the code value calculation unit 500, respectively. a comparison unit 600 that compares; Defect notification unit 900 for expressing the comparison result to the outside based on the comparison result of the comparison unit 600; a data storage unit 1000 for storing time-domain data 410 and frequency-domain data 420 of the vibration sensor 100 and the acoustic sensor 200 before and after the defect when it is determined from the comparison result; and a communication unit 1100 that transmits data stored in the data storage unit 1000 to the external device 1200 and receives a control command from the external device 1200; Machine using vibration and noise signals comprising: A fault diagnosis device is provided.

Description

Machine fault diagnostic device using vibration and noise signal and big data based smart sensor system using signals therefrom

The present invention relates to vibration and noise measurement and monitoring, and more particularly, to a machine fault diagnosis apparatus using vibration and noise signals and a big data-based smart sensor system using the signals.

Monitoring technology provides site-based production facilities, buildings, bridges, vibration, noise, pressure, temperature, strain, ozone concentration, pH, organic matter content, BOD, COD, etc. of vibration, noise, pressure, temperature, soil, etc. By measuring, analyzing, and diagnosing environmental physical quantities, it is a technology that not only maximizes the efficiency of production facilities or improves the safety of structures, but also enables efficient environmental monitoring by minimizing the production defect rate.

Up to now, products related to monitoring technology use various sensors that can measure physical quantities such as vibration, noise, temperature, pressure, strain, ozone concentration, pH, organic content, BOD, and COD required for each site by site. It has been made in a way that measures the measurement results and uses the expensive monitoring system installed in the unit site, has a separate operator, and continuously analyzes the monitoring results to diagnose the condition of the facility.

Among them, vibration and noise signals, unlike other parameters such as temperature and pressure, must be frequency-converted using a lot of time history data to determine the mechanical fault state (frequency) included in the frequency component. Therefore, in order to monitor vibration and noise signals, a frequency analysis instrument or signal analysis device is absolutely necessary. Also, experts in this field were needed to utilize such frequency analysis equipment.

In other words, until now, expensive monitoring facility investment (equipment, space, and professional manpower) was required for each individual site separately. . In particular, in vibration monitoring, where the vibration condition of production facilities has a close influence on the quality and production volume of products, if unexpected problems such as defects or breakdowns occur in production facilities, if experts with sufficient skills do not take appropriate measures promptly In the end, the company has to bear huge corporate losses resulting from poor quality, shutdown of facilities, and production setbacks. Therefore, until now, production sites with large-scale processes such as petrochemical plants and semiconductor-related production plants have recognized the need for a vibration monitoring system for important facilities, but investment in facilities and manpower for this purpose, especially the cost to maintain it, etc. It is a situation in which a large burden is felt with respect to the economic cost. In addition, economic investment alone cannot achieve the expected effect, and sufficient technology and responsiveness to efficiently maintain and manage it must be supported.

In addition, for regular vibration monitoring or noise monitoring, conventionally, an expensive vibration sensor or sound sensor is attached to a machine that induces vibration and noise, and the output of this sensor is a signal cable. A separate vibration monitoring device connected to the included computer was provided to monitor the vibration of the machine.

In the above case, the components such as sensors, vibration measuring instruments, and devices capable of processing vibration signals are very expensive, and it becomes a complex system in which several devices are connected. There was a problem in that it could be operated only by high-level personnel with knowledge. Due to this problem, up to now, only very expensive and important facilities, etc., have been partially subjected to vibration monitoring under limited conditions where there is economical investment potential.

In addition, the quality of manufactured products is improved by constantly monitoring the presence or absence of defects in major mechanical parts constituting the facilities such as cutting, coating, cleaning, and logistics equipment in power plants, petrochemical plants, and precision product manufacturing plants including semiconductors. There are many fields that can secure and prevent sudden failure of equipment at the same time. In order to apply the vibration and noise monitoring device to these various fields, a vibration and noise monitoring device consisting of a vibration sensor, acoustic sensor, measurement and processing, and analysis device is required. It should be possible to easily set diagnostic or inspection standards according to the vibration and noise characteristics of the machine.

However, until now, a person manually operated the device to measure and manage the vibration and noise of the target machine, or in the case of important facilities such as a power plant turbine, a vibration sensor was installed in advance and centralized monitoring was performed in the control room.

In the case of manual operation, when the number of target machines is large, the workload increases, data may be contaminated or incorrect judgments may be made depending on the ability of the measurer. There was a problem in that the flexibility of the system was lowered. In addition, in this case, it is difficult for the person in charge at the site where the machine is installed to directly check the correlation between the vibration state of the machine and the judgment result of the central monitoring device.

1. Republic of Korea Patent Registration No. 10-1409986 (Vibration Monitoring Fault Diagnosis Device), 2. Republic of Korea Patent Registration No. 10-0444568 (Computer-readable recording medium containing an integrated monitoring operating system business method using the Internet and a program that can implement it).

Therefore, the present invention has been devised to solve the above problems, and the problem to be solved by the present invention is to directly attach to the target machine and intuitively display the vibration and noise status of the machine with the LED of the sensor in the field to respond to the field. In addition, it is possible to read the measurement result value or raw data from the sensor using an external device in the field and check and analyze it in a user's own way, and transmit the result value or raw data from the sensor to the cloud server Based on the big data in It is to provide a smart sensor system based on big data.

Another object of the present invention is to provide an apparatus for diagnosing a mechanical defect using vibration and noise signals that can be measured by simply attaching to a part of a machine that requires measurement of vibration and noise, and can be easily removed and measured after moving to another location. It is to provide a smart sensor system based on big data using signals.

Another object of the present invention is to provide a machine fault diagnosis device using vibration and noise signals and a device for diagnosing a mechanical defect using vibration and noise signals that enable prompt follow-up by notifying the user's mobile phone when a failure or abnormality is predicted from vibration and noise. It is to provide a smart sensor system based on big data.

However, the technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned are clearly to those of ordinary skill in the art to which the present invention belongs from the description below. can be understood

In order to achieve the above technical task, a vibration sensor 100 for detecting the vibration of the machine; Acoustic sensor 200 for detecting the noise of the machine; a time and frequency data forming unit 400 for forming time domain data 410 and frequency domain data 420 from the signals of the vibration sensor 100 and the acoustic sensor 200, respectively; a code value calculator 500 for calculating a vibration code value and a noise code value from the time domain data 410 and the frequency domain data 420, respectively; If there are stored vibration standards and noise standards, they are used, but if the user sets the vibration standards and noise standards to measure and manage vibration and noise at any location on the machine, each a reference setting unit 800 for performing a function of measuring, calculating the average value and standard deviation of the measured vibration signal and the noise signal, and setting the vibration standard and the noise standard in each operating condition; Defect pattern setting unit 700 in which the defect pattern data of the machine is stored; Based on the defect pattern data of the machine read out from the defect pattern setting unit 700, the vibration standard and the noise standard of the reference setting unit 800 are set as the vibration code value and the noise code value of the code value calculation unit 500 and a comparison unit 600 for comparing them, respectively; a defect notification unit 900 for expressing the comparison result to the outside based on the comparison result of the comparison unit 600; a data storage unit 1000 for storing time domain data 410 and frequency domain data 420 of the vibration sensor 100 and the acoustic sensor 200 before and after the defect when it is determined from the comparison result; and a communication unit 1100 for transmitting the data stored in the data storage unit 1000 to the external device 1200 and receiving a control command from the external device 1200; Machine using vibration and noise signals comprising: A fault diagnosis device is provided.

In addition, the time and frequency data forming unit 400, a buffer 110 for storing the data string 120 generated by digitally sampling the signals of the vibration sensor 100 and the acoustic sensor 200, respectively; and a control unit 70 for FFT-converting the data string 120 in the buffer 110, wherein the time-domain data 410 is generated based on the data string 120, and frequency based on the FFT transformation. Area data 420 is generated.

In addition, the data string 120 overlaps the data string 120 before and after sampling by at least 50%, respectively.

In addition, the communication unit 1100 includes one of a Bluetooth communication module, a Wi-Fi communication module, an infrared communication module, a LAN communication module, and a USB communication module.

In addition, it further includes an attachment part 20 having a magnet for frequently attaching or detaching the machine fault diagnosis device 10 to the surface of the machine.

In addition, when the vibration standard and the noise standard of the reference setting unit 800 are to be set from an external input, a terminal unit 850 for external input is further included.

In addition, when the vibration standard and the noise standard of the reference setting unit 800 are to be set from an external input, they are set by the data received through the communication unit 1100 .

The object of the present invention as described above is to form a group by including a plurality of machine fault diagnosis devices 10 using the above-described vibration and noise signals, and one external device is simultaneously or It can also be achieved by a vibration and noise fault diagnosis system, characterized in that it can communicate sequentially.

The object of the present invention as described above is to form a group by including a plurality of machine fault diagnosis devices 10 using the above-described vibration and noise signals, and one external device is simultaneously or It can also be achieved by the vibration and noise defect diagnosis system, characterized in that sequential communication, a group and a plurality of external devices are configured, and the plurality of external devices communicate with the server device 1300 .

In addition, a plurality of machine fault diagnosis devices 10 using the above-described vibration and noise signals are included to form a group, and one external device communicates with a plurality of machine fault diagnosis devices 10 simultaneously or sequentially, and external devices (1200) communicates with the server device (1300),

The server device 1300 includes a database unit 1310 for storing data received from the external device 1200; a data conversion unit 1340 for converting the data stored in the database unit 1310 into a predetermined format; a big data processing unit 1360 for learning the data converted by the data conversion unit 1340; and a cloud 1380 that stores big data;

Big data stored in the cloud 1380 is stored in the defect pattern setting unit 700 as defect pattern data through the external device 1200. It can also be achieved by smart sensor systems.

In addition, it further includes a mobile phone 1250 capable of wireless communication with at least one of the plurality of machine fault diagnosis devices 10 through a connection to the server device 1300 or through the first local area network 1280.

In addition, the server device 1300 further includes means for transmitting a text message including information on the vibration state or noise state of the machine to the mobile phone 1250 .

In addition, the database unit 1310 includes: a sensor management DB 1312 in which information is stored in the machine fault diagnosis apparatus 10; Error and anomaly DB 1314 in which a history of errors and abnormalities related to vibration and noise of the machine is stored; and a text transmission DB 1316 in which text messages and transmission histories are stored; at least one of

delete

According to an embodiment of the present invention, it is possible to increase the field response ability by directly attaching to the target machine and intuitively displaying the vibration and noise status of the machine in the field with the LED of the sensor. In addition, by operating the defect diagnosis apparatus 10 based on the big data-processed data, analysis power is improved, and there is an advantage that a high-level expert can be omitted.

In addition, it can be measured by simply attaching it to the part of the machine that needs to measure vibration and noise, and it can be easily removed and moved to another location for measurement, so there is convenience and simplicity.

And, when a failure or abnormality is predicted from vibration and noise, it is notified to the user's mobile phone so that prompt follow-up measures can be taken.

However, the effects obtainable in the present invention are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those of ordinary skill in the art to which the present invention belongs from the following description. will be able

The following drawings attached to this specification illustrate preferred embodiments of the present invention, and serve to further understand the technical spirit of the present invention together with the detailed description of the present invention to be described later, so the present invention is described in such drawings It should not be construed as being limited only to
1 is an internal block diagram of a machine fault diagnosis apparatus 10 using vibration and noise signals according to an embodiment of the present invention;
2 is an external perspective view of the defect diagnosis apparatus 10 shown in FIG. 1;
3 is an explanatory diagram showing an internal processing process of the time and frequency data forming unit 400 of FIG. 1;
4a is a graph showing a peak inspection method in the frequency domain;
4b is a code value by a peak inspection method in the frequency domain;
5a is a graph showing a band inspection method in the frequency domain;
Figure 5b is a code value by the band (Band) inspection method in the frequency domain,
6a is a graph showing a curve inspection method in the frequency domain;
6b is a code value by a curve inspection method in the frequency domain;
7 is a block diagram of a big data-based smart sensor system using signals from a machine fault diagnosis device using vibration and noise signals according to an embodiment of the present invention;
FIG. 8 is a detailed table configuration diagram of the database unit 1310 of FIG. 7 .

Hereinafter, with reference to the accompanying drawings, embodiments of the present invention will be described in detail so that those of ordinary skill in the art can easily implement them. However, since the description of the present invention is merely an embodiment for structural or functional description, the scope of the present invention should not be construed as being limited by the embodiment described in the text. That is, since the embodiment may have various changes and may have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such effects, it should not be understood that the scope of the present invention is limited thereby.

The meaning of the terms described in the present invention should be understood as follows.

Terms such as “first” and “second” are for distinguishing one component from another, and the scope of rights should not be limited by these terms. For example, a first component may be termed a second component, and similarly, a second component may also be termed a first component. When a component is referred to as being “connected” to another component, it may be directly connected to the other component, but it should be understood that other components may exist in between. On the other hand, when it is mentioned that a certain element is "directly connected" to another element, it should be understood that the other element does not exist in the middle. Meanwhile, other expressions describing the relationship between elements, that is, “between” and “immediately between” or “neighboring to” and “directly adjacent to”, etc., should be interpreted similarly.

The singular expression is to be understood as including the plural expression unless the context clearly dictates otherwise, and terms such as "comprises" or "have" refer to the described feature, number, step, action, component, part or these It is intended to indicate that a combination exists, and it should be understood that it does not preclude the possibility of the existence or addition of one or more other features or numbers, steps, operations, components, parts, or combinations thereof.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. Terms defined in the dictionary should be interpreted as being consistent with the meaning of the context of the related art, and cannot be interpreted as having an ideal or excessively formal meaning unless explicitly defined in the present invention.

fault diagnosis device

Hereinafter, the configuration of the preferred embodiment will be described in detail with reference to the accompanying drawings. 1 is an internal block diagram of a machine fault diagnosis apparatus 10 using vibration and noise signals according to an embodiment of the present invention. As shown in FIG. 1 , a vibration sensor 100 for detecting the vibration of a machine and an acoustic sensor 200 for detecting the noise of the machine are provided.

The signal processing unit 300 includes a filter, an amplifier, an analog-digital converter (ADC), a digital signal processor (DSP), and the like. The signal processing unit 300 converts the electrical signals of the vibration sensor 100 and the acoustic sensor 200 into discrete data. Since these components are known components, detailed internal descriptions will be omitted.

The time and frequency data forming unit 400 forms time domain data 410 and frequency domain data 420 from the discrete data processed by the signal processing unit 300 , respectively. A detailed formation process will be described with reference to FIG. 3 .

The code value calculator 500 calculates a vibration code value and a noise code value from the formed time domain data 410 and frequency domain data 420 , respectively.

From time domain data, there is a method that uses the crest factor as a criterion for determining the presence or absence of abnormality, and the crest factor is defined as the ratio of the peak value to the RMS value (Peak/RMS). In addition, specific code values are shown in [Table 1].

Crest Factor is to detect and monitor impulse signal components or signals caused by short events. is an element Since there is a set standard for the normal signal and the crest factor of the vibration signal that is generated when there is an error in the machine, you can find out whether the bearing is abnormal by calculating the crest factor of the measured vibration signal.

4A is a graph illustrating a peak inspection method in the frequency domain, and FIG. 4B is a code value by the peak inspection method in the frequency domain. The peak inspection method is a method that uses the amplitude of the vibration value corresponding to a specific frequency component as a criterion for determining the presence or absence of abnormality. etc.) is applied.

5A is a graph showing a band inspection method in the frequency domain, and FIG. 5B is a code value by the band inspection method in the frequency domain. As shown in FIGS. 5A and 5B , the band inspection method is a method in which the sum of vibration values calculated in a certain specific frequency bandwidth is used as a criterion for determining the presence or absence of abnormality.

FIG. 6A is a graph illustrating a curve inspection method in the frequency domain, and FIG. 6B is a code value by the curve inspection method in the frequency domain. As shown in FIGS. 6A and 6B, this is a method in which the sum of all vibration values (Overall values) measured within the inspection frequency band is used as a criterion for determining the presence or absence of abnormality.

The reference setting unit 800 is a component that has a vibration reference value and a noise reference value for determining whether it is normal or abnormal. This reference value is recorded from an external input through the terminal unit 850 or recorded through the communication unit 1100 . Alternatively, when the user sets the vibration and noise standards to measure and manage vibration and noise at any location on the machine, each vibration and noise are measured multiple times according to the operating conditions, and the average value of the measured vibration and noise signals And the standard deviation is calculated and set as the vibration standard and the noise standard in each operating condition.

The defect pattern setting unit 700 stores machine defect pattern data. The defect pattern data is determined by the big data processed by the big data processing unit 1360 of the server device 1300 . For example, when vibration or noise occurs in a machine, the meaning of the vibration magnitude (eg, a harbinger of failure) or the meaning of noise can be easily understood by this defect pattern data.

The comparison unit 600 compares the vibration standard and the noise standard of the reference setting unit 800 based on the defect pattern data of the machine read from the defect pattern setting unit 700 to the vibration code value of the code value calculation unit 500 and Compare each with the noise code value. For example, when the vibration code value exceeds the vibration standard, it is determined as vibration abnormal, and when the noise code value exceeds the noise standard, it is determined as noise abnormal. In addition, even if it does not exceed the vibration standards or noise standards, in light of the defect pattern data, if it is determined that it is a sign or a precursor of a failure or abnormality, it is judged as a "defect".

The defect notification unit 900 expresses the comparison result to the outside based on the comparison result (normal or defective) of the comparison unit 600 . The expression method can be a lamp, LED, LCD lamp, warning lamp, speaker, buzzer, etc., and text transmission through the communication unit 1100 is also possible. When the defect notification unit 900 is an LED, "green" light is emitted when vibration and noise are normal, "red" light is emitted when there is a defect, and "yellow" is emitted when there is a warning.

The data storage unit 1000 stores each time domain data 410 and frequency domain data 420 of the vibration sensor 100 and the acoustic sensor 200 before and after the defect when it is determined that the comparison result is defective or abnormal. Save. The data storage unit 1000 may be a flash memory or an SSD, and if necessary, the entire time domain data 410 and frequency domain data 420 of the vibration sensor 100 and the acoustic sensor 200 regardless of the determination result. can also be saved.

The communication unit 1100 transmits data stored in the data storage unit 1000 to the external device 1200 and receives a control command from the external device 1200 . The communication unit 1100 may be at least one of a Bluetooth communication module, a Wi-Fi communication module, an infrared communication module, a LAN communication module, and a USB communication module.

The power supply unit 50 supplies power to the entire defect diagnosis apparatus 10 and may be a rechargeable secondary battery.

The control unit 70 controls the overall control, operation, and operation of the defect diagnosis apparatus 10, and may be implemented by a CPU, MICOM, or the like.

The external device 1200 may be one of a laptop computer, a tablet PC, a dedicated terminal, and a mobile phone capable of wireless communication with the Internet.

FIG. 2 is an external perspective view of the defect diagnosis apparatus 10 shown in FIG. 1 . As shown in FIG. 2 , the defect notification unit 900 is formed of an exclamation mark-shaped LCD on its upper surface.

The terminal unit 850 is provided on the side and is internally connected to the reference setting unit 800 . The cable support part 30 supports the cable connected to the terminal part 850 not to be bent. The terminal unit 850 may be a USB cable terminal.

The attachment part 20 is composed of a permanent magnet, can be easily attached to the surface of a machine made of steel, and can be removed by hand. Accordingly, the user can measure the vibration and noise while holding the defect diagnosis device 10 here and there on the machine. The attachment part 20 may be attached by an adhesive, and may be coupled to a machine by a bolt or screw.

3 is an explanatory diagram illustrating an internal processing of the time and frequency data forming unit 400 of FIG. 1 . As shown in FIG. 3 , the signals of the vibration sensor 100 and the acoustic sensor 200 are ODR-sampled and stored as a data string 120 in the buffer 110 . There are 2 ⁿ data streams (2048, 4096, etc.). In order to improve processing speed, adjacent data streams 120 have duplicate data streams 130 by 50% each. The time domain data 410 is formed through the averaging of the data string 120 and the like. In addition, the data string 120 forms the frequency domain data 420 through FFT (Fast Fourier Transform).

smart sensor system

7 is a block diagram of a big data-based smart sensor system using signals from a machine fault diagnosis device using vibration and noise signals according to an embodiment of the present invention, and FIG. 8 is a detailed view of the database unit 1310 in FIG. 7 and 8, the defect diagnosis apparatus 10, the first defect diagnosis apparatus 10a, and the second defect diagnosis apparatus 10b form a first group, and The group external device 1200a is matched. That is, the fault diagnosis device 10, the first fault diagnosis device 10a, and the second fault diagnosis device 10b are respectively attached to various positions among one machine, and the user around the first group external device 1200a You will be carrying a tablet PC. Vibration and noise measurement data of the first group is collected in the first group external device 1200a through the second local area network 1290 . The second local area network 1290 may be Bluetooth communication, Wi-Fi communication, infrared communication, LAN communication, USB communication, or the like.

The first group is devices installed at the first site, and the second group is devices installed at a second site located at a remote location from the first site. In this way, the vibration and noise data measured in a plurality of groups (each remote site) is stored in the server device 1300 through the first, second, and third group external devices 1200a, 1200b, and 1200c respectively. .

The mobile phone 1260 connects to the server device 300 through wireless communication (base station) so that bidirectional communication is possible. The mobile phone 1260 may be a mobile phone, a laptop computer, or a tablet PC. The mobile phone 1260 may access the server device 1300 to search and inquire the database unit 1310 , and may access the cloud 1380 . Since the mobile phone 1260 can be carried by a user on a business trip to a remote location, the user can check the vibration and noise conditions of the machine at any time and anywhere and order necessary actions.

The mobile phone 1260 may be connected to the plurality of defect diagnosis apparatuses 10 through the first local area network 1280 . The first local area network 1280 may be Bluetooth communication, Wi-Fi communication, infrared communication, LAN communication, USB communication, or the like.

The server device 1300 may be configured as a server computer, a workstation, or the like. A database unit 1310 , a data conversion unit 1340 , a big data processing unit 1360 , a cloud 1380 , and the like are provided inside the server device 1300 .

As shown in FIG. 8 , the database unit 1300 (eg, SCADA DB) includes a database table for maintenance of the entire system and a database table for storing transmitted measurement data.

In the sensor management DB 1312 , fields such as serial number, location, date of manufacture, date of purchase, firmware updater version and update date are defined in the defect diagnosis device 10 .

The error and abnormality DB 1314 sequentially stores the history of errors, defects, and abnormalities related to vibration and noise of the machine. To this end, the error and anomaly DB 1314 has fields such as the order of occurrence, the date of occurrence, the type of error, and follow-up actions.

The text sending DB 1316 stores the text message sent to the user's mobile phone 1260 when an abnormality occurs in the machine and the sending history (sending date, sending content, sending status, etc.).

The data DB 1318 stores measured data regarding noise and vibration.

The data conversion unit 1340 is configured to convert the vibration and noise data stored in the database unit 1312 into big data in a predetermined format. The data conversion unit 1340 may be an executable data conversion program installed in the server device 1300 . The data conversion unit 1340 converts the measurement data into a predetermined format (eg, in the form of an Excel file) so that the big data processing unit 1360 can use it as input data.

The big data processing unit 350 applies a learning algorithm (eg, neural network learning, fuzzy logic learning, deep learning, chatbot) using the big data converted by the data conversion unit 330 and uses these artificial intelligence techniques. It creates a defect pattern in which an abnormality or defect of the machine occurs.

These defect patterns and big data are stored in the cloud 1380 and are continuously accumulated. The cloud 1380 may be a hard disk or memory.

These defect patterns are transmitted to and stored in the defect pattern setting unit 700 through the external device 1200 regularly or in real time.

The server device 1300 may transmit a text message including information on the vibration state or noise state of the machine to the mobile phone 1250 . Users who check the text message can inquire about and take action on defective machines in real time.

The detailed description of the preferred embodiments of the present invention disclosed as described above is provided to enable any person skilled in the art to make and practice the present invention. Although the above has been described with reference to preferred embodiments of the present invention, it will be understood by those skilled in the art that various modifications and changes can be made to the present invention without departing from the scope of the present invention. For example, those skilled in the art can use each configuration described in the above-described embodiments in a way in combination with each other. Accordingly, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The present invention may be embodied in other specific forms without departing from the spirit and essential characteristics of the present invention. Accordingly, the above detailed description should not be construed as restrictive in all respects but as exemplary. The scope of the present invention should be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present invention are included in the scope of the present invention. The present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein. In addition, claims that are not explicitly cited in the claims may be combined to form an embodiment, or may be included as new claims by amendment after filing.

10: fault diagnosis device,
10a: a first fault diagnosis device;
10b: a second defect diagnosis device;
20: attachment part;
30: cable support,
50: power unit,
70: control unit;
100: acoustic sensor,
110: buffer,
120 : data string,
130: duplicate data string,
200: vibration sensor,
300: signal processing unit,
400: time and frequency data forming unit,
410: time domain data,
420: frequency domain data,
500: code value calculation unit,
600: comparison unit,
700: defect pattern setting unit,
800: standard setting unit,
850: terminal part,
900: defect notification unit,
1000: data storage unit,
1100: communication department;
1200: external device,
1200a: first group external device;
1200b: second group external device;
1200c: third group external device;
1250: wireless network;
1260: mobile phone;
1270: Internet,
1280: the first local area network;
1290: a second local area network;
1300: server device,
1310: database unit;
1312: sensor management DB,
1314: Error and abnormal DB,
1316: Text sending DB,
1318: data DB,
1340: data conversion unit,
1360: big data processing unit,
1380: Cloud.

Claims (13)

Vibration sensor 100 for detecting the vibration of the machine;
an acoustic sensor 200 for detecting the noise of the machine;
a time and frequency data forming unit 400 for forming time domain data 410 and frequency domain data 420 from the signals of the vibration sensor 100 and the acoustic sensor 200, respectively;
Applying a crest factor inspection method to the time domain data 410 and applying at least one of a peak inspection method, a band inspection method, and a curve inspection method to the frequency domain data 420 to calculate a vibration code value and a noise code value, respectively code value calculator 500;
If there are stored vibration standards and noise standards, they are used, but when the user sets the vibration standards and noise standards in order to measure and manage vibration and noise at any location in the machine, the a reference setting unit 800 for performing a function of measuring a plurality of noises, calculating the average value and standard deviation of the measured vibration signal and the noise signal, and setting the vibration standard and the noise standard under each operating condition;
a defect pattern setting unit 700 in which the defect pattern data of the machine is stored;
Based on the defect pattern data of the machine read out from the defect pattern setting unit 700 , the vibration code value of the code value calculation unit 500 is based on the vibration reference and the noise standard of the reference setting unit 800 . and a comparison unit 600 for comparing each of the noise code values;
a defect notification unit 900 for expressing the comparison result to the outside based on the comparison result of the comparison unit 600;
When it is determined that there is a defect in the comparison result, a data storage unit 1000 for storing time domain data 410 and frequency domain data 420 of the vibration sensor 100 and the acoustic sensor 200 before and after the defect. ;
a communication unit 1100 for transmitting data stored in the data storage unit 1000 to an external device 1200 and receiving a control command from the external device 1200; and
an attachment portion (20) having a magnet for frequent attachment or detachment to the surface of the machine;
The time and frequency data forming unit 400,
a buffer 110 for storing a data string 120 generated by digitally sampling signals of the vibration sensor 100 and the acoustic sensor 200, respectively; and
Further comprising; a control unit 70 for FFT-converting the data string 120 in the buffer 110;
Time domain data 410 is generated based on the data string 120, and
Frequency domain data 420 is generated based on the FFT transformation,
The data string 120 is at least 50% overlapped with the data string 120 before and after the sampling. A machine fault diagnosis apparatus using vibration and noise signals. delete delete The method of claim 1,
The communication unit 1100 is a machine fault diagnosis device using vibration and noise signals, characterized in that it includes one of a Bluetooth communication module, a Wi-Fi communication module, an infrared communication module, a LAN communication module, and a USB communication module. delete The method of claim 1,
When it is desired to set the vibration standard and the noise standard of the reference setting unit 800 from an external input, a machine fault diagnosis using vibration and noise signals, characterized in that it further comprises a terminal unit 850 for the external input. Device. The method of claim 1,
When it is desired to set the vibration standard and the noise standard of the reference setting unit 800 from an external input, a mechanical defect using vibration and noise signals, characterized in that it is set by the data received through the communication unit 1100 diagnostic device. A group is formed by including a plurality of machine fault diagnosis devices (10) using vibration and noise signals according to any one of claims 1, 4, 6 and 7,
A vibration and noise defect diagnosis system, characterized in that one external device can communicate simultaneously or sequentially with a plurality of the machine defect diagnosis devices (10). A group is formed by including a plurality of machine fault diagnosis devices (10) using vibration and noise signals according to any one of claims 1, 4, 6 and 7,
One external device communicates with the plurality of machine fault diagnosis devices 10 simultaneously or sequentially,
A plurality of the group and the external device are configured,
A vibration and noise defect diagnosis system, characterized in that the plurality of external devices communicate with the server device (1300). A group is formed by including a plurality of machine fault diagnosis devices (10) using vibration and noise signals according to any one of claims 1, 4, 6 and 7,
One external device communicates with the plurality of machine fault diagnosis devices 10 simultaneously or sequentially,
The external device 1200 communicates with the server device 1300,
The server device 1300,
a database unit 1310 for storing data received from the external device 1200;
a data conversion unit 1340 for converting the data stored in the database unit 1310 into a predetermined format;
a big data processing unit 1360 for learning the data converted by the data conversion unit 1340; and
Including a; cloud 1380 for storing the big data;
The big data stored in the cloud 1380 is stored in the defect pattern setting unit 700 as defect pattern data through the external device 1200. Data-driven smart sensor system. 11. The method of claim 10,
Connecting to the server device 1300 or further comprising a mobile phone 1250 capable of wireless communication with at least one of the plurality of machine fault diagnosis devices 10 through a first local area network 1280 A big data-based smart sensor system using a machine fault diagnosis device using vibration and noise signals. 12. The method of claim 11,
The server device (1300) is a machine defect using vibration and noise signals, characterized in that it further comprises means for transmitting a text message including information on the vibration state or noise state of the machine to the mobile phone (1250). A smart sensor system based on big data using a diagnostic device. 13. The method of claim 12,
The database unit 1310,
a sensor management DB 1312 in which information is stored in the machine fault diagnosis device 10;
Error and anomaly DB 1314 in which a history of errors and abnormalities related to vibration and noise of the machine is stored; and
a text sending DB 1316 in which the text and sending history of the text message are stored; Big data-based smart sensor system using a machine fault diagnosis device using vibration and noise signals, characterized in that it includes at least one of.

Images