CN111552247A - Equipment operation state determination method based on intelligent park and big data center - Google Patents
Equipment operation state determination method based on intelligent park and big data center Download PDFInfo
- Publication number
- CN111552247A CN111552247A CN202010384725.0A CN202010384725A CN111552247A CN 111552247 A CN111552247 A CN 111552247A CN 202010384725 A CN202010384725 A CN 202010384725A CN 111552247 A CN111552247 A CN 111552247A
- Authority
- CN
- China
- Prior art keywords
- equipment
- production
- state
- list
- target
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000004519 manufacturing process Methods 0.000 claims abstract description 267
- 239000013598 vector Substances 0.000 claims abstract description 213
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 238000006243 chemical reaction Methods 0.000 claims description 24
- 238000013507 mapping Methods 0.000 claims description 20
- 238000013500 data storage Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 230000003068 static effect Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/4183—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by data acquisition, e.g. workpiece identification
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/31—From computer integrated manufacturing till monitoring
- G05B2219/31282—Data acquisition, BDE MDE
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
The application relates to a method for determining the running state of equipment based on an intelligent park and a big data center. By applying the scheme, the operating parameters of j groups of equipment corresponding to i production equipment are determined in the first step, a parameter list is generated according to the equipment type information of i production equipment and the operating time period parameters of the operating parameters of the j groups of equipment in the second step, the parameter list is subjected to feature extraction to obtain a feature list, and the state feature vector with the maximum state weight in each target list unit is corrected based on the operating parameters of the j groups of equipment of each production equipment in the fourth step, so that the operating state vector corresponding to each production equipment is obtained. The influence among the production devices is eliminated by correcting the state characteristic vector with the maximum state weight, noise removal is realized when the operation state vector is determined, and the working state of each production device is accurately determined so as to reduce the difficulty of scheduling the production devices.
Description
Technical Field
The application relates to the technical field of industrial internet based on big data, in particular to a device running state determining method based on a smart park and a big data center.
Background
The intelligent park refers to a standard building or building group which has complete supporting facilities and reasonable layout and can meet the production and scientific experiment needs of a certain specific industry. Such as industrial parks, logistics parks, and technology parks, among others. Use industry garden as an example, through being applied to industry garden with thing networking communication, can realize the cooperative operation of the production facility in the industry garden to improve the production efficiency in industry garden. However, it is difficult to accurately determine the operating status of each production device while the mass production devices in the industrial park are running, thereby increasing the difficulty of scheduling the production devices.
Disclosure of Invention
The method is used for disclosing an equipment running state determining method based on an intelligent park and a large data center so as to solve the technical problem that the working state of each production equipment is difficult to determine in the prior art.
The first technical scheme of the disclosure is an equipment operation state determining method based on an intelligent park, which is applied to a big data center communicating with a plurality of production equipment, and the method comprises the following steps:
determining j groups of equipment operating parameters respectively corresponding to the i production equipment from a preset storage space for storing the equipment operating parameters; wherein, m kinds of running state marks are included in the i production devices at least;
generating a parameter list according to the equipment type information of the i production equipment and the operation time interval parameters of the operation parameters of the j group of equipment; the parameter list is i rows and j columns;
performing feature extraction on the parameter list according to a preset feature extraction logic to obtain a feature list formed by the equipment model information of the i production equipment and the influence weights of the m running state identifiers respectively corresponding to the i production equipment; wherein the feature list is i rows and m columns;
searching a target list unit corresponding to each production device in the feature list, and correcting the state feature vector with the maximum state weight in the target list unit based on j groups of device operation parameters of each production device to obtain an operation state vector corresponding to each production device; wherein the operation state vector is used for representing the working state of the production equipment.
Optionally, the method further includes:
determining a first state type and a second state type according to a preset production line information set; the first state type is used for representing the type of the running state vector of the production equipment in the continuous running state, and the second state type is used for representing the type of the running state vector of the production equipment in the discontinuous running state;
and determining current production line information from the production line information set, dividing the running state vector corresponding to each production device into the first state category or the second state category according to the current production line information, and scheduling the running state of each production device according to the running state vector in the first state category and the running state vector in the second state category.
Optionally, the method further comprises:
acquiring a production line adjusting instruction;
determining target production line information from the production line information set according to a production line identification in the production line adjustment instruction;
and readjusting the running state vector corresponding to each production device under the first state category or the second state category according to the current production line information, and scheduling the running state of each production device based on the adjusted running state vector under the first state category and the adjusted running state vector under the second state category.
Optionally, the determining, from a preset storage space for storing the device operation parameters, j groups of device operation parameters respectively corresponding to the i production devices further includes:
acquiring a graph data structure sequence corresponding to each group of equipment operation parameters in the storage space and acquiring a data storage format sequence corresponding to the storage space; the graph data structure sequence and the data storage structure sequence respectively comprise data units with different structure compatibility degrees, the graph data structure sequence is used for representing the storage form of the equipment operation parameters in the storage space, and the data storage format sequence is used for representing the data format conversion logic of the storage space during the storage of the equipment operation parameters;
extracting a first structural parameter section of each group of equipment operating parameters in any data unit of the graph data structure sequence, and determining a data unit of each group of equipment operating parameters with the minimum structural compatibility in the data storage format sequence as a first data unit;
projecting the first structural parameter section to the first data unit according to each production device and the device operation parameter corresponding to the production device, and obtaining a second structural parameter section in the first data unit; generating a first structural conversion list of the storage space corresponding to each set of equipment operating parameters based on the first structural parameter section and the second structural parameter section;
acquiring a second structural parameter section in the first data unit by taking the second structural parameter section as a reference parameter section, projecting the second structural parameter section to a second data unit where the first structural parameter section is located according to a second structural conversion list with reverse conversion logic to the first structural conversion list, and acquiring a graph data relation sequence corresponding to the second structural parameter section in the second data unit where the first structural parameter section is located; wherein, each group of graph data relation sequence corresponds to a group of equipment operation parameters;
and performing format conversion on each group of equipment operation parameters in the storage space based on the graph data relation sequence to obtain target equipment operation parameters expressed in a character coding form, and determining j groups of target equipment operation parameters respectively corresponding to i production equipment.
Optionally, the generating a parameter list according to the device type information of the i pieces of production devices and the operation period parameter of the operation parameter of the j group of devices further includes:
extracting target field information of each group of equipment type information, and extracting field characteristics based on the target field information to obtain type field characteristics of each group of equipment type information; the target field information is information corresponding to a parameter list thread of the big data center in each group of equipment type information;
comparing the type field characteristics of each group of equipment type information with the target type field characteristics of each sample type information in a preset field characteristic set to obtain a comparison result; target type field characteristics corresponding to a plurality of sample type information and heterogeneous coefficients corresponding to the target type field characteristics are stored in the preset field characteristic set;
when the comparison result represents that the type field characteristics of the equipment type information are similar to the corresponding target type field characteristics, correcting the target field information of the equipment type information according to the heterogeneous coefficient corresponding to the target field type characteristics and setting a first identifier; when the comparison result represents that the type field characteristics of the equipment type information are not similar to the corresponding target type field characteristics, setting a second identifier for the target field information corresponding to the equipment type information;
and carrying out one-to-one correspondence on the equipment type information of the i production equipment and the operation time interval parameters of the j group equipment operation parameters according to the sequence of the first identification and the second identification, and generating the parameter list based on the one-to-one correspondence result.
Optionally, the searching for the target list unit corresponding to each production device in the feature list further includes:
determining a first mapping value of the equipment type information of each production equipment in the feature list and a second mapping value of the equipment operation parameter in the feature list;
determining the relative position of each production device in the feature list according to the first mapping value and the second mapping value;
and determining a target list unit corresponding to each production device according to the relative position.
Optionally, the modifying, based on the j group device operation parameter of each production device, the state feature vector with the largest state weight in the target list unit to obtain an operation state vector corresponding to each production device, further includes:
clustering j groups of equipment operation parameters corresponding to each production equipment to obtain an operation parameter set corresponding to each production equipment;
and extracting the clustering feature vector corresponding to the operation parameter set, and weighting the clustering feature vector and the state feature vector with the maximum state weight in the target list unit to obtain the operation state vector corresponding to each production device.
A second technical solution of the present disclosure is a big data center, where the big data is communicated with a plurality of production devices, and the big data center is specifically configured to:
determining j groups of equipment operating parameters respectively corresponding to the i production equipment from a preset storage space for storing the equipment operating parameters; wherein, m kinds of running state marks are included in the i production devices at least;
generating a parameter list according to the equipment type information of the i production equipment and the operation time interval parameters of the operation parameters of the j group of equipment; the parameter list is i rows and j columns;
performing feature extraction on the parameter list according to a preset feature extraction logic to obtain a feature list formed by the equipment model information of the i production equipment and the influence weights of the m running state identifiers respectively corresponding to the i production equipment; wherein the feature list is i rows and m columns;
searching a target list unit corresponding to each production device in the feature list, and correcting the state feature vector with the maximum state weight in the target list unit based on j groups of device operation parameters of each production device to obtain an operation state vector corresponding to each production device; wherein the operation state vector is used for representing the working state of the production equipment.
A third technical solution of the present disclosure is a big data center, including: the system comprises a processor, a memory and a network interface, wherein the memory and the network interface are connected with the processor; the network interface is connected with a nonvolatile memory in the big data center; when the processor runs, the processor calls the computer program from the nonvolatile memory through the network interface and runs the computer program through the memory so as to execute the method.
A fourth technical solution of the present disclosure is a readable storage medium applied to a computer, where the readable storage medium is burned with a computer program, and the computer program implements the method when running in a memory of a big data center.
When the technical scheme disclosed by the disclosure is executed, firstly, j groups of equipment operation parameters respectively corresponding to i production equipment are determined, secondly, a parameter list is generated according to equipment type information of the i production equipment and operation time period parameters of the j groups of equipment operation parameters, thirdly, feature extraction is carried out on the parameter list, a feature list formed by the equipment model information of the i production equipment and influence weights of m kinds of operation state identifications respectively corresponding to the i production equipment is obtained, and fourthly, the state feature vector with the maximum state weight in each target list unit is corrected based on the j groups of equipment operation parameters of each production equipment, so that the operation state vector corresponding to each production equipment is obtained.
Therefore, when the operation state vector is determined, the influence of the production equipment communicating with each other can be taken into account, the influence between the production equipment is eliminated by correcting the state characteristic vector with the largest state weight, the noise removal is realized when the operation state vector is determined, the working state of each production equipment is accurately determined, and the difficulty of production equipment scheduling is reduced.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
Fig. 1 is a communication architecture diagram of an intelligent campus-based device operation status determination system according to an exemplary embodiment of the present application.
FIG. 2 is a flow chart illustrating a method for determining an operational status of a smart park-based device according to an exemplary embodiment of the present application.
Fig. 3 is a block diagram illustrating an embodiment of a method and apparatus for determining an operating status of a device based on a smart campus according to an exemplary embodiment of the present disclosure.
Fig. 4 is a hardware structure diagram of a big data center in which the device is located according to the method for determining the operating state of the device based on the smart campus.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application.
In order to accurately determine the working state of each production device and reduce the scheduling difficulty of the production devices, the equipment running state determining method based on the intelligent park and the big data center are disclosed.
To facilitate the above-mentioned solution, please refer to fig. 1, which is a schematic diagram of a communication architecture of an intelligent campus-based device operation status determination system 100 according to the present disclosure. The equipment operating state determination system 100 includes production equipment 200 and a large data center 300 distributed at various locations within an industrial park. Wherein the big data center 300 communicates with each production device 200 to form an intelligent internet of things production line for the industrial park.
The big data center 300 can be used to control and schedule each production facility 200 to ensure production efficiency throughout the industrial park. The production equipment 300 may be configured and arranged in different types according to differences of product lines, and is not limited herein.
On the basis of the above, please refer to fig. 2, which is a flowchart of the method for determining the operating status of the intelligent park-based equipment according to the present disclosure, the method can be applied to the big data center 300 in fig. 1, and specifically, the method can include the following steps.
Step S21, determining j groups of equipment operating parameters respectively corresponding to the i production equipment from a preset storage space for storing the equipment operating parameters; wherein, m kinds of running state marks are included in the i production equipment at least.
In the present disclosure, a storage space may be understood as a database, wherein the type of the database is not limited. For example, the database may be a mysql database or a janussgraph database, among other different types of databases. It is understood that the device type information differs from production device to production device. The i production devices are distributed in the industrial park, the operation time period parameters corresponding to the operation parameters of each group of devices are different, the influence weights of the production devices corresponding to the m operation state identifiers are different, the influence weights are used for representing the influence of each production device on the whole production line of the industrial park, and the influence weights can be values between 0 and 1. Further, i, j, and m are all positive integers.
Step S22, generating a parameter list according to the equipment type information of the i production equipment and the operation time interval parameter of the operation parameter of the j group of equipment; the parameter list is i rows and j columns.
Step S23, extracting the characteristics of the parameter list according to a preset characteristic extraction logic to obtain a characteristic list formed by the equipment model information of the i production equipments and the influence weights of the m running state identifications respectively corresponding to the i production equipments; wherein the feature list is i rows and m columns.
Step S24, searching a target list unit corresponding to each production device in the feature list, and correcting the state feature vector with the maximum state weight in the target list unit based on the j group device operation parameters of each production device to obtain an operation state vector corresponding to each production device; wherein the operation state vector is used for representing the working state of the production equipment.
In the disclosure, the state weight is used to represent the degree of association between the production equipment corresponding to the target list unit and other production equipment, and the greater the state weight is, the higher the degree of association between the production equipment corresponding to the target list unit and other production equipment is, the more easily the production equipment is influenced by the operating state of other production equipment.
When the method disclosed in the above step S21-step S24 is executed, the first step determines j sets of device operation parameters corresponding to i production devices, the second step generates a parameter list according to the device type information of the i production devices and the operation time period parameters of the j sets of device operation parameters, the third step performs feature extraction on the parameter list to obtain a feature list formed by the device model information of the i production devices and the influence weights of m types of operation state identifiers corresponding to the i production devices, and the fourth step corrects the state feature vector with the largest state weight in each target list unit based on the j sets of device operation parameters of each production device to obtain the operation state vector corresponding to each production device.
By applying the scheme disclosed above, when determining the operation state vector, the influence of the production devices communicating with each other can be taken into account, and the influence between the production devices is eliminated by correcting the state feature vector with the largest state weight, so that noise removal is realized when determining the operation state vector, the working state of each production device is accurately determined, and the difficulty in scheduling the production devices is reduced.
The inventor finds that when the technical scheme is implemented, if the device operating parameters stored in the storage space are stored in the form of graph data, if the graph data are directly extracted and subjected to subsequent analysis and processing, it is difficult to generate a relevant list and a relevant feature list due to different data structures.
To improve the above problem, in step S21, the j groups of device operation parameters respectively corresponding to the i production devices are determined from the preset storage space for storing the device operation parameters, which can be further implemented as follows.
Step S211, acquiring a graph data structure sequence corresponding to each group of equipment operation parameters in the storage space and acquiring a data storage format sequence corresponding to the storage space; the graph data structure sequence and the data storage structure sequence respectively comprise data units with different structure compatibility degrees, the graph data structure sequence is used for representing the storage form of the equipment operation parameters in the storage space, and the data storage format sequence is used for representing the data format conversion logic of the storage space during the storage of the equipment operation parameters.
Step S212, extracting a first structural parameter segment of each set of device operating parameters in any data unit of the graph data structure sequence, and determining a data unit of each set of device operating parameters having a minimum structural compatibility in the data storage format sequence as a first data unit.
Step S213, projecting the first structural parameter section to the first data unit according to each production device and the device operation parameter corresponding to the production device, and obtaining a second structural parameter section in the first data unit; and generating a first structural conversion list of the storage space corresponding to each group of equipment operation parameters based on the first structural parameter section and the second structural parameter section.
Step S214, obtaining a second structural parameter segment in the first data unit by using the second structural parameter segment as a reference parameter segment, projecting the second structural parameter segment to a second data unit where the first structural parameter segment is located according to a second structural conversion list having an inverse conversion logic with respect to the first structural conversion list, and obtaining a graph data relationship sequence corresponding to the second structural parameter segment in the second data unit where the first structural parameter segment is located; and each group of graph data relation sequence corresponds to one group of equipment operation parameters.
Step S215, based on the graph data relation sequence, performing format conversion on each group of equipment operation parameters in the storage space to obtain target equipment operation parameters expressed in a character coding form, and determining j groups of target equipment operation parameters respectively corresponding to i production equipment.
By executing the contents described in the above steps S211 to S215, each set of device operation parameters in the storage space can be format-converted, so as to convert the device operation parameters in the graph data format into the target device operation parameters in the character encoding format, and thus, the uniformity of the data structure can be ensured, and the target device operation parameters can be directly processed and used subsequently.
In an implementation, after the operation state vector of each production device is accurately determined, in order to quickly and reliably schedule the production device to flexibly adjust the production line of the industrial park, the method may further include the following steps on the basis of the steps S21 to S24.
Step S25, determining a first state type and a second state type according to a preset production line information set; the first state type is used for representing the type of the running state vector of the production equipment in the continuous running state, and the second state type is used for representing the type of the running state vector of the production equipment in the discontinuous running state.
Step 26, determining current production line information from the production line information set, dividing the operation state vector corresponding to each production device into the first state category or the second state category according to the current production line information, and scheduling the operation state of each production device according to the operation state vector in the first state category and the operation state vector in the second state category.
In the specific implementation process, through the contents described in the above steps S25 to S26, the first state category and the second state category can be determined based on the preset production line information set, and then the operation state vector corresponding to each production equipment is divided into the first state category or the second state category according to the current production line information, so that the production equipment is quickly and reliably scheduled according to the division result to flexibly adjust the production line of the industrial park.
On the basis of the above steps S25-S26, in order to further rapidly and reliably schedule the production equipment, the method may further include the following steps.
In step S27, a line adjustment instruction is acquired.
And step S28, determining target production line information from the production line information set according to the production line identification in the production line adjusting instruction.
Step S29, readjusting the operation state vector corresponding to each production device in the first state category or the second state category according to the current production line information, and scheduling the operation state of each production device based on the adjusted operation state vector in the first state category and the adjusted operation state vector in the second state category.
It can be understood that, by the above, the operation state vector corresponding to each production device can be readjusted in the first state category or the second state category based on the target production line information, thereby increasing the speed of adjusting the operation state vector. In this way, production equipment can be scheduled quickly and reliably.
In practical applications, the inventors found that, when generating the parameter list, the types of different production devices need to be considered to avoid that the heterogeneity among the production devices affects the integrity of the parameter list. To achieve the above object, in step S22, the step of generating the parameter list according to the device type information of the i-station production devices and the operation period parameters of the operation parameters of the j-group device may specifically include the following steps.
Step S221, extracting target field information of each group of equipment type information, and extracting field characteristics based on the target field information to obtain type field characteristics of each group of equipment type information; and the target field information is information corresponding to the parameter list thread of the big data center in each group of equipment type information.
Step S222, comparing the type field characteristics of each group of equipment type information with the target type field characteristics of each sample type information in a preset field characteristic set to obtain a comparison result; and target type field characteristics corresponding to a plurality of sample type information and heterogeneous coefficients corresponding to the target type field characteristics are stored in the preset field characteristic set.
Step S223, when the comparison result represents that the type field characteristics of the equipment type information are similar to the corresponding target type field characteristics, correcting the target field information of the equipment type information according to the heterogeneous coefficient corresponding to the target field type characteristics and setting a first identifier; and when the comparison result represents that the type field characteristics of the equipment type information are not similar to the corresponding target type field characteristics, setting a second identifier for the target field information corresponding to the equipment type information.
Step S224, performing one-to-one correspondence between the device type information of the i production devices and the operation time period parameters of the operation parameters of the j group of devices according to the sequence of the first identifier and the second identifier, and generating the parameter list based on the one-to-one correspondence result.
It is understood that, through the contents described in the above steps S221 to S224, the device types of different production devices can be taken into consideration, so that the target field information of each set of device type information is corrected and identity set based on the heterogeneous coefficient between the production devices. Therefore, the one-to-one corresponding relation between the equipment type information and the operation time period parameters can be ensured, and the influence on the integrity of the parameter list is avoided. Thus, the parameter list can be completely and accurately determined.
In a specific implementation, in order to avoid the problem of repeated searching when searching for the target list unit, in step S24, the searching for the target list unit corresponding to each production device in the feature list may specifically include: determining a first mapping value of the equipment type information of each production equipment in the feature list and a second mapping value of the equipment operation parameter in the feature list; and determining the relative position of each production device in the feature list according to the first mapping value and the second mapping value, and determining a target list unit corresponding to each production device according to the relative position.
In the above, the first mapping value may be a number of rows of the list and the second mapping value may be a number of columns of the list. Through the content, the target list unit corresponding to each production device can be accurately searched based on the first mapping value and the second mapping value, and the problem of repeated searching when the target list unit is searched is solved.
In practical applications, in order to increase the speed of determining the operation state vector, in step S24, the state feature vector with the largest state weight in the target list unit is corrected based on the j groups of device operation parameters of each production device, so as to obtain the operation state vector corresponding to each production device.
Step S241, clustering the j groups of device operation parameters corresponding to each production device to obtain an operation parameter set corresponding to each production device.
Step S242, extracting the clustering feature vector corresponding to the operation parameter set, and weighting the clustering feature vector and the state feature vector with the largest state weight in the target list unit to obtain an operation state vector corresponding to each production device.
When the contents described in the above steps S241 to S242 are applied, the j groups of device operation parameters corresponding to each production device can be clustered, so that the state feature vector with the largest state weight in the target list unit is weighted based on the extracted cluster feature vector. Therefore, the state characteristic vector is not required to be corrected in sequence by adopting each group of equipment operation parameters, and the determination speed of the operation state vector is improved.
In an alternative embodiment, in order to accurately determine the operation state vector corresponding to each production device, it is necessary to avoid an error occurring in the vector weighting process, and for this purpose, in step S242, the clustering feature vector is weighted with the state feature vector with the largest state weight in the target list unit to obtain the operation state vector corresponding to each production device, which further includes the following steps.
Step S2421, determining a first feature dimension of the clustering feature vector and a second feature dimension of the state feature vector with the largest state weight in the target list unit.
Step S2422, judging whether the first characteristic dimension and the second characteristic dimension are the same; if yes, go to step S2423; if not, the process proceeds to step S2424.
Step S2423, when the first characteristic dimension is the same as the second characteristic dimension, weighting the clustering characteristic vector and the state characteristic vector according to the corresponding relation of the first characteristic dimension and the second characteristic dimension to obtain the running state vector.
Step S2424, when the first characteristic dimension is different from the second characteristic dimension, acquiring a cluster identifier of the cluster characteristic vector and each characteristic vector value; and if the clustering feature vector contains the dynamic dimension classification based on the clustering identification, calculating a vector difference value between each feature vector value of the clustering feature vector in the static dimension classification and each feature vector value of the clustering feature vector in the dynamic dimension classification according to the feature vector value of the clustering feature vector in the dynamic dimension classification and the feature vector weight thereof.
Step S2425, importing the target feature vector value of the clustering feature vector in the static dimension classification into the dynamic dimension classification according to the vector difference value; if the clustering feature vector contains a plurality of feature vector values in the static dimension classification, determining a vector difference value between the feature vector values of the clustering feature vector in the static dimension classification according to the feature vector values of the clustering feature vector in the dynamic dimension classification and the feature vector weight thereof, and classifying the feature vector values in the static dimension classification according to the vector difference value between the feature vector values to obtain a first classification set and a second classification set.
Step S2426, importing all eigenvector values in the first classification set into the dynamic dimension classes, and determining first eigenvectors of the clustering eigenvectors according to the eigenvector values of the clustering eigenvectors in the static dimension classes; and when the first characteristic dimension is the same as the second characteristic dimension, weighting the clustering characteristic vector and the state characteristic vector according to the corresponding relation of the first characteristic dimension and the second characteristic dimension to obtain the running state vector.
When the contents described in the steps S2421 to S2426 are applied, the consistency of the dimensions of the clustering feature vectors and the state feature vectors can be ensured before the vector weighting is performed, so that errors can be avoided in the vector weighting process, and the operation state vector corresponding to each production device can be accurately determined.
In an alternative embodiment, the inventors have found that although the device operating state of each device can be determined by the operating state vector, it is difficult to determine the detailed content and the complete content of the device operating state of each production device by the operating state vector, which makes it difficult to satisfy the subsequent establishment of an operation log for the production device. Therefore, in order to conveniently create the operation log of each production device, the method may further include the following steps on the basis of the steps S21 to S24.
Step S31, determining state identification information corresponding to each state vector value of the operating state vector and a state coefficient of each state vector value, where the state coefficient represents a size of the state information of each state vector value of the operating state vector; the state coefficients include at least: a first state information capacity and a second state information capacity representing each state vector value of the operating state vector.
Step S32, acquiring a preset identifier list corresponding to the state identifier information, where the preset identifier list includes path information of pre-extracted state identifier information, and the path information of the state identifier information indicates a restoration path of state information of each state vector value located in the preset identifier list and corresponding to the state identifier information; the path information of the state identification information at least comprises: and the first state information capacity and the second state information capacity represent each state vector value corresponding to the list structure information contained in the preset identification list.
Step S33, according to the state identification information and the state coefficient, searching for target path information matched with each vector value in the running state vector in the preset identification list, and restoring each state vector value according to each target path information to obtain device running state information corresponding to the running state vector.
It can be understood that, through the steps S31 to S33, detailed and complete device operating state information of the device operating state of each production device can be determined through the operating state vector, so that it is convenient to subsequently establish an operating log of the production device directly according to the device operating state information.
On the basis of the above, the present disclosure also discloses an embodiment of the apparatus corresponding to the above method embodiment, please refer to fig. 3 together, and the specific description about the device 310 for determining the operation status of the equipment based on the intelligent campus is as follows.
A1. An equipment running state determining device based on a smart park is applied to a big data center communicating with a plurality of production equipment, the device comprises:
a parameter determining module 311, configured to determine, from a preset storage space for storing device operation parameters, j groups of device operation parameters respectively corresponding to i production devices; wherein, m kinds of running state marks are included in the i production devices at least;
a list generating module 312, configured to generate a parameter list according to the device type information of the i-station production device and the operation time period parameter of the operation parameter of the j-group device; the parameter list is i rows and j columns;
a feature extraction module 313, configured to perform feature extraction on the parameter list according to a preset feature extraction logic, to obtain a feature list formed by the device model information of the i production devices and the influence weights of the m running state identifiers respectively corresponding to the i production devices; wherein the feature list is i rows and m columns;
the vector correction module 314 is configured to search for a target list unit corresponding to each production device in the feature list, and correct the state feature vector with the largest state weight in the target list unit based on the j group device operation parameter of each production device, so as to obtain an operation state vector corresponding to each production device; wherein the operation state vector is used for representing the working state of the production equipment.
A2. The apparatus of a1, further comprising a status scheduling module 315 configured to:
determining a first state type and a second state type according to a preset production line information set; the first state type is used for representing the type of the running state vector of the production equipment in the continuous running state, and the second state type is used for representing the type of the running state vector of the production equipment in the discontinuous running state;
and determining current production line information from the production line information set, dividing the running state vector corresponding to each production device into the first state category or the second state category according to the current production line information, and scheduling the running state of each production device according to the running state vector in the first state category and the running state vector in the second state category.
A3. The apparatus of a2, the status scheduling module 315 further configured to:
acquiring a production line adjusting instruction;
determining target production line information from the production line information set according to a production line identification in the production line adjustment instruction;
and readjusting the running state vector corresponding to each production device under the first state category or the second state category according to the current production line information, and scheduling the running state of each production device based on the adjusted running state vector under the first state category and the adjusted running state vector under the second state category.
A4. The apparatus of any of A1-A3, the parameter determination module 311, further to:
acquiring a graph data structure sequence corresponding to each group of equipment operation parameters in the storage space and acquiring a data storage format sequence corresponding to the storage space; the graph data structure sequence and the data storage structure sequence respectively comprise data units with different structure compatibility degrees, the graph data structure sequence is used for representing the storage form of the equipment operation parameters in the storage space, and the data storage format sequence is used for representing the data format conversion logic of the storage space during the storage of the equipment operation parameters;
extracting a first structural parameter section of each group of equipment operating parameters in any data unit of the graph data structure sequence, and determining a data unit of each group of equipment operating parameters with the minimum structural compatibility in the data storage format sequence as a first data unit;
projecting the first structural parameter section to the first data unit according to each production device and the device operation parameter corresponding to the production device, and obtaining a second structural parameter section in the first data unit; generating a first structural conversion list of the storage space corresponding to each set of equipment operating parameters based on the first structural parameter section and the second structural parameter section;
acquiring a second structural parameter section in the first data unit by taking the second structural parameter section as a reference parameter section, projecting the second structural parameter section to a second data unit where the first structural parameter section is located according to a second structural conversion list with reverse conversion logic to the first structural conversion list, and acquiring a graph data relation sequence corresponding to the second structural parameter section in the second data unit where the first structural parameter section is located; wherein, each group of graph data relation sequence corresponds to a group of equipment operation parameters;
and performing format conversion on each group of equipment operation parameters in the storage space based on the graph data relation sequence to obtain target equipment operation parameters expressed in a character coding form, and determining j groups of target equipment operation parameters respectively corresponding to i production equipment.
A5. The apparatus of a1, the list generation module 312, further configured to:
extracting target field information of each group of equipment type information, and extracting field characteristics based on the target field information to obtain type field characteristics of each group of equipment type information; the target field information is information corresponding to a parameter list thread of the big data center in each group of equipment type information;
comparing the type field characteristics of each group of equipment type information with the target type field characteristics of each sample type information in a preset field characteristic set to obtain a comparison result; target type field characteristics corresponding to a plurality of sample type information and heterogeneous coefficients corresponding to the target type field characteristics are stored in the preset field characteristic set;
when the comparison result represents that the type field characteristics of the equipment type information are similar to the corresponding target type field characteristics, correcting the target field information of the equipment type information according to the heterogeneous coefficient corresponding to the target field type characteristics and setting a first identifier; when the comparison result represents that the type field characteristics of the equipment type information are not similar to the corresponding target type field characteristics, setting a second identifier for the target field information corresponding to the equipment type information;
and carrying out one-to-one correspondence on the equipment type information of the i production equipment and the operation time interval parameters of the j group equipment operation parameters according to the sequence of the first identification and the second identification, and generating the parameter list based on the one-to-one correspondence result.
A6. The apparatus of a1, the vector modification module 314, further configured to:
determining a first mapping value of the equipment type information of each production equipment in the feature list and a second mapping value of the equipment operation parameter in the feature list;
determining the relative position of each production device in the feature list according to the first mapping value and the second mapping value;
and determining a target list unit corresponding to each production device according to the relative position.
A7. The apparatus of a1, the vector modification module 314, further configured to:
clustering j groups of equipment operation parameters corresponding to each production equipment to obtain an operation parameter set corresponding to each production equipment;
and extracting the clustering feature vector corresponding to the operation parameter set, and weighting the clustering feature vector and the state feature vector with the maximum state weight in the target list unit to obtain the operation state vector corresponding to each production device.
A8. The apparatus of a7, the vector modification module 314, further configured to:
determining a first characteristic dimension of the clustering characteristic vector and a second characteristic dimension of a state characteristic vector with the largest state weight in the target list unit;
judging whether the first characteristic dimension and the second characteristic dimension are the same;
when the first characteristic dimension is the same as the second characteristic dimension, weighting the clustering characteristic vector and the state characteristic vector according to the corresponding relation of the first characteristic dimension and the second characteristic dimension to obtain the running state vector;
when the first characteristic dimension is different from the second characteristic dimension, acquiring a clustering identifier of the clustering characteristic vector and each characteristic vector value; if the clustering feature vector contains dynamic dimension classification based on the clustering identification, calculating a vector difference value between each feature vector value of the clustering feature vector in static dimension classification and each feature vector value of the clustering feature vector in dynamic dimension classification according to the feature vector value of the clustering feature vector in the dynamic dimension classification and the feature vector weight thereof;
leading the target characteristic vector value of the clustering characteristic vector in the static dimension classification into the dynamic dimension classification according to the vector difference value; if the clustering feature vector contains a plurality of feature vector values in the static dimension classification, determining a vector difference value between the feature vector values of the clustering feature vector in the static dimension classification according to the feature vector values of the clustering feature vector in the dynamic dimension classification and the feature vector weight thereof, and classifying the feature vector values in the static dimension classification according to the vector difference value between the feature vector values to obtain a first classification set and a second classification set;
leading each feature vector value in the first classification set into the dynamic dimension classification, and determining a first feature dimension of the clustering feature vector according to the feature vector value of the clustering feature vector in the static dimension classification; and when the first characteristic dimension is the same as the second characteristic dimension, weighting the clustering characteristic vector and the state characteristic vector according to the corresponding relation of the first characteristic dimension and the second characteristic dimension to obtain the running state vector.
A9 the apparatus of A1, the apparatus further comprising an information retrieval module 316 to:
determining state identification information corresponding to each state vector value of the operation state vector and a state coefficient of each state vector value, wherein the state coefficient represents the size of the state information of each state vector value of the operation state vector; the state coefficients include at least: a first state information capacity and a second state information capacity representing each state vector value of the operating state vector;
acquiring a preset identification list corresponding to the state identification information, wherein the preset identification list comprises pre-extracted path information of the state identification information, and the path information of the state identification information represents a restoration path of the state information of each state vector value which is positioned in the preset identification list and corresponds to the state identification information; the path information of the state identification information at least comprises: a first state information capacity and a second state information capacity representing each state vector value corresponding to list structure information contained in the preset identification list;
and searching target path information matched with each vector value in the running state vector in the preset identification list according to the state identification information and the state coefficient, and restoring each state vector value according to each target path information to obtain equipment running state information corresponding to the running state vector.
On the basis of the above embodiments, the present disclosure further provides a schematic diagram of a hardware structure of a big data center to which the above apparatus is attached, please refer to fig. 4, where the big data center 300 includes a processor 321, and a memory 322 and a network interface 323 connected to the processor 321. Wherein the network interface 323 is connected 324 with the non-volatile memory in the big data center 300. Further, the processor 321 retrieves a computer program from the non-volatile memory 324 through the network interface 323 and runs the computer program through the memory 322 when running, so as to execute the above method.
In addition, the present disclosure also discloses a readable storage medium applied to a computer, wherein a computer program is burned on the readable storage medium, and the computer program realizes the method when running in the memory 322 of the big data center 300.
When the technical scheme disclosed by the disclosure is executed, firstly, j groups of equipment operation parameters respectively corresponding to i production equipment are determined, secondly, a parameter list is generated according to equipment type information of the i production equipment and operation time period parameters of the j groups of equipment operation parameters, thirdly, feature extraction is carried out on the parameter list, a feature list formed by the equipment model information of the i production equipment and influence weights of m kinds of operation state identifications respectively corresponding to the i production equipment is obtained, and fourthly, the state feature vector with the maximum state weight in each target list unit is corrected based on the j groups of equipment operation parameters of each production equipment, so that the operation state vector corresponding to each production equipment is obtained.
Therefore, when the operation state vector is determined, the influence of the production equipment communicating with each other can be taken into account, the influence between the production equipment is eliminated by correcting the state characteristic vector with the largest state weight, the noise removal is realized when the operation state vector is determined, the working state of each production equipment is accurately determined, and the difficulty of production equipment scheduling is reduced.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. A device operation state determination method based on an intelligent park is applied to a big data center which is communicated with a plurality of production devices, and comprises the following steps:
determining j groups of equipment operating parameters respectively corresponding to the i production equipment from a preset storage space for storing the equipment operating parameters; wherein, m kinds of running state marks are included in the i production devices at least;
generating a parameter list according to the equipment type information of the i production equipment and the operation time interval parameters of the operation parameters of the j group of equipment; the parameter list is i rows and j columns;
performing feature extraction on the parameter list according to a preset feature extraction logic to obtain a feature list formed by the equipment model information of the i production equipment and the influence weights of the m running state identifiers respectively corresponding to the i production equipment; wherein the feature list is i rows and m columns;
searching a target list unit corresponding to each production device in the feature list, and correcting the state feature vector with the maximum state weight in the target list unit based on j groups of device operation parameters of each production device to obtain an operation state vector corresponding to each production device; wherein the operation state vector is used for representing the working state of the production equipment.
2. The method of claim 1, further comprising:
determining a first state type and a second state type according to a preset production line information set; the first state type is used for representing the type of the running state vector of the production equipment in the continuous running state, and the second state type is used for representing the type of the running state vector of the production equipment in the discontinuous running state;
and determining current production line information from the production line information set, dividing the running state vector corresponding to each production device into the first state category or the second state category according to the current production line information, and scheduling the running state of each production device according to the running state vector in the first state category and the running state vector in the second state category.
3. The method of claim 2, further comprising:
acquiring a production line adjusting instruction;
determining target production line information from the production line information set according to a production line identification in the production line adjustment instruction;
and readjusting the running state vector corresponding to each production device under the first state category or the second state category according to the current production line information, and scheduling the running state of each production device based on the adjusted running state vector under the first state category and the adjusted running state vector under the second state category.
4. The method according to any one of claims 1 to 3, wherein the determining j groups of device operation parameters respectively corresponding to the i production devices from a preset storage space for storing the device operation parameters further comprises:
acquiring a graph data structure sequence corresponding to each group of equipment operation parameters in the storage space and acquiring a data storage format sequence corresponding to the storage space; the graph data structure sequence and the data storage structure sequence respectively comprise data units with different structure compatibility degrees, the graph data structure sequence is used for representing the storage form of the equipment operation parameters in the storage space, and the data storage format sequence is used for representing the data format conversion logic of the storage space during the storage of the equipment operation parameters;
extracting a first structural parameter section of each group of equipment operating parameters in any data unit of the graph data structure sequence, and determining a data unit of each group of equipment operating parameters with the minimum structural compatibility in the data storage format sequence as a first data unit;
projecting the first structural parameter section to the first data unit according to each production device and the device operation parameter corresponding to the production device, and obtaining a second structural parameter section in the first data unit; generating a first structural conversion list of the storage space corresponding to each set of equipment operating parameters based on the first structural parameter section and the second structural parameter section;
acquiring a second structural parameter section in the first data unit by taking the second structural parameter section as a reference parameter section, projecting the second structural parameter section to a second data unit where the first structural parameter section is located according to a second structural conversion list with reverse conversion logic to the first structural conversion list, and acquiring a graph data relation sequence corresponding to the second structural parameter section in the second data unit where the first structural parameter section is located; wherein, each group of graph data relation sequence corresponds to a group of equipment operation parameters;
and performing format conversion on each group of equipment operation parameters in the storage space based on the graph data relation sequence to obtain target equipment operation parameters expressed in a character coding form, and determining j groups of target equipment operation parameters respectively corresponding to i production equipment.
5. The method of claim 1, wherein generating the parameter list according to the device type information of the i production devices and the operation period parameters of the operation parameters of the j group of devices further comprises:
extracting target field information of each group of equipment type information, and extracting field characteristics based on the target field information to obtain type field characteristics of each group of equipment type information; the target field information is information corresponding to a parameter list thread of the big data center in each group of equipment type information;
comparing the type field characteristics of each group of equipment type information with the target type field characteristics of each sample type information in a preset field characteristic set to obtain a comparison result; target type field characteristics corresponding to a plurality of sample type information and heterogeneous coefficients corresponding to the target type field characteristics are stored in the preset field characteristic set;
when the comparison result represents that the type field characteristics of the equipment type information are similar to the corresponding target type field characteristics, correcting the target field information of the equipment type information according to the heterogeneous coefficient corresponding to the target field type characteristics and setting a first identifier; when the comparison result represents that the type field characteristics of the equipment type information are not similar to the corresponding target type field characteristics, setting a second identifier for the target field information corresponding to the equipment type information;
and carrying out one-to-one correspondence on the equipment type information of the i production equipment and the operation time interval parameters of the j group equipment operation parameters according to the sequence of the first identification and the second identification, and generating the parameter list based on the one-to-one correspondence result.
6. The method of claim 1, wherein the searching for a target list element in the feature list corresponding to each production device further comprises:
determining a first mapping value of the equipment type information of each production equipment in the feature list and a second mapping value of the equipment operation parameter in the feature list;
determining the relative position of each production device in the feature list according to the first mapping value and the second mapping value;
and determining a target list unit corresponding to each production device according to the relative position.
7. The method of claim 1, wherein the modifying the state feature vector with the largest state weight in the target list unit based on the j groups of device operation parameters of each production device to obtain an operation state vector corresponding to each production device further comprises:
clustering j groups of equipment operation parameters corresponding to each production equipment to obtain an operation parameter set corresponding to each production equipment;
and extracting the clustering feature vector corresponding to the operation parameter set, and weighting the clustering feature vector and the state feature vector with the maximum state weight in the target list unit to obtain the operation state vector corresponding to each production device.
8. A big data center, wherein the big data center communicates with a plurality of production devices, the big data center being specifically configured to:
determining j groups of equipment operating parameters respectively corresponding to the i production equipment from a preset storage space for storing the equipment operating parameters; wherein, m kinds of running state marks are included in the i production devices at least;
generating a parameter list according to the equipment type information of the i production equipment and the operation time interval parameters of the operation parameters of the j group of equipment; the parameter list is i rows and j columns;
performing feature extraction on the parameter list according to a preset feature extraction logic to obtain a feature list formed by the equipment model information of the i production equipment and the influence weights of the m running state identifiers respectively corresponding to the i production equipment; wherein the feature list is i rows and m columns;
searching a target list unit corresponding to each production device in the feature list, and correcting the state feature vector with the maximum state weight in the target list unit based on j groups of device operation parameters of each production device to obtain an operation state vector corresponding to each production device; wherein the operation state vector is used for representing the working state of the production equipment.
9. A big data center, comprising:
a processor, and
a memory and a network interface connected with the processor;
the network interface is connected with a nonvolatile memory in the big data center;
the processor, when running, retrieves a computer program from the non-volatile memory via the network interface and runs the computer program via the memory to perform the method of any of claims 1-7.
10. A readable storage medium applied to a computer, wherein the readable storage medium is burned with a computer program, and the computer program realizes the method of any one of the above claims 1 to 7 when running in the memory of a big data center.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011199005.3A CN112306024A (en) | 2020-05-08 | 2020-05-08 | Equipment operation state determination method combined with intelligent park and big data center |
| CN202011197902.0A CN112306023A (en) | 2020-05-08 | 2020-05-08 | Equipment operation state determination method applied to intelligent park and big data center |
| CN202010384725.0A CN111552247B (en) | 2020-05-08 | 2020-05-08 | Equipment operation state determination method based on intelligent park and big data center |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010384725.0A CN111552247B (en) | 2020-05-08 | 2020-05-08 | Equipment operation state determination method based on intelligent park and big data center |
Related Child Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011197902.0A Division CN112306023A (en) | 2020-05-08 | 2020-05-08 | Equipment operation state determination method applied to intelligent park and big data center |
| CN202011199005.3A Division CN112306024A (en) | 2020-05-08 | 2020-05-08 | Equipment operation state determination method combined with intelligent park and big data center |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111552247A true CN111552247A (en) | 2020-08-18 |
| CN111552247B CN111552247B (en) | 2021-01-15 |
Family
ID=72004480
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011197902.0A Withdrawn CN112306023A (en) | 2020-05-08 | 2020-05-08 | Equipment operation state determination method applied to intelligent park and big data center |
| CN202011199005.3A Withdrawn CN112306024A (en) | 2020-05-08 | 2020-05-08 | Equipment operation state determination method combined with intelligent park and big data center |
| CN202010384725.0A Active CN111552247B (en) | 2020-05-08 | 2020-05-08 | Equipment operation state determination method based on intelligent park and big data center |
Family Applications Before (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011197902.0A Withdrawn CN112306023A (en) | 2020-05-08 | 2020-05-08 | Equipment operation state determination method applied to intelligent park and big data center |
| CN202011199005.3A Withdrawn CN112306024A (en) | 2020-05-08 | 2020-05-08 | Equipment operation state determination method combined with intelligent park and big data center |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN112306023A (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113592043B (en) * | 2021-10-02 | 2021-12-07 | 武汉聚财荣和科技有限公司 | Carton classification method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000321176A (en) * | 1999-05-17 | 2000-11-24 | Mitsui Eng & Shipbuild Co Ltd | Method and device for detecting abnormal condition |
| US20100228854A1 (en) * | 2009-03-09 | 2010-09-09 | At&T Mobility Ii Llc | Network operation management |
| CN109375609A (en) * | 2018-10-18 | 2019-02-22 | 北京鼎力信安技术有限公司 | The detection method and device of abnormal aggression |
| CN110009889A (en) * | 2019-04-09 | 2019-07-12 | 湘潭大学 | Holographic perception power information nonredundancy effective transmission technique towards the full direct-current micro-grid of intelligent building |
| CN110073301A (en) * | 2017-08-02 | 2019-07-30 | 强力物联网投资组合2016有限公司 | The detection method and system under data collection environment in industrial Internet of Things with large data sets |
| CN110647894A (en) * | 2018-06-07 | 2020-01-03 | 佛山市顺德区美的电热电器制造有限公司 | Fault diagnosis method and system of electrical equipment, cloud server and storage medium |
-
2020
- 2020-05-08 CN CN202011197902.0A patent/CN112306023A/en not_active Withdrawn
- 2020-05-08 CN CN202011199005.3A patent/CN112306024A/en not_active Withdrawn
- 2020-05-08 CN CN202010384725.0A patent/CN111552247B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000321176A (en) * | 1999-05-17 | 2000-11-24 | Mitsui Eng & Shipbuild Co Ltd | Method and device for detecting abnormal condition |
| US20100228854A1 (en) * | 2009-03-09 | 2010-09-09 | At&T Mobility Ii Llc | Network operation management |
| CN110073301A (en) * | 2017-08-02 | 2019-07-30 | 强力物联网投资组合2016有限公司 | The detection method and system under data collection environment in industrial Internet of Things with large data sets |
| CN110647894A (en) * | 2018-06-07 | 2020-01-03 | 佛山市顺德区美的电热电器制造有限公司 | Fault diagnosis method and system of electrical equipment, cloud server and storage medium |
| CN109375609A (en) * | 2018-10-18 | 2019-02-22 | 北京鼎力信安技术有限公司 | The detection method and device of abnormal aggression |
| CN110009889A (en) * | 2019-04-09 | 2019-07-12 | 湘潭大学 | Holographic perception power information nonredundancy effective transmission technique towards the full direct-current micro-grid of intelligent building |
Non-Patent Citations (4)
| Title |
|---|
| LIANG Z , ACADEMY N .: "Big data mining technology based on semantic similarity association feature extraction", 《INTELLIGENT COMPUTER AND APPLICATIONS》 * |
| MINGHAO A , XIANJUN G , XIAOHUI W , ET AL.: "A Big Data analysis based new method for power grid dispatch and control training simulation》", 《CHINA INTERNATIONAL CONFERENCE ON ELECTRICITY DISTRIBUTION》 * |
| 江秀臣, 盛戈皞: "电力设备状态大数据分析的研究和应用", 《高电压技术》 * |
| 钱洵, 黄振峰, 毛汉领,等: "基于振动信号特征提取的糖机运行状态分析", 《设备管理与维修》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112306023A (en) | 2021-02-02 |
| CN112306024A (en) | 2021-02-02 |
| CN111552247B (en) | 2021-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113435509B (en) | Small sample scene classification and identification method and system based on meta-learning | |
| US11188731B2 (en) | Feature data processing method and device | |
| CN111552247B (en) | Equipment operation state determination method based on intelligent park and big data center | |
| CN111432003B (en) | Data pushing method and device applied to cloud computing, electronic equipment and system | |
| CN114255187A (en) | Multi-level and multi-level image optimization method and system based on big data platform | |
| CN113743650B (en) | Power load prediction method, device, equipment and storage medium | |
| CN113377964B (en) | Knowledge graph link prediction method, device, equipment and storage medium | |
| US20080147576A1 (en) | Data processing apparatus, data processing method data processing program and computer readable medium | |
| CN117291259A (en) | Operator optimization method and device, electronic equipment and storage medium | |
| CN111767324A (en) | Intelligent associated self-adaptive data analysis method and device | |
| CN115422486B (en) | Cloud service online page optimization method based on artificial intelligence and big data system | |
| CN115098482A (en) | Incomplete data correction and additional recording method | |
| CN116975742A (en) | Partial discharge pattern recognition method, apparatus, device, and storage medium | |
| CN110348509B (en) | Method, device and equipment for adjusting data augmentation parameters and storage medium | |
| CN113255927A (en) | Logistic regression model training method and device, computer equipment and storage medium | |
| CN117194991B (en) | High-dimensional data recommendation system and method based on GPU cluster | |
| CN110874465A (en) | Mobile equipment entity identification method and device based on semi-supervised learning algorithm | |
| CN111860635A (en) | Method, device, terminal and storage medium for training integrated SVM (support vector machine) by using Boosting | |
| CN113657445B (en) | Resnet-based single-row text picture comparison method and system | |
| CN114240242A (en) | Work order sorting method, device, terminal and medium based on gull optimization algorithm | |
| CN113988185A (en) | Data processing method and related device | |
| CN118277952A (en) | Power sensing data self-adaptive fusion method and system in extreme environment | |
| CN117150356A (en) | Service policy adjustment method and device, storage medium and electronic equipment | |
| CN115527075A (en) | Multi-core learning method and system based on manifold structure kernel function and related equipment | |
| CN114296894A (en) | Call chain intelligent analysis method and device based on log data and electronic equipment |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Kunming Institute of information engineering and automation, 253 Xuefu Road, Wuhua District, Kunming City, Yunnan Province 650091 Applicant after: Chen Xiaoqing Address before: Tongda Institute of information science and technology, No.9, Siyuan Road, Chongchuan District, Nantong City, Jiangsu Province, 226019 Applicant before: Chen Xiaoqing |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201202 Address after: No. 617, Lijiagou village, Heshun Town, Linzhou City, Anyang City, Henan Province Applicant after: Wang Rui Address before: Kunming Institute of information engineering and automation, 253 Xuefu Road, Wuhua District, Kunming City, Yunnan Province 650091 Applicant before: Chen Xiaoqing |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231031 Address after: Room 606, 6th floor, block a, Yonghe Longzihu Plaza, 197 Ping'an Avenue, Zhengdong New District, Zhengzhou City, Henan Province, 450000 Patentee after: HENAN YUNTUO INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: No. 617, Lijiagou village, Heshun Town, Linzhou City, Anyang City, Henan Province 456550 Patentee before: Wang Rui |