KR-102961252-B1 - FAULT DETECTING APPARATUS AND METHOD FOR DETERMINING OPTIMAL FAULT DETECTING RULE THEREOF

KR102961252B1KR 102961252 B1KR102961252 B1KR 102961252B1KR-102961252-B1

Abstract

A defect detection device and a method for determining an optimal defect detection rule in said device are disclosed. A defect detection device according to one embodiment of the present invention includes: a defect detection unit for detecting a defect in a target device; a cause probability calculation unit for calculating the cause probability of each of a plurality of defect causes corresponding to the detected defect, by considering one or more of the recent occurrence date, cumulative occurrence frequency, and preset priority of each of the plurality of defect causes; and a rule update unit for recalculating one or more of the threshold value and exclusion time of the rule used to detect the defect when it is determined that the cause probability calculation result is the highest.

Inventors

민지홍
이민형
장화선

Assignees

삼성에스디에스 주식회사

Dates

Publication Date: 20260508
Application Date: 20170124

Claims (18)

A defect detection unit that detects defects in target equipment; A cause probability calculation unit that calculates the cause probability of each of the plurality of defect causes corresponding to the detected defect by considering one or more of the recent occurrence date, cumulative occurrence frequency, and preset priority of each of the plurality of defect causes; and If the result of the above cause probability calculation determines that the probability of false detection is highest, the rule update unit recalculates one or more of the threshold value and exclusion time of the rule used to detect the defect, and The above rule update unit recalculates one or more of the threshold value and the exclusion time using measurement data of a history determined to be a false detection and a history determined to be a defect among the past defect detection history, and The above rule update unit is the following mathematical formula (Here, v normal is the measurement data of the history determined to be false detections among the past defect detection history, and v defect is the measurement data of the history determined to be actual defects) A defect detection device that recalculates the above threshold value by...
In claim 1, The above-mentioned cause probability calculation unit calculates a recency point for each action guide based on the most recent occurrence date of each of the plurality of defect causes, and A defect detection device in which the above recency score is set to be inversely proportional to the elapsed days from the above recent occurrence date to the above point in time for calculating the likelihood of cause.
In claim 1, The above-mentioned cause probability calculation unit calculates a frequency point for each defect cause based on the cumulative selection frequency of each of the above-mentioned plurality of defect causes, and A defect detection device, wherein the above frequency score is set to be proportional to the above cumulative selection frequency.
In claim 3, The above-mentioned cause probability calculation unit is a defect detection device that calculates a frequency score for each of the above-mentioned defect causes by additionally considering the cumulative selection frequency of each of the above-mentioned multiple defect causes obtained from other equipment belonging to the same equipment group as the above-mentioned target equipment.
In claim 1, The above possibility of cause is expressed by the following mathematical formula (Here, A is the Recency Point of the corresponding defect cause, B is the Frequency Point of the corresponding defect cause, C is the Priority Point of the corresponding defect cause, and max(A), max(B), and max(C) are the maximum values of A, B, and C, respectively) Calculated by, The above recency score is a score that is set so that the closer the above recent occurrence date and the time of calculation of the above causal possibility are, the higher the recency score becomes. The above frequency score is a score set to be proportional to the above cumulative occurrence frequency, and A defect detection device in which the above priority score is a score that is set higher as the priority for each defect cause increases.
delete
delete
In claim 1, The above rule update unit is the following mathematical formula (Here, v normal is the measurement data of the history determined to be false detections among the past defect detection history, and v defect is the measurement data of the history determined to be actual defects) A defect detection device that recalculates the above-mentioned exclusion time by means of.
In claim 1, A defect detection device further comprising a simulation unit that calculates the expected number of defect detections when the recalculated threshold or exclusion time is applied to a past defect detection history, and displays the calculated result on a screen by comparing it with the number of defect detections according to the existing threshold or exclusion time.
One or more processors, and A method performed in a computing device having a memory for storing one or more programs executed by the above-mentioned one or more processors, wherein A step of detecting defects in target equipment; For a plurality of defect causes corresponding to the detected defect, a step of calculating the causal probability of each of the plurality of defect causes by considering one or more of the recent occurrence date, cumulative occurrence frequency, and preset priority of each of the plurality of defect causes; and If the result of the above cause probability calculation determines that the probability of false detection is highest, the method includes a rule update step of recalculating one or more of the threshold value and exclusion time of the rule used to detect the defect, and The above rule update step recalculates one or more of the threshold and the exclusion time using measurement data of the history determined to be a false detection and measurement data of the history determined to be a defect among the past defect detection history, and The above rule update step is the following mathematical formula A method for determining an optimal defect detection rule, wherein the threshold value is recalculated based on (wherein vnormal is measurement data of a history judged to be a false detection among past defect detection history, and vdefect is measurement data of a history judged to be an actual defect).
In claim 10, The step of calculating the above-mentioned causal probability calculates a recency point for each action guide based on the most recent occurrence date of each of the plurality of defect causes, wherein The above recency score is set to be inversely proportional to the elapsed days from the most recent occurrence date to the point of calculating the likelihood of cause, in an optimal defect detection rule determination method.
In claim 10, The step of calculating the above-mentioned cause probability calculates a frequency point for each defect cause based on the cumulative selection frequency of each of the plurality of defect causes, wherein A method for determining an optimal defect detection rule, wherein the above frequency score is set to be proportional to the above cumulative selection frequency.
In claim 12, The step of calculating the above-mentioned cause probability is a method for determining an optimal defect detection rule, wherein the cumulative selection frequency of each of the above-mentioned multiple defect causes obtained from other equipment belonging to the same equipment group as the above-mentioned target equipment is additionally considered to calculate a frequency score for each of the above-mentioned defect causes.
In claim 10, The above possibility of cause is expressed by the following mathematical formula (Here, A is the Recency Point of the corresponding defect cause, B is the Frequency Point of the corresponding defect cause, C is the Priority Point of the corresponding defect cause, and max(A), max(B), and max(C) are the maximum values of A, B, and C, respectively) Calculated by, The above recency score is a score that is set so that the closer the above recent occurrence date and the time of calculation of the above causal possibility are, the higher the recency score becomes. The above frequency score is a score set to be proportional to the above cumulative occurrence frequency, and A method for determining optimal defect detection rules, wherein the above priority score is a score that is set higher as the priority for each defect cause increases.
delete
delete
In claim 10, The above rule update step is the following mathematical formula (Here, v normal is the measurement data of the history determined to be false detections among the past defect detection history, and v defect is the measurement data of the history determined to be actual defects) A method for determining an optimal defect detection rule that recalculates the above-mentioned exclusion time by means of.
In claim 10, A method for determining an optimal defect detection rule, further comprising the step of calculating the expected number of defect detections when the recalculated threshold or exclusion time is applied to a past defect detection history, and displaying the calculated result on a screen by comparing it with the number of defect detections according to the existing threshold or exclusion time.

Description

FAULT DETECTING APPARATUS AND METHOD FOR DETERMINING OPTIMAL FAULT DETECTING RULE THEREOF Embodiments of the present invention relate to a technology for determining an optimal defect detection rule for detecting defects in equipment, etc., installed in buildings, etc. Generally, various types of equipment are installed within a building. Furthermore, depending on the size of the building, multiple units of the same equipment may be installed. For example, when air conditioning equipment is installed in a building, a single unit or multiple units may be installed depending on the building's scale. In addition, the adoption of building automation systems is increasing in order to manage these various pieces of equipment in an integrated manner. In building automation systems, detecting and diagnosing defects in installed equipment is an essential function for maintaining a comfortable environment within the building and conserving energy. To detect defects, a threshold is required to determine whether the status values measured by the equipment fall within the normal range. If the threshold is set too low, an excessive number of defects will be detected, compromising system reliability; conversely, if set too high, necessary defects may go undetected. Therefore, it is crucial to set the optimal threshold based on the characteristics of each piece of equipment. Furthermore, since HVAC units and boilers installed in buildings require time for warming up, they have the characteristic of taking a certain amount of time to reach a stable state within the threshold set by the system after startup. Therefore, if a state value deviating from the threshold detected immediately after startup is unconditionally reported as a fault without considering these characteristics, it leads to a decrease in system reliability. FIG. 1 is a block diagram illustrating a defect detection device according to an embodiment of the present invention. Figure 2 is a graph showing the trend of variation in the probability of occurrence of defects by cause listed in Table 10, by date. FIG. 3 is a flowchart illustrating a method for determining an optimal defect detection rule according to an embodiment of the present invention. Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. The following detailed description is provided to facilitate a comprehensive understanding of the methods, apparatuses, and/or systems described herein. However, this is merely illustrative and the present invention is not limited thereto. In describing the embodiments of the present invention, detailed descriptions of known technologies related to the present invention are omitted if it is determined that such descriptions might unnecessarily obscure the essence of the invention. Furthermore, the terms described below are defined considering their functions in the present invention, and these may vary depending on the intentions or practices of the user or operator. Therefore, such definitions should be based on the content throughout this specification. Terms used in the detailed description are intended merely to describe the embodiments of the present invention and should not be limiting in any way. Unless explicitly stated otherwise, expressions in the singular form include the meaning of the plural form. In this description, expressions such as "include" or "comprise" are intended to refer to certain characteristics, numbers, steps, actions, elements, parts thereof, or combinations thereof, and should not be interpreted to exclude the existence or possibility of one or more other characteristics, numbers, steps, actions, elements, parts thereof, or combinations thereof other than those described. FIG. 1 is a block diagram illustrating a defect detection device (100) according to an embodiment of the present invention. As illustrated, the defect detection device (100) according to an embodiment of the present invention includes a storage unit (102), a defect detection unit (104), a cause probability calculation unit (106), and a rule update unit (108), and may further include a simulation unit (110) as needed. In embodiments of the present invention, the target equipment may be any type of object requiring defect detection and action thereon. For example, the target equipment may be an air conditioner, heating and cooling equipment, a water chiller, lighting, or elevator device installed in a building. However, it should be noted that the foregoing examples are merely illustrative, and the scope of the present invention is not limited to a specific type of device or equipment. The storage unit (102) stores and manages defects that may occur in the target equipment and a plurality of action guides corresponding to each defect. In one embodiment, the storage unit (102) may define the attributes that each piece of equipment may have as a formula and store them in the form of rules. For example, in the case