Abnormality sign diagnosis device and abnormality sign diagnosis method

Abstract

To detect an abnormality sign in a load device driven by an electric motor.SOLUTION: A facility 10 is provided with an electric motor 16 that is driven with current supplied from a drive circuit 14, a control circuit 12 that outputs a control signal MC to the drive circuit 14 on the basis of a command value SC for commanding the operation state of the electric motor 16, and a load device 18 that is driven by the electric motor 16. An abnormality sign diagnosis device 30 is provided with an operation monitoring unit 32 that acquires from the facility 10 the command value SC and a current value IM of current outputted from the drive circuit 14, and records the values in an operation database 52, a correlation learning unit 34 that learns a correlation between the command value SC and the current value IM and acquires a learning result 54, and a sign diagnosis unit 36 that diagnoses the presence / absence of an abnormality sign in the facility 10 on the basis of the command value SC, the current value IM, and the learning result 54 and records the diagnosis result in a diagnosis result database 56.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an abnormality sign diagnostic device and an abnormality sign diagnostic method. [Background technology]

[0002] As background art in this technical field, the abstract of Patent Document 1 listed below states that "the motor control device according to the present invention comprises a controller that controls the AC power supplied to the motor by switching-controlling an inverter that performs power conversion in response to a torque command, and a current sensor that detects phase currents flowing in an AC cable connecting the motor and the inverter, and the controller acquires the phase currents detected by the current sensor as phase current detection values, calculates phase current command values ​​for the motor based on the torque command, and has a break detection unit that determines whether or not there is a break in the AC cable for each phase based on the transition results of the difference value between the phase current command value and the phase current detection value for each phase." [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2019 / 155585 Summary of the Invention [Problem to be solved by the invention]

[0004] Generally, electric motors are used to rotate and drive various load devices. In a rolling mill, which is an example of a load device, rolls are driven from the electric motor via a drive shaft, a transmission mechanism, and other paths to roll steel sheets, etc. Therefore, not only a break in the power cable but also a mechanical abnormality may occur somewhere between the electric motor and the rolls. However, the above-mentioned Patent Document 1 does not specifically mention detecting signs of an abnormality in a load device driven by an electric motor. The present invention has been made in view of the above-mentioned circumstances, and has an object to provide an abnormality sign diagnosis device and an abnormality sign diagnosis method that can detect abnormality signs in a load device driven by an electric motor. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, the abnormality sign diagnosis device of the present invention is characterized by comprising: an operation monitoring unit that acquires from equipment including an electric motor driven by a current supplied from a drive circuit, a control circuit that outputs a control signal to the drive circuit based on a command value that commands the operating state of the electric motor, and a load device driven by the electric motor, the command value and the current value of the current output by the drive circuit, and records the acquired value in an operation database; a correlation learning unit that learns the correlation between the command value and the current value and acquires the learning results; and a sign diagnosis unit that diagnoses the presence or absence of an abnormality sign in the equipment based on the command value, the current value, and the learning results, and records the diagnosis results in a diagnosis result database. [Effects of the Invention]

[0006] According to the present invention, it is possible to detect a sign of abnormality in a load device driven by an electric motor. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a block diagram of a rolling system according to a first embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the contents of an operation database. [Figure 3] FIG. 3 is a diagram showing an example of the contents of a correlation database applied to the first embodiment. [Figure 4] FIG. 1 is a block diagram of a computer. [Figure 5] FIG. 11 is a diagram showing an example of the contents of a correlation database applied to the second embodiment. [Figure 6] FIG. 10 is a block diagram of a rolling system according to a third embodiment. [Figure 7]FIG. 11 is a diagram showing an example of the contents of a correlation database applied to the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0008] [First embodiment] FIG. 1 is a block diagram of a rolling system 1 according to a first embodiment. The rolling system 1 includes rolling equipment 10 (equipment), an abnormality sign diagnosis device 30 (computer), and a database unit 50. The rolling equipment 10 includes a command value generating unit 11, a control circuit 12, a drive circuit 14, a current sensor 15, an electric motor 16, a roll unit 18 (load device), and a drive power supply unit 20. The abnormality sign diagnosis device 30 includes an operation monitoring unit 32 (operation monitoring process), a correlation learning unit 34 (correlation learning process), and a sign diagnosis unit 36 ​​(sign diagnosis process). The database unit 50 includes an operation database 52, a correlation database 54 (learning results), and a diagnosis result database 56.

[0009] Although the detailed configuration of the roll unit 18 in the rolling equipment 10 is not shown in the drawings, the roll unit 18 includes a drive shaft, a speed change mechanism, multiple rolling rolls, etc., and rolls metal sheets such as steel sheets. An electric motor 16 drives the multiple rolls to rotate via a speed change mechanism in the roll unit 18. A drive circuit 14 is, for example, an inverter equipped with switching elements, and supplies AC current to the electric motor 16. A control circuit 12 outputs a control signal MC to the drive circuit 14. This control signal MC is, for example, a signal that commands the on / off state of the above-mentioned switching elements.

[0010] The command value generating unit 11 outputs a speed command value SC (command value) that commands the speed of the electric motor 16 in accordance with the rolling process. The above-mentioned control circuit 12 sets the content of the above-mentioned control signal MC based on the speed command value SC. For example, the control circuit 12 sets the on / off frequency of the switching element in accordance with the speed command value SC. The current sensor 15 measures the current supplied from the drive circuit 14 to the electric motor 16 and outputs the measurement result as a current value IM.

[0011] FIG. 2 is a diagram showing an example of the contents of the operation database 52. As shown in FIG. The operation database 52 is a database having a plurality of records (rows). Each record represents a measurement result for each predetermined sampling period, and is generated in chronological order from top to bottom. Each record includes a speed command value SC and a current value IM. The speed command value SC is measured in units of, for example, "rpm," and the current value IM is measured in units of, for example, "A."

[0012] FIG. 3 is a diagram showing an example of the contents of the correlation database 54 applied to the first embodiment. The correlation database 54 is a database having multiple records (rows), and each record includes a reference command value SCS, a reference current value IMS, a correlation degree CD, and a current value allowable deviation ΔIM. The reference command value SCS is a representative value of the speed command value SC that appears in the operation database 52 (see FIG. 2). The reference current value IMS is a reference value of the current value IM relative to this reference command value SCS.

[0013] The allowable current deviation ΔIM is the deviation between the reference current value IMS and the measured current value IM, and indicates the normal range of the current value IM in amperes. In other words, if the deviation exceeds the allowable current deviation ΔIM, it indicates an abnormal state or a state predicting an abnormality.

[0014] Here, an abnormal state refers to a state in which the operation of the rolling equipment 10 is being affected. A pre-abnormal state refers to a state in which the operation of the rolling equipment 10 is not being affected, but which is considered to have a high tendency to become an abnormal state in the future. A normal state refers to a state in which no pre-abnormal signs are occurring. The correlation degree CD represents the degree of correlation between the reference command value SCS and the reference current value IMS, and in the illustrated example, is expressed in four levels: "High," "Middle," "Low," and "None." When the correlation degree CD is "High," this indicates that the allowable current deviation ΔIM from the reference current value IMS is relatively small. "Middle" indicates that the allowable current deviation ΔIM is somewhat large, and "Low" indicates that it is even larger. When the correlation degree CD is "None," this indicates that the correlation between the reference current value IMS and the reference command value SCS is ignored. In this case, the allowable current deviation ΔIM is undefined. The correlation degree CD does not necessarily have to be included in the correlation database 54.

[0015] Returning to FIG. 1 , the operation monitoring unit 32 in the abnormality sign diagnosis device 30 stores time-series data of the speed command value SC and the current value IM in the operation database 52. The correlation learning unit 34 performs machine learning on the correlation between the speed command value SC and the current value IM under normal conditions from the contents of the operation database 52, and obtains the resulting machine learning data (not shown). Then, based on the machine learning data, a correlation database 54 is generated. Note that the contents of the correlation database 54 do not need to be the exact results obtained by machine learning; for example, the user may modify the contents of the correlation database 54 as needed.

[0016] The sign diagnosis unit 36 ​​compares the speed command value SC and current value IM supplied from the rolling facility 10 with the contents of the correlation database 54. As a result, the sign diagnosis unit 36 ​​detects that some kind of abnormality sign has occurred when there is a deviation between the current value IM and the reference current value IMS that exceeds the current value allowable deviation ΔIM. Then, the sign diagnosis unit 36 ​​stores the diagnosis result indicating whether or not an abnormality sign has occurred in the diagnosis result database 56.

[0017] For example, according to record 52a in FIG. 2, the speed command value SC is 2700 rpm, and the current value IM is 3.8 A. On the other hand, according to record 54a in FIG. 3, the reference current value IMS is 4.9 A, and the current value allowable deviation ΔIM is ±1.0 A, relative to the reference command value SCS of 2700 rpm. In other words, the normal range for the current value IM is 4.8 to 5.0 A, and record 52a falls outside that range. This causes the predictive diagnostic unit 36 ​​to detect that some kind of abnormality predictive value has occurred, and stores this information in the diagnostic result database 56.

[0018] 4 is a block diagram of the computer 980. The abnormality sign diagnosis device 30 shown in the figure includes one or more computers 980 shown in FIG. 4, a computer 980 includes a CPU 981, a storage unit 982, a communication I / F (interface) 983, an input / output I / F 984, and a media I / F 985. Here, the storage unit 982 includes a RAM 982a, a ROM 982b, and an SSD (Solid State Drive) 982c.

[0019] The communication I / F 983 is connected to a communication circuit 986. The input / output I / F 984 is connected to an input / output device 987. The media I / F 985 reads and writes data from a recording medium 988. The ROM 982b stores an IPL (Initial Program Loader) and the like executed by the CPU. The SSD 982c stores application programs, various data, and the like. The CPU 981 executes application programs and the like loaded from the SSD 982c to the RAM 982a, thereby realizing various functions. The interior of the abnormality sign diagnosis device 30 shown in FIG. 1 is primarily shown as blocks representing functions realized by application programs and the like.

[0020] [Second embodiment] Next, a rolling system according to a second embodiment will be described. The configuration of the rolling system according to the second embodiment is the same as that of the rolling system 1 according to the first embodiment (see FIGS. 1 to 4), except for the points described below. In the description of each embodiment, parts corresponding to parts in the other embodiments described above are given the same reference numerals, and their description may be omitted. In the second embodiment, a correlation database 62 shown in FIG. 5 is applied instead of the correlation database 54 (see FIG. 4) in the first embodiment.

[0021] FIG. 5 is a diagram showing an example of the contents of the correlation database 62 applied to the second embodiment. The correlation database 62 is a database having a plurality of records (rows), and similarly to the correlation database 54 of the first embodiment (see FIG. 3), each record includes a reference command value SCS, a reference current value IMS, a correlation degree CD, and an allowable current deviation ΔIM. Furthermore, in the correlation database 62 of this embodiment, each record includes a material type MT. The material type MT is information that defines the quality and thickness of the plate material (not shown) to be rolled. Furthermore, although the operation database of this embodiment is not shown, each record of the operation database 52 of the first embodiment (see FIG. 2) includes a material type MT similar to that of the correlation database 62.

[0022] Generally, when the material and thickness of the plate material change, the reference current value IMS and the allowable current deviation ΔIM also change. Therefore, in this embodiment, the predictive diagnostic unit 36 ​​(see FIG. 1) compares the records in the operation database 52 with the records in the correlation database 62 that have the corresponding material type MT to determine whether or not there is an abnormality predictive value. This enables more accurate abnormality predictive diagnostics.

[0023] [Third embodiment] FIG. 6 is a block diagram of a rolling system 3 according to the third embodiment. The rolling system 3 according to the third embodiment includes a rolling facility 10, an abnormality sign diagnosis device 30, and a database unit 50, similar to the rolling system 1 according to the first embodiment (see FIG. 1). The rolling equipment 10 includes the same elements as those in the first embodiment, and further includes a plurality (n pieces) of vibration sensors 22-1 to 22-n. The vibration sensors 22-1 to 22-n detect vibrations in the electric motor 16 and the roll unit 18, and output the results as vibration values ​​VM-1 to VM-n. These vibration values ​​VM-1 to VM-n may be collectively referred to as "vibration value VM."

[0024] Moreover, the abnormality sign diagnosing device 30 has the same elements as those in the first embodiment, and further has a cause diagnosing unit 38. Moreover, the database unit 50 has a correlation database 64 instead of the correlation database 54 in the first embodiment. Moreover, although the operation database 52 in this embodiment is not shown, a material type MT and a vibration value VM are included for each record in the operation database 52 (see FIG. 2) in the first embodiment. Except for the points mentioned above, the configuration of the rolling system 3 according to the third embodiment is similar to that of the rolling system 1 according to the first embodiment (see FIGS. 1 to 4).

[0025] FIG. 7 is a diagram showing an example of the contents of the correlation database 64 applied to the third embodiment. The correlation database 64 is a database having a plurality of records (rows), and similarly to the correlation database 54 of the first embodiment (see FIG. 3), each record includes a reference command value SCS, a reference current value IMS, a correlation degree CD, and an allowable current deviation ΔIM. Furthermore, in the correlation database 62 of this embodiment, each record includes a material type MT and a reference vibration value VMS. The content of the material type MT is the same as that of the second embodiment described above.

[0026] Furthermore, the reference vibration value VMS includes reference vibration values ​​VMS-1 to VMS-n which are reference values ​​for each of the vibration values ​​VM-1 to VM-n described above. These reference vibration values ​​VMS-1 to VMS-n are representative values ​​(for example, median or average value) of the vibration values ​​VM-1 to VM-n when the rolling equipment 10 is in a normal state.

[0027] As described above, the sign diagnosis unit 36 ​​determines the presence or absence of an abnormality sign by comparing the record in the operation database 52 with the corresponding record in the correlation database 64. Then, when the occurrence of an abnormality sign is detected by the sign diagnosis unit 36, the cause diagnosis unit 38 compares the vibration value VM in the corresponding record in the operation database 52 with the reference vibration value VMS in the record in the correlation database 64.

[0028] Here, let us assume that there is a large deviation between vibration value VM-i (where 1≦i≦n) among vibration values ​​VM-1 to VM-n and the corresponding reference vibration value VMS-i. Then, the cause diagnosing unit 38 determines that the installation location of the vibration sensor 22-i corresponding to the vibration value VM-i is likely to be the cause of the occurrence of the abnormality sign. As a result, according to this embodiment, the cause of the occurrence of the abnormality sign can be quickly found.

[0029] [Variations] The present invention is not limited to the above-described embodiments and various modifications are possible. The above-described embodiments are provided as examples to facilitate understanding of the present invention and are not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. It is also possible to delete part of the configuration of each embodiment, or to add or replace other configurations. Furthermore, the control lines and information lines shown in the figures are those considered necessary for explanation, and do not necessarily represent all control lines and information lines necessary for the product. In reality, it is acceptable to consider that almost all components are interconnected. Possible modifications of the above-described embodiments include, for example, the following:

[0030] (1) In the above embodiments, the speed command value SC is used as a specific example of the command value. However, the command value is not limited to the speed command value SC, and may be another command value that commands the operating state of the electric motor 16, such as a torque command value.

[0031] (2) Since the hardware of the abnormality sign diagnosis device 30 in each of the above embodiments can be realized by a general computer, the programs for executing the various processes described above may be stored on a storage medium (a computer-readable storage medium on which the programs are recorded) or distributed via a transmission path.

[0032] (3) In the above embodiments, the various processes described above are described as software processes using programs, but some or all of them may be replaced with hardware processes using ASICs (Application Specific Integrated Circuits) or FPGAs (Field Programmable Gate Arrays), etc.

[0033] (4) The various processes executed in each of the above embodiments may be executed by a server computer via a network (not shown), and the various data stored in the above embodiments may also be stored in the server computer.

[0034] (5) Furthermore, the abnormality sign diagnosis device 30 in each of the above embodiments can be applied not only to the rolling facility 10 but also to various facilities such as power generation facilities and production facilities. As a result, in these facilities, excellent performance can be exhibited according to the application.

[0035] [Effects of the embodiment] As described above, according to the embodiment, the abnormality sign diagnosis device 30 includes the operation monitoring unit 32 that acquires the command value (SC) and the current value IM of the current output by the drive circuit 14 and records them in the operation database 52, the correlation learning unit 34 that learns the correlation between the command value (SC) and the current value IM and acquires the learning results (54, 62, 68), and the sign diagnosis unit 36 ​​that diagnoses the presence or absence of an abnormality sign in the equipment (10) based on the command value (SC), the current value IM, and the learning results (54, 62, 68) and records the diagnosis results in the diagnosis result database 56. This makes it possible to detect the presence or absence of an abnormality sign in the load device (18).

[0036] Furthermore, as in the second embodiment, it is more preferable that the correlation learning unit 34 learns the correlation between the material type MT, which is the material and thickness of the plate material, the command value (SC), and the current value IM and acquires the learning results (62, 68), and the sign diagnosing unit 36 ​​diagnoses the presence or absence of an abnormality sign in the equipment (10) based on the command value (SC), the current value IM, the material type MT, and the learning results (62, 68). In this way, the presence or absence of an abnormality sign in the load device (18) can be detected according to the material type MT.

[0037] Furthermore, as in the third embodiment, it is more preferable that the equipment (10) further includes a plurality of vibration sensors 22-1 to 22-n attached to respective parts of the electric motor 16 or the load device (18) and each outputting vibration values ​​VM-1 to VM-n, and further includes a cause diagnosing unit 38 that, when an abnormality sign occurs, estimates a location corresponding to the abnormality sign based on the vibration values ​​VM-1 to VM-n. In this way, the location corresponding to the abnormality sign can be estimated. [Explanation of symbols]

[0038] 10 Rolling equipment (equipment) 12 Control circuit 14 Drive circuit 16 Electric motor 18 Roll section (load device) 22-1 to 22-n Vibration Sensors 30 Abnormality prediction diagnostic device (computer) 32 Operation monitoring section (operation monitoring process) 34 Correlation learning section (correlation learning process) 36 Predictive diagnosis section (predictive diagnosis process) 38 Cause Diagnosis Department 52 operational databases 54,62,68 Correlation database (learning results) IM current value MT Material Type SC Speed ​​command value (command value) VM-1~VM-n vibration values

Claims

1. an operation monitoring unit that acquires from equipment including an electric motor driven by a current supplied from a drive circuit, a control circuit that outputs a control signal to the drive circuit based on a command value that commands an operating state of the electric motor, and a load device driven by the electric motor, the command value and the current value of the current output by the drive circuit, and records the command value in an operation database; a correlation learning unit that learns a correlation between the command value and the current value and acquires a learning result; a symptom diagnosis unit that diagnoses whether or not there is a symptom of an abnormality in the facility based on the command value, the current value, and the learning result, and records the diagnosis result in a diagnosis result database. An abnormality sign diagnosis device characterized by:

2. the facility is a rolling facility that rolls a plate material using the loading device, the correlation learning unit learns a correlation between a material type, which is a material quality and a thickness of the plate material, the command value, and the current value, and acquires a learning result; The sign diagnosing unit diagnoses whether or not there is a sign of abnormality in the equipment based on the command value, the current value, the material type, and the learning result.

2. The abnormality sign diagnosis device according to claim 1.

3. the facility is a rolling facility that rolls a plate material using the loading device, The facility further includes a plurality of vibration sensors attached to each of the electric motors or the load devices, each of which outputs a vibration value; The vehicle further includes a cause diagnosis unit that, when the abnormality sign occurs, estimates a location corresponding to the abnormality sign based on the vibration value.

3. The abnormality sign diagnosis device according to claim 2.

4. an operation monitoring process for acquiring, from equipment including: an electric motor driven by a current supplied from a drive circuit; a control circuit that outputs a control signal MC to the drive circuit based on a command value that commands the operating state of the electric motor; and a load device driven by the electric motor, the command value and the current value of the current output by the drive circuit, and recording the command value in an operation database; a correlation learning process for learning a correlation between the command value and the current value and acquiring a learning result; a sign diagnosis process for diagnosing whether or not there is a sign of abnormality in the equipment based on the command value, the current value, and the learning result, and recording the diagnosis result in a diagnosis result database.

1. A method for diagnosing an abnormality sign, comprising:

Images