CN115796027A - Method for improving bearing replacement efficiency of cold rolling unit by using virtual reality technology - Google Patents
Method for improving bearing replacement efficiency of cold rolling unit by using virtual reality technology Download PDFInfo
- Publication number
- CN115796027A CN115796027A CN202211495963.4A CN202211495963A CN115796027A CN 115796027 A CN115796027 A CN 115796027A CN 202211495963 A CN202211495963 A CN 202211495963A CN 115796027 A CN115796027 A CN 115796027A
- Authority
- CN
- China
- Prior art keywords
- cold rolling
- fcst
- virtual reality
- bearing
- reality technology
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for improving bearing replacement efficiency of a cold rolling unit by using a virtual reality technology, which comprises the following steps: s1, physical simulation: measuring parts such as a bearing of a cold rolling unit by using a measuring tool, and inputting measured data into physical simulation software for simulation processing so as to obtain a corresponding virtual space; s2, three-dimensional modeling: detecting surrounding scenes such as a bearing seat, a sealing element and the like matched with parts such as a bearing of a cold rolling unit and the like, and inputting the surrounding scenes into three-dimensional software to perform three-dimensional modeling; s3, immersion operation: firstly, an operator wears an immersion helmet, and then scene data of the unit implementation are acquired through the immersion helmet worn by the operator; the method designed by the invention can realize repeated bearing replacement, improve the fault tolerance rate and the proficiency, better reduce the replacement time and the occurrence frequency of operation errors and improve the production efficiency.
Description
Technical Field
The invention relates to the technical field of digitization in the field of metallurgy, in particular to a method for improving bearing replacement efficiency of a cold rolling unit by using a virtual reality technology.
Background
The cold rolling unit is mainly used for quickly producing parts with simple deformation, and the bearings of the cold rolling unit need to be frequently replaced because the cold rolling unit produces the parts quickly, so that the production precision of the cold rolling unit is ensured.
If the authorization notice number is CN212338102U, and the authorization notice date is 2021-01-12, the device for quickly replacing the gear shifting bearing of the reduction box of the cold rolling unit belongs to the technical field of reversible cold rolling unit equipment and is used for quickly replacing the gear shifting bearing of the reduction box of the cold rolling unit. The technical scheme is as follows: the inner end of the gear shifting shaft is sleeved with a gear shifting bearing, the gear shifting bearing is positioned with the gear shifting shaft through a clamp spring, the outer ring of the gear shifting bearing is connected with an inner hole of a gear shifting gear, a pair of semi rings are installed on the outer side gear shifting shaft of the gear shifting bearing, a positioning sleeve is sleeved on the periphery of each semi ring, a gear shifting arm is sleeved on the outer side gear shifting shaft of each semi ring and the positioning sleeve, and a locking nut is arranged at the outer end of the gear shifting shaft outside the gear shifting arm and is connected with the gear shifting shaft in a locking mode. The utility model discloses simple structure, convenient to use, the gear shift bearing directly need not hang out the gear of shifting from the assembly in the gear shift arm outside, has solved the problem that the gear shift gear of rolling mill reducing gear box need be unpacked and hung out the gear of shifting and could change after damaging, has saved a large amount of maintenance duration and manpower, has improved maintenance work efficiency, has guaranteed going on smoothly of production.
The fault-tolerant rate is higher among the bearing replacement process among the above-mentioned technique, and misoperation easily appears, leads to changing the time and becomes long, influences the production efficiency of cold rolling unit, leads to needing skilled workman just can change when changing, consequently, needs to design a method that application virtual reality technique improves cold rolling unit and changes bearing efficiency and solves above-mentioned problem urgently.
Disclosure of Invention
The invention aims to provide a method for improving bearing replacement efficiency of a cold rolling unit by using a virtual reality technology, so as to solve the defects in the prior art.
In order to achieve the above purpose, the invention provides the following technical scheme:
a method for improving bearing replacement efficiency of a cold rolling unit by using a virtual reality technology comprises the following steps:
s1, physical simulation: measuring parts such as a bearing of a cold rolling unit by using a measuring tool, and inputting measured data into physical simulation software for simulation processing so as to obtain a corresponding virtual space;
s2, three-dimensional modeling: detecting surrounding scenes such as a bearing seat, a sealing element and the like matched with parts such as a bearing of a cold rolling unit and the like, and inputting the surrounding scenes into three-dimensional software to perform three-dimensional modeling;
s3, immersion operation: firstly, an operator wears an immersion helmet, then scene data of a unit implementation is acquired through the immersion helmet worn by the operator, a virtual space is combined with a real world scene according to a constructed three-dimensional scene model, the mounting and dismounting of a bearing in the virtual world are controlled, and a result is fed back to the operator so that the operator can improve operation steps;
s4, recording and storing: in the operation process, the camera records the whole replacement process and then stores the replacement process in the storage medium, so that reference is provided for future training and teaching.
Further, the physical simulation software in S1 is established by a virtual reality technology, and the data threshold is calculated by an algorithm during simulation in S1, and the process requires four steps: selecting and initializing, calculating and dividing, calculating again and repeating circularly.
Further, the selecting and initializing steps are specifically as follows: some threshold classes/sets are first selected and their respective center points are randomly initialized.
Further, the center point is a position having the same length as each data point vector, and the number of classes (i.e., the number of center points) needs to be predicted in advance.
Further, the calculation and division steps are specifically as follows: the distance of each data point to the center point is calculated, and the class to which the data point is closest to which center point is classified.
Further, the recalculating step is specifically as follows: calculating the central point in each class as a new central point, and adopting the following method for the cyclic repeating step: the method comprises the following steps: repeating the steps until the center of each type does not change greatly after each iteration; the second method comprises the following steps: the central point is also randomly initialized for many times, and then the best one of the operation results is selected; the third method comprises the following steps: from the two types of points obtained, re-computing the centroid (shortest distance to all points of the class) of the two types of points re-assigns all points to one of two new centroids. The above process is repeated until the center of each class does not change much after each iteration.
Further, the threshold calculation algorithm is composed of three modules, and the three modules are respectively: the system comprises a machine learning module, an algorithm realization module and an abnormity judgment processing module, wherein the machine learning module comprises the following algorithms:
import pandas as pd
import numpy as np
from sklearn. cluster import KMeans；
the algorithm implementation module algorithm is as follows:
y =[470, 509，500, 511,435,489,483,483,482。483, 504, 472,464,481, 501, 581，507,558, 569,467,38
km =KMeans(n_ clusters-2)
km.fit(y)
y['fcst'] = km.predict(y)
inputting a y, defining and dividing the y into two classes (one class is normal automatically and the other class is abnormal), recording a predicted classification result by a field fcst, and recording two classes 0 and 1, wherein the field fcst does not know which class is normal, and a reasonable assumption is made that most of the classes are normal and less of the classes are abnormal;
the algorithm of the abnormity judgment processing module is as follows:
labele = y[y.fcst==0]['fcst']. count()
label1= y[y.fcst==1]['fcst']. count()
if labell<=labele:
y[' isAbnormal ']=y['fcst']
else:
y.1oc[y['fcst'] == 0，'isAbnormal']=1
y.1oc[y['fcst'] == 1，' isAbnormal']=0
y.columns = [ 'data','fcst',' isAbnormal']
y[' isAbnormal']= y[ ' isAbnormal ']. astype(int)
y = y['data',' isAbnormal'll
in which the number classified as 1 and the number classified as 0 are recorded, and finally whether or not abnormal is recorded with a field isadenormal, 0 being normal and 1 being abnormal.
Furthermore, the three-dimensional modeling software in S2 adopts one of AutoCAD, solidWorks, MASTERCAM, creo, inventor, cimatron, abaqus, solidedge, labVIEW, alias, 3d-max, flash, and photoshop.
Furthermore, the virtual space is not only combined with the real world scene during the immersion operation in the step S3, but also connected with the collecting device, the immersion type helmet and the practical operation mechanism, wherein the collecting device comprises a sensor and a camera, the collecting device is established according to the field monitoring of the existing cold rolling mill train, the practical operation mechanism comprises an industrial robot and a cold rolling mill train, and the industrial robot is used for operating the bearing installation on the cold rolling mill train.
Further, the storage medium in S4 is composed of a cloud storage platform and a physical storage module, the storage module is implemented by any type of volatile or nonvolatile storage device or a combination thereof, the storage module is implemented by a static random access memory, an electrically erasable programmable read only memory, an erasable programmable read only memory, a magnetic memory, a flash memory, a magnetic disk or an optical disk, and the cloud storage platform is one of a hundred-degree cloud platform, a hua-shi cloud platform, a WPS cloud disk, an ari cloud disk, a fast cloud disk, a quark cloud disk and the like.
In the technical scheme, the method for improving the bearing replacement efficiency of the cold rolling unit by using the virtual reality technology (1) can realize repeated bearing replacement actions, improve the fault tolerance rate and the proficiency, better reduce the replacement time and the occurrence frequency of operation errors and improve the production efficiency; (2) According to the virtual equipment, the real operation mechanism and the acquisition equipment designed by the invention, when the operation is carried out by the method, the virtual equipment and the real operation mechanism are matched to enable an operator to carry out actual operation on the cold rolling unit when the real operation mechanism carries out virtual operation and drilling, and then the operator knows the difference of operation between virtual operation and actual operation through the data acquired by the acquisition equipment, so that the operator can complete the installation of the bearing according to more practical requirements; (3) The invention can control the installation and the disassembly of the bearing in the virtual world through the technology, and record the operation process through the acquisition equipment, thereby providing reference for future training and teaching and improving the convenience of subsequent teaching.
Drawings
In order to more clearly illustrate the embodiments of the present application or technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings are obtained by those skilled in the art according to the drawings.
Fig. 1 is a flowchart of a method for improving bearing replacement efficiency of a cold rolling mill train by using a virtual reality technology according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating operation of an embodiment of the method for improving bearing replacement efficiency of a cold rolling mill train using a virtual reality technology.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the present invention will be further described in detail with reference to the accompanying drawings.
As shown in fig. 1-2, a method for improving bearing replacement efficiency of a cold rolling mill by using a virtual reality technology provided by an embodiment of the present invention includes the following steps:
s1, physical simulation: measuring parts such as a bearing of a cold rolling unit by using a measuring tool, and inputting measured data into physical simulation software for simulation processing so as to obtain a corresponding virtual space;
s2, three-dimensional modeling: detecting surrounding scenes such as a bearing seat, a sealing element and the like matched with parts such as a bearing of a cold rolling unit and the like, and inputting the surrounding scenes into three-dimensional software to perform three-dimensional modeling;
s3, immersion operation: firstly, an operator wears an immersion helmet, then scene data of a unit implementation is acquired through the immersion helmet worn by the operator, a virtual space is combined with a scene of a real world by depending on a constructed three-dimensional scene model, the mounting and dismounting of a bearing in the virtual world are controlled, and meanwhile, a result is fed back to the operator, so that the operator can improve operation steps;
s4, recording and storing: in the operation process, the camera records the whole replacement process and then stores the whole replacement process in the storage medium, so that reference is provided for future training and teaching.
Specifically, the present embodiment includes the following steps:
s1, physical simulation: measuring parts such as a bearing of a cold rolling unit by using a measuring tool, and inputting measured data into physical simulation software for simulation processing so as to obtain a corresponding virtual space;
s2, three-dimensional modeling: detecting surrounding scenes such as a bearing seat, a sealing element and the like matched with parts such as a bearing of a cold rolling unit and the like, and inputting the surrounding scenes into three-dimensional software to perform three-dimensional modeling;
s3, immersion operation: firstly, an operator wears an immersion helmet, then scene data of a unit implementation is acquired through the immersion helmet worn by the operator, a virtual space is combined with a scene of a real world by depending on a constructed three-dimensional scene model, the mounting and dismounting of a bearing in the virtual world are controlled, and meanwhile, a result is fed back to the operator, so that the operator can improve operation steps;
s4, recording and storing: in the operation process, the camera records the whole replacement process and then stores the replacement process in the storage medium, so that reference is provided for future training and teaching.
The method for improving the bearing replacement efficiency of the cold rolling unit by using the virtual reality technology can realize repeated bearing replacement actions, improve the fault tolerance rate and the proficiency, better reduce the replacement time and the occurrence frequency of operation errors and improve the production efficiency.
In another embodiment provided by the invention, the physical simulation software in the S1 is established by a virtual reality technology, a data threshold is calculated by an algorithm during simulation in the S1, and the process needs four steps: selecting and initializing, calculating and dividing, calculating again and repeating circularly.
In another embodiment provided by the present invention, the selecting and initializing steps are specifically as follows: some threshold classes/sets are first selected and their respective center points are randomly initialized.
In another embodiment provided by the present invention, the center point is the same position as the length of each data point vector, and the number of classes (i.e. the number of center points) needs to be predicted in advance.
In another embodiment provided by the present invention, the calculation and division steps are specifically as follows: the distance of each data point to the center point is calculated, and the class to which the data point is closest to which center point is classified.
In another embodiment provided by the present invention, the recalculating step is specifically as follows: calculating the central point in each class as a new central point, and repeating the steps circularly by adopting the following method: the method comprises the following steps: repeating the steps until the change of each type of center after each iteration is not large; the second method comprises the following steps: the central point is also initialized randomly for many times, and then the best one of the operation results is selected; the third method comprises the following steps: from the two types of points obtained, re-computing the centroid (shortest distance to all points of the class) of the two types of points re-assigns all points to one of two new centroids. The above process is repeated until the center of each class does not change much after each iteration.
In another embodiment provided by the present invention, the threshold calculation algorithm is composed of three modules, and the three modules are respectively: the system comprises a machine learning module, an algorithm realization module and an abnormity judgment processing module, wherein the machine learning module comprises the following algorithms:
import pandas as pd
import numpy as np
from sklearn. cluster import KMeans；
the algorithm implementation module algorithm is as follows:
y =[470, 509，500, 511,435,489,483,483,482。483, 504, 472,464,481, 501, 581，507,558, 569,467,38
km =KMeans(n_ clusters-2)
km.fit(y)
y['fcst'] = km.predict(y)
wherein, inputting a y, defining and dividing into two categories (automatic one category is normal, one category is abnormal), the field fcst records the predicted classification result, there are two categories 0 and 1, but we do not know which category is normal, we have a reasonable assumption, more in the category are normal, less are abnormal;
the algorithm of the abnormity judgment processing module is as follows:
labele = y[y.fcst==0]['fcst']. count()
label1= y[y.fcst==1]['fcst']. count()
if labell<=labele:
y[' isAbnormal ']=y['fcst']
else:
y.1oc[y['fcst'] == 0，'isAbnormal']=1
y.1oc[y['fcst'] == 1，' isAbnormal']=0
y.columns = [ 'data','fcst',' isAbnormal']
y[' isAbnormal']= y[ ' isAbnormal ']. astype(int)
y = y['data',' isAbnormal'll
wherein the number classified as 1 and the number classified as 0 are recorded, and finally whether the field isAbnormal is abnormal or not is recorded, wherein 0 is normal and 1 is abnormal.
It should be noted that the result of the above calculation is as follows:
in another embodiment provided by the invention, the three-dimensional modeling software in S2 is one of AutoCAD, solidWorks, MASTERCAM, creo, inventor, cimatron, abaqus, solidedge, labVIEW, alias, 3d-max, flash, and photoshop.
In another embodiment provided by the invention, the virtual space in the immersion operation in S3 is not only combined with a real world scene, but also connected with a collection device, an immersion helmet and an actual operation mechanism, wherein the collection device comprises a sensor and a camera, the collection device is established according to the field monitoring of the existing cold rolling mill train, the actual operation mechanism comprises an industrial robot and the cold rolling mill train, and the industrial robot is used for operating the bearing installation on the cold rolling mill train.
In another embodiment of the present invention, the storage medium in S4 is composed of a cloud storage platform and a physical storage module, and the storage module is implemented by any type of volatile or nonvolatile storage device or a combination thereof, the storage module is implemented by a static random access memory, an electrically erasable programmable read only memory, an erasable programmable read only memory, a magnetic memory, a flash memory, a magnetic disk or an optical disk, and the cloud storage platform is one of a hundred-degree cloud platform, a hua-shi cloud platform, a WPS cloud disk, an ari cloud disk, a fast cloud disk, a quark cloud disk, and the like.
Example 1
A method for improving bearing replacement efficiency of a cold rolling unit by using a virtual reality technology comprises the following steps:
s1, physical simulation: measuring parts such as a bearing of a cold rolling unit by using a measuring tool, and inputting measured data into physical simulation software for simulation processing so as to obtain a corresponding virtual space;
s2, three-dimensional modeling: detecting surrounding scenes such as a bearing seat, a sealing element and the like matched with parts such as a bearing of a cold rolling unit and the like, and inputting the surrounding scenes into three-dimensional software to perform three-dimensional modeling;
s3, immersion operation: firstly, an operator wears an immersion helmet, then scene data of a unit implementation is acquired through the immersion helmet worn by the operator, a virtual space is combined with a scene of a real world by depending on a constructed three-dimensional scene model, the mounting and dismounting of a bearing in the virtual world are controlled, and meanwhile, a result is fed back to the operator, so that the operator can improve operation steps;
s4, recording and storing: in the operation process, the camera records the whole replacement process and then stores the whole replacement process in the storage medium, so that reference is provided for future training and teaching.
Example 2
The embodiment is further limited on the basis of embodiment 1, wherein physical simulation software in S1 is established by a virtual reality technology, a data threshold is calculated by an algorithm during simulation in S1, and the process requires four steps: selecting and initializing, calculating and dividing, calculating again and repeating circularly; the selection and initialization steps are as follows: first selecting some threshold classes/groups and initializing their respective center points randomly; the center point is a position with the same length as each data point vector, and the number of classes (i.e. the number of center points) needs to be predicted in advance; the calculation and division steps are as follows: calculating the distance from each data point to the central point, and dividing the data point into which class the data point is closest to which central point; the recalculation step is specifically as follows: calculating the central point in each class as a new central point, and repeating the steps circularly by adopting the following method: the method comprises the following steps: repeating the steps until the center of each type does not change greatly after each iteration; the second method comprises the following steps: the central point is also randomly initialized for many times, and then the best one of the operation results is selected; the third method comprises the following steps: from the two types of points obtained, re-computing the centroid (shortest distance to all points of the class) of the two types of points re-assigns all points to one of two new centroids. Repeating the above process until the center of each class does not change much after each iteration; the threshold calculation algorithm is composed of three modules, and the three modules are respectively: the system comprises a machine learning module, an algorithm realization module and an abnormity judgment processing module, wherein the machine learning module comprises the following algorithms:
import pandas as pd
import numpy as np
from sklearn. cluster import KMeans；
the algorithm implementation module algorithm is as follows:
y =[470, 509，500, 511,435,489,483,483,482。483, 504, 472,464,481, 501, 581，507,558, 569,467,38
km =KMeans(n_ clusters-2)
km.fit(y)
y['fcst'] = km.predict(y)
wherein, inputting a y, defining and dividing into two categories (automatic one category is normal, one category is abnormal), the field fcst records the predicted classification result, there are two categories 0 and 1, but we do not know which category is normal, we have a reasonable assumption, more in the category are normal, less are abnormal;
the algorithm of the abnormity judgment processing module is as follows:
labele = y[y.fcst==0]['fcst']. count()
label1= y[y.fcst==1]['fcst']. count()
if labell<=labele:
y[' isAbnormal ']=y['fcst']
else:
y.1oc[y['fcst'] == 0，'isAbnormal']=1
y.1oc[y['fcst'] == 1，' isAbnormal']=0
y.columns = [ 'data','fcst',' isAbnormal']
y[' isAbnormal']= y[ ' isAbnormal ']. astype(int)
y = y['data',' isAbnormal'll
recording the number classified into 1 and the number classified into 0, and finally recording whether the abnormal condition exists by using a field isAbnormal, wherein 0 is normal and 1 is abnormal; the three-dimensional modeling software in the S2 adopts one of AutoCAD, solidWorks, MASTERCAM, creo, inventor, cimatron, abaqus, solidedge, labVIEW, alias, 3d-max, flash and photoshop; in S3, the virtual space is combined with a real world scene during immersion operation and is also connected with an acquisition device, an immersion type helmet and an actual operation mechanism, wherein the acquisition device comprises a sensor and a camera and is established according to field monitoring of the existing cold rolling unit, the actual operation mechanism comprises an industrial robot and a cold rolling unit, and the industrial robot is used for operating bearing installation on the cold rolling unit; the storage medium in the S4 is composed of a cloud storage platform and a physical storage module, the storage module is implemented by any type of volatile or nonvolatile storage device or a combination thereof, the storage module is implemented by a static random access memory, an electrically erasable programmable read only memory, an erasable programmable read only memory, a magnetic memory, a flash memory, a magnetic disk or an optical disk, and the cloud storage platform is one of a hundred-degree cloud platform, a Hua-cloud disk, a WPS cloud disk, an ari cloud disk, a fast cloud disk, a quark cloud disk and the like.
The working principle is as follows: measuring parts such as bearings of a cold rolling unit by using a measuring tool, inputting measured data into physical simulation software established by a virtual reality technology for simulation processing so as to obtain a corresponding virtual space, calculating a data threshold value by an algorithm in the simulation process, wherein the process needs four steps: selecting and initializing, calculating and dividing, calculating again and repeating circularly; detecting surrounding scenes such as a bearing seat and a sealing element which are matched with parts such as a bearing of a cold rolling unit, and the like, and inputting the detected surrounding scenes into three-dimensional software of AutoCAD, solidWorks, MASTERCAM, creo, inventor, cimatron, abaqus, solidedge, labVIEW, alias, 3d-max, flash and photoshop to perform three-dimensional modeling; firstly, an operator wears an immersive helmet, then scene data of a unit implementation is acquired through the immersive helmet worn by the operator, a virtual space is combined with a scene of a real world by depending on a constructed three-dimensional scene model, the mounting and dismounting of a bearing in the virtual world are controlled, meanwhile, the virtual equipment and the real operating mechanism are matched to enable the real operating mechanism to carry out actual operation on the cold rolling unit when the virtual operation of the operator is performed, then the operator knows the difference of operation between virtual and real through the data acquired by the acquisition equipment, the operator can complete the mounting of the bearing according to more complex actual requirements, and the result is fed back to the operator in the process, so that the operator can improve the operation steps; in the operation process, the camera records the whole replacement process and then stores the whole replacement process in the storage medium, so that reference is provided for future training and teaching.
While certain exemplary embodiments of the present invention have been described above by way of illustration only, it will be apparent to those of ordinary skill in the art that the described embodiments may be modified in various different ways without departing from the spirit and scope of the invention. Accordingly, the drawings and description are illustrative in nature and are not to be construed as limiting the scope of the invention.
Claims (10)
1. A method for improving bearing replacement efficiency of a cold rolling unit by using a virtual reality technology is characterized by comprising the following steps:
s1, physical simulation: measuring parts such as a bearing of a cold rolling unit by using a measuring tool, and inputting measured data into physical simulation software for simulation processing so as to obtain a corresponding virtual space;
s2, three-dimensional modeling: detecting surrounding scenes matched with parts of the cold rolling unit, and inputting the surrounding scenes into three-dimensional software to perform three-dimensional modeling;
s3, immersion operation: firstly, an operator wears an immersion helmet, then scene data of a unit implementation is acquired through the immersion helmet worn by the operator, a virtual space is combined with a scene of a real world by depending on a constructed three-dimensional scene model, the mounting and dismounting of a bearing in the virtual world are controlled, and meanwhile, a result is fed back to the operator, so that the operator can improve operation steps;
s4, recording and storing: in the operation process, the camera records the whole replacement process and then stores the whole replacement process in the storage medium, so that reference is provided for future training and teaching.
2. The method for improving bearing replacement efficiency of the cold rolling mill train by using the virtual reality technology as claimed in claim 1, wherein the physical simulation software in the step S1 is established by using the virtual reality technology, the data threshold is calculated by an algorithm during simulation in the step S1, and the process requires four steps: selecting and initializing, calculating and dividing, calculating again and repeating circularly.
3. The method for improving bearing replacement efficiency of a cold rolling mill train by using a virtual reality technology according to claim 2, wherein the selecting and initializing steps are as follows: some threshold classes/sets are first selected and their respective center points are randomly initialized.
4. The method of claim 2, wherein the center point is the same length as each data point vector and the number of classes is predicted in advance.
5. The method for improving the bearing replacement efficiency of the cold rolling mill train by using the virtual reality technology as claimed in claim 3, wherein the calculation and division steps are specifically as follows: the distance of each data point to the center point is calculated, and the class to which the data point is closest to which center point is classified.
6. The method for improving bearing replacement efficiency of a cold rolling mill train by using the virtual reality technology as claimed in claim 2, wherein the recalculating step is specifically as follows: calculating the central point in each class as a new central point, and the step of repeating the cycle can adopt the following method: the method comprises the following steps: repeating the steps until the change of each type of center after each iteration is not large; the second method comprises the following steps: randomly initializing a central point for many times, and then selecting the best one of the operation results; the third method comprises the following steps: according to the obtained two types of points, the centroid in the two types of points is recalculated, all the points are classified into one of two new centroids, and the process is repeated until the change of the center of each type is not large after each iteration.
7. The method for improving the bearing replacement efficiency of the cold rolling mill train by using the virtual reality technology according to claim 2, wherein the threshold calculation algorithm is composed of three modules, and the three modules are respectively: the system comprises a machine learning module, an algorithm realization module and an abnormity judgment processing module, wherein the algorithm of the machine learning module is as follows:
import pandas as pd
import numpy as np
from sklearn. cluster import KMeans；
the algorithm implementation module algorithm is as follows:
y =[470, 509,500, 511,435,489,483,483,482,483, 504, 472,464,481, 501, 581,507,558, 569,467,38
km =KMeans(n_ clusters-2)
km.fit(y)
y['fcst'] = km.predict(y)
wherein, inputting a y, defining and dividing into two categories (automatic one category is normal, one category is abnormal), the field fcst records the predicted classification result, there are two categories 0 and 1, assuming that more of the categories are normal, and less are abnormal;
the algorithm of the abnormity judgment processing module is as follows:
labele = y[y.fcst==0]['fcst']. count()
label1= y[y.fcst==1]['fcst']. count()
if labell<=labele:
y[' isAbnormal ']=y['fcst']
else:
y.1oc[y['fcst'] == 0，'isAbnormal']=1
y.1oc[y['fcst'] == 1，' isAbnormal']=0
y.columns = [ 'data','fcst',' isAbnormal']
y[' isAbnormal']= y[ ' isAbnormal ']. astype(int)
y = y['data',' isAbnormal'll
in which the number classified as 1 and the number classified as 0 are recorded, and finally whether or not abnormal is recorded with a field isadenormal, 0 being normal and 1 being abnormal.
8. The method for improving bearing replacement efficiency of a cold rolling mill train by using a virtual reality technology according to claim 1, wherein the three-dimensional modeling software in S2 is one of AutoCAD, solidWorks, MASTERCAM, creo, inventor, cimatron, abaqus, solidedge, labVIEW, alias, 3d-max, flash, and photoshop.
9. The method for improving bearing replacement efficiency of the cold rolling mill train by using the virtual reality technology is characterized in that the virtual space in the immersion operation in the step S3 is not only combined with a real world scene, but also connected with a collection device, an immersion helmet and a real operating mechanism, wherein the collection device comprises a sensor and a camera, the collection device is established according to the field monitoring of the existing cold rolling mill train, and the real operating mechanism comprises an industrial robot and the cold rolling mill train, and the industrial robot is used for operating the bearing installation on the cold rolling mill train.
10. The method for improving bearing replacement efficiency of a cold rolling mill train by using a virtual reality technology according to claim 1, wherein the storage medium in S4 is composed of a cloud storage platform and a physical storage module, the storage module is realized by any type of volatile or nonvolatile storage device or a combination thereof, the storage module is realized by a static random access memory, an electrically erasable programmable read only memory, an erasable programmable read only memory, a magnetic memory, a flash memory, a magnetic disk or an optical disk, and the cloud storage platform is one of a hundred-degree cloud, a hua-degree cloud, a WPS cloud, an ari cloud, a xu-ray cloud and a quark cloud.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211495963.4A CN115796027A (en) | 2022-11-26 | 2022-11-26 | Method for improving bearing replacement efficiency of cold rolling unit by using virtual reality technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211495963.4A CN115796027A (en) | 2022-11-26 | 2022-11-26 | Method for improving bearing replacement efficiency of cold rolling unit by using virtual reality technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115796027A true CN115796027A (en) | 2023-03-14 |
Family
ID=85441827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211495963.4A Pending CN115796027A (en) | 2022-11-26 | 2022-11-26 | Method for improving bearing replacement efficiency of cold rolling unit by using virtual reality technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115796027A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080162262A1 (en) * | 2006-12-30 | 2008-07-03 | Perkins Cheryl A | Immersive visualization center for creating and designing a "total design simulation" and for improved relationship management and market research |
| DE102010018861A1 (en) * | 2010-04-30 | 2011-11-03 | Umwelttechnikbüro Fricke/Schran GbR (vertretungsberechtigter Gesellschafter Eckhard Schran, 07613 Crossen) | Training and service device for experimenting operation of small energy plant, has internal server transmitting data regarding operating mode of power generating unit to external data processing unit through communication network |
| CN106095105A (en) * | 2016-06-21 | 2016-11-09 | 西南交通大学 | A kind of traction substation operator on duty's virtual immersive Training Simulation System and method |
| US20170046977A1 (en) * | 2015-08-12 | 2017-02-16 | Illinois Tool Works Inc. | Welding training system interface |
| CN106548678A (en) * | 2016-12-12 | 2017-03-29 | 墨宝股份有限公司 | A kind of three-dimensional Driving Test analog systemss and its implementation based on immersion VR |
| CN106843150A (en) * | 2017-02-28 | 2017-06-13 | 清华大学 | A kind of industry spot simulation method and device |
| WO2018141023A1 (en) * | 2017-02-02 | 2018-08-09 | Advancing Projects Pty Ltd | A vehicle driving simulator for training or use of automotive car drivers or mobile devices controlled or occupied by humans |
| CN110162179A (en) * | 2019-05-24 | 2019-08-23 | 北京理工大学 | A kind of Intellisense virtual assembly system |
| US20200234049A1 (en) * | 2017-10-09 | 2020-07-23 | Björn Schwerdtfeger | Mixed reality simulator for professional training |
| US10977956B1 (en) * | 2016-11-01 | 2021-04-13 | State Farm Mutual Automobile Insurance Company | Systems and methods for virtual reality based driver training |
-
2022
- 2022-11-26 CN CN202211495963.4A patent/CN115796027A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080162262A1 (en) * | 2006-12-30 | 2008-07-03 | Perkins Cheryl A | Immersive visualization center for creating and designing a "total design simulation" and for improved relationship management and market research |
| DE102010018861A1 (en) * | 2010-04-30 | 2011-11-03 | Umwelttechnikbüro Fricke/Schran GbR (vertretungsberechtigter Gesellschafter Eckhard Schran, 07613 Crossen) | Training and service device for experimenting operation of small energy plant, has internal server transmitting data regarding operating mode of power generating unit to external data processing unit through communication network |
| US20170046977A1 (en) * | 2015-08-12 | 2017-02-16 | Illinois Tool Works Inc. | Welding training system interface |
| CN106095105A (en) * | 2016-06-21 | 2016-11-09 | 西南交通大学 | A kind of traction substation operator on duty's virtual immersive Training Simulation System and method |
| US10977956B1 (en) * | 2016-11-01 | 2021-04-13 | State Farm Mutual Automobile Insurance Company | Systems and methods for virtual reality based driver training |
| CN106548678A (en) * | 2016-12-12 | 2017-03-29 | 墨宝股份有限公司 | A kind of three-dimensional Driving Test analog systemss and its implementation based on immersion VR |
| WO2018141023A1 (en) * | 2017-02-02 | 2018-08-09 | Advancing Projects Pty Ltd | A vehicle driving simulator for training or use of automotive car drivers or mobile devices controlled or occupied by humans |
| CN106843150A (en) * | 2017-02-28 | 2017-06-13 | 清华大学 | A kind of industry spot simulation method and device |
| US20200234049A1 (en) * | 2017-10-09 | 2020-07-23 | Björn Schwerdtfeger | Mixed reality simulator for professional training |
| CN110162179A (en) * | 2019-05-24 | 2019-08-23 | 北京理工大学 | A kind of Intellisense virtual assembly system |
Non-Patent Citations (3)
| Title |
|---|
| 梁斌炜: "质量管理异常判定方法（SPC统计过程控制整 合机器学习算法）", pages 1 - 5, Retrieved from the Internet <URL:(https://www.statr> * |
| 梁斌炜: "质量管理异常统计判定方法（SPC统计过程控制整合机器学习算法）", pages 1 - 4, Retrieved from the Internet <URL:https://www.statr.cn/?p=515%25252525252525252526> * |
| 王大虎;王敬冲;刘海洋;: "悬臂式掘进机虚拟仿真平台设计", 测控技术, no. 06 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10510195B2 (en) | System and method for monitoring stress cycles | |
| US20200370996A1 (en) | System And Method For Operational-Data-Based Detection Of Anomaly Of A Machine Tool | |
| CN105988910B (en) | Storage device life monitoring system and storage device life monitoring method thereof | |
| US10889099B2 (en) | System and method for automatic support device generation | |
| CN114237155A (en) | Error prediction and compensation method, system and medium for multi-axis CNC machining | |
| CN114239708B (en) | Combustion engine abnormity detection method based on quality control chart theory | |
| CN112001409A (en) | A method and system for abnormal diagnosis of line loss in distribution network based on K-means clustering algorithm | |
| CN116738353B (en) | Pharmaceutical workshop air filter element performance detection method based on data analysis | |
| CN113110355A (en) | Method for predicting and optimizing machining energy consumption of workpiece driven by digital twin | |
| CN115796027A (en) | Method for improving bearing replacement efficiency of cold rolling unit by using virtual reality technology | |
| CN115297184B (en) | Data acquisition system for digital twins | |
| JP4967088B2 (en) | Information processing apparatus having failure analysis function, failure analysis method, and failure analysis program | |
| JP2020170357A (en) | Predictive maintenance facility, predictive maintenance method and predictive maintenance program | |
| CN117851810B (en) | Method and system for detecting and solving faults of shield machine | |
| JP7154100B2 (en) | Machining abnormality detection device for machine tools | |
| KR102558133B1 (en) | Method of deriving optimal parameters for CNC machine through artificial intelligence | |
| CN103821673B (en) | A kind of gear case of blower vibrating sensor collocation method based on structural analysis | |
| CN108627242B (en) | Ring cooling machine air leakage rate detection method based on blind source separation unilateral detection method | |
| CN110263949A (en) | Merge the data processing method and system of machine mechanism and intelligent algorithm system | |
| CN118760104B (en) | Intelligent optimization process for precise numerical control machining and application | |
| CN113515089B (en) | Five-axis linkage fork type swinging head temperature compensation method | |
| EP4462204A1 (en) | System and method for performing virtual orchestration for managing and using a machining equipment | |
| CN119130763B (en) | Intelligent auxiliary monitoring device and monitoring method for new energy power plant | |
| TWI851986B (en) | Intelligent monitoring system and method for machine equipment | |
| JP2013109744A (en) | Storage system and product state management method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230314 |