Integrated Remote Monitoring and Self-Diagnosis System for Fire Protection Facilities and Method Thereof

Abstract

The present invention relates to an integrated remote monitoring and self-diagnosis system for firefighting equipment and a method thereof, wherein an IoT terminal unit (200) is connected to a firefighting equipment unit (100) comprising a detector (110), a receiver (120), a fire pump (130), and a sprinkler system (140) to collect status data in real time, and a self-diagnosis unit (300) determines whether there is an abnormality based on an abnormality judgment index (ADI) and a failure probability index (FPI), automatically detects the shut-off operation of the fire pump (130), and monitors voltage drop to generate a compensation control signal.

Description

Technology Field

[0001] The present invention relates to an integrated remote monitoring and self-diagnosis system for firefighting equipment and a method thereof. More specifically, the invention relates to an integrated remote monitoring and self-diagnosis system for firefighting equipment and a method thereof that collects status data in real time from a plurality of firefighting equipment, including detectors, receivers, fire pumps, and sprinkler systems installed in a multi-unit building, determines whether there is an abnormality using a self-diagnosis algorithm based on the Anomaly Detection Index (ADI) and the Probability of Failure Index (FPI), automatically detects the shut-off operation of fire pumps, and monitors and compensates for voltage drops in the power supply system. Background Technology

[0002] In general, multi-unit buildings are equipped with numerous firefighting facilities, such as detectors for detecting heat or smoke, receivers indicating the location of ignition, fire pumps, and sprinkler systems; these facilities must be maintained in a normal operating state at all times to protect lives and property in the event of a fire.

[0003] Under the Act on Installation, Maintenance, and Safety Management of Firefighting Facilities, firefighting equipment is required to undergo periodic self-inspections and comprehensive precision inspections. However, in most cases, inspections are conducted manually at fixed intervals, which presents a problem in that it is difficult to promptly detect abnormal conditions in firefighting equipment that occur between inspection cycles.

[0004] In addition, in the case of fire pumps, if shut-off operation continues, pump overheating and burnout may occur, and although power supply failures or wiring abnormalities in detectors and receivers can directly lead to fire detection failures, there is currently no system to monitor this in real time and immediately notify the manager.

[0005] Furthermore, existing fire safety monitoring systems are limited to determining only whether a simple threshold is exceeded; consequently, complex anomaly detection that reflects the statistical variation characteristics of measurements and the importance of each equipment type is not performed, leading to frequent false alarms and failure to detect.

[0006] Accordingly, there is a need to develop an intelligent firefighting equipment monitoring system that collects status data from multiple firefighting facilities in real time, precisely determines abnormalities using a statistical-based composite index, and integrates inspection history management with notifications for statutory inspection cycles. The problem to be solved

[0007] The present invention has been devised to solve the problems of the aforementioned prior art. First, it provides an integrated remote monitoring and self-diagnosis system and method for firefighting equipment that collects status data in real time, including operating status, power supply status, operating current value, pressure value, and sensor measurement value from a plurality of firefighting equipment installed in a multi-unit building, precisely determines whether there is an abnormality in the firefighting equipment based on the Anomaly Detection Index (ADI) and the Failure Probability Index (FPI), and automatically notifies an administrator terminal when an abnormality is detected.

[0008] Second, the invention provides an integrated remote monitoring and self-diagnosis system and method for firefighting equipment that prevents damage to the fire pump by comprehensively analyzing the discharge pressure, flow rate, and operating current values ​​of the fire pump to detect whether shut-off operation is occurring in real time, and by generating an automatic stop control signal for the fire pump when shut-off operation is determined.

[0009] Third, the invention provides an integrated remote monitoring and self-diagnosis system and method for firefighting equipment that monitors the main line voltage and terminal voltage of the commercial power and emergency power supplied to the firefighting equipment in real time to determine voltage drop abnormalities and generates a control signal for output voltage compensation of the power supply unit or the emergency power supply unit.

[0010] Fourth, the invention provides an integrated remote monitoring and self-diagnosis system for firefighting equipment and a method thereof that stores and manages inspection history data of firefighting equipment and automatically sends an inspection schedule notification to an administrator's terminal when the statutory inspection cycle is due.

[0011] The problems that the present invention aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by those skilled in the art from the description below. means of solving the problem

[0012] A firefighting equipment integrated remote monitoring and self-diagnosis system according to one embodiment of the present invention comprises: a firefighting equipment unit (100) including a detector (110) for detecting heat or smoke, a receiver (120) for specifying the location of ignition, a fire pump (130), and a sprinkler system (140); an IoT terminal unit (200) connected to each firefighting equipment of the firefighting equipment unit (100) and collecting status data in real time including the operating status, power supply status, operating current value, pressure value, and sensor measurement value of each firefighting equipment; a self-diagnosis unit (300) that learns the time-series pattern of the status data collected from the IoT terminal unit (200) to set a normal operating range for each firefighting equipment and determines an abnormality when the measurement value deviates from the normal operating range; an alert processing unit (400) that generates abnormality alert information including location information of the firefighting equipment where an abnormality is detected, the type of abnormality, and the time of occurrence of the abnormality according to the judgment result of the self-diagnosis unit (300), and automatically transmits it to a pre-registered administrator terminal (700); and the inspection date and time of the firefighting equipment unit (100), inspection It may include an inspection history database (500) that stores and manages inspection history data including content, inspector information and action history, and a fire pump self-diagnosis module (600) that analyzes the operating current value and pressure value of the fire pump (130) to detect whether the fire pump (130) is in cutoff operation and generates an automatic stop control signal for the fire pump (130) when cutoff operation is detected.

[0014] According to one embodiment of the present invention, the IoT terminal unit (200) may include a power monitoring module (210) that measures the main line voltage and the terminal voltage of the commercial power and emergency power supplied to the fire fighting equipment unit (100), a communication interface module (220) that is connected to each fire fighting equipment communication port of the fire fighting equipment unit (100) to collect operation status signals, and a data transmission module (230) that transmits the collected status data to the self-diagnosis unit (300) via a wired or wireless communication network.

[0016] According to one embodiment of the present invention, the self-diagnosis unit (300) determines that there is a voltage drop abnormality when the difference between the main line voltage and the terminal voltage measured by the power monitoring module (210) exceeds a preset allowable lower limit range relative to the rated voltage, and transmits the voltage drop abnormality information to the administrator terminal (700) through the notification processing unit (400), while simultaneously generating a control signal for output voltage compensation of the power supply unit (810) or the emergency power supply unit (820).

[0018] According to one embodiment of the present invention, the self-diagnosis unit (300) calculates an abnormality judgment index (ADI) for each fire fighting facility according to the following formula 1, wherein Xm is the current measured value, μ is the normal operation moving average value, σ is the normal operation standard deviation, and W is a weighting factor for each type of fire fighting facility, such that for a fire pump (130) it is 0.4 or more and 0.5 or less, for a power supply facility it is 0.3 or more and 0.4 or less, and for a detector (110) and receiver (120) it is 0.1 or more and 0.3 or less. If the absolute value of the calculated ADI is greater than or equal to a value set in the range of a preset abnormality judgment threshold (ADI_th) of 2.0 or more and 3.0 or less, the fire fighting facility can be judged to be in an abnormal state.

[0019] (Equation 1) ADI = (Xm - μ) / σ × W

[0021] According to one embodiment of the present invention, the self-diagnosis unit (300) calculates the probability of failure (FPI) according to the following formula 2, wherein Nf is the number of times the ADI threshold is exceeded within a preset period (T), Nt is the total number of measurements within the same period, and Δ is the rate of change of ADI relative to the previous measurement cycle, calculated as (ADI_current - ADI_prev) / ADI_prev. When the calculated FPI is greater than or equal to a value set within the range of 0.3 or more and 0.7 or less, which is a preset prediction threshold (FPI_th), it can generate a prediction anomaly notification information for the firefighting equipment and transmit it to an administrator terminal (700) through the notification processing unit (400).

[0022] (Equation 2) FPI = (Nf / Nt) × (1 + ΔADI)

[0024] According to one embodiment of the present invention, the fire pump self-diagnosis module (600) can analyze the number of starts, start time, operating current value, and discharge pressure value of the fire pump (130) in combination, and determine that if the discharge pressure value exceeds 140% of the rated pressure and the flow rate is less than a preset minimum flow rate for a preset time or longer, it is considered to be shut-off operation and can generate an automatic stop control signal for the fire pump (130).

[0026] According to one embodiment of the present invention, the inspection history database (500) is linked to a statutory inspection history including the results of self-inspections of firefighting facilities, and can generate an inspection schedule notification for firefighting equipment for which an inspection cycle has arrived and transmit it to an administrator terminal (700) through the notification processing unit (400).

[0028] A method for integrated remote monitoring and self-diagnosis of firefighting equipment according to one embodiment of the present invention may include: (a) a step in which an IoT terminal unit (200) collects status data in real time including operation status, power supply status, operating current value, pressure value and sensor measurement value from each firefighting equipment of a firefighting equipment unit (100); (b) a step in which a self-diagnosis unit (300) calculates an ADI for each firefighting equipment according to the above formula 1 and determines the firefighting equipment to be in an abnormal state if the absolute value of the ADI is greater than or equal to a preset abnormality judgment threshold; (c) a step in which, when an abnormality is detected, an notification processing unit (400) generates abnormality notification information and automatically transmits it to an administrator terminal (700); (d) a step in which a fire pump self-diagnosis module (600) determines cut-off operation and generates an automatic stop control signal; and (e) a step in which an inspection history database (500) stores and manages the inspection date and time, inspection details, and action history.

[0030] According to one embodiment of the present invention, in step (b), the self-diagnosis unit (300) may further include the step of calculating a failure probability index (FPI) according to the formula 2, and generating a prediction anomaly notification information when the FPI is greater than or equal to a preset prediction threshold (FPI_th).

[0032] According to one embodiment of the present invention, the step of (a) further includes measuring the main line voltage and the terminal voltage of the commercial power and emergency power supplied to the fire fighting equipment unit (100), respectively, and the step of (b) further includes determining that there is an abnormal voltage drop when the difference between the main line voltage and the terminal voltage exceeds a preset allowable lower limit range relative to the rated voltage, and generating a control signal for output voltage compensation of the power supply unit (810) or the emergency power supply unit (820).

[0034] The means to be solved by the present invention are not limited to the means mentioned above, and other unmentioned means will be clearly understood by those skilled in the art from the description below. Effects of the invention

[0036] According to the present invention, first, by collecting operating status, power supply status, operating current value, pressure value, and sensor measurement value in real time from a plurality of firefighting equipment installed in a multi-unit building and precisely determining whether there is an abnormality based on the Abnormality Detection Index (ADI), false alarms and non-detection can be significantly reduced compared to the conventional simple threshold comparison method, and the safety of the firefighting equipment can be improved.

[0037] Second, by utilizing the Failure Probability Index (FPI) to calculate the combined frequency rate of ADI anomalies and the rate of change of ADI, it is possible to predict failures in firefighting equipment in advance and enable preventive maintenance, thereby increasing the availability of firefighting equipment.

[0038] Third, when the discharge pressure value of the fire pump (130) exceeds 140% of the rated pressure and the flow rate is below the minimum flow rate for a certain period of time or longer, it is determined to be a shut-off operation and an automatic stop control signal is generated, thereby preventing overheating and damage to the fire pump and reducing maintenance costs of the fire fighting equipment.

[0039] Fourth, when the difference between the main line voltage and the terminal voltage exceeds the preset allowable lower limit range relative to the rated voltage, a voltage drop abnormality is detected and an output voltage compensation control signal is generated, thereby supplying stable power to the firefighting equipment and ensuring normal operation of the firefighting equipment in the event of a fire.

[0040] Fifth, by automatically transmitting inspection schedule notifications for firefighting equipment whose statutory inspection cycle has arrived, it is possible to systematically support managers in fulfilling their legal obligations regarding the maintenance of firefighting facilities.

[0041] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description below. Brief explanation of the drawing

[0042] FIG. 1 is an overall configuration diagram of an integrated remote monitoring and self-diagnosis system for firefighting equipment according to one embodiment of the present invention. FIG. 2 is a detailed configuration diagram of an IoT terminal unit (200) according to one embodiment of the present invention. FIG. 3 is a flowchart for calculating the abnormality judgment index (ADI) of a self-diagnosis unit (300) according to one embodiment of the present invention. FIG. 4 is a flowchart for calculating the probability of failure index (FPI) of a self-diagnosis unit (300) according to one embodiment of the present invention. FIG. 5 is a flowchart of the cut-off operation judgment of a fire pump self-diagnosis module (600) according to one embodiment of the present invention. FIG. 6 is a block diagram of voltage drop monitoring and compensation control according to one embodiment of the present invention. FIG. 7 is an overall operation sequence diagram of an integrated remote monitoring and self-diagnosis system for firefighting equipment according to one embodiment of the present invention. Specific details for implementing the invention

[0043] Specific details of other embodiments are included in the detailed description and drawings.

[0044] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. Unless otherwise specified in the following description, all numbers, values, and / or expressions representing components, reaction conditions, and the content of components in the present invention should be understood as being modified by the term "approximately" in all cases, as these numbers are approximations reflecting the various uncertainties of measurement that occur in obtaining these values ​​among essentially different things. Furthermore, where a numerical range is disclosed in this description, such range is continuous and, unless otherwise indicated, includes all values ​​from the minimum value of such range to the maximum value including the maximum value. Furthermore, where such range refers to an integer, it includes all integers from the minimum value to the maximum value including the maximum value, unless otherwise indicated.

[0045] Additionally, when a range is described for a variable in the present invention, it will be understood that the variable includes all values ​​within the described range, including the described endpoints of the range. For example, the range "5 to 10" will be understood to include not only the values ​​5, 6, 7, 8, 9, and 10, but also any sub-ranges such as 6 to 10, 7 to 10, 6 to 9, 7 to 9, etc., and any values ​​between integers valid for the category of the described range, such as 5.5, 6.5, 7.5, 5.5 to 8.5, and 6.5 to 9. For example, the range “10% to 30%” will be understood to include all integers including values ​​such as 10%, 11%, 12%, 13%, etc. and up to 30%, as well as any sub-range such as 10% to 15%, 12% to 18%, 20% to 30%, etc., and any value between valid integers within the stated range categories such as 10.5%, 15.5%, 25.5%, etc.

[0047] According to one embodiment of the present invention, in a firefighting equipment integrated remote monitoring and self-diagnosis system for managing a plurality of firefighting equipment installed in a multi-unit building, the firefighting equipment unit (100) including a detector (110) for detecting heat or smoke, a receiver (120) for specifying the location of ignition, a fire pump (130), and a sprinkler system (140); an IoT terminal unit (200) connected to each firefighting equipment of the firefighting equipment unit (100) and collecting status data in real time including the operating status, power supply status, operating current value, pressure value, and sensor measurement value of each firefighting equipment; a self-diagnosis unit (300) that learns the time-series pattern of the status data collected from the IoT terminal unit (200) to set a normal operating range for each firefighting equipment and determines an abnormality when the measurement value deviates from the normal operating range; and an alert processing unit (400) that generates abnormality alert information including location information of the firefighting equipment where an abnormality is detected, the type of abnormality, and the time of occurrence of the abnormality according to the judgment result of the self-diagnosis unit (300), and automatically transmits it to a pre-registered administrator terminal (700). An integrated remote monitoring and self-diagnosis system for firefighting equipment is provided, comprising: an inspection history database (500) that stores and manages inspection history data including the inspection date and time, inspection details, inspector information, and action history of the firefighting equipment unit (100); and a fire pump self-diagnosis module (600) that analyzes the operating current value and pressure value of the fire pump (130) to detect whether the fire pump (130) is in cut-off operation, and generates an automatic stop control signal for the fire pump (130) when cut-off operation is detected.

[0048] In the present invention, the IoT terminal unit (200) comprises: a power monitoring module (210) that measures the main line voltage and the terminal voltage of the commercial power and emergency power supplied to the fire fighting equipment unit (100), respectively; a communication interface module (220) that is connected to each fire fighting equipment communication port of the fire fighting equipment unit (100) to collect operation status signals; and a data transmission module (230) that transmits the collected status data to the self-diagnosis unit (300) via a wired or wireless communication network.

[0049] The present invention will be described in more detail below with reference to the drawings.

[0050] Figure 1 shows an overall configuration diagram of an integrated remote monitoring and self-diagnosis system for firefighting equipment according to one embodiment of the present invention.

[0051] Referring to FIG. 1, a firefighting equipment integrated remote monitoring and self-diagnosis system according to one embodiment of the present invention comprises a firefighting equipment unit (100), an IoT terminal unit (200), a self-diagnosis unit (300), a notification processing unit (400), an inspection history database (500), a fire pump self-diagnosis module (600), and an administrator terminal (700).

[0052] The above firefighting equipment unit (100) is composed of a plurality of firefighting equipment including a detector (110) that detects heat or smoke, a receiver (120) that indicates the location of the fire, a fire pump (130), and a sprinkler system (140).

[0053] The above IoT terminal unit (200) is connected to each fire fighting equipment of the above fire fighting equipment unit (100) and collects status data in real time including the operation status, power supply status, operating current value, pressure value, and sensor measurement value of each fire fighting equipment.

[0054] The self-diagnosis unit (300) learns the time-series pattern of status data collected from the IoT terminal unit (200) to set a normal operating range for each fire fighting facility, and determines an abnormality if the measured value deviates from the normal operating range. The self-diagnosis unit (300) can store and retrieve inspection history data by bidirectionally linking with the inspection history database (500).

[0055] The above notification processing unit (400) generates abnormality notification information including the location information of the firefighting equipment where an abnormality was detected, the type of abnormality, and the time of occurrence of the abnormality, based on the judgment result of the above self-diagnosis unit (300), and automatically transmits it to a pre-registered administrator terminal (700). In addition, the above notification processing unit (400) performs the function of receiving an inspection cycle arrival notification from the above inspection history database (500) and transmitting it to the administrator terminal (700).

[0056] The inspection history database (500) stores and manages inspection history data including the inspection date and time, inspection details, inspector information, and action history of the fire fighting equipment unit (100). The inspection history database (500) is linked to a statutory inspection history including the results of self-inspections of fire fighting facilities, and generates an inspection schedule notification for fire fighting facilities whose inspection cycle has arrived, and transmits it to an administrator terminal (700) through the notification processing unit (400).

[0057] The above fire pump self-diagnosis module (600) receives operating current value and pressure value data of the fire pump (130) from the IoT terminal (200) to detect whether the fire pump (130) is in cutoff operation, and if cutoff operation is detected, generates an automatic stop control signal for the fire pump (130).

[0059] FIG. 2 shows a detailed configuration diagram of an IoT terminal unit (200) according to one embodiment of the present invention.

[0060] Referring to FIG. 2, the IoT terminal unit (200) is configured to include a power monitoring module (210), a communication interface module (220), and a data transmission module (230).

[0061] The power monitoring module (210) measures the main line voltage and the terminal voltage of the commercial power and emergency power supplied to the fire fighting equipment unit (100), respectively. Specifically, the power monitoring module (210) includes a main line voltage measuring unit (211) for measuring the main line voltage, a terminal voltage measuring unit (212) for measuring the terminal voltage, and a terminal voltage measuring unit (213) for measuring the terminal voltage at the fire fighting equipment terminal (850).

[0062] Here, the self-diagnosis unit (300) determines that there is a voltage drop abnormality when the difference between the main line voltage and the terminal voltage measured by the power monitoring module (210) exceeds a preset allowable lower limit range relative to the rated voltage. It is preferable to set the allowable lower limit range to 10% or more and 15% or less of the rated voltage. If the allowable lower limit range is less than 10% of the rated voltage, frequent abnormality determinations may occur due to routine voltage fluctuations, and unnecessary notifications may be sent to the administrator. On the other hand, if the allowable lower limit range exceeds 15% of the rated voltage, it may not be determined as an abnormality even if a voltage drop affecting the normal operation of the fire fighting equipment occurs. Therefore, by setting the allowable lower limit range to 10% or more and 15% or less of the rated voltage, it is possible to detect voltage drop abnormalities in a timely manner while minimizing false alarms.

[0063] When the self-diagnosis unit (300) determines that there is an abnormal voltage drop, it transmits the abnormal voltage drop information to the administrator terminal (700) via the notification processing unit (400) and simultaneously generates a control signal for compensating the output voltage of the power supply unit (810) or the emergency power supply unit (820).

[0064] The communication interface module (220) is connected to each fire fighting equipment communication port of the fire fighting equipment unit (100) to collect operation status signals.

[0065] The data transmission module (230) transmits the collected status data to the self-diagnosis unit (300) via a wired or wireless communication network.

[0067] FIG. 3 shows a flowchart for calculating the abnormality judgment index (ADI) of a self-diagnosis unit (300) according to one embodiment of the present invention.

[0068] Referring to FIG. 3, in step (S10), the self-diagnosis unit (300) collects current measurements (Xm) including operating current, pressure, voltage, and various sensors from the IoT terminal unit (200).

[0069] (S20) In step, the self-diagnosis unit (300) calculates a normal operation moving average value (μ) from the previously stored normal operation data.

[0070] (S30) In step, the self-diagnosis unit (300) calculates the normal operation standard deviation (σ).

[0071] (S40) In step, the self-diagnosis unit (300) determines the type of fire fighting equipment and applies a weight (W) for each type of fire fighting equipment. The weight (W) is set to 0.4 or more and 0.5 or less for the fire pump (130), 0.3 or more and 0.4 or less for the power supply equipment, and 0.1 or more and 0.3 or less for the detector (110) and receiver (120).

[0072] The reason for limiting the weight (W) for the fire pump (130) to 0.4 or higher and 0.5 or lower is as follows. If the weight (W) is less than 0.4, the abnormal sensitivity of the fire pump (130) decreases, making it difficult to detect dangerous abnormal conditions such as shut-off operation at an early stage, and the abnormal detection rate becomes significantly lower. On the other hand, if the weight (W) exceeds 0.5, the proportion of abnormal judgments by the fire pump (130) becomes excessively high, increasing the false alarm rate and decreasing the abnormal detection sensitivity of other equipment such as power supply equipment and detectors. Therefore, it is desirable to set the weight (W) of the fire pump (130) to 0.4 or higher and 0.5 or lower to optimize the balance between the abnormal detection rate and the false alarm rate.

[0073] The reason for limiting the weight (W) for power supply equipment to between 0.3 and 0.4 is as follows. Since a malfunction in power supply equipment can lead to the inability of the entire firefighting system to operate, a higher weight must be assigned than that of detectors and receivers. If the weight (W) is less than 0.3, the importance of power supply malfunctions is underestimated, making timely detection difficult; if it exceeds 0.4, it overlaps with the weight of fire pumps, compromising the consistency of the overall weight sum system.

[0074] The reason for limiting the weight (W) for the detector (110) and receiver (120) to between 0.1 and 0.3 is as follows. Since the frequency of abnormalities occurring at the individual equipment unit level for detectors and receivers is high, the false alarm rate increases rapidly when an excessive weight is applied. If the weight (W) is less than 0.1, abnormalities in the detector and receiver do not have a substantial impact on the ADI calculation, and if it exceeds 0.3, false alarms due to frequent malfunctions occur frequently, thereby lowering the system reliability.

[0075] (S50) In step, the self-diagnosis unit (300) calculates an abnormality judgment index (ADI) according to the following formula 1.

[0076] (Equation 1) ADI = (Xm - μ) / σ × W

[0077] (S60) In step, the self-diagnosis unit (300) determines whether the absolute value of the calculated ADI is greater than or equal to a preset abnormality judgment threshold (ADI_th). It is preferable to set the ADI_th within the range of 2.0 or greater and 3.0 or less. If ADI_th is less than 2.0, an abnormality is judged even by temporary fluctuations in measurement values ​​within the normal range, causing a rapid increase in false alarm rates; if it exceeds 3.0, a non-detection problem occurs where an actual abnormal state is not detected even if it occurs. If the absolute value of ADI is greater than or equal to ADI_th (S70), the firefighting equipment is judged to be in an abnormal state, and abnormality notification information is generated through the notification processing unit (400) and automatically transmitted to the administrator terminal (700). If the absolute value of ADI is less than ADI_th (S80), it is judged to be normal and monitoring continues.

[0079] (Example)

[0080] An embodiment of the present invention will be described.

[0081] [Example 1 ― Evaluation of Anomaly Detection Performance According to Weight (W) and ADI_th]

[0082] In a simulation environment for monitoring firefighting equipment in an apartment building (1 fire pump, 1 power supply system, 10 detectors, 1 receiver), the ADI_th was fixed at 2.5 and the weight (W) for each equipment type was varied to measure the abnormal detection rate and false alarm rate for 90 days. The abnormal detection rate is the ratio of accurately detected events compared to actual abnormal events, and the false alarm rate is the ratio of events misidentified as abnormal in normal sections.

[0083] division Fire pump W Power W Detector / Receiver W Anomaly Detection Rate (%) False alarm rate (%) Example 1 0.45 0.35 0.20 96.2 2.8 Example 2 0.40 0.40 0.20 94.7 3.1 Example 3 0.50 0.30 0.20 95.8 3.3 Comparative Example 1 0.30 0.40 0.30 77.4 12.6 Comparative Example 2 0.55 0.25 0.20 88.3 19.1 Comparative Example 3 0.25 0.45 0.30 71.2 8.9

[0084] As shown in Table 1, Comparative Examples 1 and 3, in which the fire pump W is less than 0.4, showed abnormal detection rates of only 77.4% and 71.2%, respectively, which are significantly lower than those of the Examples, and Comparative Example 2, in which the fire pump W exceeds 0.5, showed a false alarm rate of 19.1%, which is more than six times higher than that of the Examples. On the other hand, Examples 1 to 3, in which the fire pump W was set to between 0.4 and 0.5, achieved an abnormal detection rate of 94% or higher and a false alarm rate of 4% or lower. Through this, it was confirmed that setting the fire pump weight (W) to between 0.4 and 0.5 optimizes the abnormal detection performance.

[0085] [Example 2 ― Evaluation of Anomaly Detection Performance According to ADI_th]

[0086] The weighting conditions of Example 1 (fire pump W=0.45, power supply W=0.35, detector W=0.20) were fixed, and the abnormal detection rate and false alarm rate were measured by changing ADI_th.

[0087] division ADI_th Anomaly Detection Rate (%) False alarm rate (%) Example A 2.0 97.1 5.4 Example B 2.5 96.2 2.8 Example C 3.0 93.5 1.2 Comparative Example A 1.5 98.3 22.7 Comparative Example B 3.5 81.6 0.8

[0088] As shown in Table 2, Comparative Example A, where ADI_th is less than 2.0, shows a sharp increase in the false alarm rate to 22.7%, significantly degrading system reliability, while Comparative Example B, where ADI_th exceeds 3.0, shows a decrease in the abnormality detection rate to 81.6%, increasing the risk of non-detection. On the other hand, Examples A to C, in which ADI_th was set to 2.0 or higher and 3.0 or lower, were able to maintain an abnormality detection rate of 93% or higher while managing the false alarm rate to 6% or lower. Through this, it was confirmed that setting ADI_th to 2.0 or higher and 3.0 or lower is desirable.

[0089] FIG. 4 shows a flowchart for calculating the probability of failure index (FPI) of a self-diagnosis unit (300) according to one embodiment of the present invention.

[0090] Referring to FIG. 4, in step (S10), the self-diagnosis unit (300) collects ADI history data within a preset period (T).

[0091] (S20) In step, the self-diagnosis unit (300) calculates the number of times (Nf) the ADI threshold was exceeded within a preset period (T).

[0092] (S30) In step, the self-diagnosis unit (300) calculates the total number of measurements (Nt) within the same period.

[0093] (S40) In step, the self-diagnosis unit (300) calculates the rate of change of ADI (Δ) relative to the previous measurement cycle. Δ is calculated as (ADI_current - ADI_prev) / ADI_prev, and a positive value of Δ indicates that the abnormal condition is worsening.

[0094] (S50) In step, the self-diagnosis unit (300) calculates the probability of failure index (FPI) according to the following formula 2.

[0095] (Equation 2) FPI = (Nf / Nt) × (1 + ΔADI)

[0096] Here, (Nf / Nt) represents the rate of anomaly occurrence within a preset period (T), and (1 + Δ term is a correction factor reflecting the recent ADI change trend.

[0097] (S60) In step, the self-diagnosis unit (300) determines whether the calculated FPI is greater than or equal to a preset prediction threshold (FPI_th). It is preferable to set the FPI_th within the range of 0.3 to 0.7. If FPI_th is less than 0.3, a prediction anomaly notification occurs even in the initial stage where the anomaly frequency rate is low, causing unnecessary inspection by the manager. On the other hand, if FPI_th exceeds 0.7, a prediction notification is not sent even when an actual failure is imminent, resulting in a loss of effectiveness for preventive maintenance. Therefore, by setting FPI_th to 0.3 to 0.7, the timeliness of preventive maintenance can be ensured while minimizing unnecessary notifications. If FPI is greater than or equal to FPI_th (S70), a prediction anomaly notification information for the firefighting equipment is generated and transmitted to the manager terminal (700) via the notification processing unit (400). If FPI is less than FPI_th (S80), it is determined to be normal and monitoring continues.

[0099] [Example 3 ― Evaluation of Predicted Anomaly Detection Performance According to FPI_th]

[0100] The weighting conditions of Example 1 and ADI_th=2.5 were applied, and FPI_th was varied to measure the prediction success rate and unnecessary notification rate 14 days before the actual failure occurred.

[0101] division FPI_th Prediction success rate (%) 14 days ago Unnecessary notification rate (%) Example D 0.3 97.8 8.2 Example E 0.5 94.3 3.9 Example F 0.7 88.6 1.4 Comparative Example C 0.2 98.5 31.7 Comparative Example D 0.8 72.1 0.6

[0102] As shown in Table 3, Comparative Example C, where FPI_th is less than 0.3, shows a problem where the unnecessary notification rate surges to 31.7%, leading to an excessive workload for the manager, while Comparative Example D, where FPI_th exceeds 0.7, shows a decrease in the 14-day prediction success rate to 72.1%, resulting in a significant reduction in the effectiveness of preventive maintenance. On the other hand, Examples D to F, with FPI_th set to between 0.3 and 0.7, achieved a 14-day prediction success rate of 88% or higher while maintaining the unnecessary notification rate at 10% or less. Through this, it was confirmed that setting FPI_th to between 0.3 and 0.7 optimizes the performance of predictive anomaly detection.

[0104] FIG. 5 shows a flowchart of the cut-off operation judgment of a fire pump self-diagnosis module (600) according to one embodiment of the present invention.

[0105] Referring to FIG. 5, the fire pump self-diagnosis module (600) determines whether to operate in a cutoff state by analyzing the number of starts, start time, operating current value, and discharge pressure value of the fire pump (130), and if a cutoff state is detected, generates an automatic stop control signal for the fire pump (130).

[0106] (S10) In step, the fire pump (130) starts operating.

[0107] (S20) In step, the fire pump self-diagnosis module (600) measures the discharge pressure value, flow rate, and operating current value of the fire pump (130).

[0108] In step (S30), the fire pump self-diagnosis module (600) determines whether the discharge pressure value exceeds 140% of the rated pressure. If the discharge pressure value does not exceed 140% of the rated pressure (S80), it is determined to be normal operation and monitoring continues.

[0109] The reason for establishing the condition where the discharge pressure value exceeds 140% of the rated pressure as the criterion for determining shut-off operation is as follows. According to the fire pump performance test standards (KFI certification standard KFI-IC-100 and related laws), the pump characteristic curve must be designed so that the shut-off pressure of a fire pump is 140% or less of the rated discharge pressure. Therefore, if the discharge pressure value exceeds 140% of the rated pressure, it means that the fire pump is in a shut-off or equivalent no-flow operation state, and if this state persists, the internal temperature of the pump may rise and mechanical damage may occur.

[0110] In step (S40), the fire pump self-diagnosis module (600) determines whether the flow rate is less than a preset minimum flow rate. If the flow rate is greater than or equal to the minimum flow rate (S80), it is determined to be normal operation and monitoring continues.

[0111] (S50) In step, the fire pump self-diagnosis module (600) measures the duration of the state in which the discharge pressure value exceeds 140% of the rated pressure and the flow rate is less than the preset minimum flow rate.

[0112] (S60) In step, the fire pump self-diagnosis module (600) determines whether the duration of the corresponding state is longer than a preset time. The reason for establishing a duration determination criterion is to prevent misjudging such an excessive state as shut-off operation, as a phenomenon in which the discharge pressure temporarily rises may occur during the initial start of the fire pump.

[0113] In step (S70), the fire pump self-diagnosis module (600) makes a final determination of shut-off operation and generates an automatic stop control signal for the fire pump (130). At the same time, a shut-off operation alarm is transmitted to the administrator terminal (700) through the notification processing unit (400).

[0115] FIG. 6 shows a voltage drop monitoring and compensation control block diagram according to one embodiment of the present invention.

[0116] Referring to FIG. 6, the power supply unit (810) supplies commercial power to the fire fighting equipment unit (100) through the main line (830), and the emergency power supply unit (820) supplies emergency power through the main line (840). The fire fighting equipment end (850) represents each fire fighting equipment end of the fire fighting equipment unit (100).

[0117] The above power monitoring module (210) measures the voltage of the main line (830) and the main line (840) through the main line voltage measuring unit (211), and measures the voltage at the end of the fire fighting equipment (850) through the end voltage measuring unit (212) and the end voltage measuring unit (213).

[0118] The self-diagnosis unit (300) determines that there is a voltage drop abnormality when the difference between the main line voltage and the terminal voltage exceeds a preset allowable lower limit range relative to the rated voltage. When a voltage drop abnormality is determined, an abnormality notification (410) is generated to transmit the voltage drop abnormality information to the administrator terminal (700) via the notification processing unit (400), and a compensation control (420) signal is generated to compensate the output voltage of the power supply unit (810) or the emergency power supply unit (820).

[0119] In a method for integrated remote monitoring and self-diagnosis of firefighting equipment according to one embodiment of the present invention, step (a) further includes the step of measuring the main line voltage and the terminal voltage of the commercial power and emergency power supplied to the firefighting equipment unit (100), respectively, and step (b) further includes the step of determining that there is an abnormal voltage drop when the difference between the main line voltage and the terminal voltage exceeds a preset allowable lower limit range relative to the rated voltage, and generating a control signal for output voltage compensation of the power supply unit (810) or the emergency power supply unit (820).

[0121] FIG. 7 shows an overall operation sequence diagram of an integrated remote monitoring and self-diagnosis system for fire fighting equipment according to one embodiment of the present invention.

[0122] Referring to FIG. 7, ① the firefighting equipment unit (100) requests the IoT terminal unit (200) to collect status data, and as step (a), the IoT terminal unit (200) collects status data in real time, including operation status, power supply status, operating current value, pressure value and sensor measurement value from each firefighting equipment of the firefighting equipment unit (100).

[0123] ② The IoT terminal unit (200) transmits ADI calculation request data including Xm, μ, σ, and W to the self-diagnosis unit (300).

[0124] ③ (b) As a step, the self-diagnosis unit (300) calculates ADI = (Xm - μ) / σ × W according to Formula 1. Here, W is 0.4 or more and 0.5 or less for the fire pump (130), 0.3 or more and 0.4 or less for the power supply equipment, and 0.1 or more and 0.3 or less for the detector (110) and receiver (120), and ADI_th is set in the range of 2.0 or more and 3.0 or less.

[0125] ④ The self-diagnosis unit (300) calculates FPI = (Nf / Nt) × (1 + ΔADI) according to Equation 2. FPI_th is set in the range of 0.3 to 0.7.

[0126] ⑤ The self-diagnosis unit (300) transmits abnormal judgment or predicted abnormality notification information to the notification processing unit (400) based on the ADI and FPI judgment results.

[0127] ⑥ (c) As a step, the notification processing unit (400) generates abnormality notification information including location information of the firefighting equipment where an abnormality was detected, the type of abnormality, and the time of occurrence of the abnormality, and automatically notifies the administrator terminal (700).

[0128] ⑦ The IoT terminal unit (200) transmits the cut-off operation detection data of the fire pump (130) to the self-diagnosis unit (300).

[0129] ⑧ (d) As a step, the self-diagnosis unit (300) determines that the discharge pressure value exceeds 140% of the rated pressure and the flow rate is less than the preset minimum flow rate for a preset time or longer, and generates an automatic stop control signal for the fire pump (130) and transmits it to the IoT terminal unit (200).

[0130] Meanwhile, as step (e), the inspection history database (500) stores and manages the inspection date, inspection details, and action history of the firefighting equipment unit (100), and in conjunction with the statutory inspection history, generates an inspection schedule notification for firefighting equipment for which an inspection cycle has arrived, and transmits it to the administrator terminal (700) through the notification processing unit (400).

[0132] A person skilled in the art to which the present invention pertains will understand that the present invention may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. The scope of the present invention is defined by the claims set forth below rather than by the detailed description above, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts should be interpreted as being included within the scope of the present invention. Explanation of the symbols

[0134] 100: Firefighting Equipment Department 110: Detector 120: Receiver 130: Fire pump 140: Sprinkler system 200: IoT terminal unit 210: Power monitoring module 211: Main line voltage measurement unit 212: Terminal voltage measuring unit 213: Terminal voltage measuring unit (lower) 220: Communication interface module 230: Data transmission module 300: Self-diagnosis section 400: Notification processing unit 410: Anomaly notification 420: Compensation Control 500: Inspection History Database 600: Fire Pump Self-Diagnosis Module 700: Administrator Terminal 810: Power supply unit 820: Emergency Power Supply Unit 830: Main line (Commercial power) 840: Main line (emergency power) 850: Firefighting equipment end

Claims

Claim 1 A firefighting equipment integrated remote monitoring and self-diagnosis system for managing multiple firefighting equipment installed in a multi-unit building comprises: a firefighting equipment unit (100) including a detector (110) for detecting heat or smoke, a receiver (120) for specifying the location of ignition, a fire pump (130), and a sprinkler system (140); an IoT terminal unit (200) connected to each firefighting equipment of the firefighting equipment unit (100) and collecting status data in real time including the operating status, power supply status, operating current value, pressure value, and sensor measurement value of each firefighting equipment; a self-diagnosis unit (300) that learns the time-series pattern of the status data collected from the IoT terminal unit (200) to set a normal operating range for each firefighting equipment and determines an abnormality if the measurement value deviates from the normal operating range; and an alert processing unit (400) that generates abnormality alert information including location information of the firefighting equipment where an abnormality is detected, the type of abnormality, and the time of occurrence of the abnormality according to the judgment result of the self-diagnosis unit (300), and automatically transmits it to a pre-registered administrator terminal (700). An inspection history database (500) that stores and manages inspection history data including the inspection date and time, inspection details, inspector information, and action history of the above fire fighting equipment unit (100); and a fire pump self-diagnosis module (600) that analyzes the operating current value and pressure value of the fire pump (130) to detect whether the fire pump (130) is in cut-off operation, and generates an automatic stop control signal for the fire pump (130) when cut-off operation is detected; wherein the self-diagnosis unit (300) calculates an abnormality judgment index (ADI) for each fire fighting equipment according to the following formula 1, (Formula 1) ADI = (Xm - μ) / σ × W, where Xm is the current measured value, μ is the normal operation moving average value, σ is the normal operation standard deviation, and W is a weighting factor for each type of fire fighting equipment, such that for the fire pump (130) it is 0.4 or more and 0.5 or less, for the power supply equipment it is 0.3 or more and 0.4 or less, and for the detector (110) and receiver (120) it is 0.1 or more and 0.An integrated remote monitoring and self-diagnosis system for firefighting equipment characterized by determining the firefighting equipment to be in an abnormal state when the absolute value of the calculated ADI is 3 or less and is greater than or equal to a preset abnormality judgment threshold (ADI_th). Claim 2 In claim 1, the IoT terminal unit (200) comprises: a power monitoring module (210) that measures the main line voltage and terminal voltage of the commercial power and emergency power supplied to the fire fighting equipment unit (100), respectively; a communication interface module (220) that is connected to each fire fighting equipment communication port of the fire fighting equipment unit (100) to collect operation status signals; and a data transmission module (230) that transmits the collected status data to the self-diagnosis unit (300) via a wired or wireless communication network; characterized in that the fire fighting equipment integrated remote monitoring and self-diagnosis system. Claim 3 In paragraph 2, the self-diagnosis unit (300) determines that there is a voltage drop abnormality when the difference between the main line voltage and the terminal voltage measured by the power monitoring module (210) exceeds a preset allowable lower limit range relative to the rated voltage, and transmits the voltage drop abnormality information to the administrator terminal (700) through the notification processing unit (400), while simultaneously generating a control signal for output voltage compensation of the power supply unit (810) or the emergency power supply unit (820). Claim 4 delete Claim 5 In claim 1, the self-diagnosis unit (300) calculates a fault occurrence probability index (FPI) according to the following formula 2, (Formula 2) FPI = (Nf / Nt) × (1 + ΔADI), where Nf is the number of times the ADI threshold is exceeded within a preset period (T), Nt is the total number of measurements within the same period, and Δ is the rate of change of ADI relative to the previous measurement cycle, calculated as (ADI_Current - ADI_Previous) / ADI_Previous, and if the calculated FPI is greater than or equal to a preset prediction threshold (FPI_th), it generates a prediction anomaly notification information for the firefighting equipment and transmits it to an administrator terminal (700) through the notification processing unit (400), thereby characterizing the firefighting equipment integrated remote monitoring and self-diagnosis system. Claim 6 In claim 1, the fire pump self-diagnosis module (600) is characterized by performing a combined analysis of the number of starts, start time, operating current value, and discharge pressure value of the fire pump (130), determining that shut-off operation occurs when the discharge pressure value exceeds 140% of the rated pressure and the flow rate is less than a preset minimum flow rate for a preset time or longer, and generating an automatic stop control signal for the fire pump (130). Claim 7 A firefighting equipment integrated remote monitoring and self-diagnosis system, wherein, in claim 1, the inspection history database (500) is linked to a statutory inspection history including the results of self-inspections of firefighting facilities, and generates an inspection schedule notification for firefighting equipment for which an inspection cycle has arrived and transmits it to an administrator terminal (700) through the notification processing unit (400). Claim 8 A method for integrated remote monitoring and self-diagnosis of firefighting equipment for integrated management of multiple firefighting equipment installed in a multi-unit building, comprising: (a) a step in which an IoT terminal unit (200) collects in real time status data including operation status, power supply status, operating current value, pressure value, and sensor measurement value from each firefighting equipment of a firefighting equipment unit (100), which includes a detector (110) that detects heat or smoke, a receiver (120) that specifies the location of ignition, a fire pump (130), and a sprinkler system (140); (b) a step in which a self-diagnosis unit (300) calculates an abnormality judgment index (ADI) for each firefighting equipment according to the following formula 1, and determines the firefighting equipment to be in an abnormal state if the absolute value of the ADI is greater than or equal to a preset abnormality judgment threshold (ADI_th); (Formula 1) ADI = (Xm - μ) / σ × W, where Xm is the current measurement value, μ is the normal operation moving average value, σ is the normal operation standard deviation, and W is a weighting factor for each type of firefighting equipment (c) when an abnormality is detected, the fire pump (130) is 0.4 or more and 0.5 or less, the power supply equipment is 0.3 or more and 0.4 or less, and the detector (110) and receiver (120) are 0.1 or more and 0.3 or less; (d) when an abnormality is detected, the notification processing unit (400) generates abnormality notification information including location information of the fire fighting equipment where the abnormality was detected, the type of abnormality, and the time of occurrence of the abnormality, and automatically transmits it to a pre-registered administrator terminal (700); (d) when the fire pump self-diagnosis module (600) determines that the discharge pressure value of the fire pump (130) exceeds 140% of the rated pressure and the flow rate is less than the preset minimum flow rate for a preset time or longer, it is shut-off operation, and generates an automatic stop control signal for the fire pump (130); and (e) a step of storing and managing the inspection date, inspection details, and action history of the firefighting equipment unit (100) in an inspection history database (500); characterized by a firefighting equipment integrated remote monitoring and self-diagnosis method. Claim 9 A method for integrated remote monitoring and self-diagnosis of firefighting equipment according to claim 8, wherein step (b) further comprises the step of calculating a probability of failure index (FPI) according to the following formula 2, and generating an abnormal prediction notification if the FPI is greater than or equal to a preset prediction threshold (FPI_th). (Formula 2) FPI = (Nf / Nt) × (1 + ΔADI) where Nf is the number of times the ADI threshold is exceeded within a preset period (T), Nt is the total number of measurements within the same period, and Δ is the rate of change of ADI relative to the previous measurement cycle, calculated as (ADI_Current - ADI_Previous) / ADI_Previous. Claim 10 In claim 8, the above step (a) further includes the step of measuring the main line voltage and the terminal voltage of the commercial power and emergency power supplied to the fire fighting equipment unit (100), respectively, and the above step (b) further includes the step of determining that there is an abnormal voltage drop when the difference between the main line voltage and the terminal voltage exceeds a preset allowable lower limit range relative to the rated voltage, and generating a control signal for output voltage compensation of the power supply unit (810) or the emergency power supply unit (820).

Images