Abnormality sign detection device, abnormality sign detection system, abnormality sign detection method, and abnormality sign detection program

Abstract

To provide an abnormality sign detection device that suppresses erroneous detection of an abnormality sign that may occur even when facility equipment is normal, due to the influence of noise.SOLUTION: An abnormality sign detection device 10 includes a processing unit 12 that performs processing to: predict, in a time series, future values of cyclical data, which is data having periodicity extracted from time-series operation data that is a chronological compilation of operation data of equipment installed in a monitored facility, and set a normal range for the cyclical data; determine whether or not there is an abnormality sign in the operation data based on the cyclical data deviating from the normal range of the cyclical data at least twice; and display the abnormality sign determination result.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to an abnormality sign detection device, an abnormality sign detection system, an abnormality sign detection method, and an abnormality sign detection program that detect signs of abnormality in facility equipment. [Background technology]

[0002] When managing facilities such as buildings, factories, and plants where lighting equipment, air conditioning systems, and other equipment are installed, it is necessary to monitor the condition of the equipment, detect signs of abnormalities that could interfere with normal operation, and perform maintenance and inspections of the equipment.

[0003] Patent Document 1 discloses a failure prediction device that collects sensor data from facility equipment and generates a regression model and a correlation model between sensors, thereby calculating the degree of deviation from the normal state of the facility equipment. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2018-112852 Summary of the Invention [Problem to be solved by the invention]

[0005] The failure prediction device disclosed in Patent Document 1 may erroneously detect an abnormality when the measurement value of the sensor data becomes abnormal due to the influence of noise even though the facility equipment is normal.

[0006] The present disclosure has been made in consideration of the above, and aims to provide an abnormality sign detection device that suppresses false detection of abnormality signs due to the influence of noise even when facility equipment is normal. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the objectives, the abnormality sign detection device according to the present disclosure includes a processing unit that performs processing to time-series predict future values ​​of cyclical data, which is data having periodicity extracted from time-series operation data that is a chronological compilation of operation data of equipment installed in a monitored facility, to set a normal range for the cyclical data, to determine whether or not there is an abnormality sign in the operation data based on the cyclical data deviating from the normal range of the cyclical data at least twice, and to display the abnormality sign determination result. [Effects of the Invention]

[0008] According to the present disclosure, it is possible to obtain an anomaly sign detection device that is suppressed from falsely detecting an anomaly sign due to the influence of noise even when facility equipment is normal. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing a configuration of an abnormality sign detection system according to a first embodiment. [Figure 2] Functional block diagram of an abnormality sign detection system according to the first embodiment [Figure 3] 1 is a flowchart showing the flow of operations of the abnormality sign detection system according to the first embodiment. [Figure 4] FIG. 1 is a diagram showing an example of time-series operation data acquired by the abnormality sign detection system according to the first embodiment. [Figure 5] 1 is a flowchart showing a process flow for determining whether or not there is a deviation in the abnormality sign detection system according to the first embodiment. [Figure 6] FIG. 1 is a diagram showing an example of time series prediction, setting of normal ranges, and deviation detection in the anomaly sign detection system according to the first embodiment. [Figure 7] FIG. 10 is a diagram showing a first example of display of the determination result of an abnormality sign of the abnormality sign detection system according to the first embodiment; [Figure 8] FIG. 10 is a diagram showing a second example of display of the abnormality sign determination result of the abnormality sign detection system according to the first embodiment; [Figure 9] FIG. 10 is a diagram showing a third example of display of the abnormality sign determination result of the abnormality sign detection system according to the first embodiment; [Figure 10] FIG. 10 is a diagram showing a fourth example of display of the abnormality sign determination result of the abnormality sign detection system according to the first embodiment; [Figure 11] Functional block diagram of an abnormality sign detection system according to a second embodiment [Figure 12] FIG. 10 is a diagram showing a first method for determining whether or not there is an abnormality sign in the abnormality sign detection system according to the second embodiment. [Figure 13] 10 is a flowchart showing the flow of a first method for determining whether or not there is a sign of abnormality in the abnormality sign detection system according to the second embodiment. [Figure 14] FIG. 10 is a diagram showing a second method for determining whether or not there is an abnormality sign in the abnormality sign detection system according to the second embodiment. [Figure 15] 10 is a flowchart showing the flow of a second method for determining whether or not there is a sign of abnormality in the abnormality sign detection system according to the second embodiment. [Figure 16] FIG. 10 is a diagram showing the configuration of an abnormality sign detection system according to a third embodiment. [Figure 17] Functional block diagram of an abnormality sign detection system according to a third embodiment [Figure 18] FIG. 10 is a diagram showing a first example of facility connection relationship information used in the abnormality sign detection system according to the third embodiment; [Figure 19] FIG. 10 is a diagram showing a second example of facility connection relationship information used in the anomaly sign detection system according to the third embodiment; [Figure 20] 10 is a flowchart showing the flow of operations of an abnormality sign detection system according to a third embodiment. [Figure 21] 10 is a flowchart showing the flow of an abnormality sign determination method of an abnormality sign detection system according to a third embodiment. [Figure 22] FIG. 10 is a diagram showing an example of determining an abnormality sign in the abnormality sign detection system according to the third embodiment. [Figure 23] Functional block diagram of an abnormality sign detection system according to a fifth embodiment [Figure 24] FIG. 10 is a diagram showing an example of a hardware configuration that realizes a processing unit included in an abnormality sign detection device according to the first to fifth embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0010] An abnormality sign detection device, an abnormality sign detection system, an abnormality sign detection method, and an abnormality sign detection program according to embodiments will be described in detail below with reference to the accompanying drawings.

[0011] Embodiment 1 1 is a diagram showing the configuration of an abnormality sign detection system according to embodiment 1. The abnormality sign detection system 100 according to embodiment 1 is used for managing a building 80, which is a facility to be monitored. The abnormality sign detection system 100 includes an abnormality sign detection device 10 and a building monitoring control system server 20. The abnormality sign detection system 100 is connected to an information display terminal 40 via a network 30.

[0012] A building 80, which is a facility to be monitored, is equipped with a plurality of pieces of equipment 81, each equipped with at least one device 811. Each device 811 outputs at least one signal. Here, the signal value of each signal output by each device 811 installed in each piece of equipment 81 in the building 80 is referred to as "operating data," and the operating data compiled in chronological order is referred to as "time-series operating data."

[0013] The building monitoring control system server 20 is a server that controls equipment 81 and devices 811, which are facility devices installed in a building 80, which is a facility to be monitored. The building monitoring control system server 20 collects operation data from the equipment 81 and devices 811 installed in the building 80, which is a facility to be monitored.

[0014] 2 is a functional block diagram of the abnormality sign detection system according to embodiment 1. The abnormality sign detection device 10 includes a communication unit 11 that communicates with other devices connected to the network 30, a processing unit 12 that performs processing to determine whether or not there are signs of abnormality in the facility 81 and the equipment 811, and a storage unit 13 that stores information.

[0015] The storage unit 13 includes a time-series operational data storage unit 131 that stores time-series operational data.

[0016] The processing unit 12 includes an operating data acquisition unit 121 that acquires operating data from the building monitoring control system server 20 and updates the time-series operating data accumulated in a time-series operating data accumulation unit 131, a periodic data extraction unit 122 that extracts periodic data, which is data with periodicity, from the time-series operating data accumulated in the time-series operating data accumulation unit 131, a time-series prediction unit 123 that predicts future values ​​of the cyclical data in time series, and a normal range setting unit 124 that sets a normal range for predicted values ​​of the time-series operating data. The processing unit 12 also includes a deviation determination unit 125 that determines whether the acquired time-series data deviates from the normal range, an abnormality sign determination unit 126 that determines an abnormality sign in a signal output by the device 811 based on the deviation determined by the deviation determination unit 125, and a display processing unit 127 that displays the determination result of the abnormality sign on the information display terminal 40.

[0017] 3 is a flowchart showing the flow of operations of the abnormality sign detection system according to Embodiment 1. In step S1, the operation data acquisition unit 121 acquires operation data from the devices 811 of the equipment 81 installed in the building 80, which is the facility to be monitored, and updates the time-series operation data accumulated in the time-series operation data accumulation unit 131.

[0018] In step S2, the periodic data extraction unit 122 extracts periodic data, which is data having periodicity, from the time-series driving data accumulated in the time-series driving data accumulation unit 131. A known method such as frequency analysis can be applied to extract the periodic data.

[0019] FIG. 4 is a diagram illustrating an example of time-series operation data acquired by the anomaly sign detection system according to the first embodiment. The time-series operation data illustrated in FIG. 4 is data acquired every hour. The actual measurement value of signal A on January 1st changed from 0.13066, 0.059992, and 0.003407 between 1:00 and 3:00, and changed from 0.014998, 0.010374, and 0.067061 between 9:00 and 11:00. This suggests that similar changes occur every nine hours. Therefore, the periodicity data extraction unit 122 extracts signal A as periodic data. Furthermore, the actual measurement value of signal E on January 1st remains approximately constant. Therefore, the periodicity data extraction unit 122 extracts signal E as periodic data. Signals B, C, and D show no periodicity in the changes in their actual measurement values. Therefore, the periodic data extraction unit 122 does not extract the signals B, C, and D as periodic data.

[0020] In general, power consumption, air conditioning operation intensity, lighting intensity, and energy consumption change in a daily cycle pattern. Therefore, the periodicity data extraction unit 122 may extract, as periodicity data, time series data of signal names that include energy-related morphemes such as "power," "air conditioning," "lighting," and "energy."

[0021] In step S3, the time series prediction unit 123 predicts, in time series, future values ​​of the cyclical data extracted by the cyclical data extraction unit 122. The time series prediction unit 123 predicts, in time series, future values ​​of the cyclical data based on the period of change in the cyclical data and the actual measured values ​​of the cyclical data.

[0022] In step S4, the normal range setting unit 124 sets a normal range for the cyclical data based on a predicted value of the future value of the cyclical data in a time series.

[0023] In step S5, the deviation determination unit 125 determines whether or not there is a deviation in the cyclical data. FIG. 5 is a flowchart showing the flow of processing for determining whether or not there is a deviation in the anomaly sign detection system according to embodiment 1. In step S51, the deviation determination unit 125 determines whether or not the actual measured value of the current cyclical data is outside the normal range of the preset cyclical data. If the actual measured value of the current cyclical data is within the normal range of the preset cyclical data, the result is No in step S51, and the deviation determination unit 125 determines that there is no deviation in step S53. If the actual measured value of the current cyclical data is outside the normal range of the preset cyclical data, the result is Yes in step S51, and the deviation determination unit 125 determines that there is a deviation in step S52.

[0024] FIG. 6 is a diagram illustrating an example of time series prediction, setting of a normal range, and deviation detection in the anomaly sign detection system according to the first embodiment. Based on the actual measured values ​​of the cyclical data up to the present, the time series prediction unit 123 predicts future values ​​of the cyclical data in a time series. In FIG. 6, the solid lines indicate the actual measured values ​​of the cyclical data, and the dashed lines indicate the predicted values ​​of the cyclical data. The normal range setting unit 124 sets the normal range of the cyclical data based on the predicted values ​​of the cyclical data. For example, the normal range setting unit 124 sets the normal range to a range of ±α based on the predicted values ​​of the cyclical data. Here, α is a preset value. In FIG. 6, the dashed-dotted lines indicate the upper and lower limits of the normal range. Each time cyclical data is extracted during the period in which the normal range is set, the deviation determination unit 125 determines whether the actual measured values ​​of the cyclical data are outside the normal range. If the actual measured values ​​of the cyclical data are within the normal range, the deviation determination unit 125 determines that a deviation has occurred. In the example illustrated in FIG. 6, the actual measured values ​​of the cyclical data are outside the normal range at time t1, and therefore a deviation has occurred.

[0025] In step S6, the abnormality sign determination unit 126 determines whether or not there is an abnormality sign in the signal output by the device 811, based on the determination by the deviation determination unit 125 that there is at least two deviations.

[0026] In step S7, the display processing unit 127 transmits the abnormality sign determination result to the information display terminal 40, and causes the abnormality sign determination result to be displayed.

[0027] FIG. 7 is a diagram illustrating a first display example of the abnormality sign determination results of the abnormality sign detection system according to the first embodiment. The display processing unit 127 displays a determination result table 401 on the information display terminal 40. The determination result table 401 displays, in a table format, the date and time when the abnormality sign was detected, the facility name, device name, and signal name associated with the signal determined to contain an abnormality sign, a signal tag that is an identifier for the signal, and the type of abnormality. The type of abnormality is used to distinguish, for example, between a case where the actual measurement value of the periodic data exceeds the upper limit of the normal range and is determined to contain an abnormality sign, and a case where the actual measurement value falls below the lower limit of the normal range and is determined to contain an abnormality sign. By displaying the determination result table 401 on the information display terminal 40, a user viewing the determination result table 401 displayed on the information display terminal 40 can understand which device 811 output the signal, when it was determined to contain an abnormality sign, and what type of abnormality sign it was.

[0028] FIG. 8 is a diagram illustrating a second display example of the abnormality sign determination results of the abnormality sign detection system according to the first embodiment. The display processing unit 127 causes the information display terminal 40 to display a tree diagram 402 of the determination results. The tree diagram 402 of the determination results displays the names of facilities and devices installed in the facility and the names of signals output from each device 811 in a tree structure. Symbols representing the facility name, facility name, device name, and signal name are displayed in a different color when an abnormality is present than when the system is normal. Note that the symbol representing the signal name is displayed in a different color when it is determined that an abnormality sign is present than when the system is normal. Symbols representing the facility name and device name are displayed in a different color when a preset condition is satisfied. In the example illustrated in FIG. 8, the symbol for light 1 is set to be displayed in a different color from when the system is normal if more than half of its child nodes are abnormal. Therefore, the symbol for light 1 is displayed in a color indicating a normal state. On the other hand, the symbol for general power 1 is set to be displayed in a different color from when the system is normal if more than half of its child nodes are abnormal. For this reason, the symbol for general power 1 is displayed in a color that indicates an abnormal state. Since a signal tag, which is an identifier for the signal, is displayed along with the signal name, it is possible to distinguish between signals even when there are multiple signals with the same name. For example, a signal called Power 1 output by Light 1 and a signal called Power 1 output by Light 2 have the same signal name, but their signal tags are different, 1000000001 and 1000000003, respectively, making them distinguishable. By displaying the tree diagram 402 of the determination results on the information display terminal 40, a user viewing the tree diagram 402 of the determination results displayed on the information display terminal 40 can easily understand which facilities 81, devices 811, and signals are normal and which facilities 81, devices 811, and signals are abnormal.

[0029] 9 is a diagram showing a third display example of the determination result of an abnormality sign by the abnormality sign detection system according to the first embodiment. The display processing unit 127 causes the information display terminal 40 to display a Sankey diagram 403 of the determination result. In the Sankey diagram 403 of the determination result, values ​​allocated to each device 811 for physical properties common to the plurality of devices 811 installed in the facility 81 are displayed, with the thickness of the lines representing the values. Furthermore, symbols representing the facility 81 and device 811 with an abnormality are displayed in a different color from the equipment 81 and device 811 without an abnormality. The symbol representing the device 811 is displayed in a different color from the case where there is no abnormality when a preset condition is satisfied. For example, when there is an abnormality sign in any of the signals output by the device 811, the symbol representing the device 811 is displayed in a different color from the case where there is no abnormality. 9, the amount of power allocated to each device 811, whose device names are air conditioner A, air conditioner B, air conditioner C, light A, light B, and light C, installed in facility 81, whose facility name is floor A, is indicated by the thickness of the line, with respect to the physical property value of power common to the devices. The symbol for light A, which has an abnormality, is displayed in a different color from the symbols for air conditioner A, air conditioner B, air conditioner C, light B, and light C, which have no abnormality. By displaying Sankey diagram 403 of the determination results on information display terminal 40, a user viewing Sankey diagram 403 of the determination results displayed on information display terminal 40 can easily understand which device 811 has an abnormality and what proportion of the physical property allocated to the abnormal device 811 accounts for the physical property of the entire facility 81.

[0030] 10 is a diagram showing a fourth example of display of the determination results of the abnormality sign detection system according to the first embodiment. The display processing unit 127 causes the information display terminal 40 to display a trend graph 404 of the determination results. In the trend graph 404 of the determination results, a scatter plot with signal strength on the vertical axis and time on the horizontal axis is shown, and the plots of the signal at each time are connected by curves to represent the change in signal value over time. A user viewing the trend graph 404 of the determination results displayed on the information display terminal 40 can easily grasp the trend of the change in signal strength over time from the graph line.

[0031] The abnormality sign detection system 100 according to the first embodiment determines whether or not there is an abnormality sign in the operating data based on the periodic data deviating from the normal range of the periodic data at least twice, and therefore can prevent false detection of an abnormality sign due to the influence of noise even when the equipment 81 and the device 811 are normal.

[0032] Embodiment 2 11 is a functional block diagram of an abnormality sign detection system according to Embodiment 2. The abnormality sign detection system 100 according to Embodiment 2 differs from the abnormality sign detection system 100 according to Embodiment 1 in that the abnormality sign detection device 10 includes a determination result storage unit 132. The determination result storage unit 132 stores the deviation determination results obtained by the deviation determination unit 125.

[0033] In the abnormality sign detection system 100 according to the second embodiment, the abnormality sign judgment unit 126 uses a plurality of temporally consecutive deviation judgment results stored in the judgment result storage unit 132 to judge whether or not there is an abnormality sign in the signal output by the device 811 based on the temporal continuity of the deviation.

[0034] 12 is a diagram showing a first method for determining the presence or absence of an abnormality sign in the abnormality sign detection system according to Embodiment 2. When the deviation determination unit 125 determines that a deviation has occurred, the abnormality sign determination unit 126 refers to the deviation determination results for the most recent preset number of times, and determines that an abnormality sign has occurred if all of them indicate a deviation. That is, when the deviation determination unit 125 determines that a deviation has occurred for the preset number of consecutive times, the abnormality sign determination unit 126 determines that an abnormality sign has occurred.

[0035] 13 is a flowchart showing the flow of a first method for determining the presence or absence of an abnormality sign in the abnormality sign detection system according to Embodiment 2. In step S61, the abnormality sign determination unit 126 determines whether or not the deviation determination unit 125 has determined that a deviation has occurred at the current time. If the deviation determination unit 125 has determined that a deviation has occurred at the current time, the answer is Yes in step S61, and the process proceeds to step S62. If the deviation determination unit 125 has not determined that a deviation has occurred at the current time, the answer is No in step S61, and the process proceeds to step S64.

[0036] In step S62, the abnormality sign determination unit 126 determines whether the departure determination unit 125 has determined that there is a departure a preset number of times in succession up to the current time. If the departure determination unit 125 has determined that there is a departure a preset number of times in succession up to the current time, the answer to step S62 is Yes, and the process proceeds to step S63. If the departure determination unit 125 has not determined that there is a departure a preset number of times in succession up to the current time, the answer to step S62 is No, and the process proceeds to step S64.

[0037] In step S63, the abnormality sign determination unit 126 determines that there is an abnormality sign. After step S63 is completed, the abnormality sign determination unit 126 ends the process of determining whether there is an abnormality sign.

[0038] In step S64, the abnormality sign determination unit 126 determines that there is no abnormality sign. After step S64 is completed, the abnormality sign determination unit 126 ends the process of determining whether there is an abnormality sign.

[0039] Although the example given here considers only the presence or absence of a deviation, the abnormality sign determination unit 126 may determine the presence or absence of an abnormality sign by considering the magnitude of the deviation in addition to the presence or absence of a deviation. For example, if the magnitude of the deviation is gradually increasing, the abnormality sign determination unit 126 may determine that there is an abnormality sign when the number of deviation occurrences is smaller than when deviations of the same magnitude occur consecutively. Also, if the magnitude of the deviation is gradually decreasing, the abnormality sign determination unit 126 may determine that there is an abnormality sign when the number of deviation occurrences is greater than when deviations of the same magnitude occur consecutively.

[0040] 14 is a diagram showing a second method for determining the presence or absence of an abnormality sign in the abnormality sign detection system according to Embodiment 2. When the deviation determination unit 125 determines that a deviation has occurred at the current time, the abnormality sign determination unit 126 refers to the most recent, preset number of deviation occurrence determination results, and determines that an abnormality sign has occurred if the deviation has occurred the preset number of times or more. In other words, the abnormality sign determination unit 126 determines that an abnormality sign has occurred if the proportion of deviation occurrence determination results of the most recent, preset number of deviation occurrence determination results is equal to or greater than a preset threshold.

[0041] 15 is a flowchart showing the flow of a second method for determining the presence or absence of an abnormality sign in the abnormality sign detection system according to Embodiment 2. In step S65, the abnormality sign determination unit 126 determines whether or not the deviation determination unit 125 has determined that a deviation has occurred at the current time. If the deviation determination unit 125 has determined that a deviation has occurred at the current time, the answer is Yes in step S65, and the process proceeds to step S66. If the deviation determination unit 125 has not determined that a deviation has occurred at the current time, the answer is No in step S65, and the process proceeds to step S68.

[0042] In step S66, the abnormality sign determination unit 126 determines whether the proportion of deviation-occurring results among the most recent predetermined number of deviation occurrence determination results is equal to or greater than a predetermined threshold. If the proportion of deviation-occurring results among the most recent predetermined number of deviation occurrence determination results is equal to or greater than the predetermined threshold, step S66 returns Yes, and processing proceeds to step S67. If the proportion of deviation-occurring results among the most recent predetermined number of deviation occurrence determination results is not equal to or greater than the predetermined threshold, step S66 returns No, and processing proceeds to step S68.

[0043] In step S67, the abnormality sign determination unit 126 determines that there is an abnormality sign. After step S67 is completed, the abnormality sign determination unit 126 ends the process of determining whether there is an abnormality sign.

[0044] In step S68, the abnormality sign determination unit 126 determines that there is no abnormality sign. After step S68 is completed, the abnormality sign determination unit 126 ends the process of determining whether there is an abnormality sign.

[0045] The abnormality sign detection system 100 according to the second embodiment determines whether or not there is an abnormality sign based on the temporal continuity of deviations, and therefore does not detect an abnormality sign when a deviation occurs temporarily due to the influence of noise. This prevents the system from determining that there is an abnormality in the signal output by the device 811, even though the equipment 81 and the device 811 installed in the building 80 are normal.

[0046] Embodiment 3 16 is a diagram showing the configuration of an abnormality sign detection system according to Embodiment 3. The abnormality sign detection system 100 according to Embodiment 3 differs from the abnormality sign detection system 100 according to Embodiment 2 in that the abnormality sign detection system 100 according to Embodiment 3 includes an equipment connection relationship information storage device 50 that stores equipment connection relationship information indicating the connection topology of equipment 81 and devices 811 in a building 80.

[0047] 17 is a functional block diagram of an abnormality sign detection system according to Embodiment 3. In the abnormality sign detection system 100 according to Embodiment 3, an abnormality sign detection device 10 includes an equipment connection relationship information acquisition unit 128 and an equipment connection relationship information storage unit 133. The equipment connection relationship information acquisition unit 128 communicates with an equipment connection relationship information storage device 50 using the communication unit 11 to acquire equipment connection relationship information. The equipment connection relationship information storage unit 133 stores the equipment connection relationship information acquired by the equipment connection relationship information acquisition unit 128.

[0048] 18 is a diagram showing a first example of facility connection relationship information used in the anomaly sign detection system according to the third embodiment. The facility connection relationship information of the first example is tree-structured data indicating the connection topology of facility 81 and equipment 811 installed in a building 80. In the facility connection relationship information of the first example, a facility node, which is the root node, has equipment nodes as child nodes, and the equipment nodes have equipment nodes as child nodes. The equipment nodes have signal nodes, which are leaf nodes, as child nodes. The relationship between each signal can be determined based on the number of edges between the nodes.

[0049] 19 is a diagram showing a second example of facility connection relationship information used in the anomaly sign detection system according to embodiment 3. The facility connection relationship information in the second example is data indicating the relationship between the device 811 and a signal. The relationship between each signal can be determined based on the number of edges between nodes.

[0050] 20 is a flowchart showing the flow of operations of the abnormality sign detection system according to embodiment 3. The processes from step S1 to step S5 and step S7 are the same as those of the abnormality sign detection system 100 according to embodiment 1. After step S5, the processes of steps S8 and S9 are executed, and then the process of step S7 is executed.

[0051] In step S8, the facility connection relationship information acquisition unit 128 acquires the facility connection relationship information from the facility connection relationship information storage device 50 and stores it in the facility connection relationship information storage unit 133.

[0052] In step S9, the abnormality precursor determination unit 126 determines whether or not there are abnormality precursors based on the time-series operating data stored in the time-series operating data storage unit 131 and the equipment connection relationship information stored in the equipment connection relationship information storage unit 133.

[0053] 21 is a flowchart showing the flow of an abnormality sign determination method of the abnormality sign detection system according to embodiment 3. In step S91, the abnormality sign determination unit 126 determines whether or not the deviation determination unit 125 has determined that a signal that is the object of abnormality sign determination at the current time has deviated. If the deviation determination unit 125 has determined that a signal that is the object of abnormality sign determination at the current time has deviated, the answer in step S91 is Yes, and the process proceeds to step S92. If the deviation determination unit 125 has not determined that a signal that is the object of abnormality sign determination at the current time has deviated, the answer in step S91 is No, and the process proceeds to step S94.

[0054] In step S92, the abnormality sign determination unit 126 determines whether the rate at which deviation occurs among other signals whose shortest path length to the signal being determined for abnormality sign is equal to or less than a preset value is equal to or greater than a preset threshold. If the rate at which deviation occurs among other signals whose shortest path length to the signal being determined for abnormality sign is equal to or less than the preset threshold is equal to or greater than the preset threshold, the answer to step S92 is Yes, and the process proceeds to step S93. If the rate at which deviation occurs among other signals whose shortest path length to the signal being determined for abnormality sign is equal to or less than the preset threshold is not equal to or greater than the preset threshold, the answer to step S92 is No, and the process proceeds to step S94.

[0055] In step S93, the abnormality sign determination unit 126 determines that there is an abnormality sign. After step S93 is completed, the abnormality sign determination unit 126 ends the process of determining an abnormality sign.

[0056] In step S94, the abnormality sign determination unit 126 determines that there is no abnormality sign. After step S94 is completed, the abnormality sign determination unit 126 ends the process of determining the abnormality sign.

[0057] FIG. 22 is a diagram illustrating an example of abnormality sign determination in the abnormality sign detection system according to the third embodiment. For example, when the deviation determination unit 125 determines that a deviation has occurred in the signal that is the target of abnormality sign determination, the abnormality sign determination unit 126 refers to the deviation determination results of related signals, which are other signals whose shortest path length to the signal that is the target of abnormality sign determination is equal to or less than a preset value, and determines that an abnormality sign has occurred if the rate at which deviation has occurred is equal to or greater than a preset threshold. In the example illustrated in FIG. 22, it is assumed that the signal that is the target of abnormality sign determination is signal A, that signals whose shortest path length is equal to or less than 2 are set as related signals, and that the threshold is set to 50%. When the deviation determination unit 125 determines that a deviation has occurred in signal A, the abnormality sign determination unit 126 refers to the deviation determination results of related signals, that is, signals B, C, and D. In this example, deviation has occurred in signals B and C, but not in signal D, so the deviation occurrence rate of related signals of signal A is 66.7%, which exceeds the threshold. Therefore, the abnormality sign determination unit 126 determines that the signal A has an abnormality sign.

[0058] In the abnormality sign detection system 100 according to the third embodiment, the abnormality sign determination unit 126 determines whether or not there is an abnormality sign based on the spatial continuity of deviations within the facility, and therefore does not determine that there is an abnormality sign even if a deviation occurs due to the influence of noise as long as the deviation occurrence rate of related signals is equal to or lower than a threshold value. Therefore, the abnormality sign detection system 100 according to the third embodiment can prevent the signal output by the facility 81 and the facility 811 from being determined to contain an abnormality sign even when the facility 81 and the facility 811 are normal.

[0059] Embodiment 4 The configuration of the abnormality sign detection system 100 according to embodiment 4 is the same as that of the abnormality sign detection system 100 according to embodiment 3. The abnormality sign detection system 100 according to embodiment 4 combines the abnormality sign determination based on temporal continuity described in embodiment 2 and the abnormality sign determination based on spatial continuity described in embodiment 3. It may be determined that an abnormality sign is present when both the conditions of temporal continuity and spatial continuity are satisfied, or it may be determined that an abnormality sign is present when either one of them is satisfied.

[0060] Like the abnormality sign detection system 100 according to embodiment 2 and the abnormality sign detection system 100 according to embodiment 3, the abnormality sign detection system 100 according to embodiment 4 can prevent the signal output by the equipment 811 from being determined to contain an abnormality sign even when the facility 81 and the equipment 811 are normal.

[0061] Embodiment 5 23 is a functional block diagram of an abnormality sign detection system according to embodiment 5. The abnormality sign detection system 100 according to embodiment 5 differs from the abnormality sign detection system 100 according to embodiment 1 in that the abnormality sign detection device 10 includes a control instruction unit 129.

[0062] When the abnormality sign determination unit 126 detects an abnormality sign, the control instruction unit 129 sends an instruction to the building monitoring and control system server 20 to control the devices 811 so as to avoid the abnormality. For example, when an abnormality sign is detected because the temperature of any of the devices 811 becomes abnormally high and deviates from the normal range, the control instruction unit 129 sends an instruction to the building monitoring and control system server 20 to stop the device 811 determined to have an abnormality sign or to lower the set temperature of the air conditioning equipment to cool the device 811 for which an abnormality sign has been detected.

[0063] The abnormality sign detection system 100 of embodiment 5 controls the equipment 811 so that the abnormality is avoided when an abnormality sign is detected, and therefore can prevent the equipment 811 that is determined to have an abnormality sign from breaking down.

[0064] Next, a description will be given of the hardware configuration of the processing unit 12 included in the abnormality sign detection device 10. Fig. 24 is a diagram showing an example of a hardware configuration realizing the processing unit included in the abnormality sign detection device according to embodiments 1 to 5. The processing unit 12 is realized as a computer system by a processing circuit including a processor 91 that executes various processes, a memory 92 that is a main memory, and a storage device 93 that stores information.

[0065] The processor 91 may be a computing means such as an arithmetic device, a microprocessor, a microcomputer, a CPU (Central Processing Unit), or a DSP (Digital Signal Processor). The memory 92 may be a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable Read Only Memory), or an EEPROM (Electrically Erasable Programmable Read Only Memory). The storage device 93 stores programs for extracting periodic data from time-series operation data, predicting future values ​​of the periodic data in a time series, determining whether or not there is a deviation, and determining whether or not there is a sign of an abnormality. The processor 91 reads the programs stored in the storage device 93 into the memory 92 and executes them. The processor 91 reads the programs stored in the storage device 93 into the memory 92 and executes them, thereby realizing the functions of the processing unit 12.

[0066] The configurations shown in the above embodiments are merely examples of the content, and may be combined with other known technologies, or parts of the configurations may be omitted or modified without departing from the spirit of the invention.

[0067] Various aspects of the present disclosure are summarized below as appendices.

[0068] (Appendix 1) An anomaly sign detection device comprising: a processing unit that performs processing to time-series predict future values ​​of cyclical data, which is data having periodicity extracted from time-series operation data that is a chronological compilation of operation data of equipment installed in a monitored facility, to set a normal range of the cyclical data, to determine whether or not there is a sign of an abnormality in the operation data based on the cyclical data deviating from the normal range of the cyclical data at least twice, and to display the result of the anomaly sign determination. (Appendix 2) The processing unit an operating data acquisition unit that acquires the operating data from a device that controls the facility equipment; a periodicity data extraction unit that extracts the periodicity data from the time-series operation data; a time series prediction unit that predicts future values ​​of the periodic data in time series; a normal range setting unit that sets the normal range of the periodic data based on a time series predicted value of the periodic data; a deviation determination unit that determines a deviation of the periodic data from the normal range; an abnormality sign determination unit that determines an abnormality sign of the facility equipment based on at least two determinations of the deviation by the deviation determination unit. (Appendix 3) The abnormality sign detection device according to claim 2, wherein the periodic data extraction unit extracts the time-series operation data in which an energy-related morpheme is included in a signal name as the periodic data. (Appendix 4) The abnormality sign detection device according to Supplementary Note 2 or 3, wherein the abnormality sign determination unit determines that there is an abnormality sign when at least one of the following conditions is met: when the deviation determination unit determines that there is a deviation a predetermined number of times consecutively; and when a proportion of the deviation occurrence determination results for the most recent predetermined number of times is equal to or greater than a predetermined threshold value. (Appendix 5) The processing unit an equipment connection relationship information acquisition unit that acquires equipment connection relationship information indicating the connection relationship of the equipment; The abnormality sign detection device according to any one of Supplementary Note 2 to Supplementary Note 4, wherein the abnormality sign determination unit determines whether or not there is an abnormality sign based on the equipment connection relationship information and at least two detections of the deviation by the deviation determination unit. (Appendix 6) The abnormality sign detection device according to any one of Supplementary Note 2 to Supplementary Note 5, wherein the processing unit has a control instruction unit that instructs a device that controls the facility equipment to execute control of the facility equipment based on the abnormality sign determination result. [Explanation of symbols]

[0069] 10 Anomaly sign detection device, 11 Communication unit, 12 Processing unit, 13 Memory unit, 20 Building monitoring and control system server, 30 Network, 40 Information display terminal, 50 Equipment connection relationship information storage device, 80 Building, 81 Equipment, 91 Processor, 92 Memory, 93 Storage device, 100 Anomaly sign detection system, 121 Operation data acquisition unit, 122 Periodicity data extraction unit, 123 Time series prediction unit, 124 Normal range setting unit, 125 Deviation judgment unit, 126 Anomaly sign judgment unit, 127 Display processing unit, 128 Equipment connection relationship information acquisition unit, 129 Control instruction unit, 131 Time series operation data accumulation unit, 132 Judgment result accumulation unit, 133 Equipment connection relationship information accumulation unit, 401 Judgment result table, 402 Judgment result tree diagram, 403 Judgment result Sankey diagram, 404 Judgment result trend graph, 811 device.

Claims

1. An anomaly sign detection device comprising: a processing unit that performs processing to time-series predict future values ​​of cyclical data, which is data having periodicity extracted from time-series operation data that is a chronological compilation of operation data of equipment installed in a monitored facility, to set a normal range of the cyclical data, to determine whether or not there is a sign of an abnormality in the operation data based on the cyclical data deviating from the normal range of the cyclical data at least twice, and to display the result of the anomaly sign determination.

2. The processing unit an operating data acquisition unit that acquires the operating data from a device that controls the facility equipment; a periodicity data extraction unit that extracts the periodicity data from the time-series operation data; a time series prediction unit that predicts future values ​​of the periodic data in time series; a normal range setting unit that sets the normal range of the periodic data based on a time series predicted value of the periodic data; a deviation determination unit that determines a deviation of the periodic data from the normal range; 2. The abnormality sign detection device according to claim 1, further comprising an abnormality sign determination unit that determines an abnormality sign of the facility equipment based on at least two determinations of the deviation by the deviation determination unit.

3. 3. The abnormality sign detection device according to claim 2, wherein the periodicity data extraction unit extracts the time-series operation data in which a signal name contains an energy-related morpheme as the periodic data.

4. The abnormality sign detection device according to claim 2, characterized in that the abnormality sign determination unit determines that there is an abnormality sign when at least one of the following conditions is met: when the deviation determination unit determines that there is a deviation a predetermined number of times consecutively; and when the proportion of deviations among the most recent predetermined number of deviation occurrence determination results is equal to or greater than a predetermined threshold value.

5. The processing unit an equipment connection relationship information acquisition unit that acquires equipment connection relationship information indicating the connection relationship of the equipment; The abnormality sign detection device according to claim 2, wherein the abnormality sign determination unit determines whether or not there is an abnormality sign based on the equipment connection relationship information and the detection of the deviation by the deviation determination unit at least two times.

6. The abnormality sign detection device according to claim 2, characterized in that the processing unit has a control instruction unit that instructs a device that controls the facility equipment to execute control of the facility equipment based on the abnormality sign determination result.

7. a server that collects operation data from equipment installed in the monitored facility; An abnormality sign detection system comprising the abnormality sign detection device according to any one of claims 1 to 6.

8. A process of predicting future values ​​of cyclical data in a time series, the cyclical data being data having periodicity extracted from time-series operation data obtained by compiling operation data of equipment installed in a monitored facility in a time series, and setting a normal range for the cyclical data; a process of determining whether or not there is a sign of abnormality in the operating data based on the periodic data deviating from the normal range of the periodic data at least twice; and displaying the abnormality sign determination result.

9. A process of predicting future values ​​of cyclical data in a time series, the cyclical data being data having periodicity extracted from time-series operation data obtained by compiling operation data of equipment installed in a monitored facility in a time series, and setting a normal range for the cyclical data; a process of determining whether or not there is a sign of abnormality in the operating data based on the periodic data deviating from the normal range of the periodic data at least twice; and displaying the abnormality sign determination result.

Images