Integrated facility management system and method thereof

The integrated facility management system addresses the challenge of diverse equipment and abnormality types by using worker data collection and PHM servers for real-time equipment diagnosis, reducing prediction and work times and minimizing downtime through efficient abnormality type identification.

WO2024237398A1PCT designated stage expired Publication Date: 2024-11-21HYUNDAI MOTOR CO LTD +1
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/KR2023/014526
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-15
Filing Date
2023-09-22
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

In equipment diagnosis, the reliance on tacit knowledge and manual books leads to varying work data for each worker, resulting in increased man-hours and diagnostic time, which can cause equipment downtime due to the diversity of equipment and abnormality types, necessitating a reduction in abnormality type prediction time and operator work time.

Method used

An integrated facility management system and method that collects worker work data, including video and eye-tracking information, and uses a data learning unit to predict equipment abnormality types, with a Prognostics and Health Management (PHM) server for real-time diagnosis and threshold-based equipment status assessment, outputting predicted abnormality types and matching work data for external display.

Benefits of technology

This approach significantly shortens abnormality type prediction time and operator work time, minimizing equipment downtime by leveraging learned data for efficient diagnosis and reducing the need for manual interventions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2023014526_21112024_PF_FP_ABST
    Figure KR2023014526_21112024_PF_FP_ABST
Patent Text Reader

Abstract

The present invention relates to an integrated facility management system and a method thereof. The integrated facility management system comprises: a work data collection unit for collecting work data of a worker for a facility to be diagnosed; a data learning unit for learning the work data of the worker collected by the work data collection unit, diagnostic data of the facility according to the work of the worker, and the type of abnormality in the facility calculated through the work data and the diagnostic data; and an external server for performing real-time facility state diagnosis on the basis of the work data, the diagnostic data, and the type of abnormality in the facility, which are pre-learned by the data learning unit, predicting the type of abnormality when an abnormality occurs in the facility as a result of the diagnosis, and outputting the predicted type of abnormality and the work data of the worker matching the type of abnormality to the outside.
Need to check novelty before this filing date? Find Prior Art

Description

Integrated facility management system and method thereof

[0001] The present invention relates to an integrated facility management system and method thereof, and more particularly, to an integrated facility management system and method thereof for shortening the time for predicting abnormality types and the work time of workers when diagnosing facilities on an external server based on previously learned worker work data and facility diagnostic data.

[0002] In the facility sector, prognostics and health management (PHM) is increasingly being applied to diagnose the current condition of equipment and predict failures. PHM collects status information from machinery, equipment, aircraft, and power plants to detect system abnormalities and optimize facility management by predicting failures in advance through analysis and predictive diagnosis. PHM is rapidly growing, not only reducing costs but also ensuring stable system operation and enabling cost-effective, downtime-free maintenance.

[0003] Meanwhile, in typical industrial settings, workers rely on tacit knowledge and extensive manuals when working on equipment. This leads to different work data for each worker, resulting in significant variations in the time it takes to diagnose anomalies. Furthermore, the sheer diversity of equipment types, equipment components, and anomaly types limits workers' ability to take swift action on each individual piece of equipment being diagnosed.

[0004] These issues ultimately increase the labor required for equipment maintenance, increasing the time workers spend learning tacit knowledge and extensive manuals. Furthermore, increased equipment diagnostic time can lead to equipment line shutdowns.

[0005] Accordingly, a method is needed to shorten the abnormal type prediction time and the worker's working time.

[0006] The matters described as background technology above are only intended to enhance understanding of the background of the present invention, and should not be taken as an admission that they correspond to prior art already known to those skilled in the art.

[0007] Prior art related to this includes KR 10-2021-0115440 A.

[0008] The present invention provides an integrated facility management system and method for reducing the time required to predict abnormality types and the work time of workers when diagnosing facilities on an external server based on previously learned worker work data and facility diagnostic data.

[0009] 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 can be clearly understood by a person having ordinary skill in the technical field to which the present invention belongs from the description below.

[0010] As a means for solving the above technical problem, the present invention configures an integrated facility management system including: a work data collection unit that collects a worker's work data for a facility to be diagnosed; a data learning unit that learns diagnostic data of the facility according to the worker's work and an abnormality type of the facility calculated through the work data and the diagnostic data; and an external server that performs real-time facility status diagnosis based on the work data, diagnostic data, and abnormality type of the facility learned in the data learning unit, predicts the abnormality type when an abnormality occurs in the facility as a result of the diagnosis, and outputs the predicted abnormality type and the worker's work data matching the abnormality type to the outside.

[0011] For example, the work data collection unit can collect work data including the worker's work history and work video of the worker.

[0012] For example, the work data collection unit can collect video of the worker's work through an eye tracker that tracks the user's eye movements.

[0013] For example, the work data collection unit can set the worker's start and end movements, and the start and end times of the work video can be determined based on the time when the worker's start and end movements are detected through the eye tracker.

[0014] For example, when multiple work images are collected, the work data collection unit can sequentially connect the multiple work images to obtain a continuous work image and learn the obtained continuous work images.

[0015] For example, the data learning unit can learn equipment diagnostic data including equipment performance data, temperature data inside the equipment, and vibration data.

[0016] For example, an external server can perform equipment status diagnosis by setting a threshold value for each diagnostic data value based on the work data, diagnostic data, and equipment abnormality types learned in the data learning unit and determining whether each measured diagnostic data value is greater than or equal to the preset threshold value.

[0017] For example, the external server may include a Prognostics and Health Management (PHM) server that performs equipment condition diagnosis in a way that predicts equipment failure or lifespan and calculates when to replace the equipment.

[0018] For example, an external server can transmit predicted anomaly types and worker work data corresponding to the anomaly types to the data learning unit.

[0019] For example, it may further include a display unit that receives and displays abnormal types output from an external server and work data of workers matching the abnormal types.

[0020] For example, the work data collection unit can collect work data of a worker performing work based on information reflecting the abnormal type displayed on the display unit and the work data of the worker matching the abnormal type.

[0021]

[0022] As a method for solving the above technical problem, the present invention comprises an integrated facility management method including a step of collecting a worker's work data for a facility to be diagnosed in a work data collection unit; a step of learning, in a data learning unit, the worker's work data collected in the work data collection unit, diagnostic data of the facility according to the worker's work, and an abnormality type of the facility calculated through the work data and the diagnostic data; a step of performing a real-time facility status diagnosis based on the work data, diagnostic data, and abnormality type of the facility learned in the data learning unit; a step of predicting the abnormality type when an abnormality occurs in the facility as a result of the diagnosis; and a step of externally outputting the predicted abnormality type and the worker's work data matching the abnormality type.

[0023] For example, the step of performing real-time equipment status diagnosis may include a step of setting a threshold value for each diagnostic data value based on previously learned work data and diagnostic data; and a step of performing equipment status diagnosis by determining whether each measured diagnostic data value is equal to or greater than the previously set threshold value.

[0024] For example, the method may further include a step of receiving and displaying an abnormal type output to the outside and the work data of a worker matching the abnormal type.

[0025] According to the integrated facility management system and method of the present invention, the time for predicting the type of abnormality and the worker's work time can be shortened when diagnosing facilities on an external server based on previously learned worker's work data and facility diagnosis data.

[0026] The effects that can be obtained from the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by a person having ordinary skill in the art to which the present invention belongs from the description below.

[0027] Figure 1 is a block diagram showing an integrated facility management system according to one embodiment of the present invention.

[0028] FIG. 2 is a drawing showing in detail the configuration of an integrated facility management system according to one embodiment of the present invention.

[0029] Figure 3 is a flowchart showing the recording and editing process for a worker's work video according to one embodiment of the present invention.

[0030] Figure 4 is a flowchart illustrating the operation of an integrated facility management system according to one embodiment of the present invention.

[0031] Hereinafter, embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Regardless of the drawing numbers, identical or similar components are given the same reference numbers and redundant descriptions thereof will be omitted.

[0032] The suffixes "module" and "part" used for components in the following description are given or used interchangeably only for the convenience of writing specifications, and do not have distinct meanings or roles in themselves.

[0033] In describing the embodiments disclosed in this specification, if it is determined that a detailed description of related known technology may obscure the gist of the embodiments disclosed in this specification, the detailed description thereof will be omitted. In addition, the attached drawings are only intended to facilitate easy understanding of the embodiments disclosed in this specification, and the technical ideas disclosed in this specification are not limited by the attached drawings, and it should be understood that they include all modifications, equivalents, and substitutes included in the spirit and technical scope of the present invention. Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but the components are not limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

[0034] When a component is referred to as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components intervening. Conversely, when a component is referred to as being "directly connected" or "connected" to another component, it should be understood that there are no other components intervening.

[0035] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0036] In this specification, terms such as “include” or “have” are intended to specify the presence of a feature, number, step, operation, component, part or combination thereof described in the specification, but should be understood not to exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

[0037]

[0038] Figure 1 is a block diagram illustrating an integrated facility management system according to one embodiment of the present invention. Figure 1 primarily illustrates components related to this embodiment, and it is obvious that an actual integrated facility management system may include fewer or more components.

[0039]

[0040] Referring to FIG. 1, an integrated facility management system (100) according to one embodiment may include a work data collection unit (110), a data learning unit (120), an external server (130), and a display unit (140).

[0041] First, when a worker starts working on the equipment to be diagnosed, the work data collection unit (110) can collect the worker's work data on the equipment to be diagnosed. Here, the worker's work data includes the worker's work history and the worker's work video. The worker's work history includes the time the worker spent working on the equipment, the number of parts consumed in the work, the worker's actions, etc., and the work video includes the video taken while the worker was performing the work. The work video can be collected through an eye tracker. Eye tracking is a technology that tracks the eye movements of a worker to determine exactly where the worker's gaze is staying, and can be utilized when analyzing the time the worker stays in the center of the visual field or the pattern of processing information through the gaze path.

[0042] In addition, the data learning unit (120) can learn the worker's work data collected by the work data collection unit (110), the equipment's diagnostic data according to the worker's work, and the equipment's abnormality type calculated through the work data and the diagnostic data. Here, the equipment's diagnostic data refers to data indicating the equipment's status diagnosed as a result of the worker's work on the equipment. For example, the equipment's diagnostic data may include equipment's performance data, temperature data inside the equipment, and vibration data. The equipment's abnormality type is calculated through the worker's work data and the equipment's diagnostic data, and the calculated abnormality type is stored in the data learning unit (120) and can be utilized as a database (DB) for predicting the abnormality type of an external server.

[0043] In this way, the data learning unit (120) stores each piece of data, and by organizing the stored data, the time required to determine the type of equipment abnormality and the cause of the abnormality in an external server can be significantly shortened. Accordingly, equipment downtime can be minimized.

[0044] Additionally, the external server (130) can perform real-time equipment status diagnosis based on the work data, diagnostic data, and equipment abnormality types learned by the data learning unit (120). Here, the external server (130) is preferably a PHM server. The PHM server performs equipment status diagnosis by predicting equipment failure or lifespan and calculating the equipment replacement time.

[0045] In the present invention, the external server (130) predicts the type of abnormality when a facility malfunction occurs as a result of a diagnosis, and outputs the predicted abnormality type and the worker's work data matching the abnormality type to the outside. This allows the worker to check the work data, including previous work videos, when performing equipment work by matching the worker's work data with the corresponding abnormality type. This significantly reduces the effort required to ask colleagues for countermeasures or search through thick manuals one by one. Furthermore, the worker can intuitively understand the work content by viewing the video of the work performed, thereby reducing work time and minimizing downtime.

[0046] More specifically, the external server (130) can perform equipment status diagnosis by setting a threshold value for each diagnostic data value based on the work data, diagnostic data, and equipment abnormality types learned in the data learning unit (120) and determining whether each measured diagnostic data value is equal to or greater than the preset threshold value. For example, when a value exceeding the threshold standard of vibration data values ​​among the equipment diagnostic data is detected, equipment abnormality and failure can be predicted.

[0047] In addition, the external server (130) can output the predicted abnormality type and the worker's work data corresponding to the abnormality type to the outside, as well as transmit them to the data learning unit (120) or the display unit (140). The data learning unit (120) receives and stores the predicted abnormality type and the worker's work data corresponding to the abnormality type, and uses them as data when diagnosing the equipment status of the external server (130) in the future.

[0048] In addition, the display unit (140) can receive and display the abnormality type outputted externally from the external server (130) and the worker's work data matching the abnormality type. Here, the display unit (140) may be performed by the work data collection unit (110) or the data learning unit (120). The display unit (140) is displayed so that the worker can recognize the received data while carrying a mobile device such as a tablet. When an abnormality occurs in the external server (130), the worker can perform the work based on the abnormality type displayed through the display unit (140), thereby reducing the worker's work time.

[0049] Accordingly, the work data collection unit (110) collects the work data of the worker working based on the information reflecting the abnormal type displayed on the display unit (140) and the work data of the worker matching the abnormal type, so that the time for predicting the abnormal type when diagnosing equipment of the external server (130) can be significantly shortened as described above.

[0050] Each configuration will be described in more detail with reference to Fig. 2.

[0051] Figure 2 is a detailed diagram illustrating the configuration of an integrated facility management system (100) according to one embodiment of the present invention. It will be apparent to those skilled in the art that the components performing each function may be integrated or separated.

[0052] Referring to FIG. 2, the system (100) according to the present invention may include a memory device (101), a communication unit (102), and a power unit (103). The worker may provide work data including a work image to the system (100) according to the present invention. The display unit (140) may classify the image based on the received real-time work image of the worker, prediction information received from an external server (130), and ETS (Eye Tracking System) information (141) which is information collected through an eye tracker. This may be accomplished through an AI image classification module (141). In addition, the display unit (140) may display an abnormality type output to the outside from the external server (130) and the worker's work data matching the abnormality type through a user interface (145). The system (100) transmits diagnostic data of equipment according to the worker's work, and the work data collection unit (110) can map work data (111) including work images by abnormality type (113). In addition, the work data collection unit (110) can edit and record (115) work images using the collected work data.

[0053] In addition, the data learning unit (120) may be an ERP (Enterprise Resource Planning). ERP is a software system (100) that enables an organization to automate and manage core business processes for optimal performance. It learns the worker's work data collected by the work data collection unit (110) and the equipment's diagnostic data (reference information, 121) according to the worker's work and transmits it to an external server (130). The equipment's diagnostic data can be processed and transmitted from the work site (factory, 200) through the Industrial Internet of Things (IIOT, 210).

[0054] In addition, the external server (130) receives the worker's work data and the equipment's diagnostic data according to the worker's work from the system (100) (131), performs real-time equipment status diagnosis, and can predict the type of equipment abnormality through the abnormality prediction module (133).

[0055] Figure 3 is a flowchart showing the recording and editing process for a worker's work video according to one embodiment of the present invention.

[0056] Referring to FIG. 3, first, the work data collection unit (110) can receive work images through the eye tracker worn by the worker (S301). Thereafter, the work data collection unit (110) plays the work images (S303) and determines whether all work images have ended (S305). If the work images have ended, the work data collection unit (110) can check all recorded images (S307) and determine whether the number of recorded worker work images exceeds 1 (S309). If it is determined that the number of recorded images exceeds 1 (YES in S309), the work data collection unit (110) sequentially stitches together multiple work images to obtain a continuous work image if multiple work images have been collected (S311), and the obtained continuous work images are stored (S313). If the work images have not ended, the work data collection unit (110) can determine the start and end times based on the start and end actions of the worker described above.

[0057] Before explaining this, the work data collection unit (110) can set the worker's start and end movements. This is a task to select a valid part excluding unnecessary parts from a single work video, and the worker's start and end movements can be detected through an eye tracker (S315, S317). Based on the time at which the worker's start and end movements are detected, the work data collection unit (110) can determine the start and end times of the work video. When the start movement is detected, recording of the work video begins (S317), and when the end movement is detected, recording of the work video ends and playback of the work video continues (S321).

[0058] Based on the configuration of the integrated facility management system (100) described above, an integrated facility management method according to an embodiment is described with reference to FIG. 4.

[0059] Figure 4 is a flowchart showing the operation of an integrated facility management system (100) according to one embodiment of the present invention.

[0060] Referring to Fig. 4, first, a worker performs a task for diagnosing the equipment (S401). Thereafter, the worker wears an eye tracker (S403) and can transmit the collected work data from the work data collection unit (110) to the data learning unit (120) in real time (S405). At the same time, the worker diagnoses the equipment while checking the information displayed through the display unit (140) (S407). Thereafter, the data learning unit (120) receives the equipment diagnostic data according to the worker's work (S413) and learns the worker's work data collected in the work data collection unit (110) and the equipment diagnostic data according to the worker's work (S409, S415). The data learning unit (120) transmits the learned work data to an external server (130), thereby completing the maintenance procedure (S411).

[0061] Thereafter, the external server (130) performs a real-time equipment status diagnosis based on the work data including the worker's work video, diagnostic data, and equipment abnormality type from the work data collection unit (110) (S431). The external server (130) can predict the abnormality type when an abnormality occurs in the equipment based on the diagnosis results and match the corresponding work data of the worker (S433).

[0062] Additionally, the external server (130) can further perform step S420. Step S420 consists of steps S421 and S423. Even if the data predicted by the external server (130) is the same or similar, the type of defect that occurred in the equipment and the condition at the time may be different. Therefore, the video of the equipment analysis and action process is referenced together with the predicted data, and the 'a' information is updated and output (S421). Through this, more accurate and detailed work data can be confirmed together, which can be used as a reference for maintenance work.

[0063] The external server (130) can transmit related images by referring to the worker's work data collected in the pre-learned work data collection unit (110) based on the predicted data, the equipment diagnostic data according to the worker's work, and the equipment abnormality type (S423). Through this operation, when identical or similar data occurs, the worker's abnormality analysis process and know-how can be confirmed by referring to the worker's eye movement path and chronological order, so that the equipment abnormality type analysis can be performed quickly and accurately. Thereafter, the external server (130) transmits the aforementioned 'a' information to the display unit (140) (S435), and the work image classification model can be continuously improved through additional learning considering the 'a' information (S437).

[0064] According to the embodiments of the present invention described so far, the time for predicting the type of abnormality and the work time of the worker can be shortened when diagnosing equipment on an external server based on the previously learned work data of the worker and the diagnostic data of the equipment.

[0065]

[0066] Although the present invention has been illustrated and described with respect to specific embodiments thereof, it will be apparent to those skilled in the art that the present invention may be variously improved and modified without departing from the technical spirit of the present invention as defined by the following claims.

[0067]

[0068] [Explanation of symbols]

[0069] 100: Integrated facility management system

[0070] 110: Work data collection unit

[0071] 120: Data Learning Department

[0072] 130: External server

[0073] 140: Display

Claims

1. Work data collection unit that collects the worker’s work data for the equipment to be diagnosed; A data learning unit that learns the worker's work data collected in the work data collection unit, the equipment's diagnostic data according to the worker's work, and the equipment's abnormality type calculated through the work data and diagnostic data; and An integrated facility management system including an external server that performs real-time facility status diagnosis based on work data, diagnostic data, and facility abnormality types learned in the data learning unit, predicts the abnormality type when an abnormality occurs in the facility as a result of the diagnosis, and outputs the predicted abnormality type and the worker's work data matching the abnormality type to the outside.

2. In claim 1, An integrated facility management system characterized in that the work data collection unit collects work data including the worker's work history and work video of the worker.

3. In claim 2, An integrated facility management system characterized by a work data collection unit that collects images of workers' work through an eye tracker that tracks the user's eye movements.

4. In claim 3, An integrated facility management system characterized in that the work data collection unit sets the start and end movements of a worker, and the start and end times of a work video are determined based on the time at which the start and end movements of the worker are detected through an eye tracker.

5. In claim 4, An integrated facility management system characterized in that, when multiple work images are collected, the work data collection unit sequentially connects multiple work images to obtain continuous work images, and learns the obtained continuous work images.

6. In claim 1, An integrated facility management system characterized by a data learning unit that learns facility diagnostic data including facility performance data, facility internal temperature data, and facility vibration data.

7. In claim 6, An integrated facility management system characterized in that the external server sets a threshold value for each diagnostic data value based on the work data, diagnostic data, and facility abnormality types learned in the data learning unit, and performs facility status diagnosis by determining whether each measured diagnostic data value is higher than the preset threshold value.

8. In claim 1, An integrated facility management system characterized in that the external server includes a PHM (Prognostics and Health Management) server that performs facility status diagnosis in a way that predicts facility failure or lifespan and calculates the time of facility replacement.

9. In claim 1, An integrated facility management system characterized in that the external server transmits predicted abnormality types and worker work data corresponding to the abnormality types to the data learning unit.

10. In claim 1, An integrated facility management system, characterized by further comprising a display unit that receives and displays abnormal types output from an external server and work data of workers matching the abnormal types.

11. In claim 10, An integrated facility management system characterized in that the work data collection unit collects the work data of a worker performing work based on information reflecting the abnormal type displayed on the display unit and the work data of the worker matching the abnormal type.

12. A step for collecting the worker’s work data for the equipment to be diagnosed in the work data collection unit; A step of learning the worker's work data collected in the work data collection unit from the data learning unit, the equipment's diagnostic data according to the worker's work, and the equipment's abnormality type calculated through the work data and diagnostic data; A step of performing real-time equipment status diagnosis based on work data, diagnostic data, and equipment abnormality types learned in the data learning department; A step for predicting the type of abnormality when an abnormality occurs in the equipment as a result of the diagnosis; and An integrated facility management method, comprising: a step of externally outputting predicted abnormal types and work data of workers matching the abnormal types.

13. In claim 12, The steps to perform real-time equipment status diagnosis are: A step of setting a threshold value for each diagnostic data value based on learned work data and diagnostic data; and An integrated facility management method, characterized by including a step of performing facility status diagnosis by determining whether each measured diagnostic data value is greater than or equal to a preset threshold value.

14. In claim 12, An integrated facility management method, characterized in that it further includes a step of receiving and displaying an abnormal type output to the outside and a worker's work data matching the abnormal type.

Citation Information

Patent Citations

  • Measurement solution service providing system

    JP2019096008A

  • Big data based on potential failure mode analysis method using progonstics system of machine equipment

    KR102373787B1

  • Industrial facility failure prediction diagnosis data learning labeling system and method based on artificial intelligence

    KR102383139B1

  • SYSTEM AND METHOD FOR MANAGING SAFETY IN WORK SITE THROUGH IoT SENSOR DATA AND VIDEO DATA ANALYSIS BASED ON ARTIFICIAL INTELLIGENCE

    KR102454671B1

  • AI IoT-based Elevator Predictive Maintenance System Project

    KR102484018B1