Apparatus and method for evaluating reducer of robot

Abstract

The present disclosure relates to an apparatus and a method for evaluating a decelerator of a robot. The apparatus for evaluating a decelerator of a robot according to the present disclosure includes: a motor state input module configured to receive a driving state of a driving motor directly connected to the decelerator; a storage device; a memory configured to store an executable program; and a processor operatively coupled to the motor state input module, the storage device, and the memory, where the processor receives the driving current and the rotational speed from the motor state input module, establishes big data, stores the big data in the storage device, and stores the big data in the storage device. A learning model for evaluating the decelerator is established on the basis of the drive current and the rotational speed stored in the storage device, machine learning is performed, and then an abnormality of the decelerator is diagnosed by the input drive current and the input rotational speed on the basis of the diagnostic learning model.

Description

Technical Field

[0001] Exemplary embodiments of the present disclosure relate to an apparatus and method for evaluating a reducer of a robot, and more particularly, to an apparatus and method for evaluating a reducer of a robot, which are capable of detecting a current applied to a drive motor and a rotational speed of the drive motor directly connected to the reducer of the robot, and performing learning based on machine learning to diagnose faults and predict lifespan. Background Art

[0002] Generally, an industrial robot refers to a handling machine that can be specially programmed with respect to direction, position, and work progress with respect to a plurality of motion axes in a state where the handling machine is equipped with a tool suitable for the purpose of automatically handling an object.

[0003] Such an industrial robot includes a tool configured to perform a manufacturing process on an object, a wrist on which the tool is mounted, an arm and an upper unit configured to change the position of the wrist, a pivot portion configured to rotate about a pivot axis to change the direction in which the wrist is pointing, a base portion configured to support the pivot portion, and a drive portion configured to provide a driving force for performing the manufacturing process.

[0004] In this case, the driving part may include a driving motor and a reducer, in which lubricating oil is filled for lubrication. The constituent material of the reducer is iron, and when the reducer is worn according to the operation time of the driving part, the constituent material is mixed with the lubricating oil. During the manufacturing process, foreign matter mixed with the lubricating oil causes a sudden erroneous operation of the reducer. In order to cope with the erroneous operation, all of the multiple industrial robots installed on the production line need to be stopped.

[0005] The background technology of the present disclosure is disclosed in Korean Patent Application Publication No. 10-2016-0083392 (published on July 12, 2016, entitled “Industrial Robot System”). Summary of the invention

[0006] Since the reducer and the drive motor are in direct contact with each other, when the reducer of the industrial robot erroneously operates, the excessive heat of the drive motor is transferred through the reducer housing and affects the reducer, and there is a problem that the encoder of the drive motor is damaged by the high temperature heat of the drive motor. In addition, when the high temperature heat of the drive motor is transferred through the reducer housing, there is a problem that the life of the grease in the reducer housing is shortened.

[0007] Various embodiments relate to an apparatus and method for evaluating a reducer of a robot, which is capable of detecting the rotational speed of a drive motor directly connected to the reducer of the robot and the current applied to the drive motor, and performing learning based on machine learning to diagnose faults and predict life.

[0008] In an embodiment, a device for evaluating a reducer of a robot includes: a motor state input module, configured to receive a driving state of a driving motor directly connected to the reducer; a storage device; a memory, configured to store an executable program; and a processor, operatively connected to the motor state input module, the storage device and the memory, wherein the processor receives a driving current and a rotational speed from the motor state input module, establishes big data, stores the big data in the storage device, establishes a learning model for evaluating the reducer based on the driving current and the rotational speed stored in the storage device, performs machine learning, and then diagnoses abnormalities of the reducer based on the input driving current and the input rotational speed based on the diagnostic learning model.

[0009] In the present disclosure, the apparatus may further include: an output module configured to output a diagnosis result, wherein the processor outputs the diagnosis result of diagnosing the abnormality of the speed reducer through the output module.

[0010] In the present disclosure, the motor state input module may receive a driving current and a rotation speed from a motor driver configured to operate a driving motor through a network.

[0011] In the present disclosure, the processor may output the result of evaluating the reducer to the motor driver.

[0012] In the present disclosure, the processor may store the result of evaluating the reducer in a storage device and periodically improve the diagnosis learning model.

[0013] In another embodiment, a method for evaluating a reducer of a robot includes: receiving, by a processor, a driving current and a rotational speed of a driving motor through a motor state input module; establishing, by the processor, big data based on the input driving current and the input rotational speed, and storing the big data in a storage device; establishing, by the processor, a learning model for evaluating the reducer based on the driving current and the rotational speed, and performing machine learning; and diagnosing abnormalities of the reducer through the driving current and rotational speed input from the motor state input module based on the diagnostic learning model, by the processor.

[0014] In the present disclosure, the method may further include: outputting, by the processor, a diagnosis result of diagnosing the abnormality of the speed reducer by an output module.

[0015] In the present disclosure, the method may further include: outputting, by the processor, a result of evaluating the reducer to the motor driver.

[0016] In the present disclosure, the method may further include: storing, by the processor, the result of evaluating the reducer in a storage device, and regularly improving the diagnosis learning model.

[0017] According to one aspect of the present disclosure, an apparatus and method for evaluating a reducer of a robot can detect the rotational speed of a drive motor directly connected to the reducer of the robot and the current applied to the drive motor, diagnose faults by performing learning based on machine learning, predict life, and provide the diagnosis results to a motor driver so that the motor driver performs operations to protect the drive motor. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a block diagram showing a configuration of an apparatus for evaluating a reducer of a robot according to an embodiment of the present disclosure.

[0019] Figure 2 is a flowchart illustrating a method for evaluating a reducer of a robot according to another embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] Hereinafter, an apparatus and method for evaluating a reducer of a robot will be described by various exemplary embodiments with reference to the accompanying drawings. Here, for the sake of clarity and convenience of description, the thickness of the lines shown in the drawings, the size of the constituent elements, etc. may be exaggerated. In addition, the terms used below are defined in consideration of the functions in the present disclosure and may differ according to the intention or common practice of the user or operator. Therefore, these terms should be defined based on the entire contents of this specification.

[0021] Figure 1 is a block diagram showing a configuration of an apparatus for evaluating a reducer of a robot according to an embodiment of the present disclosure.

[0022] like Figure 1 As shown, the apparatus for evaluating a reducer of a robot according to an embodiment of the present disclosure may include a motor state input module 10 , a storage device 40 , an output module 50 , a memory 20 , and a processor 30 .

[0023] The motor state input module 10 may receive a driving state of a driving motor 70 directly connected to a speed reducer 80 .

[0024] The driving state of the driving motor 70 may include a driving current applied to operate the driving motor 70 and a rotation speed of the driving motor 70 .

[0025] In this case, the motor state input module 10 may be connected to the motor driver 60 controlling the operation of the drive motor 70 through a network and receive a driving current and a rotation speed from the motor driver 60 .

[0026] The storage device 40 may create and store big data related to the driving current and the rotation speed of the driving motor 70 input through the motor state input module 10 .

[0027] In this case, the storage device 40 may collect the driving current and the rotation speed in a normal state to establish a diagnosis learning model, and establish and store big data.

[0028] The output module 50 provides an interface for outputting the diagnosis result. The output module 50 can output the diagnosis result not only to a high-level control device (not shown), but also to a display (not shown).

[0029] The memory 20 may store data and executable programs for diagnosing abnormalities of the reducer of the robot, and the processor 30 may select the stored information as needed.

[0030] That is, the memory 20 stores various types of data generated in the process of executing an operating system or an application (program or applet) for operating a device for evaluating a reducer of a robot. In this case, the memory 20 is collectively referred to as a non-volatile storage device and a volatile storage device, the non-volatile storage device is configured to continuously retain the stored information even if power is not supplied, and the volatile storage device is configured to require power to retain the stored information. In addition, the memory 20 can be used to temporarily or permanently store data to be processed by the processor 30. In this case, in addition to a volatile storage device configured to require power to retain the stored information, the memory 20 may also include a magnetic storage medium or a flash memory storage medium. However, the scope of the present disclosure is not limited to this.

[0031] The processor 30 can be operably connected to the motor state input module 10, the storage device 40, the output module 50 and the memory 20, copy various types of programs stored in the memory 20 in the RAM, and execute the programs to perform various types of operations, thereby controlling the overall operation of the device for evaluating the reducer of the robot.

[0032] In various embodiments, the processor 30 may be implemented as a digital signal processor (DSP), a microprocessor, or a time controller (TCON) for processing digital signals. However, the present disclosure is not limited thereto. The processor 30 may include or be defined as a term for one or more of a central processing unit (CPU), a microcontroller unit (MCU), a microprocessing unit (MPU), a controller, an application processor (AP), a communication processor (CP), and an ARM processor. In addition, the processor 30 may be implemented as a system on chip (SoC) or a large-scale integration (LSI) embedded with a processing algorithm, or in the form of a field programmable gate array (FPGA).

[0033] That is, the processor 30 executes the executable diagnostic program stored in the memory 20 , receives the driving current and the rotation speed from the motor state input module 10 , creates big data, and stores the big data in the storage device 40 .

[0034] Afterwards, the processor 30 can establish a learning model for evaluating the reducer 80 based on the driving current and the rotation speed stored in the storage device 40 based on the artificial neural network, and perform machine learning. Then, the processor 30 can diagnose the abnormality of the reducer and predict the life span through the input driving current and the input rotation speed based on the diagnostic learning model.

[0035] In addition, the processor 30 may store the results of evaluating the reducer 80 in the storage device 40 and periodically improve the diagnostic learning model.

[0036] In this context, artificial neural network (ANN) refers to a machine learning algorithm that mathematically models the way the brain learns to store information by sending or receiving information through neurons and the synapses that connect them. In an artificial neural network, neurons can be defined as nodes and synapses can be defined as weight values.

[0037] The artificial neural network may include any one of a deep neural network (DNN), a recurrent neural network (RNN), and a convolutional neural network (CNN). In addition, the artificial neural network may be created by combining at least one of a deep neural network (DNN) and a recurrent neural network (RNN). In addition, in addition to the above-mentioned artificial neural networks, various deep learning algorithms may be applied. A deep neural network (DNN) may be an artificial neural network having a plurality of hidden layers, and a recurrent neural network (RNN) may be a neural network having a recursive structure different from a deep neural network (DNN). A recurrent neural network (RNN) may be a suitable neural network for analyzing time series data, because the RNN remembers past information, and applies the information to learning by storing the data in a hidden layer and recursively using the data for the next learning.

[0038] As described above, the processor 30 can diagnose the abnormality of the reducer 80 through the driving current and the rotational speed based on the diagnosis learning model, and output the diagnosis result to the high-level control device or the display through the output module 50.

[0039] In addition, the processor 30 may output the result of evaluating the speed reducer 80 to the motor driver 60 , and the motor driver 60 may perform a protection operation by controlling the driving motor 70 according to the abnormal state and life of the speed reducer 80 .

[0040] As described above, the device for evaluating the reducer of a robot according to an embodiment of the present disclosure can detect the rotational speed of the drive motor directly connected to the reducer of the robot and the current applied to the drive motor, diagnose faults by performing learning based on machine learning, predict life, and provide the diagnosis results to the motor driver so that the motor driver performs operations to protect the drive motor.

[0041] Figure 2 is a flowchart illustrating a method for evaluating a reducer of a robot according to another embodiment of the present disclosure.

[0042] like Figure 2 As shown, first, in the method for evaluating a reducer of a robot according to an embodiment of the present disclosure, the processor 30 receives a driving current and a rotation speed of the driving motor 70 through the motor state input module 10 ( S10 ).

[0043] In this case, the motor state input module 10 may be connected to the motor driver 60 controlling the operation of the drive motor 70 through a network and receive a driving current and a rotation speed from the motor driver 60 .

[0044] When the processor 30 receives the driving current and the rotation speed of the driving motor 70 in step S10 , the processor 30 creates big data based on the input driving current and the input rotation speed and stores the big data in the storage device 40 ( S20 ).

[0045] After the processor 30 creates big data based on the driving current and the rotation speed in step S20, the processor 30 creates a learning model for evaluating the reducer 80 for the big data stored in the storage device 40 based on an artificial neural network and performs machine learning (S30).

[0046] In this context, artificial neural network (ANN) refers to a machine learning algorithm that mathematically models the way the brain learns to store information by sending or receiving information through neurons and the synapses that connect neurons. In an artificial neural network, neurons can be defined as nodes and synapses can be defined as weight values.

[0047] After the processor 30 performs machine learning in step S30 , the processor 30 diagnoses abnormality of the speed reducer 80 with respect to the driving current and the rotation speed input through the motor state input module 10 based on the diagnosis learning model ( S40 ).

[0048] After the processor 30 diagnoses the abnormality of the speed reducer 80 in step S40, the processor 30 outputs the diagnosis result of the abnormality of the speed reducer 80 to a high-level control device (not shown) through the output module 50, or outputs the diagnosis result to a display (not shown) (S50).

[0049] In addition, the processor 30 may store the diagnosis results in the storage device 40 and then periodically improve the diagnosis learning model.

[0050] On the other hand, the processor 30 may output the result of evaluating the reducer 80 to the motor driver 60 , and the motor driver 60 may perform a protection operation by controlling the driving motor 70 according to the abnormal state and life of the reducer 80 .

[0051] As described above, the method for evaluating the reducer of a robot according to an embodiment of the present disclosure can detect the rotational speed of a drive motor directly connected to the reducer of the robot and the current applied to the drive motor, diagnose faults by performing learning based on machine learning, predict life, and provide the diagnosis results to the motor driver so that the motor driver performs operations to protect the drive motor.

[0052] For example, the configuration described in this specification may be implemented as a method or process, a device, a software program, a data stream or a signal. Even if a single form of implementation is described (e.g., only a method is described), the features may also be implemented in other forms (e.g., a device or a program). The device may be implemented as appropriate hardware, software, firmware, etc. For example, the method may be implemented by a device such as a processor, which generally refers to a processing device including a computer, a microprocessor, an integrated circuit, a programmable logic device, etc. The processor also includes a communication device, such as a computer, a cellular phone, a portable / personal information terminal (personal digital assistant (PDA)), and other devices that facilitate information communication with an end user.

[0053] Although the present disclosure has been described with reference to the embodiments described in the drawings, these embodiments are for illustrative purposes only, and those skilled in the art to which this technology pertains will appreciate that various modifications of these embodiments and any other embodiments equivalent thereto are available.

[0054] Therefore, the true technical protection scope of the present disclosure should be determined by the appended claims.

[0055] Although the exemplary embodiments of the present disclosure are disclosed for illustrative purposes, it will be understood by those skilled in the art that various modifications, additions and substitutions may be made without departing from the scope and spirit of the present disclosure as defined by the appended claims. Therefore, the true technical scope of the present disclosure should be defined by the appended claims.

Claims

1. A device for evaluating a reducer of a robot, the device comprising: a motor state input module configured to receive a driving state of a driving motor directly connected to the reducer; Storage device; a memory configured to store an executable program; as well as a processor operatively coupled to the motor state input module, the storage device and the memory, Among them, the processor receives the driving current and the speed from the motor state input module, establishes big data, stores the big data in the storage device, establishes a learning model for evaluating the reducer based on the driving current and the speed stored in the storage device, performs machine learning, and then diagnoses the abnormality of the reducer based on the input driving current and the input speed based on the diagnostic learning model.

2. The device according to claim 1, further comprising: An output module is configured to output a diagnosis result, wherein the processor outputs the diagnosis result of diagnosing the abnormality of the reducer through the output module.

3. The device according to claim 1, wherein: The motor status input module receives a driving current and a rotation speed from a motor driver configured to operate the driving motor through a network.

4. The device according to claim 1, wherein: The processor outputs a result of evaluating the speed reducer to the motor driver.

5. The device according to claim 1, wherein: The processor stores the result of evaluating the reducer in the storage device and periodically improves the diagnostic learning model.

6. A method for evaluating a reducer of a robot, the method comprising: By means of the processor, a driving current and a rotation speed of the driving motor are received through a motor state input module; By means of the processor, big data is established based on the input drive current and the input rotation speed, and the big data is stored in a storage device; By means of the processor, a learning model for evaluating the reducer is established based on the driving current and the rotation speed, and machine learning is performed; as well as The processor diagnoses abnormality of the reducer based on a diagnosis learning model using the drive current and rotation speed input from the motor state input module.

7. The method according to claim 6, further comprising: The processor outputs a diagnosis result of diagnosing abnormality of the reducer through an output module.

8. The method according to claim 6, further comprising: The processor outputs the result of evaluating the reducer to the motor driver.

9. The method according to claim 6, further comprising: The processor stores the result of evaluating the reducer in the storage device and periodically improves the diagnostic learning model.

Images