Equipment failure prediction and diagnosis device and method

Abstract

The present invention relates to an equipment failure prediction and diagnosis device and method, and introduces an equipment failure prediction and diagnosis device including an equipment data collection unit equipped with at least one individual board having a plurality of input channels corresponding to the type of equipment to be diagnosed and into which data of the equipment to be diagnosed is input, and an equipment data processing unit equipped with a common board that supplies power to the equipment data collection unit and performs real-time data judgment on data of the equipment to be diagnosed input from at least one of the plurality of input channels as a diagnostic model corresponding to that channel, the equipment data collection unit and the equipment data processing unit being connected by a serial communication interface and integrally combined.

Description

[Technical Field]

[0001] The present invention relates to an equipment failure prediction and diagnosis device and method for miniaturizing the device by integrally combining an equipment data collection unit and an equipment data processing unit, and ensuring the scalability and maintainability of line application. [Background technology]

[0002] In the equipment field, there is a trend towards applying prognostics and health management (PHM) to diagnose the current state of equipment and predict failures. Prognostic management is growing rapidly because it not only reduces costs but also enables stable system operation and realizes cost-effective, downtime-free maintenance.

[0003] In addition, unlike cloud computing data centers, which manage data in a centralized manner in physically distant locations, edge systems are used that support computing at the edge of the network, close to devices (things), allowing each device to analyze and utilize individual data.

[0004] Meanwhile, typical equipment failure prediction and diagnosis devices have separate systems for edge computing. To perform edge computing functions, there is a separate device for collecting data from the equipment being diagnosed and a separate device for processing the collected data. The connection between the two devices is typically via wired communication such as Universal Serial Bus (USB) or Ethernet. However, USB connections are slow, and Ethernet methods also have the risk of data loss. Ultimately, connecting individual devices results in poorer maintainability and scalability than configuring them as a single system.

[0005] Therefore, there is a need for a solution that can miniaturize a system for performing edge computing into a single device and transmit data at high speed while preventing data loss and noise.

[0006] The matters described above as background art are merely intended to enhance understanding of the background of the present invention and should not be construed as admitting that they constitute prior art already known to those having ordinary skill in the art. Summary of the Invention [Problem to be solved by the invention]

[0007] The present invention aims to provide an equipment failure prediction and diagnosis device and method that reduces costs by making the device smaller through a structure in which an equipment data collection unit and an equipment data processing unit are integrally combined, enables predictive maintenance by performing equipment status diagnosis in real time, and ensures scalability and maintainability of line application. [Means for solving the problem]

[0008] As a means for solving the above technical problems, the present invention can include an equipment failure prediction and diagnosis device that includes an equipment data collection unit equipped with at least one individual board having a plurality of input channels corresponding to the type of equipment to be diagnosed and into which data of the equipment to be diagnosed is input, and an equipment data processing unit equipped with a common board that supplies power to the equipment data collection unit and performs real-time data judgment on data of the equipment to be diagnosed input from at least one of the plurality of input channels as a diagnostic model corresponding to that channel, wherein the equipment data collection unit and the equipment data processing unit are connected by a serial communication interface and integrally combined.

[0009] For example, the equipment data processing unit transmits the collected data to an external server, and the external server may include a PHM (Prognostics and Health Management) server that diagnoses the condition of the equipment based on the processed data, predicts the equipment's failure or lifespan, and judges the data in a manner that calculates the time to replace the equipment.

[0010] For example, the external server stores multiple diagnostic models corresponding to at least one of the equipment condition diagnosis and lifespan prediction algorithms, and the equipment data processing unit can receive from the external server a diagnostic model corresponding to the type of equipment recognized on the common board.

[0011] For example, the equipment data collection unit may convert data input via at least one of a plurality of input channels into a digital signal, parse the converted data, and store it in a buffer.

[0012] For example, the buffer may include a first buffer that stores parsed data parsed at a first sampling rate and a second buffer that stores parsed data downsampled at a second sampling rate that is lower than the first sampling rate.

[0013] For example, the equipment data processing unit can transmit the data in the first buffer to an external server and store the data in the second buffer in a database.

[0014] For example, the data input from the equipment to be diagnosed may include at least one of speed data, vibration data, current data, and temperature data obtained from the equipment.

[0015] For example, at least one individual board may be provided in a removable manner.

[0016] For example, if the accumulated data stored in the buffer is larger than a predetermined size, the equipment data collection unit can insert the data into a data queue so that the data can be thread-processed by the equipment data processing unit.

[0017] For example, the equipment data processing unit can determine whether the size of the data queue is equal to or greater than 0, and extract data from the data queue if the size of the data queue is equal to or greater than 0.

[0018] For example, the serial communication can include SPI communication.

[0019] As a method for solving the above technical problems, the present invention provides an equipment failure prediction and diagnosis method for controlling an equipment failure prediction and diagnosis device in which an equipment data collection unit and an equipment data processing unit, each of which is equipped with at least one individual board having a plurality of input channels and connected to each other via a serial communication interface, are integrally coupled, the method comprising the steps of: inputting data of equipment to be diagnosed; The method may include a step of performing real-time data judgment using data of the equipment to be diagnosed input from at least one of the plurality of input channels as a diagnostic model corresponding to that channel.

[0020] For example, the method may further include a step of evaluating the data in a manner that diagnoses the state of the equipment based on the processed data, predicts the failure or lifespan of the equipment, and calculates the time to replace the equipment.

[0021] For example, the method may further include converting data input via at least one of the plurality of input channels into a digital signal, parsing the converted data, and storing the parsed data in a buffer.

[0022] For example, if the accumulated data stored in the buffer is larger than a predetermined size, the method may further include inserting the data into a data queue so that the data can be thread-processed in the equipment data processing unit.

[0023] For example, the method may further include determining whether the size of the data queue is equal to or greater than 0, and extracting data from the data queue if the size of the data queue is equal to or greater than 0. [Effects of the Invention]

[0024] According to the equipment failure prediction and diagnosis device and method of the present invention, the equipment data collection unit and the equipment data processing unit are integrated into a single structure, which allows for a smaller device and reduced costs, enables real-time equipment status diagnosis to enable predictive maintenance, and ensures scalability and maintainability of line application. Furthermore, the integrated and integrated structure reduces design costs compared to an external connecting structure, and allows for a compact configuration adjacent to the equipment.

[0025] The effects obtained by the present invention are not limited to those described above, and other effects not described above will be clearly understood by those having ordinary skill in the art to which the present invention pertains from the following description. [Brief explanation of the drawings]

[0026] [Figure 1] 1 is an external perspective view showing an equipment failure prediction and diagnosis device according to an embodiment of the present invention. [Figure 2] FIG. 2 is a diagram showing the configuration of an equipment data collection unit and an equipment data processing unit that constitute the equipment failure prediction and diagnosis device. [Figure 3] 10 is a table showing the reliability verification results of data input via an input channel. [Figure 4] FIG. 2 is a functional block diagram of the entire system. [Figure 5] 10 is a diagram illustrating a process in which the equipment data collector parses data converted into a digital signal and stores the data in a first buffer and a second buffer. FIG. [Figure 6] 10 is a flowchart illustrating a method for collecting and storing data in an equipment failure prediction and diagnosis device. DETAILED DESCRIPTION OF THE INVENTION

[0027] With respect to the embodiments of the present invention disclosed in this specification or application, specific structural or functional descriptions are merely exemplary for describing the embodiments according to the present invention, and the embodiments according to the present invention may be embodied in various forms and are not limited to the embodiments described in this specification or application.

[0028] Since the embodiments of the present invention can be modified in various ways and can have various forms, specific embodiments will be illustrated in the drawings and described in detail in this specification or application. However, this is not intended to limit the embodiments according to the concept of the present invention to the specific disclosed forms, and it should be understood that the present invention includes all modifications, equivalents, and alternatives included in the spirit and technical scope of the present invention.

[0029] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which this invention pertains. Terms as defined in commonly used dictionaries should be interpreted in a way that is consistent with the meaning they have in the context of the relevant art, and should not be interpreted in an idealized or overly formal sense unless expressly defined herein.

[0030] The present invention will now be described in detail by describing preferred embodiments thereof with reference to the accompanying drawings, in which the same reference numerals in the various drawings denote the same elements.

[0031] Before describing an equipment failure prediction and diagnosis method according to an embodiment of the present invention, the configuration of an equipment failure prediction and diagnosis device 1000 applicable to the embodiment will be described first.

[0032] 1 and 2 are respectively an external perspective view of an equipment failure prediction and diagnosis device 1000 according to one embodiment of the present invention, and a functional diagram of an equipment data collection unit 400 and an equipment data processing unit 500 that constitute the equipment failure prediction and diagnosis device 1000.

[0033] FIG. 1 is an external perspective view of an equipment failure prediction and diagnosis device 1000. The equipment failure prediction and diagnosis device 1000 is also called a CMS (Condition Monitoring System) module. The equipment failure prediction and diagnosis device 1000 may include a housing case 100, cooling fins 200, an equipment data collection unit 400, an equipment data processing unit 500, and an external connection port. First, the housing case 100 surrounds the exterior of the equipment failure prediction and diagnosis device 1000 and is made of aluminum, thereby reducing the weight of the equipment failure prediction and diagnosis device 1000. In addition, the interior and exterior of the equipment failure prediction and diagnosis device 1000 may be connected by a bolted structure, facilitating the attachment and detachment of individual boards 410 and 420, which will be described later. In addition, a plurality of cooling fins 200 are provided on the exterior of the housing case 100 and can dissipate heat generated by the CPU 513A and the GPU 513B.

[0034] In addition, the equipment failure prediction and diagnosis device 1000 can be manufactured in a monolithic structure in which one service is configured as one huge structure, compared to a system configuration capable of edge computing. The equipment failure prediction and diagnosis device 1000 has a low height and a width greater than its front-to-back length, which lowers the center of gravity and ensures stability.

[0035] Meanwhile, the equipment failure prediction and diagnosis device 1000 may be provided with an external connection port 300 for connection to the outside. The external connection port 300 may include an 8-channel BNC (Bayonet Neill-Concelman) connector (411) and a VCC (Voltage of Common Collector) / GND (Ground) port, which may be provided on the front of the equipment failure prediction and diagnosis device 1000. A power connector, a HDMI (High-Definition Multimedia Interface) connection port, a USB (Universal Serial Bus) connection port, and a LAN (Local Area Network) connection port may be provided on the rear of the equipment failure prediction and diagnosis device 1000. LED lights for indicating the status of each input channel and the power supply status may be provided on the front of the equipment failure prediction and diagnosis device 1000. It is preferable that the external connection port 300 described above be provided on the equipment data collection unit 400 side, as shown in FIG. 1, in terms of data input and output.

[0036] 2, there can be seen a functional block diagram of the equipment data collection unit 400 and the equipment data processing unit 500 constituting the equipment failure prediction and diagnosis device 1000. The equipment data collection unit 400 may be equipped with at least one individual board 410, 420 having a plurality of input channels corresponding to the type of equipment to be diagnosed. In this case, each individual board 410, 420 is detachably provided, and various data may be collected according to the customization of the individual board 410, 420.

[0037] In addition, a module package for directly collecting and controlling data can be designed as each individual board 410, 420, and a circuit can be configured with multiple channels, for example, 8 channels, to input data from the equipment to be diagnosed. Data can be input from the equipment to be diagnosed through at least one of the multiple channels provided in a BNC connector 411 provided in the individual board 410, and the acquired data can be converted from an analog signal to a digital signal via an ADC (Analog to Digital Converter) 412.

[0038] The data converted into a digital signal is transmitted to an attenuator 413 and attenuated according to the device control voltage, and the attenuated data can be collected in a microcontroller unit (MCU) 414. The collected data can be parsed and stored in a buffer of the controller (MCU) 414. Here, data parsing refers to the process of assembling and refining data into desired data.

[0039] Meanwhile, the equipment data to be diagnosed input to the multiple input channels may include at least one of speed data, vibration data, current data, and temperature data acquired from sensors provided in each equipment. The types of data described above are merely examples and are not necessarily limited thereto, and any type of data that can be collected from the equipment may be used.

[0040] A system for ensuring the reliability of equipment data to be diagnosed input through input channels will be described. The system for reliability confirmation can be configured in the form of a single-ended GND by connecting VCC and GND via a power supply to the BNC connector 411 and terminal block of the equipment failure prediction and diagnosis device 1000. When a voltage is applied from 1V to 24V in 1V increments through the power supply, the values ​​output from the ADC 412 can be stored and the average value can be calculated by receiving data from each of the 8 channels 10 times.

[0041] The results of verifying reliability using this configuration are shown in Figure 3.

[0042] During the verification process, 2 23 The bit resolution of the equipment failure prediction and diagnosis device was set to 24 bits so that the value would be expressed as an ADC412 value when 24 V was applied.

[0043] Specifically, the base voltage was 0.475 V, and in order to check the reproducibility of the high-speed sampling rate, the sampling rate was divided into 8 kS / s and 16 kS / s, and data was collected for 10 seconds at each sampling rate. First, the mean / standard deviation of the ADC412 output values ​​plotted and expressed when only the equipment failure prediction and diagnosis device 1000 was present was checked, and the mean / standard deviation of the ADC412 output values ​​when a vibration sensor was attached to the equipment failure prediction and diagnosis device 1000 was checked and compared.

[0044] As shown in Figure 3, the floating value is almost constant, which confirms that the noise of the equipment failure prediction and diagnosis device 1000 itself is at a negligible level and that there is no significant difference with changes in sampling rate. When the equipment failure prediction and diagnosis device 1000 is combined with a vibration sensor, the ratio of the average to the standard deviation is 0.19% at 8 kS / s and 0.14% at 16 kS / s, confirming that there is almost no deviation. This confirms that the reliability of the data collected by connecting the vibration sensor is ensured.

[0045] An Ethernet module 420 may be provided as one of the individual boards 410, 420. The controller (MCU) 414 of the Ethernet module may also be powered by the POE 511B method and may exchange data with Giga Ethernet 512H. The controller (MCU) 414 may also be connected to multiple Ethernet connectors via an Ethernet hub chipset. External devices may be connected to each of the Ethernet connectors via an Ethernet cable.

[0046] 2, the equipment data processing unit 500 may be provided with a common board 510 that performs real-time data judgment on data of the equipment to be diagnosed input from at least one of a plurality of input channels as a diagnostic model corresponding to that channel. Here, the common board 510 may be composed of a power stage 511, an interface stage 512, and a processing device stage 513.

[0047] Specifically, by connecting an RJ-45 connector port 511A to the power stage 511, power generated via a Power of Ethernet (POE) 511B can be transferred to the individual boards 410 and 420 of the equipment data collector 400. The power stage 511 supplies power to the equipment data collector 400 and can also supply power to the processing unit 513 in the form of 1.1V, 1.5V, 1.8V, or 3.3V. The power supply form is not limited to the above. The interface stage 512 can be configured to communicate with the processing unit 513 via an LPDDR4 (512A) and a DDR32-bit interface. The interface stage 512 can be configured as a flash memory and controller integrated package and can be configured to communicate with the processing unit 513 via an embedded multi-media controller (eMMC) 512B and an MMC interface.

[0048] A Status LED 512C for power or channel stage data collection status alarms can be connected via GPIO (General-Purpose Input / Output), and a debugger / downloader 512D for firmware can be connected to the processing unit stage 513 via USB and UART (Universal Asynchronous Receiver / Transmitter).

[0049] In addition, an Audio AMP 512E for generating a fault alarm after data evaluation can be connected to the processing unit stage 513 via an I2S (Integrated Interchip Sound) method. Cooperation between the controller (MCU) 414 and the CPU 513A in the equipment data collection unit 400 can be performed via SPI communication 512F (described later) and can be interfaced via an RGMII (Reduced Gigabit Media Independent Interface) method. Meanwhile, the wireless method supports Bluetooth and Wifi 512G, and a Giga Ethernet 512H for an Ethernet module can be configured.

[0050] In addition, the CPU 513A and the GPU 513B constitute the processing unit stage 513, and the CPU 513A and the GPU 513B can command data collection and pre-processing in real time and be equipped with AI-driven algorithms to perform edge computing with real-time data judgment.

[0051] The equipment data processing unit 500 may also be connected to the equipment data collecting unit 400 via a serial communication interface. To process data at high speed without data loss or noise, it is preferable to use a serial communication interface, which is a short-distance communication interface. For example, serial communication includes SPI (Serial Peripheral Interface) communication 512F. While Ethernet and other methods may be considered for connecting the equipment data processing unit 500 and the equipment data collecting unit 400, Ethernet is not preferable due to the risk of data loss during data transmission. However, SPI communication 512F has the advantage of enabling high-speed, real-time transmission over short distances without data loss. Therefore, using SPI communication 512F enables high-speed data processing, and the equipment data processing unit 500 can evaluate data in real time through an AI-driven algorithm. Therefore, the SPI communication 512F method can be said to be a communication method suitable for an equipment failure prediction and diagnosis device 1000 in which the equipment data collecting unit 400 and the equipment data processing unit 500 are integrally combined into a single device.

[0052] FIG. 4 is a functional block diagram 600 of the overall system.

[0053] 4, a functional block diagram 600 of the CPU 513A may include a Linux-based operating system 610, a communication protocol 620, and an IoT framework 630, which is embedded software. The communication protocol 620 includes HTTP (HyperText Transfer Protocol) 621, which is a protocol for hypertext transfer, TCP / IP (Transmission Control Protocol / Internet Protocol) 622, which is an Internet information transmission protocol, and MQTT (Message Queueing Telemetry Transport) 623, which is a message queuing protocol; these are merely examples and are not necessarily limited to these.

[0054] Meanwhile, the IoT framework 630 may be composed of a result monitoring part 631, a data collection / transmission part 632, a device discovery part 633, a resource management part 634, a data storage part 635, and a management part 636.

[0055] First, the device search part 633 can search for external devices connected to the equipment failure prediction and diagnosis device 1000. The resource management part 634 can manage resources stored in the CPU 513A, and the data storage part 635 can store data collected from the equipment. The management part 636 provides information on which diagnostic model to install. It also provides a location for storing data within the device and manages resources by checking the occupation rates of the CPU 513A and GPU 513B within the device. The data collection / transmission part 632 receives data collected from the equipment via the BNC connector 411 through each channel, and collects and transmits the data in real time via the internal buffer of the controller (MCU) 414 of the equipment data collection unit 400 and then the internal buffer of the CPU 513A. The diagnostic model loading and determination part 650 can load diagnostic models corresponding to the types of equipment recognized by the common board 510, provided by the external server 2000, onto the virtual machine of the AI ​​framework 640, thereby providing different diagnostic models for each channel. This allows for real-time data assessment of the transmitted data, and the results monitored in the result monitoring part 631 can be visualized together with the data, while also enabling edge computing functions.

[0056] The external server 2000 may also include a Prognostics and Health Management (PHM) server that diagnoses the state of the equipment based on the processed data, predicts equipment failure or lifespan, and calculates the timing of equipment replacement. The external server 2000 may perform predictive maintenance of the equipment based on the data transmitted from the equipment data processing unit 500. In this case, the external server 2000 may store a plurality of diagnostic models corresponding to at least one of the equipment state diagnosis and lifespan prediction algorithms and provide these to the equipment data processing unit 500. As a result, the equipment data processing unit 500 may receive a diagnostic model corresponding to the type of equipment recognized by the common board 510 from the stored diagnostic models and determine data in real time.

[0057] FIG. 5 is a diagram illustrating a process in which the equipment data collector 400 parses the digitally converted data and stores the parsed data in the first and second buffers.

[0058] Referring to the left side of FIG. 5, a process in which data from the equipment data collector 400 is divided and stored in a first buffer and a second buffer can be seen. The equipment failure prediction and diagnosis device 1000, which can operate at a high sampling rate, can receive and parse up to 16,000 samples per second from the BNC connector 411. To receive all parsed data without omission, an intermediate buffer is provided for primary storage, and data transmission is controlled using a message queue. Since data is divided and transmitted to a data transmission thread and a data monitoring thread, it can be divided and stored in two buffers. Parsed data parsed at a first sampling rate, which is a high sampling rate, can be stored in the first buffer before being transmitted to the data transmission thread. Furthermore, to transmit to the data monitoring thread, the parsed data can be downsampled at a second sampling rate, which is lower than the first sampling rate, and stored in the second buffer.

[0059] In this case, to utilize the shared resource of the CPU 513A, called threads, a method of accessing data by synchronizing with time control can be used. Mutex is used as a synchronization mechanism provided by Pthread, and the amount of data inserted into the data queue can be stopped or transmitted using the mutex_lock command. The data queue is realized as temporary storage using a ring buffer, and data transmission can be performed on a first-in, first-out (FIFO) basis.

[0060] Referring to the left side of Figure 5, the equipment data processing unit 500 can be seen to transmit data from the first buffer to the external server 2000 and transmit data from the second buffer to the database for storage in the database. More specifically, the data temporarily stored in the first and second buffers is queued first to be transmitted to each thread, and a mutex_lock command can be used to control access to the shared resource called the thread, thereby blocking and transmitting data. Each thread can also be controlled by a mutex_lock command to automatically adjust resources required for data transmission and extraction, preventing data loss. As a result, data extracted from the thread can be transmitted to the external server 2000 or the database (DB) 3000 via the TCP / IP protocol and managed.

[0061] Based on the configuration of the equipment failure prediction and diagnosis device 1000 described above, an equipment failure prediction and diagnosis method (S700) according to the embodiment will be described with reference to FIG.

[0062] FIG. 6 is a flowchart (S700) showing a method for collecting and storing data in an equipment failure prediction and diagnosis device 1000 in which an equipment data collection unit 400 and an equipment data processing unit 500, each equipped with at least one individual board 410, 420 having a plurality of input channels as shown in FIG. 1, are connected by a serial communication interface.

[0063] First, data collected from the BNC connector 411 is converted into a digital signal via the ADC 412 and temporarily stored in the controller (MCU) 414, and then transmitted to the platform module CPU 513A via the internal SPI communication 512F (S701). Then, a large amount of data parsed at a high speed (16 kS / s) by the CPU 513A is parsed and stored and accumulated in a first buffer that stores parsed data parsed at a first sampling rate and a second buffer that stores parsed data downsampled at a second sampling rate lower than the first sampling rate (S702). The data can be divided and stored in two buffers to be transmitted separately to a data transmission thread and a data monitoring thread.

[0064] The equipment data collection unit 400 may determine whether the cumulative data stored in the first buffer is larger than a predetermined size (N) to determine whether the amount of data stored in the buffer is sufficient for storage (S703). This is to check the amount of data accumulated in the buffer and determine whether the amount of data stored in the buffer is sufficient for storage. If it is determined that the cumulative data stored in the first buffer is not larger than the predetermined size (N), additional data is received (N in S703). However, if it is determined that the cumulative data stored in the first buffer is larger than the predetermined size (N) (Y in S703), the data may be inserted into a data queue to be thread-processed by the equipment data processing unit 500 (S704). When all data is accumulated in the data queue, the first buffer becomes empty to receive the next data (S705). The processes described above can be performed by the equipment data collection unit 400 (S701 to S705).

[0065] The process in which the equipment data processor 500 transmits data to the external server 2000 and the database (DB) 3000 after the buffer becomes empty will now be described.

[0066] The equipment data processing unit 500 checks the current size of the data queue and can prepare data collection using the CPU 513A (S710). It can determine whether the size of the data queue is equal to or greater than 0 and decide whether to extract data from the data queue (S711). If the size of the data queue is less than 0, it continues to check the size of the data queue (N in S711). However, if the size of the data queue is equal to or greater than 0 (Y in S711), it can extract data from the data queue (S712). At this time, if there is data in the data queue, it can simultaneously use the mutex_lock command to perform time-synchronized access control from the data queue and extract the data.

[0067] The extracted data is then transmitted to the server via the TCP / IP protocol (S713). The equipment data processing unit 500 receives the data reception result from the external server 2000 and can again prepare new data extraction from the data queue (S714). Through the above-described data processing process, the equipment data processing unit 500 can smoothly perform real-time data judgment using the data of the equipment to be diagnosed as a diagnostic model corresponding to the channel.

[0068] Ultimately, the integrated structure of the equipment data collection unit and equipment data processing unit allows for the miniaturization of the device, reducing costs, and enables predictive maintenance of the equipment by diagnosing the equipment status in real time through AI algorithms, ensuring the scalability and maintainability of line applications.

[0069] Meanwhile, the present invention can be realized as computer-readable code on a medium having a program recorded thereon. Computer-readable media include all types of recording devices on which data readable by a computer system is stored. Examples of computer-readable media include hard disk drives (HDDs), solid-state disks (SSDs), silicon disk drives (SDDs), ROMs, RAMs, CD-ROMs, magnetic tapes, floppy disks, and optical data storage devices. Therefore, the above detailed description should not be construed as limiting in any respect, but should be considered as illustrative. The scope of the present invention should be determined by reasonable interpretation of the appended claims, and all modifications within the scope of the present invention are encompassed within the scope of the present invention. [Explanation of symbols]

[0070] 100 Housing Case 200 Cooling fins 300 external connection port 400 Equipment Data Collection Department 500 Equipment Data Processing Unit 410, 420 individual boards 411 BNC connector 412 ADC 413 Attenuator 414 Controller (MCU) 510 Common Board 511 Power Stage 511A Connector Port 511B POE 512 Interface Stage 512A LPDDR4 512B eMMC 512C Status LED 512D Debugger / Downloader 512E Audio AMP 512F SPI communication 512G Bluetooth, Wi-Fi 512H Giga Ethernet 513 Processing Unit Stage 513A CPU 513B GPU 610 Operating System 620 Communication Protocol 621 HTTP 622 TCP / IP 623 MQTT 630 IOT Framework 631 Results Monitoring Part 632 Data Collection / Transmission Part 633 Equipment Search Part 634 Resource Management Part 635 Data Storage Part 636 Management Part 640 AI Framework 650 Diagnostic Model Mounting and Judgment Part 1000 Equipment failure prediction and diagnosis device 2000 external servers 3000 databases (DB)

Claims

1. an equipment data collection unit equipped with at least one individual board having a plurality of input channels corresponding to the type of equipment to be diagnosed and into which data of the equipment to be diagnosed is input; an equipment data processing unit including a common board that supplies power to the equipment data collection unit and performs real-time data judgment on data of the equipment to be diagnosed input from at least one of a plurality of input channels as a diagnostic model corresponding to the channel; The equipment data collection unit and the equipment data processing unit are An equipment failure prediction and diagnosis device that is connected via a serial communication interface and integrated into one unit.

2. The equipment data processing unit transmits the collected data to an external server, The external server is 2. The equipment failure prediction and diagnosis device according to claim 1, further comprising a PHM (Prognostics and Health Management) server that diagnoses the state of the equipment based on the processed data, predicts the failure or lifespan of the equipment, and evaluates the data in a manner that calculates the timing of replacing the equipment.

3. The external server is A plurality of diagnostic models corresponding to at least one of the equipment condition diagnosis and life prediction algorithms are stored; The equipment data processing unit 3. The equipment failure prediction and diagnosis device according to claim 2, wherein the diagnostic model corresponding to the type of equipment recognized by the common board is provided from an external server.

4. The equipment data collection department 3. The equipment failure prediction and diagnosis device according to claim 2, wherein the data input through at least one of the plurality of input channels is converted into a digital signal, and the converted data is parsed and stored in a buffer.

5. The buffer is a first buffer for storing parsed data parsed at a first sampling rate; 5. The equipment failure prediction and diagnosis device according to claim 4, further comprising: a second buffer for storing parsed data downsampled at a second sampling rate lower than the first sampling rate.

6. The equipment data processing unit 6. The equipment failure prediction and diagnosis device according to claim 5, wherein the data in the first buffer is transmitted to an external server, and the data in the second buffer is stored in a database.

7. The data input from the equipment to be diagnosed is 2. The equipment failure prediction and diagnosis device according to claim 1, wherein the equipment failure prediction and diagnosis device includes at least one of speed data, vibration data, current data, and temperature data obtained from the equipment.

8. 2. The equipment failure prediction and diagnosis device according to claim 1, wherein at least one individual board is detachably provided.

9. The equipment data collection department 5. The equipment failure prediction and diagnosis device according to claim 4, wherein if the cumulative data stored in the buffer is larger than a predetermined size, the data is inserted into a data queue so that the data can be thread-processed in the equipment data processing unit.

10. The equipment data processing unit 10. The equipment failure prediction and diagnosis device according to claim 9, wherein it is determined whether the size of the data queue is equal to or greater than 0, and if the size of the data queue is equal to or greater than 0, data is extracted from the data queue.

11. 2. The equipment failure prediction and diagnosis device according to claim 1, wherein the serial communication includes SPI communication.

12. 1. A method for controlling an equipment failure prediction and diagnosis device, comprising: an equipment data collection unit and an equipment data processing unit, each of which is connected to one another via a serial communication interface and integrally coupled to each other; and A step of inputting data of equipment to be diagnosed; and performing real-time data judgment using data of the equipment to be diagnosed input from at least one of a plurality of input channels as a diagnostic model corresponding to the channel.

13. The equipment failure prediction and diagnosis method according to claim 12, further comprising a step of evaluating the data in a manner of diagnosing the state of the equipment based on the processed data, predicting a failure or lifespan of the equipment, and calculating a replacement time for the equipment.

14. 13. The method for predicting and diagnosing equipment failures according to claim 12, further comprising the steps of converting data input through at least one of a plurality of input channels into a digital signal, parsing the converted data, and storing the parsed data in a buffer.

15. 15. The method of claim 14, further comprising inserting the accumulated data stored in the buffer into a data queue so that the data can be thread-processed in the equipment data processing unit if the accumulated data is larger than a predetermined size.

16. 16. The equipment failure prediction and diagnosis method according to claim 15, further comprising the step of determining whether the size of the data queue is equal to or greater than 0, and extracting data from the data queue if the size of the data queue is equal to or greater than 0.

Images