JP2018041326A - Abnormality detector, abnormality detection method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an abnormality detector capable of detecting abnormality of equipment, and an abnormality detection method and a program.SOLUTION: An abnormality detector includes a data acquisition part, an equipment model storage part, a power consumption calculation part and an abnormality determination part. The data acquisition part acquires a measurement value output from a sensor of equipment, power consumption of the equipment and a setting value indicating an operation condition of the equipment. The equipment model storage part stores an equipment model for calculating the power consumption of the equipment. The power consumption calculation part calculates the power consumption with respect to the setting value on the basis of the measurement value acquired by the data acquisition part and the equipment model stored in the equipment model storage part. The abnormality determination part determines whether or not abnormality occurs in the equipment on the basis of the power consumption of the equipment acquired by the data acquisition part and the power consumption calculated by the power consumption calculation part.SELECTED DRAWING: Figure 1

Description

  Embodiments described herein relate generally to an abnormality detection device, an abnormality detection method, and a program.

  In building air conditioners and heat source machines, technology to minimize energy consumption during operation has been put into practical use by promoting energy saving. When the performance of local control of each device deteriorates, it becomes difficult to operate at the assumed optimum point. As a result, it is considered that energy consumption increases. In order to prevent this, various abnormality diagnosis techniques for plants and facilities have been proposed. For example, there is a technique for creating a normal model and a normal threshold using normal data and determining the presence or absence of abnormality by comparing measured data with data obtained from the normal model.

  In recent years, with the promotion of energy saving, air conditioners have been operating with various energy saving control methods, so the operation of the air conditioners changes due to changes in the outside air and indoor conditions. In this case, it is difficult to determine an abnormality of the air conditioner only by comparing the power consumption. In particular, in the case of an air conditioner, since the operation of the energy saving operation of the air conditioner varies depending on the season, it is difficult to set past reference data. In this specification, “energy saving” is abbreviated as “energy saving”.

JP 2009-20721 A

  The problem to be solved by the present invention is to provide an abnormality detection device, an abnormality detection method, and a program capable of detecting an abnormality of a device.

  The abnormality detection device of the embodiment includes a data acquisition unit, a device model storage unit, a power consumption calculation unit, and an abnormality determination unit. The data acquisition unit acquires a measurement value output from a sensor of the device, a power consumption amount of the device, and a setting value indicating an operation condition of the device. The device model storage unit stores a device model for calculating the power consumption of the device. The power consumption calculation unit calculates a power consumption for the set value based on the measurement value acquired by the data acquisition unit and the device model stored in the device model storage unit. The abnormality determination unit has an abnormality in the device based on the power consumption amount of the device acquired by the data acquisition unit and the power consumption amount calculated by the power consumption amount calculation unit. It is determined whether or not.

The block diagram of the abnormality detection apparatus of 1st Embodiment. The figure which shows the system | strain information of 1st Embodiment. The graph which shows the power consumption of 1st Embodiment. The flowchart which shows the procedure of the process by the abnormality detection apparatus of 1st Embodiment. The block diagram of the abnormality detection apparatus of 2nd Embodiment. The flowchart which shows the procedure of the process by the abnormality detection apparatus of 2nd Embodiment. The block diagram of the abnormality detection apparatus of 3rd Embodiment. The flowchart which shows the procedure of the process by the abnormality detection apparatus of 3rd Embodiment. The figure which shows the screen of the display part with which the abnormality detection apparatus of 3rd Embodiment is provided. The block diagram of the abnormality detection apparatus of 4th Embodiment. The flowchart which shows the procedure of the process by the abnormality detection apparatus of 4th Embodiment. The figure which shows the example of a calculation of the optimal inspection period of 4th Embodiment.

  Hereinafter, an abnormality detection device, an abnormality detection method, and a program according to embodiments will be described with reference to the drawings. The device of the embodiment is a device to which control by an energy saving control method is applied. Hereinafter, an air conditioner and a heat source machine in a building will be described as examples of devices. For the sake of simplification, an example will be described in which the heat source unit transports cold water to the air conditioner, and the air conditioner cools air using the cold water. There is a difference between the case of cooling and the case of heating such that the refrigerant to be used is different between cold water and hot water. However, the configuration and function of the abnormality detection device are the same in both cases. It is assumed that the air conditioner and the heat source machine are operating by the energy saving control method.

(First embodiment)
A first embodiment will be described with reference to FIGS. FIG. 1 shows a configuration of an abnormality detection apparatus 1 according to the first embodiment. As shown in FIG. 1, the abnormality detection device 1 includes a data acquisition unit 10, a device model storage unit 11, a system information storage unit 12, a power consumption calculation unit 13, a parameter input unit 14, and an abnormality determination unit. 15 and a rank calculation unit 16.

  The data acquisition unit 10 acquires the measurement value output from the sensor of the device, the power consumption of the device, and the set value indicating the operation condition of the device. The equipment is an air conditioner and a heat source machine. The sensor is placed in an environment where the device is placed. The measurement value output from the sensor is a measurement value other than the power consumption. For example, the measurement values output from the sensor are the outside air temperature, the outside air humidity, the indoor load, the indoor temperature, and the indoor humidity. The data acquisition unit 10 acquires the current value of the measurement value from a sensor other than the power meter. Further, the data acquisition unit 10 acquires the current value of the power consumption of the device from the wattmeter. Further, the data acquisition unit 10 acquires the current value of the setting value indicating the operation condition of the device from the device. A setting value indicating the operation condition of the device will be described later. The data acquisition unit 10 outputs the acquired measured value, the current value of the power consumption, and the current value of the set value indicating the operation condition of the device to the power consumption calculation unit 13 and the abnormality determination unit 15.

  The device model storage unit 11 and the system information storage unit 12 are volatile or nonvolatile memories. The device model storage unit 11 and the system information storage unit 12 may be configured as one storage unit.

  The device model storage unit 11 stores a device model for calculating the power consumption of the device. The device model is information indicating a calculation method of the power consumption of the device. For example, the device model is information on an expression necessary for calculating the power consumption of the device. The device model storage unit 11 stores a device model for each type of device.

  The device is included in any one of a plurality of systems. Each of the plurality of systems includes at least one device. The system information storage unit 12 stores system information indicating devices included in the system for each system. In the embodiment, in order to simultaneously diagnose a plurality of air conditioners and heat source machines, a group including air conditioners and heat source machines to be diagnosed is defined as one system. FIG. 2 shows the system information stored in the system information storage unit 12. Information on each system and the devices (air conditioners and heat source devices) included in each system are associated with each other and stored in the system information storage unit 12 as system information. For example, the system 1 includes an air conditioner 1 and a heat source device 1. Information on sensor data used for diagnosis as well as an air conditioner and a heat source machine may be included in the system information.

  The power consumption calculation unit 13 calculates the power consumption with respect to the set value related to the operation of the device based on the measurement value acquired by the data acquisition unit 10 and the device model stored in the device model storage unit 11. The power consumption calculation unit 13 selects the device model of the device indicated by the system information corresponding to the system that is the target of the abnormality determination. The power consumption amount calculation unit 13 calculates the power consumption amount of the system that is the target of abnormality determination using the selected device model.

  The parameter input unit 14 is an input interface for a user to input parameters necessary for determining whether there is an abnormality. The user inputs parameters to the abnormality detection device 1 via the parameter input unit 14. For example, the parameter is a threshold value for determining whether there is an abnormality. The parameter input unit 14 outputs the input parameters to the abnormality determination unit 15.

  The abnormality determination unit 15 determines whether an abnormality has occurred in the device based on the power consumption of the device acquired by the data acquisition unit 10 and the power consumption calculated by the power consumption calculation unit 13. judge. The abnormality determination unit 15 uses the parameter input to the parameter input unit 14 as a threshold value for abnormality determination. The abnormality determination unit 15 outputs the determination result to the rank calculation unit 16.

  The rank calculation unit 16 calculates a rank based on the magnitude of loss occurring in the system for each system including the device in which the abnormality determination unit 15 determines that an abnormality has occurred. Specifically, the rank calculation unit 16 extracts systems determined to be abnormal by the abnormality determination unit 15 and rearranges the plurality of systems in descending order of the loss of power consumption of the extracted systems. Thereby, the order | rank calculating part 16 determines the order | rank according to the necessity for the inspection of each system | strain. The rank calculation unit 16 outputs the calculated rank as a diagnosis result. By rearranging a plurality of systems in descending order of power consumption loss, an administrator or an inspector can easily determine the order of inspection for a failure or the like.

  The abnormality detection apparatus 1 may read the program and execute the read program. That is, the function of the abnormality detection device 1 may be realized by software. This program includes instructions that define the operation of the abnormality detection device 1. This program may be provided by a “computer-readable recording medium” such as a flash memory. Further, the above-described program may be transmitted from the computer having a storage device or the like in which the program is stored to the abnormality detection device 1 via a transmission medium or by a transmission wave in the transmission medium. A “transmission medium” for transmitting a program is a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line. Further, the above-described program may realize a part of the functions described above. Further, the above-described program may be a difference file (difference program) that can realize the above-described function in combination with a program already recorded in the computer.

  A specific example of the device model stored in the device model storage unit 11 will be described. For example, the following equations (1) to (3) may be used as a model for calculating the power consumption of the air conditioner and the heat source device. In the following formulas (1) and (2), as an example, the heat source machine is an air-cooled heat pump chiller. The efficiency (COP) in equation (1) is calculated based on the outside air temperature and the outside air humidity.

Heat source machine cooling electric energy (E_hs) = cooling heat quantity (Q) / efficiency (COP) (1)
Heat source machine pump electric energy (E_pump) = pump rated power consumption (E_pump_rate) × (pump flow rate (F_pump) / pump rated flow rate (F_pump_rate)) ³ (2)
Air conditioner fan power (E_fan) = fan rated power consumption (E_fan_rate) × (fan air volume (F_fan) / fan rated air volume (F_fan_rate)) ³ (3)

The following formula (4) may be used as the balance formula on the indoor side. That is, the amount of cooling heat (Q) in Equation (1) may be calculated as the indoor sensible heat load (Q_room) by Equation (4).
Indoor sensible heat load (Q_room) = specific air heat (Ca) × fan air volume (F_fan) × (room temperature (T_room) −supply air temperature (T_sa)) (4)

  A method of calculating the power consumption amount by the power consumption amount calculation unit 13 will be described. In the embodiment, the air conditioner and the heat source machine are operated by an energy saving control method. For this reason, a set value indicating an operation condition is set for the air conditioner and the heat source device by the energy saving control method. The power consumption calculation unit 13 calculates power consumption using a set value indicating the operation condition. For example, the set values indicating the operating conditions are the air conditioner supply temperature, the room temperature, and the cold water temperature of the heat source unit. The set value indicating the operation condition may be an outside air humidity, a dew point temperature, or the like.

  A method of calculating the power consumption will be specifically described with reference to FIG. FIG. 3 shows a graph of power consumption. The horizontal axis of the graph represents the air conditioner supply temperature. The air conditioner supply air temperature is a set value indicating operation conditions. The vertical axis of the graph is power consumption. In FIG. 3, each graph of air-conditioner electric energy, heat-source-equipment electric energy, and total electric power consumption is shown. The total power consumption is the total of the air conditioner power and the heat source power.

  The power consumption calculation unit 13 performs calculation using Formulas (1) to (3), the current value of the sensor measurement value, and the current value (current setting value) of the set value indicating the operation condition. The power consumption amount calculation unit 13 calculates the power consumption amount when the device is operated with the current set value. Specifically, the power consumption amount calculation unit 13 calculates an air conditioner power amount and a heat source device power amount corresponding to the currently set value, respectively. Thereafter, the power consumption calculator 13 sums the air conditioner power amount and the heat source device power amount. Thereby, the power consumption at the point P1 in FIG. 3 is calculated.

  Next, the power consumption calculation unit 13 calculates the power consumption when the air-conditioner supply temperature deviates by + 1 ° C. from the current set value. Thereby, the power consumption at the point P2 in FIG. 3 is calculated. Furthermore, the power consumption calculation unit 13 calculates the power consumption when the air-conditioner supply temperature deviates by + 2 ° C. from the current set value. Thereby, the power consumption at the point P3 in FIG. 3 is calculated. Similarly, the power consumption calculation unit 13 calculates the power consumption when the air conditioner supply temperature is deviated by −1 ° C. and −2 ° C. from the current set value. Thereby, the power consumption at the points P4 and P5 in FIG. 3 is calculated. Also for points not shown in FIG. 3, the power consumption calculation unit 13 calculates the power consumption. Thereby, the power consumption curve shown in FIG. 3 can be drawn.

  Since the air conditioner and the heat source machine operate by the energy saving control method, the total power consumption at the current set value is the minimum value in the power consumption curve. The power consumption calculation unit 13 may calculate the power consumption related to the room temperature, the chilled water temperature of the heat source unit, and the like, similarly to the power consumption related to the air supply temperature of the air conditioner.

  A specific example of determination by the abnormality determination unit 15 will be described. The abnormality determination unit 15 detects the power consumption corresponding to the currently set value in the power consumption curve. Thereby, the abnormality determination part 15 detects the power consumption with respect to the setting value set to the apparatus. Furthermore, the abnormality determination unit 15 calculates a loss amount. The loss amount is a difference between the power consumption amount with respect to the current setting value of the device and the current value of the power consumption amount of the device acquired by the data acquisition unit 10. The power consumption with respect to the current set value of the device is the power consumption at the point P1 in FIG. The abnormality determination unit 15 determines whether an abnormality has occurred in the device based on the loss amount and the threshold value input to the parameter input unit 14.

  As a specific example, the determination method will be described on the assumption that the control performance of the air supply temperature of the air conditioner has deteriorated due to the occurrence of an abnormality in the cold water valve in the air conditioner. If the chilled water valve is stuck or if a part of the mechanism fails, the chilled water valve does not operate normally, and the supply air temperature cannot be controlled to the supply air temperature set value. For example, when the supply air temperature setting value is 22 ° C., the supply air temperature may be 24 ° C. due to an abnormality in the cold water valve. As a result, the amount of cooling heat in the heat source unit decreases, but the amount of fan air increases to cool the room.

  For example, when an abnormality occurs in the cold water valve, the power consumption amount is the power consumption amount (point P3 in FIG. 3) when the air conditioner supply temperature is 2 ° C. higher than the currently set value. This power consumption is higher than the normal power consumption (point P1 in FIG. 3). This increase in power consumption is the loss. The abnormality determination unit 15 determines whether there is an abnormality in the device by comparing the loss amount with a threshold value for determining whether or not there is an abnormality. In the above example, when the loss amount is larger than the threshold value, the abnormality determination unit 15 determines that an abnormality has occurred. When the loss amount is equal to or less than the threshold value, the abnormality determination unit 15 determines that no abnormality has occurred. When it is determined that there is an abnormality, there is an abnormality in at least one device in the determination target system.

  The threshold value input to the parameter input unit 14 may be a value indicating a difference between the current set value and the set value corresponding to the power consumption at the time of abnormality. For example, when the set value indicating the operating condition is the air conditioner supply temperature, a value such as 2 ° C. is input as the threshold. The abnormality determination unit 15 calculates the power consumption when the set value indicating the operation condition is shifted by 2 ° C. from the current set value. Thereby, the abnormality determination unit 15 converts the threshold value input to the parameter input unit 14 into a power consumption threshold value. The abnormality determination unit 15 determines whether there is an abnormality in the device by comparing the current value of the power consumption and the threshold of the power consumption.

  Even if the abnormality determination unit 15 converts the power consumption amount of the device acquired by the data acquisition unit 10 into the first value of any one of the primary energy consumption amount, the CO2 emission amount, and the cost (money amount). Good. In this case, the abnormality determination unit 15 converts the power consumption calculated by the power consumption calculation unit 13 into a second value having the same index as the first value. The abnormality determination unit 15 determines whether an abnormality has occurred in the device based on the first value and the second value. For example, the abnormality determination unit 15 converts the power consumption of the device acquired by the data acquisition unit 10 into a cost. Furthermore, the abnormality determination unit 15 converts the power consumption calculated by the power consumption calculation unit 13 into a cost. The abnormality determination unit 15 determines whether an abnormality has occurred in the device based on these costs.

  When the power consumption is converted into the index, the power consumption threshold is converted into a threshold corresponding to the index. In this case, not only the threshold value of power consumption but also a parameter indicating that the threshold value is converted into a threshold value corresponding to a predetermined index is input to the parameter input unit 14.

  The operation of the abnormality detection device 1 will be described with reference to FIG. FIG. 4 shows a procedure of processing performed by the abnormality detection device 1.

  The device model of the air conditioner and heat source device to be subjected to abnormality determination is input to the device model storage unit 11. The device model storage unit 11 stores the input device model (step S100). For example, the device model is generated by an external computer.

  After step S <b> 100, information on devices in each system that is the target of abnormality determination is input to the system information storage unit 12. The system information storage unit 12 stores the input information as system information (step S101). For example, the system information is generated by the above computer.

  After step S101, a threshold for determining whether there is an abnormality is input to the parameter input unit 14 (step S102). The processing from step S100 to step S102 is performed as preprocessing for determination.

  After step S102, the data acquisition unit 10 acquires the current values of the power consumption and the measured values (outside air temperature, outside air humidity, indoor sensible heat load, indoor temperature, and indoor humidity). Further, the data acquisition unit 10 acquires the current value of the setting value indicating the operation condition (step S103). The current value acquired in step S103 is a current value related to one system to be processed.

  After step S <b> 103, the power consumption amount calculation unit 13 acquires a device model from the device model storage unit 11 and acquires system information from the system information storage unit 12. The power consumption calculation unit 13 calculates the power consumption using the current value acquired by the data acquisition unit 10, the device model, and the system information (step S104). The power consumption calculated in step S104 is the power consumption related to one system to be processed.

  After step S104, the abnormality determination unit 15 determines whether or not an abnormality has occurred in the air conditioner and the heat source apparatus in one system to be processed. At this time, the abnormality determination unit 15 uses the power consumption calculated in step S104, a threshold value for determining whether there is an abnormality, and the current value of the power consumption (step S105). In step S105, a determination is made for one system to be processed. The abnormality determination unit 15 outputs the determination result to the rank calculation unit 16.

  After step S105, it is determined whether or not the abnormality determination has been completed for all the systems (step S106). If there is a system for which an abnormality is not determined, the process in step S103 is performed. That is, the calculation of the power consumption and the determination of abnormality are repeated until the determination of abnormality for all the systems is completed.

  When the abnormality determination has been completed for all the systems, the rank calculation unit 16 extracts the system for which the abnormality determination unit 15 has determined that an abnormality has occurred. The rank calculation unit 16 calculates the rank of each system based on the extracted determination result of each system (step S107). The order calculated in step S107 indicates the order in which the devices should be checked.

  After step S107, the rank calculation unit 16 outputs the rank calculated in step S107 as a diagnosis result (step S108).

  For example, the processing from step S103 to step S108 is performed based on setting values acquired from each system in real time. The processing from step S103 to step S108 may be performed based on a set value output from each system during a predetermined period in the past.

  The abnormality detection device 1 may not have the rank calculation unit 16. For example, determination results for all systems that are the targets of abnormality determination may be output. The determination result of the system that has been determined by the abnormality determination unit 15 that no abnormality has occurred may not be output. The abnormality detection device 1 may not have the parameter input unit 14. For example, a parameter for determining whether there is an abnormality may be included in the program of the abnormality detection device 1.

  According to the first embodiment, it is possible to detect the deterioration of the control performance of each device and the failure of the device from the change in the power consumption of the device operating by the energy saving control method. That is, it is possible to detect an abnormality of the device. Further, since a specific amount of change in power consumption can be calculated, it is possible to calculate the amount of power consumption loss due to deterioration of control performance and equipment failure. Furthermore, the manager or the inspector can easily determine the order of inspection by diagnosing a plurality of systems at the same time and rearranging each system in descending order.

(Second Embodiment)
A second embodiment will be described with reference to FIGS. FIG. 5 shows a configuration of the abnormality detection device 1a of the second embodiment. The configuration shown in FIG. 5 will be described while referring to differences from the configuration shown in FIG.

  The abnormality detection device 1a includes a device model generation unit 17 in addition to the configuration of the abnormality detection device 1 shown in FIG. The device model generation unit 17 generates a device model using a regression equation. The device model generation unit 17 generates a device model of the device based on the measurement value output from the normal device sensor. The device model storage unit 11 stores the device model generated by the device model generation unit 17.

  Regarding the points other than the above, the configuration shown in FIG. 5 is the same as the configuration shown in FIG.

  The operation of the abnormality detection device 1a will be described with reference to FIG. FIG. 6 shows a processing procedure by the abnormality detection device 1a. The process shown in FIG. 6 will be described while referring to differences from the process shown in FIG.

  After step S102, the device model generation unit 17 generates a device model. At this time, the device model generation unit 17 generates a device model using data measured by sensors of the air conditioner and heat source device to be generated. The data used for generating the device model is normal data in which no abnormality has occurred in the device. For example, data after periodic inspection is used (step S110).

For example, in step S110, the device model generation unit 17 may generate a device model using a regression model. When the regression model is used, the respective expressions constituting the device model may be defined as the following expressions (5) to (7).
Heat source unit cooling electric energy (E_hs) = a1 + a2 × outside air temperature (T_amb) + a3 × heat source unit load factor (q) + a4 × cold water return temperature difference (5)
Heat source machine pump electric energy (E_pump) = b1 + b2 × pump flow rate (F_pump) (6)
Air conditioner fan electric energy (E_fan) = c1 + c2 × fan airflow (F_fan) (7)

  Equation (5) is a multiple regression equation having three explanatory variables. Equations (6) and (7) are simple regression equations having one explanatory variable. a1 to a4, b1, b2, c1, and c2 are coefficients of the regression model. The device model generation unit 17 determines the coefficient by regression analysis using the data of the variables in the equations (5) to (7). In the above regression model example, a linear equation is used. A second or higher order polynomial may be used.

  After step S110, the device model storage unit 11 stores the device model generated in step S110 (step S111). After step S111, the process in step S103 is performed.

  Regarding the points other than the above, the process shown in FIG. 6 is the same as the process shown in FIG.

  In the above example, a device model is generated using the regression model. However, the device model may be generated by a method other than the regression model. For example, the device model may be generated by a technique such as neural network or machine learning.

  Similar to the first embodiment, the abnormality detection device 1 a may not include the rank calculation unit 16 and the parameter input unit 14.

  According to the second embodiment, the same effect as in the first embodiment can be obtained. In the second embodiment, a device model is generated using normal data such as after periodic inspection. For this reason, it is possible to detect an abnormality of the device without depending on the types of the air conditioner and the heat source device. This eliminates the need to input information (device rated values, etc.) necessary for generating a device model for each type of air conditioner and heat source device. Therefore, compared with the first embodiment, the engineering load in introducing the abnormality detection device can be reduced.

(Third embodiment)
A third embodiment will be described with reference to FIGS. FIG. 7 shows the configuration of the abnormality detection device 1b of the third embodiment. The difference between the configuration shown in FIG. 7 and the configuration shown in FIG. 1 will be described.

  The abnormality detection device 1b includes a loss amount calculation unit 18 and a notification unit 19 in addition to the configuration of the abnormality detection device 1 shown in FIG. The loss amount calculation unit 18 calculates a loss amount that is a difference between the power consumption amount with respect to the set value set in the device and the power consumption amount of the device acquired by the data acquisition unit 10. The loss amount is a difference between the power consumption amount with respect to the current set value of the device and the current value of the power consumption amount of the device. The loss amount calculation unit 18 outputs the calculated loss amount to the notification unit 19. The notification unit 19 notifies the user of the rank calculated by the rank calculation unit 16. The user is an administrator or an inspector. For example, the notification unit 19 is configured as the display unit 20. The display unit 20 displays the rank calculated by the rank calculation unit 16. The display unit 20 displays the loss amount calculated by the loss amount calculation unit 18.

  The notification unit 19 may have a configuration other than the display unit 20. For example, the notification unit 19 may generate an alarm sound. Alternatively, the notification unit 19 may notify the administrator or the inspector of the diagnosis result by transmitting an e-mail to the administrator or the inspector.

  The configuration shown in FIG. 7 is the same as the configuration shown in FIG.

  The operation of the abnormality detection device 1b will be described with reference to FIG. FIG. 8 shows a procedure of processing by the abnormality detection device 1b. The process shown in FIG. 8 will be described while referring to differences from the process shown in FIG.

  After step S107, the loss amount calculation unit 18 calculates the loss amount in the system in which the abnormality determination unit 15 determines that an abnormality has occurred (step S120). After step S120, the rank calculation unit 16 outputs the rank calculated in step S107 as a diagnosis result. The loss amount calculation unit 18 outputs the loss amount calculated in step S120 as a diagnosis result. The display unit 20 displays the rank calculated in step S107 and the loss amount calculated in step S120 (step S121).

  FIG. 9 is an example of the screen of the display unit 20. The display unit 20 displays an image including the graph G1 and the table T1. The graph G1 and the table T1 indicate the ranks calculated by the rank calculation unit 16, that is, the inspection ranks. The graph G1 includes the power consumption of the air conditioners and heat source units of each system and the loss amount of each system. The power consumption of the air conditioners and heat source units of each system is shown by a bar graph. For each system, a graph of normal power consumption and a graph of current power consumption are arranged in the horizontal direction. In each power consumption graph, a graph of the power consumption of the air conditioner and a graph of the power consumption of the heat source device are arranged in the vertical direction. The loss amount of each system is shown by a broken line. The graphs of the power consumption of the air conditioners and heat source units of each system are arranged in descending order of loss. The loss amount of the system arranged on the right side is larger than the loss amount of the system arranged on the left side. That is, the priority of the inspection of the system arranged on the right side is higher than the priority of the inspection of the system arranged on the left side.

  Table T1 includes the loss amount of each system for each predetermined period. The loss amount when the current loss amount continues for a predetermined period is included in Table T1. For example, the predetermined period is one day, one month, and one year. In Table T1, the loss amount of each system is arranged in descending order of loss amount. The loss amount of the system arranged on the right side is larger than the loss amount of the system arranged on the left side. That is, the priority of the inspection of the system arranged on the right side is higher than the priority of the inspection of the system arranged on the left side.

  By displaying the graph G1 and the table T1, the manager or the inspector can easily grasp the order of inspection and the amount of loss. By displaying the table T1, the manager or the inspector can easily grasp the specific amount of loss.

  In the example illustrated in FIG. 9, the display unit 20 displays the amount of power consumption loss. The loss amount calculation unit 18 may calculate a loss amount [yen] that is a product of the loss amount [kWh] and the electric energy unit price [yen / kWh]. The display unit 20 may display the amount of loss.

  Regarding the points other than the above, the process shown in FIG. 8 is the same as the process shown in FIG.

  As in the first embodiment, the abnormality detection device 1b may not include the rank calculation unit 16. Therefore, the display unit 20 may display information on all the systems that are targets for abnormality determination. At this time, information on the system that is determined to be abnormal by the abnormality determination unit 15 may be highlighted. For example, the information on the system determined to have an abnormality and the information on the system determined to have no abnormality may be displayed in different colors. The display unit 20 may not display the information of the system that has been determined that no abnormality has occurred.

  The abnormality detection device 1b may not include the loss amount calculation unit 18. Therefore, the display unit 20 may not display the loss amount.

  According to the third embodiment, the same effect as in the first embodiment can be obtained. In the third embodiment, an image is displayed on the screen of the display unit 20 when an abnormality occurs. Alternatively, notification by e-mail or the like is performed. Thereby, it is possible to promptly notify the manager or the inspector of the occurrence of abnormality. Further, by displaying the diagnosis result on the screen of the display unit 20, the manager or the inspector can grasp the specific loss amount and can easily grasp the order of the systems to be inspected.

(Fourth embodiment)
A fourth embodiment will be described with reference to FIGS. FIG. 10 shows the configuration of the abnormality detection device 1c of the fourth embodiment. The configuration shown in FIG. 10 will be described while referring to differences from the configuration shown in FIG.

  The abnormality detection device 1c includes a loss amount calculation unit 18 and an inspection cycle calculation unit 21 in addition to the configuration of the abnormality detection device 1 shown in FIG. The loss amount calculation unit 18 is the same as the loss amount calculation unit 18 shown in FIG. The loss amount calculation unit 18 calculates a loss amount that is a difference between the power consumption amount for the set value set in the device and the power consumption amount of the device acquired by the data acquisition unit 10 for each of a plurality of periods. The inspection cycle calculation unit 21 calculates the inspection cycle based on the sum of the loss cost based on the loss amount for each of the plurality of periods and the inspection cost of the equipment for each of the plurality of periods.

  Regarding the points other than the above, the configuration shown in FIG. 10 is the same as the configuration shown in FIG.

  The operation of the abnormality detection device 1c will be described with reference to FIG. FIG. 11 shows a procedure of processing by the abnormality detection device 1c. The process shown in FIG. 11 will be described while referring to differences from the process shown in FIG.

  After step S107, the loss amount calculation unit 18 calculates the loss amount in the system in which the abnormality determination unit 15 determines that an abnormality has occurred (step S130). After step S130, the inspection cycle calculation unit 21 calculates the inspection cycle (step S131).

  In step S131, the inspection cycle calculation unit 21 calculates an inspection cycle in which the sum of the loss cost and the inspection cost is relatively small. Specifically, the inspection cycle calculation unit 21 calculates an optimal inspection cycle having the smallest loss cost and inspection cost. Below, the calculation example of the optimal inspection period by the inspection period calculating part 21 is demonstrated. The longer the inspection cycle, the smaller the number of inspections. That is, the inspection cost becomes smaller as the inspection cycle becomes longer. On the other hand, the longer the inspection cycle, the longer the loss. For this reason, the longer the inspection cycle, the greater the loss cost. Thus, there is a trade-off relationship between inspection cost and loss cost. The inspection cycle with the smallest sum of both costs is the optimal inspection cycle.

  FIG. 12 shows an example of calculating the optimum inspection period. The horizontal axis of the graph shown in FIG. 12 is the inspection period, and the vertical axis is the cost. A loss cost graph G2, an inspection cost graph G3, and a total cost graph G4 are shown.

  For example, when the loss amount corresponding to the current value of the measured value and the set value is calculated, the loss amount is stored in the memory. The amount of loss calculated at a plurality of past times is stored in the memory. The loss amount calculation unit 18 calculates a loss amount for each of a plurality of periods based on the loss amount stored in the memory. For example, when the loss amount is calculated once a day, the loss amount calculation unit 18 reads the loss amount for each day in the period from the memory. The loss amount calculation unit 18 calculates the loss amount for the period by summing the loss amounts for each day in the period. Since conditions such as the outside air temperature and the outside air humidity vary from day to day, the set values vary from day to day. As a result, the amount of loss varies from day to day. The inspection cycle calculation unit 21 calculates a loss cost based on the loss amount. In FIG. 12, the loss costs for 1 month, 2 months,..., 7 months are shown.

  Moreover, the inspection period calculating part 21 calculates the inspection cost for every several predetermined period. In the example shown in FIG. 12, the graph G3 is a straight line. That is, the inspection cost is a linear function of time. Also, the inspection cost decreases monotonously. The inspection cost may be expressed by a function of second order or higher. The total cost is the sum of the loss cost and the inspection cost. As shown in FIG. 12, when the inspection cycle is 6 months, the total cost is the smallest. Therefore, in the example shown in FIG. 12, the optimal inspection cycle is 6 months. An administrator or an inspector may input inspection cost information via the parameter input unit 14.

  After step S131, the rank calculation unit 16 outputs the rank calculated in step S107 as a diagnosis result. Further, the inspection cycle calculation unit 21 outputs the inspection cycle calculated in step S131 as a diagnosis result (step S132).

  The procedure of processing by the abnormality detection device 1c is not limited to the procedure shown in FIG. For example, after step S130 and step S131, the process in step S107 may be performed.

  Regarding the points other than the above, the process shown in FIG. 11 is the same as the process shown in FIG.

  In the above example, the inspection cycle calculation unit 21 calculates the inspection cycle having the smallest sum of the loss cost and the inspection cost. The inspection cycle calculated by the inspection cycle calculation unit 21 may be an inspection cycle in which the sum of the loss cost and the inspection cost is the second or third smallest. That is, the plurality of periods may include a first period and a second period. The sum of the loss cost and the inspection cost in the first period is smaller than the sum of the loss cost and the inspection cost in the second period. The inspection period calculation unit 21 may select the first period as the inspection period.

  Similar to the first embodiment, the abnormality detection device 1 c may not include the rank calculation unit 16 and the parameter input unit 14. Similarly to the third embodiment, the abnormality detection device 1c may include a notification unit 19 (display unit 20).

  According to the fourth embodiment, the same effect as in the first embodiment can be obtained. In the fourth embodiment, the inspection cycle with the smallest sum of the loss cost and the inspection cost when an abnormality occurs is calculated. Thereby, the manager or the inspector can easily determine the cycle for carrying out the inspection.

  According to at least one embodiment described above, it is possible to detect a device abnormality by having the abnormality determination unit 15.

  Although several embodiments of the present invention have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope and gist of the invention, and are also included in the invention described in the claims and the equivalents thereof.

  DESCRIPTION OF SYMBOLS 1,1a, 1b, 1c ... Abnormality detection apparatus, 10 ... Data acquisition part, 11 ... Apparatus model memory | storage part, 12 ... System | strain information memory | storage part, 13 ... Power consumption calculating part, 14 ... Parameter input part, 15 ... Abnormality determination , 16 ... Rank calculation unit, 17 ... Device model generation unit, 18 ... Loss amount calculation unit, 19 ... Notification unit, 20 ... Display unit, 21 ... Inspection cycle calculation unit

Claims (10)

A data acquisition unit for acquiring a measurement value output from a sensor of the device, a power consumption amount of the device, and a setting value indicating an operation condition of the device;
A device model storage unit that stores a device model for calculating the power consumption of the device;
Based on the measurement value acquired by the data acquisition unit and the device model stored in the device model storage unit, a power consumption calculation unit that calculates power consumption for the set value;
Based on the power consumption of the device acquired by the data acquisition unit and the power consumption calculated by the power consumption calculation unit, it is determined whether an abnormality has occurred in the device. An abnormality determination unit;
An abnormality detection device comprising: A system information storage unit is provided,
The device is included in any one of a plurality of systems,
Each of the plurality of systems includes at least one device,
The system information storage unit stores system information indicating the devices included in the system for each system,
The abnormality detection device according to claim 1, wherein the power consumption calculation unit selects the device model of the device indicated by the system information corresponding to the system that is a target of abnormality determination. The rank calculation part which calculates the rank based on the magnitude | size of the loss which generate | occur | produces in the said system | strain for every said system | strain including the said apparatus determined that the abnormality has generate | occur | produced by the said abnormality determination part. Anomaly detection device. The abnormality detection device according to claim 3, further comprising a notification unit that notifies the user of the rank calculated by the rank calculation unit. The abnormality detection device according to claim 4, wherein the notification unit is a display unit that displays the rank calculated by the rank calculation unit. The abnormality determination unit converts the power consumption of the device acquired by the data acquisition unit into a first value of any one index of primary energy consumption, CO2 emission, and cost,
The abnormality determination unit converts the power consumption calculated by the power consumption calculation unit into a second value of the same index as the first value,
The abnormality determination unit determines whether an abnormality has occurred in the device based on the first value and the second value.
The abnormality detection device according to claim 1. A device model generation unit that generates the device model of the device based on the measurement value output from the sensor of the normal device,
The abnormality detection device according to any one of claims 1 to 6, wherein the device model storage unit stores the device model generated by the device model generation unit. Loss amount calculation for calculating a loss amount that is a difference between the power consumption amount for the set value set in the device and the power consumption amount of the device acquired by the data acquisition unit for each of a plurality of periods. And
An inspection cycle calculation unit for calculating an inspection cycle based on a total of a loss cost based on the loss amount for each of the plurality of periods and an inspection cost of the device for each of the plurality of periods;
The abnormality detection device according to any one of claims 1 to 7, further comprising: A data acquisition step for acquiring a measurement value output from a sensor of the device, a power consumption amount of the device, and a setting value indicating an operation condition of the device;
Based on the measured value acquired by the data acquisition step and a device model for calculating the power consumption of the device, a power consumption calculation step of calculating a power consumption for the set value;
Based on the power consumption of the device acquired in the data acquisition step and the power consumption calculated in the power consumption calculation step, it is determined whether an abnormality has occurred in the device. An abnormality determination step;
An abnormality detection method comprising: A data acquisition step for acquiring a measurement value output from a sensor of the device, a power consumption amount of the device, and a setting value indicating an operation condition of the device;
Based on the measured value acquired by the data acquisition step and a device model for calculating the power consumption of the device, a power consumption calculation step of calculating a power consumption for the set value;
Based on the power consumption of the device acquired in the data acquisition step and the power consumption calculated in the power consumption calculation step, it is determined whether an abnormality has occurred in the device. An abnormality determination step;
A program that causes a computer to execute.

Images