Device Status Monitoring Device and Device Status Monitoring Method

Abstract

The device status monitoring device (1) projects a plurality of measured data onto a dimensionless space of a plurality of display shapes that represent a plurality of normal information using a common shape, based on the positional relationship between the plurality of display shapes of the plurality of normal information and the plurality of measured data, and estimates the distribution of the status of the device based on the plurality of measured data projected onto the dimensionless space.

Description

Technical Field

[0001] The present invention relates to an apparatus state monitoring device and an apparatus state monitoring method for monitoring the state of a device. Background Art

[0002] As a prior art for monitoring the state of a device, for example, there is a method for determining the maintenance period of an automotive air conditioner described in Patent Document 1. In this method, the difference between the specific enthalpy at the start point of compression and the specific enthalpy at the end point of compression of an outdoor heat exchanger, as well as a first set value and a second set value larger than the first set value, are respectively compared. At this time, when the difference in specific enthalpy is greater than the second set value, the air conditioner is determined to require maintenance.

[0003] On the other hand, when the difference in specific enthalpy is greater than the first set value and less than the second set value, a refrigeration cycle graph of a Mollier diagram (hereinafter referred to as a p-h (pressure-specific enthalpy) diagram) is created based on sensor data detected by various sensors provided in the outdoor heat exchanger. This refrigeration cycle graph is displayed together with the refrigeration cycle graph when the air conditioner is in a normal state.

[0004] In the p-h diagram, when the shape of the refrigeration cycle graph changes from the shape corresponding to the normal state, it can be determined that the performance of the air conditioner has deteriorated. When the difference in this shape exceeds a set value, it is determined that the air conditioner requires maintenance. In addition, the refrigeration cycle graph in the normal state of the air conditioner is a display shape of normal information indicating the normal state of the device, and the sensor data used to create the refrigeration cycle graph is the measured data of the state value of the device.

[0005] Prior Art Documents

[0006] Patent Documents

[0007] Patent Document 1: Japanese Unexamined Patent Application Publication No. 2015-92121 Summary of the Invention

[0008] Problems to be Solved by the Invention

[0009] Even when the set temperature of the air conditioner is the same, the shape of the refrigeration cycle graph of the p-h diagram of the air conditioner deviates depending on the external air temperature. That is, the refrigeration cycle graph in the normal state of the air conditioner becomes a different shape depending on the external air temperature. In addition, the refrigeration cycle graph compared with the refrigeration cycle graph in the normal state of the air conditioner is so-called instantaneous data based on sensor data detected at the start time point of the maintenance period determination.

[0010] In the method described in Patent Document 1, it is determined whether maintenance of the device is required by monitoring whether the state of the device shown by the instantaneous data is a normal state. Therefore, when an off-value accidentally occurs in the instantaneous data, the state of the device may be misidentified.

[0011] On the other hand, by determining the change trend of the state of the device to be monitored based on a plurality of sensor data sequentially detected within a fixed period (for example, a one-month period), the influence of off-values accidentally generated in the sensor data can be reduced. However, there is a problem as follows: when the display shape of the normal information changes due to a change in the environment outside the device (for example, the external gas temperature) or the usage method during the period, it is difficult to observe the correspondence between the plurality of sensor data and the plurality of normal information, and it is impossible to accurately identify the plurality of states of the device.

[0012] The present invention is used to solve the above problems, and its object is to obtain a device state monitoring device and a device state monitoring method capable of identifying a plurality of states of a device based on a common display shape.

[0013] Means for Solving the Problem

[0014] The device state monitoring device of the present invention includes: a data acquisition unit that acquires measured data of the state value of the device; a normal information acquisition unit that acquires normal information indicating the normal state of the device; a positional relationship acquisition unit that acquires the positional relationship of the measured data in the display shape of the normal information; a projection unit that projects a plurality of measured data into a dimensionless space that represents a plurality of display shapes of the normal information using a common shape based on the positional relationship between the plurality of display shapes of the plurality of normal information and the plurality of measured data; and a distribution estimation unit that estimates the distribution of the state of the device based on the plurality of measured data projected into the dimensionless space.

[0015] Effects of the Invention

[0016] According to the present invention, a plurality of measured data of the state value of the device are projected into a dimensionless space that represents a plurality of display shapes of normal information indicating the normal state of the device using a common shape, and the distribution of the state of the device is estimated based on the plurality of measured data projected into the dimensionless space. Thereby, a plurality of states of the device can be identified based on a common display shape. Description of the Drawings

[0017] Figure 1 is a block diagram showing the structure of the device state monitoring device according to Embodiment 1.

[0018] Figure 2 is a flowchart showing the device state monitoring method according to Embodiment 1.

[0019] Figure 3AIt is a diagram showing the relationship between multiple display shapes of multiple normal information and multiple measured data. Figure 3B It is a diagram showing the dimensionless space in Embodiment 1 where multiple measured data are projected.

[0020] Figure 4 It is a flowchart showing the position relationship calculation process in Embodiment 1.

[0021] Figure 5 It is a diagram showing the display shape of normal information and measured data.

[0022] Figure 6 It is showing Figure 5 a diagram of the display shape of normal information, measured data, and the center point of the display shape of normal information.

[0023] Figure 7 It is showing Figure 5 a diagram of the positional relationship between the display shape of normal information and measured data.

[0024] Figure 8 It is a flowchart showing the projection process of projecting measured data into the dimensionless space in Embodiment 1.

[0025] Figure 9 It is a diagram showing the dimensionless space in Embodiment 1.

[0026] Figure 10 It is showing Figure 9 a diagram of the dimensionless space and the measured data projected into this dimensionless space.

[0027] Figure 11A It is a diagram showing an overview of the state determination of a device using the distribution of measured data projected into the dimensionless space in Embodiment 1, Figure 11B It is a diagram showing an overview of the state deterioration determination of a device using the distribution of measured data projected into the dimensionless space in Embodiment 1.

[0028] Figure 12A It is a block diagram showing the hardware structure for implementing the functions of the device state monitoring device in Embodiment 1, Figure 12B It is a block diagram showing the hardware structure for executing the software that implements the functions of the device state monitoring device in Embodiment 1. Detailed Embodiment

[0029] Embodiment 1.

[0030] Figure 1It is a block diagram showing the structure of the device status monitoring device 1 of Embodiment 1. The device status monitoring device 1 is a device that monitors the status of a device based on the result obtained by comparing the measured data of the status value of the device to be monitored with the display shape of the normal information indicating the normal state of the device. As Figure 1 shown, the device status monitoring device 1 includes a data acquisition unit 11, a normal information acquisition unit 12, a position relationship acquisition unit 13, a projection unit 14, a distribution estimation unit 15, and an output unit 16. The device whose status is monitored by the device status monitoring device 1 is preferably a device provided with various sensors for detecting various states of the device, for example, an air conditioner.

[0031] The data acquisition unit 11 acquires the measured data of the status value of the device to be monitored. The measured data for a fixed period (for example, 1 month) of the status of the monitored device is acquired by the data acquisition unit 11. The measured data is, for example, sensor data detected by various sensors provided in the device. When the device to be monitored is an air conditioner, the sensors are, for example, pressure sensors and temperature sensors provided at various parts of the air conditioner. Normal information exists for each status of the device represented by the sensor data.

[0032] The normal information acquisition unit 12 acquires the normal information. For example, when the device to be monitored is an air conditioner, the normal information is the refrigeration cycle of the p-h diagram in the normal state of the air conditioner, and the display shape of the normal information is the refrigeration cycle graph. In addition, the refrigeration cycle graph in the normal state of the air conditioner changes according to the external gas temperature. That is, there are multiple shapes of the display shape of the normal information according to the external gas temperature.

[0033] In addition, the normal information acquisition unit 12 can use the sensor data in the normal state detected by the pressure sensor and the temperature sensor to calculate the refrigeration cycle (normal information) in the normal state of the air conditioner. That is, in the "acquisition" of the normal information by the normal information acquisition unit 12, in addition to the case of reading and acquiring the normal information stored in the storage device, it also includes the case of acquiring the normal information by calculation using the measured data of the status value of the device.

[0034] The position relationship acquisition unit 13 acquires the position relationship of the measured data in the display shape of the normal information. For example, when the display shape of the normal information is a polygon, the position relationship acquisition unit 13 calculates the distance between the center point of the polygon and the measured data, and calculates the angle formed by the straight line passing through the center point of the polygon and the measured data and the side of the polygon intersecting with the straight line, as the position relationship of the measured data in the polygon. The center point of the polygon is, for example, the centroid.

[0035] In addition, in the "acquisition" of the positional relationship by the positional relationship acquisition unit 13, in addition to the case of calculating the positional relationship using measured data and normal information, it also includes the case of reading and acquiring the positional relationship data stored in the storage device.

[0036] Based on the positional relationships between the multiple display shapes of the multiple normal information and the multiple measured data, the projection unit 14 projects the multiple measured data into a dimensionless space. Here, the dimensionless space refers to a space in which the multiple display shapes of the multiple normal information are represented by a common shape, and points (dimensionless) representing the positional relationships of the measured data in the display shapes using the normal information are drawn (projected).

[0037] The common shape is, for example, a circle with a radius of 1. The projection unit 14 applies the center points of the display shapes of the multiple normal information corresponding to the multiple measured data to the center point of this circle, and converts the positional relationships (distance information and angle information) between the center points of the display shapes of the normal information and the measured data into positional relationships with the center point of the circle. Thus, the multiple measured data are drawn in the dimensionless space containing this circle. The measured data drawn into the dimensionless space are points of dimensionless values represented by the positional relationships with the display shapes of the normal information. However, since the positions of the points in the dimensionless space correspond to the relationships between the display shapes of the normal information and the measured data, the distribution of the points in the dimensionless space corresponds to the distribution of the states of the device.

[0038] Based on the multiple measured data projected into the dimensionless space, the distribution estimation unit 15 estimates the distribution of the states of the device. For example, the distribution estimation unit 15 estimates the distribution of the points in the dimensionless space, that is, the distribution of the states of the device, by performing a mixture Gaussian model estimation process on the multiple points drawn in the dimensionless space. The method for estimating the distribution of the states of the device can be any method that can estimate the probability density distribution of the points in the dimensionless space. For example, the maximum likelihood method, Bayesian estimation, or the EM algorithm can be used.

[0039] The output unit 16 outputs data for monitoring the state of the device. As the data for monitoring the state of the device, for example, a dimensionless space in which the multiple display shapes of the multiple normal information are represented by a common shape and the distribution of the states of the device is set for the common shape is cited. The output unit 16, for example, causes the display device to display the dimensionless space.

[0040] Next, the operation of the device state monitoring device 1 will be described.

[0041] Figure 2It is a flowchart showing the device state monitoring method of Embodiment 1, showing the operation of the device state monitoring apparatus 1. First, the data acquisition unit 11 acquires the measured data of the state value of the device to be monitored (step ST1). For example, the data acquisition unit 11 obtains the time series of sensor data within a fixed period (hereinafter referred to as the monitoring period) of the device to be monitored, that is, the time series data of the state value of the device, by continuously or periodically inputting the sensor data (measured data) successively detected by the sensors provided on the device. Additionally, the measured data may be stored in the storage device in advance, and the data acquisition unit 11 acquires the measured data from the storage device.

[0042] Next, the normal information acquisition unit 12 acquires the normal information of the state of the device to be monitored (step ST2). For example, when the device to be monitored is an air conditioner and the display form of the normal information is the refrigeration cycle graphic data on the p-h line diagram in the normal state of the air conditioner, the normal information acquisition unit 12 calculates the refrigeration cycle graphic data in the normal state using the sensor data in the normal state detected by the pressure sensor and the temperature sensor provided on the air conditioner. In addition, the refrigeration cycle graphic data in the normal state corresponding to the external gas temperature may be stored in the storage device, and the normal information acquisition unit 12 sequentially acquires the refrigeration cycle graphic data corresponding to the external gas temperature during the monitoring period from the storage device.

[0043] The positional relationship acquisition unit 13 acquires the positional relationship of the measured data in the display form of the normal information (step ST3). Figure 3A It is a diagram showing the relationship between the display forms of multiple normal information and multiple measured data, and is a chart showing the relationship between the sensor data (1) and the sensor data (2) detected by the sensors provided on the device to be monitored. For example, the positional relationship acquisition unit 13 uses the measured data acquired by the data acquisition unit 11 and the normal information acquired by the normal information acquisition unit 12 to create Figure 3A the chart shown.

[0044] In Figure 3A the chart shown, multiple measured data composed of the sensor data (1) and the sensor data (2) are plotted, showing the shapes of multiple normal information corresponding to these measured data respectively. As Figure 3A shown, even when the states determined by the sensor data (1) and the sensor data (2) are the same, the display form of the normal information sometimes varies according to the environment outside the device or the usage method. When there is a deviation in the display form of the normal information, as Figure 3A shown, the correspondence relationship between the measured data and the display form of the normal information becomes complicated, and thus the state of the device cannot be accurately identified.

[0045] Then, the device status monitoring device 1 projects a plurality of measured data onto a dimensionless space of a plurality of display shapes that represent a plurality of normal information using a common shape. Thereby, the device status monitoring device 1 can identify a plurality of states of the device based on the common display shape. The position relationship acquisition unit 13 acquires the position relationship of the measured data in the display shape of the normal information as information for projecting the measured data onto the dimensionless space. This position relationship is, for example, the distance information between the center point of the display shape of the normal information and the measured data, and the angle information formed by the straight line passing through the center point of the display shape of the normal information and the measured data and the side of the display shape of the normal information that intersects this straight line.

[0046] The projection unit 14 projects a plurality of measured data onto a dimensionless space based on the position relationship between the plurality of display shapes of the plurality of normal information and the plurality of measured data (step ST4). Figure 3B FIG. is a diagram showing the dimensionless space in Embodiment 1 in which a plurality of measured data are projected. For example, as Figure 3B shown, the projection unit 14 applies the center points of the display shapes of the plurality of normal information corresponding to the plurality of measured data to the center point 20a of the circle 20 in the dimensionless space, and converts the position relationship between the center point of the display shape of the normal information and the measured data into the position relationship with the center point 20a of the circle 20, thereby plotting the plurality of measured data on the circle 20.

[0047] The position of a point in the dimensionless space is a position corresponding to the relationship between the measured data before projection and the display shape of the normal information. In addition, Figure 3B the component (1) shown is a component corresponding to the change of the sensor data (1), and the component (2) is a component corresponding to the change of the sensor data (2).

[0048] The distribution estimation unit 15 estimates the distribution of the state of the device based on the plurality of measured data projected onto the dimensionless space (step ST5). For example, the distribution estimation unit 15 performs a mixture Gaussian model estimation process on a plurality of points plotted in the dimensionless space, thereby estimating Figure 3B the distribution 21 in the dimensionless space shown. In the distribution 21, the color or shading is determined according to the number of points corresponding to the measured data. The number of points corresponding to the measured data is the largest in the region with the darkest color and decreases as the color fades. The output unit 16 causes the dimensionless space in which the distribution 21 is set to be displayed on the display device.

[0049] Next, the calculation process of the position relationship of the measured data in the normal information based on the position relationship acquisition unit 13 will be described in detail. Figure 4 FIG. is a flowchart showing the position relationship calculation process in Embodiment 1, showing Figure 2Detailed processing of step ST3. The position relationship acquisition unit 13 draws the measured data acquired by the data acquisition unit 11 on a two-dimensional coordinate plane, and displays the shape of the normal information acquired by the normal information acquisition unit 12 on the two-dimensional coordinate plane (step ST1a). Figure 5 It is a diagram showing the display shape of the normal information and the measured data, and shows the measured data 31 drawn in the two-dimensional coordinate plane where the display shape 32 of the normal information is displayed.

[0050] In Figure 5 , the measured data 31 is the measured data of the state value of the device determined based on the sensor data (1) and the sensor data (2) detected by the sensors provided in the device to be monitored. The display shape 32 is the normal information regarding the state shown by the measured data 31, and is a quadrilateral shape with vertices 32a to 32d.

[0051] Next, the position relationship acquisition unit 13 calculates the center point 32e of the display shape 32 (step ST2a). Figure 6 It is a diagram showing Figure 5 the display shape 32, the measured data 31, and the center point 32e of the display shape 32. For example, the position relationship acquisition unit 13 calculates the center of gravity of the outer shape of the display shape 32 as the center point 32e. In Figure 6 , since the display shape 32 is a quadrilateral, the position relationship acquisition unit 13 calculates the intersection point of the diagonal connecting vertex 32a and vertex 32c and the diagonal connecting vertex 32b and vertex 32d as the center point 32e.

[0052] Next, the position relationship acquisition unit 13 calculates the distance r between the center point 32e of the display shape 32 and the measured data 31 a , and the angle θ formed by the straight line A passing through the center point 32e of the display shape 32 and the measured data 31 and the side B on the outer shape of the display shape 32 that intersects the straight line A a (step ST3a). Figure 7 It is a diagram showing Figure 5 the positional relationship between the display shape 32 and the measured data 31. For example, the position relationship acquisition unit 13 calculates the straight line A passing through the measured data 31 and the center point 32e. After that, the position relationship acquisition unit 13 calculates the distance r between the center point 32e and the measured data 31 a , and further calculates the distance r from the center point 32e of the display shape 32 to the intersection point Ba of the straight line A and the side B on the outer shape of the display shape 32 n .

[0053] The position relationship acquisition unit 13 calculates the distance r a with respect to the length of the straight line A, that is, the distance r n of the relative ratio r R (= ra / r n )。Next, the positional relationship acquisition unit 13 calculates the angle θ formed by the straight line A and the side B a . The relative ratio r calculated by the positional relationship acquisition unit 13 R and the angle θ a are output to the projection unit 14 as the positional relationship data of the measured data 31 with respect to the center point 32e of the display shape 32

[0054] Next, the projection process of projecting the measured data by the projection unit 14 into the dimensionless space will be described in detail

[0055] Figure 8 is a flowchart showing the projection process of projecting the measured data into the dimensionless space in Embodiment 1, showing Figure 2 the detailed process of step ST4 Figure 9 is a diagram showing the dimensionless space in Embodiment 1. Here, the dimensionless space is a space where a circle 20 with a radius of 1 is set as shown Figure 9 . In the case where the angle formed with the axis of the component (1) is θ, the points on the circle 20 are represented by (1, θ). The component (1) is the component corresponding to the variation of Figure 5 the sensor data (1), and the component (2) is the component corresponding to the variation of Figure 5 the sensor data (2)

[0056] The projection unit 14 projects the measured data 31 into the dimensionless space based on the positional relationship of the measured data 31 in the display shape 32 (step ST1b) Figure 10 is a diagram showing Figure 9 the dimensionless space and the measured data 21a projected into this dimensionless space. For example, the projection unit 14 applies the center point 32e of the display shape 32 shown Figure 7 to the center point 20a of the circle 20 in the dimensionless space shown Figure 9 . Next, the projection unit 14 replaces the distance r n with the radius of the circle 20, and uses the relative ratio r of the distance from the center point 32e of the display shape 32 to the measured data 31 R and the angle θ formed by the straight line A passing through the measured data 31 and the side B of the display shape 32 a to draw the measured data 31 in the dimensionless space. Thus, the measured data 31 is converted into a point (r R , θ a ) and drawn in the dimensionless space

[0057] After that, the projection unit 14 confirms whether all the measured data 31 for which the positional relationship with the display shape 32 has been obtained has been projected onto the dimensionless space (step ST2b). Here, in the case where there is measured data 31 that has not been projected onto the dimensionless space (step ST2b; NO), the process returns to step ST1b, and the center points 32e of the plurality of display shapes 32 are sequentially applied to the center point 20a of the circle 20, and the projection process of projecting the measured data 31 onto the dimensionless space is executed. On the other hand, if there is no measured data 31 that has not been projected onto the dimensionless space (step ST2b; YES), the process Figure 8 ends.

[0058] The distribution estimation unit 15 performs a mixture Gaussian model estimation process on the plurality of points drawn by the projection unit 14 onto the dimensionless space, thereby estimating Figure 3B the distribution 21 in the dimensionless space as shown. Here, a determination of the state of the device using the distribution estimated by the distribution estimation unit 15 will be described.

[0059] Figure 11A FIG. is a diagram showing an outline of the determination of the state of the device using the distribution 21 of the measured data projected onto the dimensionless space. The distribution 21 determines the color or shading according to the number of points corresponding to the measured data, and the number of points corresponding to the measured data is the largest in the region 30a with the darkest color and decreases as the color fades.

[0060] In Figure 11A , component (1) is a component corresponding to the change in the sensor data (1), and component (2) is a component corresponding to the change in the sensor data (2). In addition, in the distribution 21, the region 30a has the largest number of points corresponding to the measured data and has a dominant influence on the characteristics of the distribution 21. The circle 20 corresponds to the normal state of the device shown by the measured data composed of the sensor data (1) and the sensor data (2).

[0061] The distribution estimation unit 15 can determine whether the state of the device to be monitored is close to the normal state based on the positional relationship between the region 30a of the distribution 21 and the circle 20. In Figure 11A the distribution 21 shown, the region 30a exists at a position separated from the circle 20, and thus the state of the device deviates from the normal state, that is, the state of the device deteriorates. In this way, in the device state monitoring device 1, the change trend of the state of the device during the monitoring period can be determined, and therefore, even if an outlier occurs accidentally in the measured data, its influence can be reduced.

[0062] Figure 11B FIG. is a diagram showing an outline of the determination of the deterioration of the state of the device using the distributions 21A and 21B of the measured data projected onto the dimensionless space. In Figure 11BIn this case, the distribution 21A is the distribution of the state of the device estimated by the distribution estimation unit 15, and is a distribution estimated based on the measured data acquired during the monitoring period (1). The distribution 21B is the distribution of the same state as the distribution 21A, but is a distribution estimated based on the measured data acquired during the monitoring period (2) after a certain period of time has passed since the monitoring period (1). In addition, the shapes of the distributions 21A and 21B are elliptical.

[0063] By monitoring the change over time of the state of the device to be monitored, the distribution 21A shifts to the distribution 21B. At this time, the shift from the center point 30a1 of the distribution 21A to the center point 30a2 of the distribution 21B can be represented by (r c , θ c ). The distance r c is the distance between the center point 30a1 and the center point 30a2, and the angle θ c is the angle formed by the line segment connecting the center point 30a1 and the center point 30a2 at the center point 30a1. Similarly, the shift from the point 30b1 on the major axis of the distribution 21A to the point 30b2 on the major axis of the distribution 21B can be represented by (r m , θ m ), and the shift from the point 30c1 on the minor axis of the distribution 21A to the point 30c2 on the minor axis of the distribution 21B can be represented by (r s , θ s ).

[0064] The distribution estimation unit 15 can determine the positional relationship between the distribution of the measured data projected onto the dimensionless space and, for example, Figure 11A the circle 20 shown, based on (r, θ) representing the shift of the distribution of the measured data projected onto the dimensionless space, and determine whether the state of the device to be monitored has deteriorated based on the determined positional relationship. In this way, by quantifying the change over time of the distribution estimated by the distribution estimation unit 15, it is possible to accurately determine whether the state of the device to be monitored has deteriorated.

[0065] So far, it has been shown that the common shape of the display shape that unifies a plurality of normal information in the dimensionless space is a circle, but it is not limited to a circle and can also be a polygon.

[0066] Next, the hardware structure for implementing the functions of the device state monitoring device 1 of Embodiment 1 will be described. The functions of the data acquisition unit 11, the normal information acquisition unit 12, the positional relationship acquisition unit 13, the projection unit 14, the distribution estimation unit 15, and the output unit 16 in the device state monitoring device 1 are implemented by a processing circuit. That is, the device state monitoring device 1 includes means for executing Figure 2The processing circuit for the processing from step ST1 to step ST5. The processing circuit can be dedicated hardware, but can also be a CPU (Central Processing Unit) that executes a program stored in a memory.

[0067] Figure 12A is a block diagram showing the hardware configuration that implements the functions of the device status monitoring device 1. Figure 12B is a block diagram showing the hardware configuration that executes the software that implements the functions of the device status monitoring device 1. In Figure 12A and Figure 12B In, the input interface 100 is an interface that relays the sensor data output from the sensors of the devices provided in the monitoring target to the device status monitoring device 1. In addition, the output interface 101 is an interface that relays the information output from the device status monitoring device 1.

[0068] When the processing circuit is Figure 12A the processing circuit 102 of the dedicated hardware shown, the processing circuit 102 corresponds to, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination thereof. The functions of the data acquisition unit 11, the normal information acquisition unit 12, the positional relationship acquisition unit 13, the projection unit 14, the distribution estimation unit 15, and the output unit 16 in the device status monitoring device 1 can be implemented by different processing circuits, or can also be implemented by a single processing circuit.

[0069] When the processing circuit is Figure 12B the processor 103 shown, the functions of the data acquisition unit 11, the normal information acquisition unit 12, the positional relationship acquisition unit 13, the projection unit 14, the distribution estimation unit 15, and the output unit 16 in the device status monitoring device 1 are implemented by software, firmware, or a combination of software and firmware. In addition, the software or firmware is described and stored in the memory 104 in the form of a program.

[0070] The processor 103 realizes the functions of the data acquisition unit 11, the normal information acquisition unit 12, the positional relationship acquisition unit 13, the projection unit 14, the distribution estimation unit 15, and the output unit 16 in the device status monitoring device 1 by reading and executing the program stored in the memory 104. For example, the device status monitoring device 1 includes a memory 104 for storing the following program, which, when executed by the processor 103, results in the execution of Figure 2The programs for the processes of steps ST1 to ST5 in the flowchart shown. These programs cause a computer to execute the steps or methods of the data acquisition unit 11, the normal information acquisition unit 12, the positional relationship acquisition unit 13, the projection unit 14, the distribution estimation unit 15, and the output unit 16. The memory 104 may also be a computer-readable storage medium storing a program for causing a computer to function as the data acquisition unit 11, the normal information acquisition unit 12, the positional relationship acquisition unit 13, the projection unit 14, the distribution estimation unit 15, and the output unit 16.

[0071] The memory 104 corresponds to, for example, non-volatile or volatile semiconductor memories such as RAM (Random Access Memory), ROM (ReadOnly Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically-EPROM), magnetic disks, floppy disks, optical disks, high-density disks, mini disks, DVDs, etc.

[0072] Regarding the functions of the data acquisition unit 11, the normal information acquisition unit 12, the positional relationship acquisition unit 13, the projection unit 14, the distribution estimation unit 15, and the output unit 16 in the device status monitoring device 1, part of them may be implemented by dedicated hardware and part by software or firmware. For example, the data acquisition unit 11, the normal information acquisition unit 12, and the positional relationship acquisition unit 13 implement their functions through the processing circuit 102 which is dedicated hardware, and the projection unit 14, the distribution estimation unit 15, and the output unit 16 implement their functions by the processor 103 reading and executing the program stored in the memory 104. In this way, the processing circuit can implement the above functions through hardware, software, firmware, or a combination of them.

[0073] As described above, the device status monitoring device 1 of Embodiment 1 includes: a data acquisition unit 11 that acquires measured data of the status value of a device; a normal information acquisition unit 12 that acquires normal information indicating the normal state of the device; a positional relationship acquisition unit 13 that acquires the positional relationship of the measured data in the display shape of the normal information; a projection unit 14 that projects a plurality of measured data into a dimensionless space that represents a plurality of display shapes of a plurality of normal information using a common shape based on the positional relationship between the plurality of display shapes of the plurality of normal information and the plurality of measured data; and a distribution estimation unit 15 that estimates the distribution of the status of the device based on the plurality of measured data projected into the dimensionless space. Thereby, it is possible to identify a plurality of statuses of the device based on a common display shape.

[0074] In addition, the present invention is not limited to the above-described embodiments, and any structural element of the embodiment can be modified or any structural element of the embodiment can be omitted within the scope of the present invention.

[0075] Industrial applicability

[0076] The device state monitoring device of the present invention can be used, for example, to monitor the operating state of an air conditioner.

[0077] Reference numeral description

[0078] 1 Device state monitoring device, 11 Data acquisition unit, 12 Normal information acquisition unit, 13 Position relationship acquisition unit, 14 Projection unit, 15 Distribution estimation unit, 16 Output unit, 20 Circle, 20a, 30a1, 30a2, 32e Center points, 21, 21A, 21B Distributions, 21a Measured data, 30a Region, 31 Measured data, 32 Display shape, 32a to 32d Vertices, 100 Input interface, 101 Output interface, 102 Processing circuit, 103 Processor, 104 Memory.

Claims

1. A device status monitoring device, characterized in that: The device status monitoring device includes: A data acquisition unit that acquires measured data of the status value of the device; A normal information acquisition unit that acquires normal information indicating the normal state of the device; A positional relationship acquisition unit that acquires the positional relationship of the measured data in the display shape of the normal information; A projection unit that projects the plurality of measured data onto a dimensionless space that represents the plurality of display shapes of the plurality of normal information using a common shape, based on the positional relationship between the plurality of display shapes of the plurality of normal information and the plurality of measured data; And A distribution estimation unit that estimates the distribution of the state of the device based on the plurality of measured data projected onto the dimensionless space, wherein when the region with the largest number of points corresponding to the measured data in the dimensionless space exists at a position separated from the common shape, it is determined that the state of the device deviates from the normal state.

2. The device status monitoring device according to claim 1, characterized in that: The positional relationship acquisition unit calculates the distance between the center point of the display shape of the normal information and the measured data, and the angle formed by the straight line passing through the center point and the measured data and the side of the display shape of the normal information that intersects the straight line, as the positional relationship of the measured data in the display shape of the normal information.

3. A device status monitoring device that monitors the status of a device, characterized in that: The device status monitoring device includes an output unit that outputs data for monitoring the status of the device, The output unit outputs a dimensionless space in which a plurality of display shapes representing a plurality of normal information indicating the normal state of the device are represented by a common shape, and the distribution of the state of the device is set for the common shape. The device status monitoring device further includes: A data acquisition unit that acquires measured data of the status value of the device; A normal information acquisition unit that acquires the normal information; A positional relationship acquisition unit that acquires the positional relationship of the measured data in the display shape of the normal information; A projection unit that projects the plurality of measured data onto the dimensionless space based on the positional relationship between the plurality of display shapes of the plurality of normal information and the plurality of measured data; And A distribution estimation unit that estimates the distribution of the state of the device based on the plurality of measured data projected onto the dimensionless space, wherein when the region with the largest number of points corresponding to the measured data in the dimensionless space exists at a position separated from the common shape, it is determined that the state of the device deviates from the normal state.

4. The device status monitoring device according to claim 3, characterized in that: The positional relationship acquisition unit calculates the distance between the center point of the display shape of the normal information and the measured data, and the angle formed by the straight line passing through the center point and the measured data and the side of the display shape of the normal information that intersects the straight line, as the positional relationship of the measured data in the display shape of the normal information.

5. A method for monitoring the state of a device, characterized in that: The method for monitoring the state of the device comprises the following steps: A data acquisition unit acquires measured data of the state value of the device; A normal information acquisition unit acquires normal information indicating the normal state of the device; A position relationship acquisition unit acquires the position relationship of the measured data in the display shape of the normal information; A projection unit projects the plurality of measured data onto a dimensionless space that uses a common shape to represent the plurality of display shapes of the plurality of normal information, based on the position relationships between the plurality of display shapes of the plurality of normal information and the plurality of measured data; And A distribution estimation unit estimates the distribution of the state of the device based on the plurality of measured data projected onto the dimensionless space, wherein when the region with the largest number of points corresponding to the measured data in the dimensionless space exists at a position separated from the common shape, it is determined that the state of the device deviates from the normal state.

Images