KR20190064916A - Efficiency Prediction System And Method For Rotating Device Using Transformation Of Learning data - Google Patents

Abstract

The present invention relates to a system for predicting the efficiency of a rotating device using conversion of learning data. The system comprises a sensing unit, a calculation unit, a processing unit, a conversion unit, a learning unit, and an efficiency map modeling unit. Accordingly, the reliability for predicting the efficiency of a rotating device may be increased.

Description

TECHNICAL FIELD [0001] The present invention relates to a system and a method for efficiently estimating efficiency of a rotating body using transformation of learning data,

The present invention relates to a system and method for estimating the efficiency of a rotating body using conversion of learning data, and more particularly, to a system and method for estimating efficiency of a rotating body by converting learning data, And more particularly, to a system and method for estimating the efficiency of a rotating body by using learning data conversion that can improve reliability of prediction of efficiency of rotation by constructing an efficiency map accumulating efficiency at each point of time according to driving time of the rotating body .

Recently, in the industry, techniques for predicting the failure probability and the remaining service life of a component that repeats a specific motion (rotation, reciprocating, translating), and for managing repair schedules, parts replacement timing and component inventory are actively developed. Part monitoring and status diagnostics are basically developed for the application of parts and systems to diagnose the effective life span.

The efficiency of a rotating body that repeats rotational motion, for example, a speed reducer that rotates in conjunction with a motor, is calculated as a ratio of the output load of the speed reducer to the input load (output load of the motor) of the speed reducer such as torque and RPM, The efficiency of the corresponding rotating body can be grasped by sensing the output load according to the entire input load.

Furthermore, by calculating the real-time efficiency of the rotating body in a state in which the rotating body is driven for a predetermined time, the efficiency change of the rotating body can be measured according to the driving time (within a predetermined time) of the rotating body.

However, in this case, the sensing of the input load and the output load must be performed in real time for the whole time the rotating body is driven, and the real-time load measurement through the sensor is limited by the limit of sensor installation space and the rotational- But there is a limitation in applying the efficiency prediction device to all the rotors produced due to factors such as an increase in the total production cost.

Therefore, the development of a technique for predicting the efficiency and efficiency change of the rotating body at a specific point in time during the entire driving time of the rotating body is being developed through the limited actual measured data of the rotating body.

[0004] Meanwhile, there has been disclosed in Korean Patent Registration No. 10-1699509 (published on Jan. 25, 2017), a decelerator breakage detecting device and a method of detecting a speed reducer breakage using the same, To a technology for monitoring the condition of a speed reducer and detecting an abnormal condition.

However, the prior art has a problem in that it is difficult to predict the efficiency and efficiency change of the rotating body at a specific point of time only by detecting the damage of the speed reducer by using specific parameters.

Korean Registered Patent Publication No. 10-1699509 (published on Feb. 25, 2017), a method for detecting a damper of a speed reducer, and a method of detecting a damper of the speed reducer using the same

SUMMARY OF THE INVENTION The present invention has been made in order to solve the above problems, and it is an object of the present invention to provide a method and apparatus for converting limited actual measured data of a rotating body into learning data through various data conversion methods, The present invention also provides a system and method for estimating the efficiency of a rotating body using transformation of learning data, which can improve the reliability of the efficiency prediction of the rotating body by constructing an efficiency map accumulating the efficiency of each point of time according to the driving time of the rotating body.

According to the present invention, the above object can be achieved by providing a control apparatus for a rotating body, comprising: a sensing unit for obtaining an output load on a real time input load of the rotating body; An operation unit for calculating efficiency of each rotation point of the rotating body based on the information obtained by the sensing unit; A processing unit for processing the efficiency of the point of view of the rotating body calculated by the calculating unit into image data of a coordinate form; A conversion unit for converting the coordinate data of the coordinate form into learning data; A learning unit for learning the transformed learning data through the deep learning technique; And an efficiency map modeling unit for modeling an efficiency map in which efficiencies of the rotating bodies are accumulated based on data learned through the learning unit. The efficiency of the rotating body can be improved.

Here, the converting unit may be configured to generate learning data by raising the resolution of the image data of the coordinate form.

Alternatively, the converting unit may include: a noise generating unit that randomly generates noise for an efficiency point that has not been measured among the imaged data of the coordinate form; And a learning data generating section for generating learning data by removing noise of a part of noise generated in the noise generating section. .

According to another aspect of the present invention, there is provided a method for controlling a rotating load of a rotating body, A second step of calculating an efficiency of each of the rotors at a time point based on the information obtained from the first step; A third step of processing the efficiency of the point of view of the rotating body calculated through the second step into image data of a coordinate form; A fourth step of converting the data processed in the third step into learning data; A fifth step of learning learning data converted through the fourth step through a deep learning technique; And a sixth step of modeling an efficiency map in which efficiencies of the revolving points of the rotating bodies are accumulated based on data learned through the fifth step. The efficiency of the rotational efficiency of the rotating body can be improved.

Here, the fourth step may include generating training data by raising the resolution of the image data of the coordinate form.

Alternatively, the fourth step may include: a 4-1 step of randomly generating noise for an efficiency point not measured among the imaged data of the coordinate form; And 4-2) generating learning data by removing noise of a part of the noise generated in the step 4-1). ≪ / RTI >

According to the present invention, limited actual measured data of a rotating body is converted into learning data through various data conversion methods, then learning is performed through deep learning, and an efficiency map is accumulated The reliability of the efficiency prediction of the rotating body can be improved.

1 is a block diagram showing the configuration of a first embodiment of a system for estimating the efficiency of a rotating body using conversion of learning data according to the present invention,
2 is a block diagram showing a configuration of a second embodiment of a system for estimating the efficiency of rotors using learning data conversion according to the present invention,
FIG. 3 is a conceptual diagram illustrating a process of constructing an efficiency map in the efficiency prediction system of a rotating body using conversion of learning data according to the present invention,
FIG. 4 is a conceptual diagram showing a process of generating learning data through resolution conversion in the efficiency prediction system of a rotating body by using learning data conversion according to the present invention,
5 is a flowchart showing a process of a first embodiment of a method for predicting the efficiency of a rotating body using conversion of learning data according to the present invention,
6 is a flowchart showing a process of a second embodiment of a method for predicting the efficiency of a rotating body using conversion of learning data according to the present invention.

Hereinafter, the configuration of the present invention will be described in detail with reference to the accompanying drawings.

In the case where it is determined that a detailed description of the related art may unnecessarily obscure the gist of the present invention, a description thereof will be omitted. The rotating body according to the present invention includes a speed reducer (preferably, a speed reducer interlocked with the induction motor) However, the present invention is not limited thereto and may be provided with various rotors used for an engine, a power transmission device, etc., and the efficiency prediction concept described in the present invention can be applied not only to a rotating body but also to various motions (reciprocating motion, translational motion) It can be applied to a power train to be carried out. In the case of the rotating body, torque and RPM are measured and applied to the input and output loads as shown in the drawing. However, in the case of parts performing reciprocating or translational motion, the force, linear velocity, Data may be measured and applied.

On the other hand, the terms used in the present specification and claims should not be construed in a dictionary meaning, and the inventor may, on the principle that the inventor can properly define the concept of a term in order to explain its invention in the best way, And should be construed in light of the meanings and concepts consistent with the technical idea of the present invention.

Therefore, the embodiments shown in the present specification and the drawings are only exemplary embodiments of the present invention, and not all of the technical ideas of the present invention are presented. Therefore, various equivalents It should be understood that water and variations may exist.

1. Detailed description of efficiency prediction system of rotating body by using learning data conversion

FIG. 1 is a block diagram showing the configuration of a first embodiment of a system for estimating the efficiency of a rotating body using learning data conversion according to the present invention. FIG. 2 is a block diagram showing a system for efficiently estimating the efficiency of a rotating body FIG. 3 is a conceptual diagram showing a process of constructing an efficiency map in the efficiency prediction system of a rotating body by using learning data conversion according to the present invention. FIG. 4 is a block diagram FIG. 2 is a conceptual diagram illustrating a process of generating learning data through resolution conversion in a system for estimating the efficiency of a rotating body using transformation of learning data.

1 and 4, a system for estimating the efficiency of a rotating body using transformation of learning data according to the present invention includes a sensing unit 10, an operation unit 20, a processing unit 30, a conversion unit 40, A learning unit 50, an efficiency map modeling unit 60, and a data collecting unit 70.

The sensing unit 10 may be provided as a torque and RPM measurement sensor installed on the input and output sides of the rotating body to perform an operation of obtaining an output load with respect to a real time input load of the rotating body.

The calculating unit 20 calculates the efficiency of each rotating point of the rotating body on the basis of the input and output load information of the rotating body acquired by the sensing unit 10, ) Of the rotation angle of the rotating body to the image data of the coordinate form.

In other words, when the efficiency of the rotation point of the rotating body in the operation unit 20 is calculated and the efficiency of each rotation point of the rotating body is converted into the coordinate data in the machining unit 30, T (1,0 (Efficiency values are shown) as coordinate forms at individual specific time points such as T (1), T (1.1), T (1,2) And it appears in the form of a measured efficiency map.

On the other hand, if the efficiency of the individual specific time points is measured and accumulated for the total driving time of the rotating body, the ideal efficiency map of FIG. 3 (all the points are efficiently measured in the coordinates) appears.

However, the ideal efficiency map is generated when the real-time sensing of the measured data is set to infinity. As a result, there is a limit in actual implementation. As shown in FIG. 3, in order to overcome this limitation, Based on the information of the measured efficiency (including the efficiency not measured), it is designed to converge the ideal efficiency map and the deep learning efficiency map by filling the measured efficiency with the deep learning technique.

In the case of FIG. 3, the actual efficiency map is constructed based on the actual efficiency of T (1,0), T (1.1), T (1,2) But the present invention is not limited to this, and it is needless to say that the time efficiency measurement standard for constructing the actual efficiency map may be set differently according to the specification of the rotating body.

On the other hand, the converting unit 40 is a characteristic feature of the present invention and plays a role of converting data processed in the processing unit 30 into learning data.

Here, the learning data is data in which the efficiency (actual efficiency) of the rotating point of the rotating body passing through the calculating section 20 and the machining section 30 is expanded, and is input to the learning section 50 to be described later, Can be generated by the following two methods.

First, as shown in FIGS. 1 and 4, the converting unit 40 may be configured to increase the resolution of the image data of the coordinate form to generate learning data.

Specifically, as shown in FIG. 4, when the resolution of the coordinate image in which the measured efficiency point is taken is 3 * 3, if the resolution of the image is increased to 5 * 5 or 7 * 7, (The efficiency point increases in the area occupied by the image). When the images having the extended efficiency points are accumulated and input to the deep learning, the efficiency is filled in the efficiency map after the learning. The deep running efficiency map converges to the ideal efficiency map.

Alternatively, as shown in FIG. 2, the converting unit 40 may include: a noise generating unit 42 for randomly generating noise for a non-observed efficiency point among the imaged data of the coordinate form; And a learning data generating section (44) for generating learning data by removing noise of a part of noise generated in the noise generating section (42); As shown in FIG.

Specifically, the noise generating portion 42 randomly performs noise processing on a plurality of efficiency points (empty efficiency points on the coordinate image) not actually observed on a coordinate image, transforms the coordinate image in the same manner as a form in which a measurement point is imaged, The learning data generating section 44 removes some of the processed noise to restore the original image data. In summary, since only a part of the noise is removed from the randomly processed noise, not the noise, the residual noise that has not been removed is recognized as the measured efficiency point, which means that the number of efficient points In the form of an increase. That is, when images with increased number of effective points are accumulated and input to the deep run, the empty efficiency is filled in the actual efficiency map after the learning, and the deep learning efficiency map is converged to the ideal efficiency map.

As a result, the efficiency of the efficiency point or the number of efficiency points is increased by the configuration of the conversion unit 40 of the present invention, and the accuracy of the efficiency prediction is improved through such data conversion.

On the other hand, the learning unit 50 plays a role of learning the transformed learning data in the transforming unit 40 through the deep learning technique.

Here, the learning data input to the learning unit 50 is the data in which the effective points are actually expanded and the number of the effective points is increased through the resolution conversion or noise removal technique in the conversion unit 40, Since the processed data is limited data based on the actual values, the configuration of the data collection unit 70 is added in the present invention in order to increase the absolute amount of the learning data. The data collecting unit 70 is configured to acquire learning target data input to the learning unit 50 over a network by a predetermined amount or more. The data collecting unit 70 randomly collects a plurality of imaged data existing on the network and acquires .

Here, collecting the learning target data over a certain amount is intended to increase the absolute amount of data input to the deep learning to increase the accuracy and reliability of efficiency prediction of the modeled efficiency map to be described later, and to collect the imaged data at random, This is to increase the probability that the efficiency that is not actually measured through running is mapped as predictive efficiency.

That is, in the learning unit 50, both the learning target data collected through the data collection unit 70 and the expanded data of the efficiency point converted through the conversion unit 40 are used as learning data for deep learning .

In addition, the data collection unit 70 may include a parameter setting unit (not shown) for setting the collection parameters of the learning target data so that the size and resolution of the data converted by the conversion unit 40 are similar within a predetermined setting range In addition, the construction of the deep learning efficiency map can be easily performed through the configuration of the parameter setting portion, and at the same time, the effect of preventing indiscreet data collection can be exhibited.

Here, the learning unit 50 is constructed by including a neural network model to which a concept of transfer of learning is applied.

Learning transfer is a concept that applies a neural network model (algorithm) created in a specific environment to other similar fields and can be usefully applied to fields lacking data. It is also possible to construct a pre-trained neural network and apply different data sets to the neural network .

Specifically, the learning unit 50 includes a pre-model construction unit (not shown) for constructing a pre-trained learning model based on the learning target data collected through the data collection unit 70, A learning model update section (not shown) for updating the learning model by applying the data converted by the conversion section 40 to a pre-trained learning model; .

That is, a relatively large amount of learning data collected through the data collection unit 70 is input to the pre-model building unit to construct a pre-trained learning model, and the converted data The learning unit 50 may be configured to update and build the final learning model.

In addition to the deep learning learning method, the learning unit 50 uses the data converted by the converting unit 40 and the learning target data collected by the data collecting unit 70, Learning can be done through a learning model built by simple merging.

The efficiency map modeling unit 60 is configured to model an efficiency map in which efficiencies of the revolving points of the rotating bodies are accumulated on the basis of data learned through the learning unit 50. The efficiency map modeling unit 60 (X-axis: RPM, y-axis: torque, z-axis: time) in which a two-dimensional image (x axis: RPM, y axis: torque) The efficiency map can be used to predict the efficiency at a specific driving point of the rotor (ie, when the efficiency change of the rotor due to driving is reflected).

2. Detailed description of the efficiency prediction method of the rotating body by using the conversion of learning data

FIG. 5 is a flowchart showing a process of a first embodiment of a method for predicting the efficiency of a rotating body using transformation of learning data according to the present invention, and FIG. 6 is a flowchart illustrating a method of predicting efficiency of a rotating body using transformation of learning data according to the present invention Fig. 7 is a flowchart showing the procedure of the second embodiment. Fig.

5 and 6, a method for estimating efficiency of a rotating body using deep running according to the present invention includes a first step (S10) of obtaining an output load with respect to a real time input load of a rotating body; A second step (S20) of calculating efficiency of each rotating point of the rotating body based on information obtained from the first step (S10); A third step (S30) of processing the efficiency of the point of view of the rotating body calculated through the second step (S20) into image data of a coordinate form; A fourth step S40 of converting the data processed in the third step S30 into learning data; A fifth step (S50) of learning the transformed learning data through the fourth learning step (S40) through a deep learning technique; And a fifth step (S60) of modeling an efficiency map in which the efficiencies of the revolutions of the rotating body are accumulated based on the data learned through the fifth step (S50); .

In the fourth step S40, as shown in FIG. 5, the step of generating learning data by raising the resolution of the image data of the coordinate form.

Alternatively, the fourth step (S40) may include a fourth step (S42) of randomly generating noise for an efficiency point that has not been measured among the imaged data of the coordinate form, as shown in FIG. And a fourth step (S44) of generating learning data by removing noise of a part of noise generated in the step 4-1 (S42). ≪ / RTI >

In order to increase the effect of the deep learning learning between the fourth step (S40) and the fifth step (S50), in order to secure the learning target data inputted to the fifth step (S50) The data collection step S35 is included.

It should be noted that the detailed description of each of the above-described steps is omitted because it is the same as the description of the efficiency prediction system of the rotating body using the conversion of the learning data previously described.

As described above, a system and method for estimating the efficiency of a rotating body using conversion of learning data according to the present invention is a system and method for estimating the efficiency of a rotating body by converting limited actual data of a rotating body into learning data through various data conversion methods, The reliability of the efficiency prediction of the rotating body can be improved by constructing an efficiency map in which the efficiency of the point of view according to the driving time of the rotating body is accumulated.

While the present invention has been described with reference to the exemplary embodiments and the drawings, it is to be understood that the technical scope of the present invention is not limited to these embodiments and that various changes and modifications will be apparent to those skilled in the art. Various modifications and variations may be made without departing from the scope of the appended claims.

Description of the Related Art [0002]
10: sensing unit
20:
30:
40:
42: Noise generating part 44: Learning data generating part
50:
60: Efficiency Map Modeling Unit
70: Data collection unit

Claims (6)

A sensing unit for acquiring an output load with respect to a real time input load of the rotating body;
An operation unit for calculating efficiency of each rotation point of the rotating body based on the information obtained by the sensing unit;
A processing unit for processing the efficiency of the point of view of the rotating body calculated by the calculating unit into image data of a coordinate form;
A conversion unit for converting the coordinate data of the coordinate form into learning data;
A learning unit for learning the transformed learning data through the deep learning technique; And
An efficiency map modeling unit for modeling an efficiency map accumulating efficiencies of the revolutions of the rotating body on the basis of data learned through the learning unit; ≪ RTI ID = 0.0 >
Efficiency Prediction System of Rotor Using Learning Data Transformation.
The method according to claim 1,
Wherein the converting unit generates learning data by raising the resolution of the image data of the coordinate form
Efficiency Prediction System of Rotor Using Learning Data Transformation.
The method according to claim 1,
Wherein,
A noise generating unit that randomly generates noise for an efficiency point that has not been measured among the imaged data of the coordinate form; And
A learning data generating section for generating learning data by removing noise of a part of noise generated in the noise generating section; ≪ RTI ID = 0.0 >
Efficiency Prediction System of Rotor Using Learning Data Transformation.
A first step of obtaining an output load with respect to a real time input load of the rotating body;
A second step of calculating an efficiency of each of the rotors at a time point based on the information obtained from the first step;
A third step of processing the efficiency of the point of view of the rotating body calculated through the second step into image data of a coordinate form;
A fourth step of converting the data processed in the third step into learning data;
A fifth step of learning learning data converted through the fourth step through a deep learning technique; And
A sixth step of modeling an efficiency map in which efficiencies of the rotors are accumulated based on the data learned through the fifth step; ≪ RTI ID = 0.0 >
A method for predicting the efficiency of a rotating body using transformation of learning data.
5. The method of claim 4,
And the fourth step is a step of generating learning data by raising the resolution of the image data of the coordinate form
A method for predicting the efficiency of a rotating body using transformation of learning data.
5. The method of claim 4,
In the fourth step,
A fourth step of randomly generating noise for an efficiency point that has not been measured among the imaged data of the coordinate form; And
A fourth step of generating learning data by removing noise of a part of noise generated in step 4-1; Characterized in that
A method for predicting the efficiency of a rotating body using transformation of learning data.

Images