KR20200077475A - Module type predictive maintenance apparatus and method to predicting flaw of facility - Google Patents

Abstract

Provided is a module type predictive maintenance apparatus which is attached to a facility to predict a defect of the facility, which comprises: a data collection unit collecting dynamic physical quantity data from at least one sensor device installed in the facility; a defect factor extraction unit extracting at least one defect factor related to the defect of the facility from the collected dynamic physical quantity data; a reference value determining unit determining a reference value for each of at least one defect factor through learning on at least one defect factor; and a defect prediction unit predicting the defect type of the facility based on a ratio between the determined reference value and the measured value of the dynamic physical quantity data.

Description

Modular predictive maintenance device and method for predicting equipment defects{MODULE TYPE PREDICTIVE MAINTENANCE APPARATUS AND METHOD TO PREDICTING FLAW OF FACILITY}

The present invention relates to a modular predictive maintenance device and method for predicting equipment defects.

The predictive maintenance system is a system that measures and monitors data related to defect characteristics of equipment to check the condition of the equipment, and predicts equipment defects through changes in data related to defect characteristics.

The conventional foresight preservation system is composed of a multi-channel (eg, 50 to 100 channel) terminal box installed in a facility, a data acquisition module (DAQ) module, and an external integrated server.

According to such a conventional predictive maintenance system, when a terminal box and a collection module collect static physical quantity data and dynamic physical quantity data (eg, vibration, etc.) from a sensor device installed in a facility, and transmit it to an external integrated server, the external integrated server Determines whether the equipment is defective.

According to such a conventional predictive maintenance system, there is a problem in that an expert analyzes a defect state of a facility through a monitor connected to an external integrated server and processes it.

Korean Registered Patent Publication No. 10-1677358 (released on August 08, 2016)

The present invention is to solve the above-described problems of the prior art, it is intended to predict the defects of the facility through a modular predictive maintenance device attached to the facility. Specifically, the present invention seeks to determine a reference value for each coupling factor by collecting dynamic physical quantity data in a modular predictive preservation device and learning defect factors related to defects of equipment extracted from the collected dynamic physical quantity data. In addition, the present invention is intended to predict the type of defects of a facility based on a ratio between a reference value determined for each defect factor and a measured value of dynamic physical quantity data collected in real time. However, the technical problems to be achieved by the present embodiment are not limited to the technical problems as described above, and other technical problems may exist.

As a technical means for achieving the above technical problem, a modular predictive maintenance device attached to a facility according to the first aspect of the present invention and predicting a defect of the facility includes dynamic physical quantity data from at least one sensor device installed in the facility. Data collection unit for collecting; A defect factor extraction unit for extracting at least one defect factor related to the defect of the facility from the collected dynamic physical quantity data; A reference value determining unit that determines a reference value for each of the at least one defect factor through learning of the at least one defect factor; And a defect prediction unit predicting a defect type of the facility based on a ratio between the determined reference value and the measured value of the dynamic physical quantity data.

A method for predicting a defect in a facility in the modular predictive maintenance device according to the second aspect of the present invention comprises the steps of collecting dynamic physical quantity data from at least one sensor device installed in the facility, from the collected dynamic physical quantity data Extracting at least one defect factor associated with a defect, determining a reference value for each of the at least one defect factor through learning of the at least one defect factor, and measuring values of the determined reference value and the dynamic physical quantity data And predicting a defect type of the facility based on the ratio of liver.

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

According to any one of the above-described problem solving means of the present invention, it is possible to predict the defect of the facility through the modular predictive maintenance device attached to the facility.

Specifically, the present invention can determine the reference value for each coupling factor by collecting dynamic physical quantity data in the modular predictive preservation device, and learning defect factors related to defects of equipment extracted from the collected dynamic physical quantity data.

In addition, the present invention can predict whether a facility is defective based on a ratio between a reference value determined for each defect factor and a measured value of dynamic physical quantity data collected in real time.

Through this, the present invention can automatically predict the defect state of the facility even if a separate expert does not reside in order to analyze the defect of the facility, so as to inform the terminal of the facility manager of the defect information of the facility.

In addition, the present invention can collect physical quantity data from the modular predictive preservation device without going through the terminal box. That is, since the terminal box does not need to be separately installed in the facility, the purchase cost of the terminal box can be reduced. In addition, since the present invention determines whether a facility is defective in a modular predictive maintenance device without having to transmit the physical quantity data collected to an existing external integrated server, it is possible to promptly inform the facility manager of the defect information of the facility.

1 is a configuration diagram of a facility defect prediction system according to an embodiment of the present invention.
FIG. 2 is a block diagram of the modular predictive preservation apparatus illustrated in FIG. 1 according to an embodiment of the present invention.
3 is a diagram illustrating a defect prediction table according to an embodiment of the present invention.
4 is a flowchart illustrating a method for predicting a defect in equipment according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present invention pertains can easily practice. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the present invention in the drawings, parts irrelevant to the description are omitted, and like reference numerals are assigned to similar parts throughout the specification.

Throughout the specification, when a part is "connected" to another part, this includes not only "directly connected" but also "electrically connected" with other elements in between. . Also, when a part “includes” a certain component, this means that other components may be further included, rather than excluding other components, unless otherwise specified.

In the present specification, the term “unit” includes a unit realized by hardware, a unit realized by software, and a unit realized by using both. Further, one unit may be realized by using two or more hardware, and two or more units may be realized by one hardware.

Some of the operations or functions described in this specification as being performed by the terminal or device may be performed instead on a server connected to the corresponding terminal or device. Similarly, some of the operations or functions described as being performed by the server may be performed in a terminal or device connected to the corresponding server.

Hereinafter, specific contents for carrying out the present invention will be described with reference to the accompanying drawings or process flow charts.

1 is a configuration diagram of a facility defect prediction system according to an embodiment of the present invention.

Referring to FIG. 1, the facility defect prediction system may include at least one modular predictive maintenance device 100, at least one sensor device 120, and a user terminal 130. However, since the facility defect prediction system of FIG. 1 is only one embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1, and may be configured differently from FIG. 1 according to various embodiments of the present invention. .

Generally, each component of the facility defect prediction system of FIG. 1 is connected through a network (not shown). The network means a connection structure capable of exchanging information between nodes such as terminals and servers, and a local area network (LAN), a wide area network (WAN), and the Internet (WWW: World) Wide Web), wired and wireless data communication networks, telephone networks, and wired and wireless television communication networks. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), Wi-Fi, Bluetooth communication, infrared communication, ultrasound Communication, Visible Light Communication (VLC), LiFi, and the like are included, but are not limited thereto.

The modular predictive preservation device 100 is a device in which functions of a terminal box, a data collection module, and an external integrated server in a conventional predictive preservation device are integrated, and may be configured as a small module. For example, it can be used in the facility 110 only by interlocking the input terminal with the sensor of the facility 110. In addition, the modular predictive maintenance device 100 may include a wireless communication module for communicating with the user terminal 130.

In this way, the predictive preservation device 100 of the present invention is configured in a modular form, and thus, it is not necessary to construct a terminal box, a data collection module, and an external integrated server like a conventional predictive maintenance device. In addition, it is possible to communicate between the modular predictive maintenance device 100 and the user terminal 130 without having to construct a separate communication network.

The modular predictive maintenance device 100 may predict a defect of the facility 110. At this time, a plurality of modular predictive preservation devices 100 may be attached to one facility 110, and one modular predictive preservation device 100 may be attached to each facility 110.

The modular predictive preservation device 100 may collect dynamic physical quantity data from at least one sensor device 120 installed in the facility 110. Here, the dynamic physical quantity data is different from the static physical quantity data such as temperature, and may include, for example, at least one of vibration, noise, and current generated in the facility 110.

The modular predictive maintenance device 100 may collect dynamic physical quantity data from at least one sensor device 120 through an input terminal composed of a plurality of channels. Here, the input terminal of the modular predictive preservation device 100 may be composed of, for example, 4 to 8 channels.

The modular predictive preservation apparatus 100 may extract at least one defect factor related to a defect of the facility 110 from the collected dynamic physical quantity data. Here, the at least one defect factor may be, for example, a defect factor for each of vibration, noise, and current.

The modular predictive preservation apparatus 100 determines a reference value for each of the at least one defect factor through learning about the at least one defect factor, and between a reference value determined for each defect factor and a measurement value of dynamic physical quantity data collected in real time It is possible to predict whether the facility 110 is defective based on the ratio.

The modular predictive maintenance device 100 may transmit an alarm message to the user terminal 130 about whether the facility 110 is defective based on a ratio between a reference value determined for each defect factor and a measured value of dynamic physical quantity data.

Hereinafter, the operation of each component of the facility defect prediction system of FIG. 1 will be described in more detail.

FIG. 2 is a block diagram of the modular foresight preservation device 100 illustrated in FIG. 1 according to an embodiment of the present invention.

Referring to FIG. 2, the modular predictive preservation apparatus 100 includes a data collection unit 200, a defect factor extraction unit 210, a reference value determination unit 220, a defect prediction unit 230, and an alarm message transmission unit 240 ) And the storage unit 250. Here, the defect factor extraction unit 210 may include a parameter determination unit 212. However, the modular predictive preservation apparatus 100 illustrated in FIG. 2 is only one example of implementation of the present invention, and various modifications are possible based on the components illustrated in FIG. 2.

The data collection unit 200 may collect dynamic physical quantity data from at least one sensor device 120 installed in the facility 110. Here, the dynamic physical quantity data may include at least one of vibration, noise, current, and voltage generated in the facility 110. For example, the data collection unit 200 may collect vibration data generated in the facility 110 from the vibration sensor device and noise data generated in the facility 110 from the noise sensor device.

The data collection unit 200 is composed of a plurality of channels for collecting dynamic physical quantity data from at least one sensor device 120. Here, the plurality of channels may be 4 to 8 channels.

The defect factor extraction unit 210 may extract at least one defect factor related to a defect of the facility 110 from the collected dynamic physical quantity data.

The defect factor extraction unit 210 may extract a frequency domain related to the defect factor using a band pass filter. Specifically, the defect factor extraction unit 210 may extract a frequency domain related to a defect factor from a spectrum of dynamic physical quantity data converted to frequency. For example, the defect factor extraction unit 210 may extract a frequency domain associated with each defect factor according to frequency characteristics of individual dynamic physical quantity data through a Fast Fourier Transform (FFT) spectrum analysis function. Alternatively, the defect factor extraction unit 210 performs primary filtering on at least one dynamic physical quantity data through a fast Fourier transform (FFT), and then secondary-filtered time waveform through an inverse fast Fourier transform (IFFT). Data can be extracted as defect factors. For example, the defect factor extraction unit 210 may extract amplitude change, period change, and waveform shape of the defect vibration frequency from the spectrum of the vibration　 frequency.

As another example, the defect factor extraction unit 210 may extract a maximum value of a waveform related to a defect factor from a time waveform of the dynamic physical quantity data before converting the dynamic physical quantity data into frequency. As another example, the defect factor extraction unit 210 may extract a representative value related to a defect factor from a spectrum or a time waveform of dynamic physical quantity data using a demodulation technique.

The parameter determination unit 212 may differently determine a parameter indicating a defect state for each of the at least one defect factor. Here, the parameter may include at least one of an overall value, a partial overall value, a value between maximum frequency peaks, a crest factor value, and a root mean square (RMS) value. . Here, the parameter may be based on data included in a frequency domain (ie, corresponding to a frequency domain of a defect factor) extracted through, for example, an interval pass filter.

For example, the parameter determination unit 212 may use the result of calculating the data included in a specific frequency domain representing a defect state of noise (or vibration, etc.) as an RMS value as a parameter. Alternatively, the parameter determining unit 212 may use a peak value or a peak-peak value in a time waveform for a defect factor of noise (or vibration, etc.) as a parameter. At this time, since the peak value (or RMS value) in the time waveform (or frequency domain) for noise and the peak value (or RMS value) in the time waveform (or frequency domain) for vibration are different, each parameter is also It can be determined differently. For example, in the case of a defect factor such as speed, acceleration, noise, current, voltage, etc., the parameter determination unit 212 may use the overall value as a parameter. For example, in the case of data included in the frequency domain extracted through the interval pass filter, the parameter determiner 212 may use the partial overall value as a parameter.

The parameter determination unit 212 may determine parameters based on the operating conditions of the facility 110. For example, the parameter determination unit 212 may determine the parameter for at least one defect factor based on the dynamic physical quantity data collected when the facility 110 is operated under a heavy load operation condition.

For example, when the facility 110 is continuously operated at the same rotational speed or the same load for 24 hours, it is not necessary to determine the parameters according to the operating conditions, and the defect factor is based on the dynamic physical quantity data collected at predetermined times. You can determine the parameters for. However, in the case of a facility 110 in which load or rotational speed is variable, the load is the greatest after determining the environmental conditions that have the greatest impact on the time zone or the facility 110 where the load is greatest during operation of the facility 110 for each cycle. The parameters for the defect factor can be determined based on the dynamic physical quantity data collected when operating in time zone or environmental requirements.

The reference value determining unit 220 may perform learning on at least one defect factor based on the operation pattern of the facility 110. For example, the reference value determining unit 220 may perform learning on at least one defect factor for each defect factor based on a variable degree of load or rotation speed of the facility 110.

The reference value determining unit 220 may differently determine a reference value for each of the at least one defect factor through learning about the at least one defect factor. For example, the reference value determining unit 220 performs learning on the first defect factor (eg, vibration) to determine a reference value for the first defect factor, and learns about the second defect factor (eg, noise). A reference value for the second defect factor can be determined under performance.

The reference value determining unit 220 may input a parameter determined for each of the at least one defect factor into a statistical processing algorithm to calculate an average value and a standard deviation for each defect factor.

The reference value determining unit 220 may determine the reference value for each defect factor using the average value and the standard deviation calculated for each defect factor. Here, the reference value can be calculated through [Equation 1].

[Equation 1]

Reference value = {Average value + (Standard deviation X 1st preset multiple (2~3))}

The defect predicting unit 230 may predict whether the facility 110 is defective (or a defect type) based on a ratio between a reference value determined for each defect factor and a measurement value of dynamic physical quantity data. For example, when the ratio between the reference value of the first defect factor and the measured value in the dynamic physical quantity data exceeds the first ratio, the defect predicting unit 230 is worn out of consumables (eg, bearings) of the facility 110 I can judge. Alternatively, when the ratio between the reference value of the first defect factor and the measured value in the dynamic physical quantity data exceeds the second ratio, the defect predicting unit 230 may malfunction or seriously defect (eg, breakage, crack, etc.) of the facility 110. ) Can be diagnosed. Alternatively, when the ratio between the reference value of the second defect factor and the measured value of the dynamic physical quantity data exceeds the first ratio, it may be determined that a defect has occurred in the consumables of the facility 110.

The alarm message transmitter 240 may transmit an alarm message for the presence or absence of a defect (or defect type) to the user terminal 130 based on a ratio between a reference value determined for each defect factor and a measured value of dynamic physical quantity data. Here, the alarm message can be extracted from the defect prediction table based on the ratio.

The defect prediction table will be described with reference to FIG. 3 for a moment. Referring to FIG. 3, the defect prediction table may include information on a ratio between a reference value and a measured value of dynamic physical quantity data, defect information (or defect type), and information on an alarm message according to the defect ratio.

For example, when the ratio between the reference value of the first defect factor and the measured value in the dynamic physical quantity data exceeds the first ratio 300, the alarm message transmitting unit 240 first ratio 300 in the defect prediction table It extracts the first alarm message corresponding to, and may transmit the first alarm message to the user terminal (130). Here, the first alarm message may include defect information on consumable replacement.

At this time, the first ratio 300 is determined based on the average value of each defect factor, and can be calculated through [Equation 2].

[Equation 2]

1st ratio = average value of each defect factor * 2nd preset multiple (0.7~1.5)

For example, when the ratio between the reference value of the first defect factor and the measured value in the dynamic physical quantity data exceeds the second ratio 302, the defect predicting unit 230 determines the second ratio 302 from the defect prediction table. The corresponding second alarm message may be extracted and the second alarm message may be transmitted to the user terminal 130. Here, the second alarm message may include defect information regarding a critical defect of the facility 110.

At this time, the second ratio 302 is determined based on the average value of each defect factor, and may be calculated through [Equation 3].

[Equation 3]

2nd ratio = average value of each defect factor * 3rd preset multiple (1.5~3)

For example, when the ratio between the reference value of the first defect factor and the measured value in the dynamic physical quantity data exceeds the third ratio 304, the defect predicting unit 230 displays the third ratio 304 in the defect prediction table. The corresponding third alarm message may be extracted and the third alarm message may be transmitted to the user terminal 130. Here, the third alarm message may include defect information including a request to stop the facility 110.

At this time, the third ratio 304 is determined based on the average value of each defect factor, and may be calculated through [Equation 4].

[Equation 4]

3rd ratio = average value of each defect factor * 4th preset multiple (3 or more)

As described above, a defect prediction table including information on the ratio between the reference value and the measured value of the dynamic physical quantity data, defect information, and alarm message according to the defect ratio is managed, and through this, a notification message according to the ratio of each defect factor By transmitting the to the user terminal 130, there is no need to analyze the data on the defects of the equipment, and accordingly, there is no need for an expert to analyze the data.

2, the storage unit 250 may store dynamic physical quantity data collected from at least one sensor device 120. Also, the storage unit 250 may classify and store parameters determined differently for each defect factor for each defect factor. Also, the storage unit 250 may store a defect prediction table. Examples of the storage unit 250 include a hard disk drive, a read only memory (ROM), a random access memory (RAM), a flash memory, and a memory card that exist inside or outside the modular predictive preservation device 100. Is included.

On the other hand, those skilled in the art, data collection unit 200, defect factor extraction unit 210, parameter determination unit 212, reference value determination unit 220, defect prediction unit 230, alarm message transmission unit 240 and storage It will be fully understood that each of the parts 250 may be implemented separately, or one or more of them may be integrated and implemented.

4 is a flowchart illustrating a method for predicting a defect in a facility 110 according to an embodiment of the present invention.

Referring to FIG. 4, in step S401, the modular foresight preservation device 100 may collect dynamic physical quantity data from at least one sensor device 120 installed in the facility 110. Here, the dynamic physical quantity data may include, for example, at least one of vibration, noise, and current generated in the facility 110.

In step S403, the modular predictive preservation apparatus 100 may extract at least one defect factor related to the defect of the facility 110 from the collected dynamic physical quantity data.

In step S405, the modular predictive maintenance apparatus 100 may determine a reference value for each of the at least one defect factor through learning about the at least one defect factor.

In step S407, the modular predictive maintenance device 100 may predict whether the facility 110 is defective based on the ratio between the determined reference value and the measured value of the dynamic physical quantity data.

In the above description, steps S401 to S407 may be further divided into additional steps or combined into fewer steps, according to an embodiment of the present invention. In addition, some steps may be omitted if necessary, and the order between the steps may be changed.

One embodiment of the present invention may also be implemented in the form of a recording medium including instructions executable by a computer, such as program modules, being executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, the computer-readable medium may include any computer storage medium. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The above description of the present invention is for illustration only, and a person having ordinary knowledge in the technical field to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts thereof should be interpreted to be included in the scope of the present invention. .

100: modular predictive preservation device
110: equipment
120: sensor device
200: data collection unit
210: defect factor extraction unit
212: parameter determination unit
220: reference value determining unit
230: defect prediction unit
240: alarm message transmission unit
250: storage

Claims (14)

In the modular predictive maintenance device attached to the facility to predict the defect of the facility,
A data collection unit for collecting dynamic physical quantity data from at least one sensor device installed in the facility;
A defect factor extraction unit for extracting at least one defect factor related to the defect of the facility from the collected dynamic physical quantity data;
A reference value determining unit that determines a reference value for each of the at least one defect factor through learning of the at least one defect factor; And
A defect prediction unit that predicts a defect type of the facility based on the ratio between the determined reference value and the measured value of the dynamic physical quantity data
Including,
The defect factor extraction unit
A parameter indicating a defect state is determined for each of the at least one defect factor based on the operating conditions of the facility,
The reference value determining unit
A modular predictive preservation device for determining a reference value for each defect factor using a parameter determined for each of the at least one defect factor.
According to claim 1,
The data collection unit is composed of a plurality of channels for collecting the dynamic physical quantity data from the at least one sensor device, modular predictive maintenance device.
According to claim 2,
The plurality of channels will be 4 to 8 channels, modular predictive preservation device.
According to claim 1,
The defect factor extraction unit
And a parameter determining unit for differently determining the parameter representing a defect state for each of the at least one defect factor.
The method of claim 4,
The parameter includes at least one of an overall value, a partial overall value, a maximum frequency peak-to-peak value, a crest factor value, and a root mean square (RMS) value. Preservation device.
The method of claim 5,
The defect factor extraction unit
Modular predictive maintenance device that extracts the frequency domain associated with the defect factor using a band pass filter.
The method of claim 6,
The parameter is based on the data included in the extracted frequency domain, modular predictive maintenance device.
The method of claim 4,
The reference value determining unit, based on the operation pattern of the facility, to perform the learning for the at least one defect factor, modular predictive maintenance device.
The method of claim 4,
The reference value determining unit
Modular predictive maintenance device that calculates an average value and a standard deviation for each defect factor by inputting a parameter determined for each of the at least one defect factor into a statistical processing algorithm.
The method of claim 9,
The reference value determining unit
Modular predictive maintenance device that determines the reference value for each defect factor by using the average value and the standard deviation calculated for each defect factor.
According to claim 1,
And an alarm message transmission unit for transmitting an alarm message for the defect to the user terminal based on a ratio between the determined reference value and the measured value of the dynamic physical quantity data.
The method of claim 11,
The alarm message is extracted based on the ratio in the defect prediction table,
The defect prediction table includes information on a ratio between a reference value and a measured value of dynamic physical quantity data, information on a defect information, and an alarm message according to the defect ratio.
According to claim 1,
The dynamic physical quantity data includes at least one of vibration, noise, and current generated in the facility.
A method for predicting a defect in a facility in a modular predictive maintenance device,
Collecting dynamic physical quantity data from at least one sensor device installed in the facility;
Extracting at least one defect factor related to the defect of the facility from the collected dynamic physical quantity data;
Determining a reference value for each of the at least one defect factor through learning of the at least one defect factor; And
Predicting a defect type of the facility based on a ratio between the determined reference value and the measured value of the dynamic physical quantity data.
Including,
Extracting the at least one defect factor is
Determining a parameter indicating a defect state for each of the at least one defect factor based on the operating conditions of the facility,
Determining the reference value is
And determining a reference value for each defect factor using a parameter determined for each of the at least one defect factor.

Images