Information processing device, information processing system, information processing method, and program

Abstract

To provide an information processing device, an information processing system, an information processing method, and a program capable of obtaining useful data for diagnosing equipment status.SOLUTION: An information processing device according to an embodiment comprises extraction means for extracting operation data representing the characteristic operation of equipment from time series data based on the distance between multiple extreme points of detected time series data in physical quantity when the equipment operates.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] An embodiment of the present invention relates to an information processing device, an information processing system, an information processing method, and a program. [Background technology]

[0002] Generally, elevators that move up and down within a hoistway are equipped with devices such as electromagnetic brakes.

[0003] Inspection (condition monitoring) of such equipment is generally performed by engineers, and inspection of the equipment involves, for example, checking the operating sounds of the equipment and measuring the components that make up the equipment using tools.

[0004] In contrast, when equipment inspection is performed automatically, a physical quantity, such as the current supplied to the equipment when the equipment is operating, is measured (detected) and the condition of the equipment is diagnosed from the physical quantity.

[0005] However, the physical quantities measured when an equipment is operating often change due to deterioration of the equipment over time or adjustment work (maintenance work) on the equipment, and it may not be possible to properly diagnose the condition of the equipment based on those physical quantities. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Publication No. 11-060099 [Patent Document 2] Patent No. 5653537 Summary of the Invention [Problem to be solved by the invention]

[0007] Therefore, an object of the present invention is to provide an information processing device, an information processing system, an information processing method, and a program that are capable of obtaining data useful for diagnosing the state of a device. [Means for solving the problem]

[0008] An information processing device according to an embodiment includes an extraction means for extracting operation data representing a characteristic operation of an appliance from time series data of a physical quantity detected when the appliance is operating, based on a distance between multiple extreme value points of the time series data of the physical quantity. [Brief description of the drawings]

[0009] [Figure 1] FIG. 2 is a block diagram showing an example of a functional configuration of the information processing apparatus according to the embodiment. [Diagram 2] FIG. 2 is a diagram showing an example of a hardware configuration of an information processing apparatus. [Diagram 3] 11 is a flowchart showing an example of a processing procedure of an information processing device. [Figure 4] FIG. 13 is a diagram showing an example of time-series data. [Diagram 5] FIG. 13 is a diagram showing an example of a plurality of extreme points identified in time series data. [Figure 6] FIG. 13 is a diagram for explaining an example of distances between a plurality of extreme points. [Figure 7] FIG. 13 is a diagram showing the correspondence between time series data and distances between a plurality of extreme points. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment will be described with reference to the drawings. The information processing device according to this embodiment is used to diagnose the state of equipment (hereinafter referred to as target equipment) such as an electromagnetic brake mounted on an elevator that moves up and down in an elevator shaft.

[0011] Fig. 1 is a block diagram showing an example of the functional configuration of an information processing device according to this embodiment. As shown in Fig. 1, the information processing device 10 includes a data input unit 11, a parameter input unit 12, a preprocessing unit 13, an extreme point identification unit 14, a distance calculation unit 15, a data division unit 16, a data extraction unit 17, a feature amount calculation unit 18, a condition diagnosis unit 19, and an output unit 20.

[0012] The data input unit 11 inputs time-series data of physical quantities measured when the target device is in operation. Note that the time-series data in this embodiment is data representing (changes in) physical quantities measured at multiple points in time over time, and includes, for example, data representing the waveform of a current or voltage supplied to the target device to operate the target device.

[0013] The parameter input unit 12 inputs parameters used in the processing of the extreme point identification unit 14, for example.

[0014] The preprocessing unit 13 performs preprocessing on the time series data input by the data input unit 11 to remove noise occurring in the time series data.

[0015] The extreme point identifying unit 14 uses the parameters input by the parameter input unit 12 to identify a plurality of extreme points of the time series data preprocessed by the preprocessing unit 13. Note that an extreme point refers to a time point at which the time series data reaches a maximum value (maximum value) within a certain range (period) and a time point at which the time series data reaches a minimum value (minimum value) within the certain range (period).

[0016] Specifically, for example, when the physical quantity measured at a first time point on the time series data is larger than a plurality of second time points located before and after the first time point on the time series data (i.e., the physical quantity measured at the first time point is the maximum value among the physical quantities measured at the first and second time points), the extreme point identifying unit 14 identifies the first time point as an extreme point (maximum point). Similarly, for example, when the physical quantity measured at a first time point on the time series data is small (i.e., the physical quantity measured at the first time point is the minimum value among the physical quantities measured at the first and second time points), the extreme point identifying unit 14 identifies the first time point as an extreme point (minimum point). In other words, an extreme point can be said to be a time point at which a physical quantity (maximum or minimum value) whose tangent slope is 0 is measured in the time series data (waveform).

[0017] The extreme point identifying unit 14 can identify a plurality of extreme points present in the time series data by repeatedly executing the process of treating each time point on the time series data as the first time point described above.

[0018] The distance calculation unit 15 calculates the distance between the multiple extreme points in the time series data based on the multiple extreme points identified by the extreme point identification unit 14. Note that while the time series data is data representing physical quantities measured at multiple time points, the distance between multiple extreme points means the time difference between one extreme point (time point) and the other extreme point (time point).

[0019] The data dividing unit 16 divides the time series data based on the distance calculated by the distance calculation unit 15. Specifically, the data dividing unit 16 divides the time series data into a plurality of intervals using the extreme value points for which the higher distances (i.e., longer distances) are calculated by the distance calculation unit 15 as division points (reference points).

[0020] The data extraction unit 17 extracts operation data representing characteristic operations of the target device from the time series data divided by the data division unit 16. Specifically, when the time series data is divided into a plurality of intervals by the data division unit 16, the data extraction unit 17 extracts, as operation data, the time series data detected in at least one of the plurality of intervals.

[0021] The feature amount calculation unit 18 calculates a feature amount relating to the operation of the target device based on the operation data extracted by the data extraction unit 17.

[0022] The state diagnosis unit 19 diagnoses the state of the target device based on the feature amount calculated by the feature amount calculation unit 18 .

[0023] The output unit 20 outputs the diagnosis result by the status diagnosis unit 19. The diagnosis result by the status diagnosis unit 19 includes, for example, whether the target device is normal or abnormal.

[0024] Fig. 2 shows an example of a hardware configuration of the information processing device 10. As shown in Fig. 2, the information processing device 10 includes a CPU 101, a non-volatile memory 102, a main memory 103, an input device 104, a display device 105, a communication device 106, and the like.

[0025] The CPU 101 is a hardware processor that controls the operation of each component in the information processing device 10. The CPU 101 may be composed of a single processor or may be composed of multiple processors. The CPU 101 executes various programs loaded from a non-volatile memory 102, which is a storage device, to a main memory 103. The programs executed by the CPU 101 include an operating system (OS) and various application programs, etc.

[0026] The input device 104 is a device configured to input various data and includes, for example, a mouse and a keyboard. The display device 105 is a device configured to display various data and includes, for example, a display. The communication device 106 is a device configured to execute, for example, wired or wireless communication with an external device.

[0027] Although only the non-volatile memory 102 and the main memory 103 are shown in FIG. 2, the information processing device 10 may further include other storage devices such as a hard disk drive (HDD) and a solid state drive (SSD).

[0028] In this embodiment, some or all of the units 11 to 20 shown in Fig. 1 are realized by causing a CPU 101 shown in Fig. 2 to execute a predetermined program, that is, by software. This program may be downloaded to the information processing device 10 via a network, or may be stored in a storage medium and distributed.

[0029] Here, it has been described that some or all of the units 11 to 20 are realized by software, but some or all of the units 11 to 20 may be realized by hardware such as an IC (Integrated Circuit), or may be realized by a configuration that combines software and hardware.

[0030] Hereinafter, an example of a processing procedure of the information processing device 10 according to the present embodiment will be described with reference to the flowchart of FIG.

[0031] In the following description, the subject device will be described as an electromagnetic brake mounted on an elevator. Note that an electromagnetic brake is a device that operates to apply a brake by an electromagnetic force generated by supplying a current or voltage.

[0032] The data input unit 11 inputs time series data (step S1). When the target device is an electromagnetic brake as described above, the time series data input in step S1 is, for example, data representing the waveform of the current supplied to the electromagnetic brake (brake current waveform). In this case, the time series data is input, for example, from a current sensor that measures the current supplied to the electromagnetic brake. Note that, in step S1, time series data designated using, for example, the input device 104 may be input from among the time series data held (accumulated) in advance.

[0033] Here, Fig. 4 shows an example of the time series data input in step S1. As shown in Fig. 4, the time series data represents a brake current waveform including current values ​​measured at each of a plurality of points in time.

[0034] In the following explanation, the time series data is assumed to be data representing a brake current waveform, but the time series data input in step S1 may also be data representing a waveform of the voltage supplied to the electromagnetic brake (brake voltage waveform).

[0035] When the process of step S1 is executed, the preprocessing unit 13 executes preprocessing on the time series data input in step S1 (step S2). The preprocessing executed in step S2 may be, for example, a process for removing noise occurring in the time series data. Specifically, the preprocessing may be, for example, a moving average filter, LOESS smoothing, Hodrick-Prescott filter, or the like. By executing the process of step S2, the time series data is processed into data with reduced noise.

[0036] In this embodiment, pre-processing is performed to remove noise from the time-series data, but if it is assumed that the time-series data contains only a small amount of noise, the process of step S2 may be omitted. In other words, whether or not to perform pre-processing may be determined according to, for example, the environment in which the electromagnetic brake is installed.

[0037] Here, it is assumed that the parameters input by the parameter input unit 12 are held in the extreme point identifying unit 14. In this case, the extreme point identifying unit 14 identifies a plurality of extreme points of the time series data by using the parameters held in the extreme point identifying unit 14 (step S3).

[0038] The process of step S3 will be described below. First, the length of the time series data (the length of time during which the current value is measured) is denoted by T, and the time series data is denoted by x. Furthermore, the time points at which the current value is measured in the time series data x are denoted by t1, t2, ..., t T At each time point t1, t2, ..., t T The current values ​​measured at x1, x2, …, x T Let L be a parameter for identifying an extreme point. This parameter L corresponds to the parameter input by the parameter input unit 12 (the parameter held in the extreme point identifying unit 14). The parameter L represents a time range. The parameter L is determined in advance by analyzing past time series data actually obtained so that an extreme point can be appropriately identified.

[0039] Here, at each of the above points in time t1, t2, ..., t T The kth time point t k At the time t k The current value measured in the range of parameter L around x (i.e., partial time series data) is k-L ,…,x k ,…,x k+L This partial time series data (current value x k-L ,…,x k ,…,x k+L ) where the current value x k When the current value x is the maximum value, k is regarded as the maximum value, and time t k can be identified as an extreme point (maximum point). On the other hand, the current value x k-L ,…,x k,…,x k+L ) where the current value x k When the current value x is the minimum value, k is regarded as the minimum value, and time t k can be identified as an extreme point (minimum point).

[0040] Here, time t k In the above, the process is performed by focusing on t1, t2, ..., t T By performing this for all of the above, it is possible to identify all extreme points present in the time series data (i.e., extreme points in the entire time series data).

[0041] FIG. 5 shows an example of a number of extreme points identified in the time series data shown in FIG. 4. As shown in FIG. 5, for example, at time t b The current value x measured at b is the time t b Since the current value is larger than the other current values ​​in the range of parameter L before and after the time t b is specified as an extreme point (maximum point). c , t e and t g is also identified as an extreme point.

[0042] In addition, since minute electromagnetic noise occurs in the time series data when measuring the current, extreme points are densely identified in a section (period) where a steady current is supplied, such as from time t1 to ta.

[0043] On the other hand, the current value changes drastically at time t a ~t b In such an interval (period), the influence of electromagnetic noise is small enough to be negligible, and therefore extreme points are difficult to identify (that is, extreme points are sparsely identified).

[0044] It should be noted that the method of identifying extreme points described in this embodiment is merely an example, and the extreme points may be identified by other methods.

[0045] 3, the distance calculation unit 15 calculates the distance between the multiple extreme points identified in step S3 (step S4). In step S4, the distance between two adjacent extreme points among the multiple extreme points identified in the time series data is calculated.

[0046] There are various definitions for the distance between extreme points. For example, the distance between extreme points at time t a and t b If t is an extreme point, the distance between two extreme points calculated in step S4 is t b -t a It shall be calculated as follows:

[0047] In this case, the distance between the two extreme points is a and time t b In other words, it may be the number of current values ​​measured during the period between time t a The i-th current value is measured at time t b If the j-th current value is measured at j, the distance between extreme points may be calculated by ji.

[0048] In addition, at time t a etc. may represent the time when the current value was measured, or may represent the order in which the current value was measured in the time-series data.

[0049] Here, an example of the distance between the multiple extreme points described in FIG. 5 will be described with reference to FIG. 6. In FIG. 6, for example, the time t a and t b With respect to the distance between the extreme points, t b -t a is time t a Also, for example, the time t b and t c With respect to the distance between the extreme points, t c-t b is time t b Furthermore, for example, the time t c and t d With respect to the distance between the extreme points, t d -t c is time t c Also, for example, the time t e and t f With respect to the distance between the extreme points, t f -t e is time t e Furthermore, for example, the time t f and t g With respect to the distance between the extreme points, t g -t f is time t f Also, for example, the time t g and t h With respect to the distance between the extreme points, t h -t g is time t g Although detailed explanation is omitted, the same applies to the distances between other extreme points.

[0050] In the example shown in FIG. 6, it can be seen that there are four peaks in the distance between extreme points. Specifically, the four peaks (i.e., the top four distances) occur at time t a The time t is plotted corresponding to a and t b Distance between time t c The time t is plotted against c and t d Distance between time t e The time t is plotted against e and t f Distance between time t g The time t is plotted corresponding to g and t h It is the distance between.

[0051] Returning to FIG. 3 again, the data dividing unit 16 divides the time series data based on the (peak of) the distance calculated in step S4 (step S5).

[0052] Based on the result of dividing the time series data in step S5, the data extraction unit 17 extracts operation data (partial time series data) that indicate a brake attraction operation and a brake release operation as characteristic operations of the electromagnetic brake (step S6). Note that the brake attraction operation refers to an operation of applying the brake by, for example, starting the supply of current (or voltage). On the other hand, the brake release operation refers to an operation of releasing the brake by, for example, stopping the supply of current (or voltage).

[0053] Here, the processes in steps S5 and S6 will be described with reference to Fig. 7. Fig. 7 shows the correspondence relationship between the time series data shown in Fig. 4 and the distances between the multiple extreme points shown in Fig. 6.

[0054] As shown in FIG. 7, the data dividing unit 16 divides the time series data using four peaks (i.e., the extreme points for which the top four distances are calculated) among the distances between the above-mentioned multiple extreme points as division points. In this case, the time series data is divided into four peaks from time t1 to time t a Partial time series data D1 representing the waveform of the current (value) measured in the section up to time t a From time t c Partial time series data D2 representing the waveform of the current (value) measured in the section up to time t c From time t e Partial time series data D3 representing the waveform of the current (value) measured in the section up to time t e From time t g Partial time series data D4 representing the waveform of the current (value) measured in the section up to time t g From time t T The data is divided into partial time series data D5 representing the waveform of the current (value) measured in the section up to

[0055] In this case, the data extracting unit 17 extracts the second partial time series data D2 and the fourth partial time series data D4 from the five partial time series data D1 to D5 into which the time series data is divided as described above. The partial time series data D2 corresponds to the operation data representing the brake attraction operation waveform. The partial time series data D4 corresponds to the operation data representing the brake release operation waveform.

[0056] In this case, an electromagnetic brake is assumed as the target device, and in the case of time series data representing the brake current waveform of the electromagnetic brake, it is assumed that it is predetermined to extract the second and fourth partial time series data as operation data (brake attraction operation waveform and brake release operation waveform) as described above. That is, in this embodiment, it is assumed that it is predetermined which partial time series data should be extracted as operation data from among the multiple partial time series data obtained by dividing the time series data as described above, depending on, for example, the type of the time series data (target device) or the like.

[0057] Returning to FIG. 3, the feature amount calculation unit 18 calculates a feature amount related to the operation of the electromagnetic brake based on the operation data extracted in step S6 (step S7).

[0058] When the partial time series data D2 is extracted as the operation data as described above, the feature amount calculation unit 18 calculates the feature amount of the brake attraction operation waveform represented by the partial time series data D2. The feature amount of the brake attraction operation waveform includes, for example, the length of the brake attraction operation waveform. a From time t c If the waveform of the current measured in the section up to c -t a The length of the brake attraction operation waveform calculated in this manner corresponds to the brake attraction operation time (that is, the time from when the supply of current to the electromagnetic brake starts until the brake acts).

[0059] Similarly, when partial time series data D4 is extracted as the operation data as described above, the feature amount calculation unit 18 calculates the feature amount of the brake release operation waveform represented by the partial time series data D4. The feature amount of the brake release operation waveform includes, for example, the length of the brake release operation waveform. e From time t g If the waveform of the current measured in the section up to g -t e The length of the brake release operation waveform calculated in this manner corresponds to the brake release operation time (that is, the time from when the supply of current to the electromagnetic brake is stopped to when the brake action is released).

[0060] The feature calculated in step S7 may be any feature that is significant for diagnosing the state of the electromagnetic brake described below, and may be, for example, the amount of change in current value (the difference between the maximum value and the minimum value) in the brake attraction operation waveform and the brake release operation waveform.

[0061] When the process of step S7 is executed, the state diagnosis unit 19 diagnoses the state of the electromagnetic brake based on the feature amounts (brake attraction operation time and brake release operation time) calculated in step S7 (step S8).

[0062] Here, the state of the electromagnetic brake can be diagnosed based on a predetermined calculation result for the feature amount calculated in step S7. Specifically, for example, assuming that the processes of steps S1 to S7 are repeatedly executed within a predetermined period (for example, within one day), the state diagnosis unit 19 can calculate the degree of variation in the brake attraction operation time and the brake release operation time calculated within that period, and diagnose the state of the electromagnetic brake based on the calculation result. According to this, for example, when there is a variation exceeding a threshold value in at least one of the brake attraction operation time and the brake release operation time, the state diagnosis unit 19 can diagnose that the state of the electromagnetic brake is abnormal. On the other hand, for example, when there is no variation exceeding a threshold value in both the brake attraction operation time and the brake release operation time, the state diagnosis unit 19 can diagnose that the state of the electromagnetic brake is normal. The degree of variation in the brake attraction operation time and the brake release operation time can be calculated using, for example, a standard deviation or the like.

[0063] The process of step S8 described here is an example, and other processes may be performed to diagnose the state of the electromagnetic brake. Specifically, the state of the electromagnetic brake may be diagnosed by comparing the feature values ​​(e.g., the brake attraction operation time and the brake release operation time) calculated in step S7 with a threshold value (i.e., determining whether the brake attraction operation time and the brake release operation time are long or short enough to say that the electromagnetic brake is abnormal).

[0064] The process of step S8 may be performed by using a learning model generated based on a technology such as artificial intelligence (AI), machine learning, or deep learning. Specifically, by generating a learning model constructed to diagnose (estimate) the state of the equipment by inputting the operation data, for example, by having the learning model learn pre-prepared learning data including a feature amount calculated based on operation data and the state (abnormal or normal, etc.) of the electromagnetic brake corresponding to the operation data, it becomes possible to obtain a diagnosis result of the state of the equipment output from the learning model by inputting the feature amount calculated in step S7 into the learning model. Note that the learning model may be constructed to diagnose the state of the equipment by inputting operation data instead of the feature amount.

[0065] When the process of step S8 is executed, the output unit 20 outputs the process result of step S8 (i.e., the diagnosis result of the state of the electromagnetic brake) (step S9). The diagnosis result in step S9 may be output to the display device 105 for display on the display device 105, for example, or may be output to the communication device 106 for transmission to an external device.

[0066] As described above, the information processing device 10 according to this embodiment inputs time-series data of physical quantities measured when the target equipment is operating, identifies multiple extreme points of the time-series data, calculates distances between the multiple extreme points in the time-series data, divides the time-series data based on the calculated distances, and extracts operation data representing characteristic operations of the target equipment from the divided time-series data.

[0067] Here, in order to diagnose the state of an electromagnetic brake mounted on an elevator, which is an example of the above-mentioned target equipment, it is considered to use time series data representing a brake current waveform measured when the electromagnetic brake operates. In this case, in order to properly diagnose the state of the electromagnetic brake, it is necessary to extract partial time series data (brake attraction operation waveform and brake release operation waveform) representing characteristic operations of the electromagnetic brake from the time series data (brake current waveform). However, the current value and the number of extreme points in the brake current waveform (i.e., the characteristics of the electromagnetic brake) may change due to periodic adjustment work (maintenance work) for the electromagnetic brake. It is difficult to properly extract the brake attraction operation waveform and brake release operation waveform (start time and end time) using the same predetermined threshold value from the amount of change in the current value in the brake current waveform, which differs before and after such adjustment.

[0068] In contrast to this, in this embodiment, even if the current value, etc. in the brake current waveform changes before and after the adjustment as described above, the characteristic that there are four peaks in the distance between multiple extreme points does not change before and after the adjustment (in other words, it does not change even if the characteristics of the electromagnetic brake change), and by focusing on this point, a configuration is adopted that extracts the brake attraction operation waveform and the brake release operation waveform, making it possible to obtain data useful for diagnosing the condition of the equipment.

[0069] Furthermore, in this embodiment, by configuring the diagnosis of the state of the electromagnetic brake based on the brake attraction operation waveform and brake release operation waveform extracted as described above (feature quantities calculated based on them), it becomes possible to diagnose the state of the electromagnetic brake with high accuracy even if the characteristics of the electromagnetic brake have changed due to adjustment work (maintenance work).

[0070] Furthermore, in this embodiment, a pre-processing may be performed to remove noise from the time series data, which reduces the effect of noise in the time series data and makes it possible to more appropriately extract the brake attraction operation waveform and the brake release operation waveform from the time series data.

[0071] In this embodiment, the target equipment has been mainly described as an electromagnetic brake mounted on an elevator, but this embodiment may also be realized as an information processing system (elevator system) including an elevator equipped with the electromagnetic brake and an information processing device 10.

[0072] Furthermore, in this embodiment, the case where the brake attraction operation waveform and brake release operation waveform of the electromagnetic brake are extracted from time series data representing the waveform of the current (or voltage) supplied to the electromagnetic brake (i.e., the information processing device 10 is used to diagnose the state of the electromagnetic brake) has been mainly described, but the information processing device 10 according to this embodiment may be used to diagnose the state of equipment other than an electromagnetic brake as long as it is configured to extract operation data representing the characteristic operation of the equipment from time series data of physical quantities detected when the equipment operates. Note that the physical quantities detected when the equipment operates may be current (value) or voltage (value), etc., but may also be other physical quantities (for example, temperature, etc.).

[0073] 1, the information processing device 10 may be configured to omit at least some of the functional units 11 to 20. Specifically, the information processing device 10 may have only a functional unit that extracts operation data used to diagnose the state of the device, and the functional unit that diagnoses the state of the device may be disposed outside the information processing device 10.

[0074] Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents described in the claims, as well as in the scope and spirit of the invention.

[0075] The following supplementary notes are further disclosed regarding the above-described embodiment. [1] An information processing device comprising: an extraction means for extracting operation data representing a characteristic operation of a device from time series data of a physical quantity measured while the device is operating, based on a distance between a plurality of extreme value points of the time series data of the physical quantity measured while the device is operating. [2] The information processing device according to [1], wherein the time series data is data representing a waveform of a current or voltage supplied to the device. [3] The information processing device according to [1] or [2], wherein the device includes an electromagnetic brake mounted on an elevator. [4] The information processing device according to [3], wherein the operation data is data representing a brake attraction operation waveform and a brake release operation waveform of the electromagnetic brake. [5] The time series data is divided based on the extreme points for which top four distances among the distances between the plurality of extreme points are calculated; The motion data is extracted from the divided time series data. The information processing device according to any one of [1] to [4]. [6] a pre-processing unit that performs pre-processing on the time series data to remove noise occurring in the time series data; A means for identifying a plurality of extreme points of the preprocessed time series data; The information processing device according to any one of [1] to [5], further comprising: [7] The information processing device according to any one of [1] to [6], further comprising an identification means for identifying the first point in time as the extreme point when a physical quantity measured at the first point in time is greater than a physical quantity measured at each of a plurality of second point in time located before and after the first point in the time series data, and when a physical quantity measured at the first point in time is smaller than a physical quantity measured at each of the plurality of second point in time. [8] The information processing device according to any one of [1] to [7], further comprising a diagnostic means for diagnosing a state of the device based on the extracted operational data. [9] The method further comprises: calculating a feature amount relating to the operation of the device based on the extracted operation data; The diagnostic means diagnoses the state of the device based on the calculated feature amount. [8] An information processing device according to the present invention.

[10] An elevator equipped with an electromagnetic brake; An information processing device used to diagnose the state of the electromagnetic brake; Equipped with The information processing device includes an extraction unit that extracts operation data representing a characteristic operation of the electromagnetic brake from the time series data based on distances between a plurality of extreme value points of the time series data of a physical quantity measured when the electromagnetic brake is operated. Information processing system.

[11] An information processing method comprising: extracting operation data representing a characteristic operation of an equipment from time series data of a physical quantity measured while the equipment is operating, based on a distance between a plurality of extreme value points of the time series data of the physical quantity.

[12] A program for causing a computer to function as an extraction means for extracting operation data representing a characteristic operation of an equipment from time series data of a physical quantity measured while the equipment is operating, based on a distance between multiple extreme points of the time series data of the physical quantity. [Explanation of symbols]

[0076] 10...information processing device, 11...data input section, 12...parameter input section, 13...preprocessing section, 14...extreme value point identification section, 15...distance calculation section, 16...data division section, 17...data extraction section, 18...feature calculation section, 19...condition diagnosis section, 20...output section, 101...CPU, 102...non-volatile memory, 103...main memory, 104...input device, 105...display device, 106...communication device.

Claims

1. An information processing device comprising: an extraction means for extracting operation data representing a characteristic operation of a device from time series data of a physical quantity measured while the device is operating, based on a distance between a plurality of extreme value points of the time series data of the physical quantity measured while the device is operating.

2. 2. The information processing apparatus according to claim 1, wherein the time series data is data representing a waveform of a current or a voltage supplied to the device.

3. The information processing apparatus according to claim 2 , wherein the device includes an electromagnetic brake mounted on an elevator.

4. 4. The information processing apparatus according to claim 3, wherein the operation data is data representing a brake attraction operation waveform and a brake release operation waveform of the electromagnetic brake.

5. The time series data is divided based on the extreme points for which the top four distances among the distances between the plurality of extreme points are calculated; The motion data is extracted from the divided time series data.

5. The information processing device according to claim 4.

6. a pre-processing unit that performs pre-processing on the time series data to remove noise occurring in the time series data; A means for identifying a plurality of extreme points of the preprocessed time series data; The information processing apparatus according to claim 1 , further comprising:

7. 2. The information processing device according to claim 1, further comprising an identification means for identifying the first point in time as the extreme point when a physical quantity measured at the first point in time is greater than a physical quantity measured at each of a plurality of second point in time located before and after the first point in time on the time series data, and when a physical quantity measured at the first point in time is smaller than a physical quantity measured at each of the plurality of second point in time.

8. 8. The information processing apparatus according to claim 1, further comprising a diagnostic means for diagnosing a state of the device based on the extracted operation data.

9. The method further comprises: calculating a feature amount relating to the operation of the device based on the extracted operation data; The diagnostic means diagnoses the state of the device based on the calculated feature amount.

9. The information processing device according to claim 8.

10. An elevator equipped with an electromagnetic brake; An information processing device used to diagnose the state of the electromagnetic brake; Equipped with The information processing device includes an extraction unit that extracts operation data representing a characteristic operation of the electromagnetic brake from the time series data based on distances between a plurality of extreme value points of the time series data of a physical quantity measured when the electromagnetic brake is operated. Information processing system.

11. An information processing method comprising: extracting operation data representing a characteristic operation of an equipment from time series data of a physical quantity measured while the equipment is operating, based on a distance between a plurality of extreme value points of the time series data of the physical quantity.

12. A program for causing a computer to function as an extraction means for extracting operation data representing a characteristic operation of an equipment from time series data of a physical quantity measured while the equipment is operating, based on a distance between multiple extreme points of the time series data of the physical quantity.

Images