CN110134040B - Method and system for processing operation data of industrial equipment - Google Patents
Method and system for processing operation data of industrial equipment Download PDFInfo
- Publication number
- CN110134040B CN110134040B CN201910376599.1A CN201910376599A CN110134040B CN 110134040 B CN110134040 B CN 110134040B CN 201910376599 A CN201910376599 A CN 201910376599A CN 110134040 B CN110134040 B CN 110134040B
- Authority
- CN
- China
- Prior art keywords
- data
- processing
- execution list
- target
- historical
- 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.)
- Active
Links
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
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0428—Safety, monitoring
-
- 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
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24024—Safety, surveillance
Abstract
The invention discloses a processing method and a system for operation data of industrial equipment, wherein the processing method comprises the following steps: acquiring historical operating parameter data of the industrial equipment within historical set time; acquiring historical operating parameter characteristic information; a preset data processing step, wherein the data processing step is recommended according to the historical operating parameter characteristic information, and the historical operating parameter data is processed according to the recommended data processing step; establishing a state acquisition model according to the processed historical operating parameter data; acquiring target operation parameter data of the industrial equipment within target set time; and inputting the target operation parameter data into the state acquisition model to acquire the operation state of the industrial equipment. According to the method and the device, the automatic analysis process of the operation parameter data is realized through the automatic recommendation analysis step, namely, the user is guided to complete the self-service data analysis process, so that the model precision of a subsequently established model is improved, the prediction result of the model is improved, and the analysis accuracy of industrial and industrial equipment is improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for processing running data of industrial equipment.
Background
At present, along with the continuous improvement of the intelligent level of industrial equipment, the remote state monitoring and intelligent operation and maintenance of the industrial equipment are gradually valued by enterprises, such as unattended operation of wind driven generators. The basis of the remote intelligent operation and maintenance of the industrial equipment is to acquire and analyze real-time operation parameters of the industrial equipment, further grasp the real-time operation state of the industrial equipment, judge whether the industrial equipment is abnormal or predict the future state of the industrial equipment, and realize the operations of prediction, maintenance and the like.
In order to improve the efficiency of data analysis of industrial equipment, reduce the threshold of data analysis, assist engineers to complete data analysis quickly and conveniently, and integrate professional knowledge into data analysis in the most convenient way, the existing general dragging operation is adopted, namely after relatively standardized modules in data analysis are combined, a graphical mode is adopted, the construction of a data analysis flow can be completed, and then data analysis and result display are completed. However, even if the necessary analysis functions are modularized, there are still many steps required for the user to select according to the characteristics of the specific problem in the analysis process, and the process of selecting which step to take in detail next still requires the user to have a relatively deep understanding of the data analysis. Therefore, the existing industrial equipment data analysis process still needs to be excessively manually involved in analysis, and the acquired data cannot be automatically analyzed; meanwhile, the accuracy of the operation state analysis result of the industrial equipment is not high.
Disclosure of Invention
The invention aims to solve the technical problems that the data processing method of the industrial equipment in the prior art cannot realize self-service analysis of the acquired data and has the defects of low analysis accuracy and the like, and the invention aims to provide the processing method and the processing system of the operation data of the industrial equipment.
The invention solves the technical problems through the following technical scheme:
the invention provides a processing method of operation data of industrial equipment, which comprises the following steps:
acquiring historical operating parameter data of the industrial equipment within historical set time;
performing characteristic analysis processing on the historical operating parameter data to obtain historical operating parameter characteristic information;
presetting data processing steps, wherein the data processing steps are arranged in a one-to-one correspondence manner with different historical operating parameter characteristic information;
recommending a data processing step according to the historical operating parameter characteristic information;
and processing the historical operating parameter data according to the recommended data processing step.
Preferably, different historical operating parameter characteristic information corresponds to different processing priorities;
the step of processing the historical operating parameter data according to the recommended data processing step further comprises:
sequencing the corresponding data processing steps in sequence according to the processing priorities of the different historical operating parameter characteristic information to form the first step execution list;
and processing the historical operating parameter data according to the data processing steps in the first step execution list.
Preferably, the step of processing the historical operating parameter data according to the recommended data processing step comprises:
and sequentially recommending the data processing steps from front to back in the sequence in the first step execution list, and sequentially processing the historical operation parameter data according to the recommended data processing steps.
Preferably, the step of processing the historical operating parameter data according to the recommended data processing step comprises:
according to the historical workflow of the industrial equipment stored in the database, counting the frequency of other data processing steps which are sequenced immediately after one data processing step, and obtaining the second step execution list according to the frequency;
integrating the first step execution list and the second step execution list to obtain a target step execution list;
wherein the processing priority for data processing steps that occur in both the first step execution list and the second step execution list is highest;
the processing priority of the data processing steps appearing only in the first step execution list is higher than the algorithm appearing only in the second step execution list;
a data processing step with higher processing priority, wherein the ranking position in the target recommendation list is more advanced;
and sequentially recommending the data processing steps from front to back in the sequence in the target step execution list, and sequentially processing the historical operation parameter data according to the recommended data processing steps.
Preferably, when the operating parameter feature information includes a missing value, a feature type, a feature quantity, a sample quantity of different classes, and feature value domain information, the data processing steps from front to back in the first step execution list include:
performing missing value processing on the operation parameter characteristic information, performing characteristic coding processing on the operation parameter characteristic information when the characteristic type does not belong to a target type, performing dimension reduction processing on the operation parameter characteristic information when the characteristic quantity reaches a set threshold value, performing undersampling or oversampling processing on the operation parameter characteristic information when the sample quantity of different types belongs to unbalanced samples, and performing data standardization processing on the operation parameter characteristic information;
wherein the missing values, the feature types, the feature quantities, the sample quantities of the different categories, and the processing priorities corresponding to the feature value range information are sequentially reduced.
Preferably, the step of processing the historical operating parameter data according to the recommended data processing step further comprises:
establishing a state acquisition model according to the processed historical operating parameter data;
acquiring target operation parameter data of the industrial equipment within target set time;
and inputting the target operation parameter data into the state acquisition model to acquire the operation state of the industrial equipment.
Preferably, the step of establishing a state acquisition model according to the processed historical operating parameter data includes:
recommending a modeling algorithm list;
and selecting a target algorithm from the recommended modeling algorithm list, and establishing the state acquisition model by adopting the target algorithm.
The invention also provides a processing system of the operation data of the industrial equipment, which comprises a historical parameter acquisition module, a historical characteristic information acquisition module, a preset module, a step recommendation module and a data processing module;
the historical parameter acquisition module is used for acquiring historical operating parameter data of the industrial equipment within historical set time;
the historical characteristic information acquisition module is used for carrying out characteristic analysis processing on the historical operating parameter data to acquire historical operating parameter characteristic information;
the preset module is used for presetting data processing steps, wherein the data processing steps are arranged in a one-to-one correspondence manner with different historical operating parameter characteristic information;
the step recommending module is used for recommending data processing steps according to the historical operating parameter characteristic information;
and the data processing module is used for processing the historical operating parameter data according to the recommended data processing steps.
Preferably, different historical operating parameter characteristic information corresponds to different processing priorities;
the processing system also comprises a first execution list acquisition module;
the first execution list acquisition module is used for sequentially sequencing the corresponding data processing steps according to the processing priorities of the different historical operating parameter characteristic information to form the first step execution list;
the data processing module is used for processing the historical operating parameter data according to the data processing steps in the first step execution list.
Preferably, the step recommending module is configured to recommend the data processing steps in the first step execution list in sequence from front to back, and process the historical operating parameter data in sequence according to the recommended data processing steps.
Preferably, the processing system further comprises a second execution list acquisition module and a target execution list acquisition module;
the second execution list acquisition module is used for counting the frequency of other data processing steps which are sequenced immediately after one data processing step according to the historical workflow of the industrial equipment stored in the database, and obtaining the second step execution list according to the frequency;
the target execution list acquisition module is used for integrating the first step execution list and the second step execution list to acquire a target step execution list;
wherein the processing priority for data processing steps that occur in both the first step execution list and the second step execution list is highest;
the processing priority of the data processing steps appearing only in the first step execution list is higher than the algorithm appearing only in the second step execution list;
a data processing step with higher processing priority, wherein the ranking position in the target recommendation list is more advanced;
the step recommending module is used for sequentially recommending the data processing steps from front to back in the sequence in the target step execution list and calling the data processing module to process the historical operation parameter data sequentially according to the recommended data processing steps.
Preferably, when the operating parameter feature information includes a missing value, a feature type, a feature quantity, a sample quantity of different classes, and feature value domain information, the data processing steps ordered sequentially from front to back in the first step execution list include:
performing missing value processing on the operation parameter characteristic information, performing characteristic coding processing on the operation parameter characteristic information when the characteristic type does not belong to a target type, performing dimension reduction processing on the operation parameter characteristic information when the characteristic quantity reaches a set threshold value, performing undersampling or oversampling processing on the operation parameter characteristic information when the sample quantity of different types belongs to unbalanced samples, and performing data standardization processing on the operation parameter characteristic information;
wherein the missing values, the feature types, the feature quantities, the sample quantities of the different categories, and the processing priorities corresponding to the feature value range information are sequentially reduced.
Preferably, the processing system further comprises an algorithm list recommending module and a target algorithm selecting module;
the algorithm list recommending module is used for recommending a modeling algorithm list;
the target algorithm selection module is used for selecting a target algorithm from the recommended modeling algorithm list and calling the model establishment module to establish the state acquisition model by adopting the target algorithm.
Preferably, the processing system further comprises a model establishing module, a target parameter obtaining module and a state obtaining module;
the model establishing module is used for establishing a state obtaining model according to the processed historical operating parameter data;
the target parameter acquisition module is used for acquiring target operation parameter data of the industrial equipment within target set time;
the state acquisition module is used for inputting the target operation parameter data into the state acquisition model to acquire the operation state of the industrial equipment.
The positive progress effects of the invention are as follows:
in the invention, after the operation parameter data of the industrial equipment is obtained, the operation parameter characteristic information of the operation parameter data is extracted, then the data processing steps are sequentially recommended to the operation parameter characteristic information, the operation parameter data is processed according to the sequentially recommended data processing steps, and the automatic analysis process of the operation parameter data is realized through the automatic recommendation analysis step, namely, the user is guided to complete the self-service data analysis process, so that the model precision of a subsequently established model is improved, the prediction result of the model is improved, and the analysis accuracy of the industrial and industrial equipment is improved; meanwhile, the defect that the user needs to participate in analysis in the existing data analysis process is overcome, so that the user can be concentrated in the business problem, and the user experience is improved.
Drawings
Fig. 1 is a flowchart of a method for processing operation data of an industrial apparatus according to embodiment 1 of the present invention.
Fig. 2 is a flowchart of a method for processing operation data of an industrial apparatus according to embodiment 2 of the present invention.
Fig. 3 is a flowchart of a method for processing operation data of an industrial apparatus according to embodiment 3 of the present invention.
Fig. 4 is a block diagram of a system for processing operation data of an industrial device according to embodiment 4 of the present invention.
Fig. 5 is a block diagram schematically showing a system for processing operation data of an industrial device according to embodiment 5 of the present invention.
Fig. 6 is a block diagram schematically showing a system for processing operation data of an industrial device according to embodiment 6 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
As shown in fig. 1, the method for processing the operation data of the industrial equipment of the embodiment includes:
s101, acquiring historical operating parameter data of the industrial equipment within historical set time;
s102, performing characteristic analysis processing on the historical operation parameter data to obtain historical operation parameter characteristic information;
s103, presetting a data processing step;
the data processing steps are set in one-to-one correspondence with different historical operating parameter characteristic information.
S104, recommending a data processing step according to the historical operating parameter characteristic information;
s105, processing the historical operating parameter data according to the recommended data processing steps;
the method comprises the steps of recommending historical operation parameter data, automatically adopting any data processing step for the historical operation parameter data on the basis of specific characteristic information of the historical operation parameter data, and continuously recommending the next data processing step after one data processing step is processed, so that the aim of automatically analyzing data is fulfilled.
In the data analysis process, the user only needs to confirm execution according to the recommended data processing steps, and the user can skip a certain data processing step according to actual requirements and then continue to execute the next recommended data processing step.
In the embodiment, after historical operation parameter data of the industrial equipment is obtained, historical operation parameter characteristic information of the historical operation parameter data is extracted, a data processing step is recommended according to the historical operation parameter characteristic information, the operation parameter data is processed according to the recommended data processing step, an automatic analysis process of the operation parameter data is realized through the automatic recommendation analysis step, namely, a user is guided to complete a self-service data analysis process, so that the model precision of a subsequently established model is improved, the prediction result of the model is improved, and the analysis accuracy of the industrial equipment is improved; meanwhile, the defect that the user needs to participate in analysis in the existing data analysis process is overcome, so that the user can be concentrated in the business problem, and the user experience is improved.
Example 2
As shown in fig. 2, the method for processing the operation data of the industrial equipment in this embodiment is a further improvement of embodiment 1, and specifically:
different historical operating parameter characteristic information corresponds to different processing priorities.
After step 103 and before step S104, the method further includes:
s10401, sequencing the corresponding data processing steps in sequence according to the processing priority of the different historical operation parameter characteristic information to form a first step execution list;
step S104 includes:
s1041, sequentially recommending data processing steps from front to back in the sequence in the first step execution list;
step S105 includes:
and S1051, processing the historical operation parameter data according to the recommended data processing steps in sequence.
For example: when the operation parameter feature information includes a missing value, a feature type, a feature quantity, a sample quantity of different types, and feature value domain information, the processing priorities corresponding to the missing value, the feature type, the feature quantity, the sample quantity of different types, and the feature value domain information are sequentially reduced.
At this time, the data processing steps sequentially ordered from front to back in the first step execution list include:
when the operation parameter characteristic information comprises a missing value, the missing value processing is carried out on the operation parameter characteristic information;
judging whether the characteristic type belongs to a target type such as a label type (a data type), if so, performing characteristic coding processing on the operation parameter characteristic information;
when the number of the characteristics reaches a set threshold value, if the number of the characteristics reaches the set threshold value, performing selection processing or dimension reduction processing on the operation parameter characteristic information;
judging whether the number of the samples of different types belongs to unbalanced samples, if so, processing the operation parameter characteristic information by adopting an undersampling or oversampling method;
and when the operating parameter characteristic information comprises the characteristic value domain information, performing data standardization processing on the operating parameter characteristic information.
The processing priority of the different historical operating parameter characteristic information is determined according to practical experience.
Step S105 is followed by:
s106, establishing a state acquisition model according to the processed historical operation parameter data; specifically, the method comprises the following steps:
s1061, recommending a modeling algorithm list;
s1062, selecting a target algorithm from the recommended modeling algorithm list, and establishing a state acquisition model by adopting the target algorithm.
S107, acquiring target operation parameter data of the industrial equipment within target set time;
and S108, inputting the target operation parameter data into the state acquisition model to acquire the operation state of the industrial equipment.
In addition, in this embodiment, after one step is executed, the next execution step is automatically recommended to the user until the process is built, that is, the recommendation is stopped when the user selects not to continue executing the subsequent process, or when the step recommendation cannot obtain any result.
In the embodiment, after historical operation parameter data of the industrial equipment is obtained, historical operation parameter characteristic information of the historical operation parameter data is extracted, data processing steps are sequentially recommended according to the historical operation parameter characteristic information, the operation parameter data are processed according to the recommended data processing steps, and an automatic analysis process of the operation parameter data is realized through the automatic recommendation analysis steps, namely, a user is guided to complete a self-service data analysis process, so that the model precision of a subsequently established model is improved, the prediction result of the model is improved, and the analysis accuracy of the industrial and industrial equipment is improved; meanwhile, the defect that the user needs to participate in analysis in the existing data analysis process is overcome, so that the user can be concentrated in the business problem, and the user experience is improved.
Example 3
As shown in fig. 3, the method for processing the operation data of the industrial equipment in this embodiment is a further improvement of embodiment 1, specifically:
the first step execution list in embodiment 2 is employed in this embodiment.
Step S103, and then step S104, further include:
s10402, counting the frequency of other data processing steps after one data processing step according to the historical workflow of the industrial equipment stored in the database, and obtaining a second step execution list according to the frequency;
s10403, integrating the first step execution list and the second step execution list to obtain a target step execution list;
wherein the processing priority for the data processing steps that occur in both the first-step execution list and the second-step execution list is highest;
the processing priority of the data processing steps appearing only in the first-step execution list is higher than the algorithm appearing only in the second-step execution list;
the higher the processing priority is, the higher the ranking position in the target recommendation list is;
step S104 includes:
s1042, sequentially recommending a target step to execute data processing steps from front to back in the list,
step S105 includes:
and S1052, processing the historical operating parameter data according to the recommended data processing steps in sequence.
The following is a detailed description with reference to examples:
taking a certain wind driven generator as an example, historical operation parameter data of the wind driven generator within historical set time, such as wind speed, wind direction, power, weather forecast and the like, are stored in a database, and are sequentially stored in the database according to a time sequence to form a corresponding time sequence; based on these historical operating parameter data, the user needs to solve the problem of wind power prediction for the wind turbine, and the specific processing procedure is as follows:
1) importing historical operation parameter data of the wind driven generator in historical set time;
2) performing characteristic analysis on the historical operating parameter data by adopting a data set characteristic analyzer to obtain historical operating parameter characteristic information corresponding to the historical operating parameter data;
3) when the historical operation parameter characteristic information contains a missing value, automatically recommending the next step in the execution list of the first step to process the missing value; meanwhile, in the second-step execution list, the data processing steps immediately after the relief of the imported data include processing missing values and encoding characteristic values, then the data processing steps recommended in the first-step execution list and the data processing steps recommended in the second-step execution list are integrated, and finally the data processing step of "processing missing values" is determined to be recommended, after the data processing step is completed, the next data processing step is continuously recommended, and the process of determining the recommended data processing step is similar to the above process, and is not repeated here.
The last step of setting the historical operating parameter characteristic information analysis processing is to carry out standardization processing on the historical operating parameter characteristic information by adopting a standardization algorithm, and further obtain the historical operating parameter characteristic information after the standardization processing, so that the accuracy of the subsequent model establishment is ensured.
4) Recommending a modeling algorithm list to a user, taking an algorithm selected by the user in the modeling algorithm list as a target algorithm, and establishing a state acquisition model according to the standardized historical operating parameter characteristic information by adopting the target algorithm;
5) acquiring target operation parameter data of the wind driven generator within target set time;
6) and inputting the target operation parameter data into the state acquisition model to predict the operation state of the wind driven generator. In the embodiment, after the operation parameter data of the industrial equipment is obtained, the operation parameter characteristic information of the operation parameter data is extracted, then the data processing steps are sequentially recommended to the operation parameter characteristic information, the operation parameter data are processed according to the sequentially recommended data processing steps, and the automatic analysis process of the operation parameter data is realized through the automatic recommendation analysis step, namely, a user is guided to complete the self-service data analysis process, so that the model precision of a subsequently established model is improved, the prediction result of the model is improved, and the analysis accuracy of the industrial and industrial equipment is improved; meanwhile, the defect that the user needs to participate in analysis in the existing data analysis process is overcome, so that the user can be concentrated in the business problem, and the user experience is improved.
Example 4
As shown in fig. 4, the system for processing the operation data of the industrial device of the present embodiment includes a history parameter obtaining module 1, a history feature information obtaining module 2, a presetting module 3, a step recommending module 4, and a data processing module 5.
The historical parameter acquisition module 1 is used for acquiring historical operating parameter data of the industrial equipment within historical set time;
the historical characteristic information acquisition module 2 is used for carrying out characteristic analysis processing on the historical operating parameter data to acquire historical operating parameter characteristic information;
the presetting module 3 is used for presetting data processing steps, wherein the data processing steps are arranged in a one-to-one correspondence manner with different historical operating parameter characteristic information;
the step recommending module 4 is used for recommending data processing steps according to the historical operating parameter characteristic information;
the data processing module 5 is used for processing the historical operating parameter data according to the recommended data processing steps;
the method comprises the steps of recommending historical operation parameter data, automatically adopting any data processing step for the historical operation parameter data on the basis of specific characteristic information of the historical operation parameter data, and continuously recommending the next data processing step after one data processing step is processed, so that the aim of automatically analyzing data is fulfilled.
In the data analysis process, the user only needs to confirm execution according to the recommended data processing steps, and the user can skip a certain data processing step according to actual requirements and then continue to execute the next recommended data processing step.
In the embodiment, after historical operation parameter data of the industrial equipment is obtained, historical operation parameter characteristic information of the historical operation parameter data is extracted, a data processing step is recommended according to the historical operation parameter characteristic information, the operation parameter data is processed according to the recommended data processing step, an automatic analysis process of the operation parameter data is realized through the automatic recommendation analysis step, namely, a user is guided to complete a self-service data analysis process, so that the model precision of a subsequently established model is improved, the prediction result of the model is improved, and the analysis accuracy of the industrial equipment is improved; meanwhile, the defect that the user needs to participate in analysis in the existing data analysis process is overcome, so that the user can be concentrated in the business problem, and the user experience is improved.
Example 5
As shown in fig. 5, the system for processing the operation data of the industrial equipment in this embodiment is a further improvement of embodiment 5, specifically:
the system for processing the operation data of the industrial equipment in the embodiment further includes a model building module 6, a target parameter obtaining module 7 and a state obtaining module 8.
The model establishing module 6 is used for establishing a state obtaining model according to the processed historical operating parameter data;
the target parameter acquisition module 7 is used for acquiring target operation parameter data of the industrial equipment within target set time;
the state obtaining module 8 is configured to input the target operation parameter data into the state obtaining model to obtain the operation state of the industrial equipment.
In addition, different historical operating parameter characteristic information corresponds to different processing priorities;
the processing system also comprises a first execution list acquisition module 9;
the first execution list acquisition module 9 is configured to sequentially order the corresponding data processing steps according to the processing priorities of different pieces of historical operating parameter feature information to form a first step execution list;
specifically, the step recommending module 4 is configured to sequentially recommend data processing steps from front to back in the first step execution list, and invoke the data processing module 5 to process the historical operating parameter data sequentially according to the recommended data processing steps.
For example: when the operation parameter feature information includes a missing value, a feature type, a feature quantity, a sample quantity of different types, and feature value domain information, the processing priorities corresponding to the missing value, the feature type, the feature quantity, the sample quantity of different types, and the feature value domain information are sequentially reduced.
At this time, the data processing steps sequentially ordered from front to back in the first step execution list include:
when the operation parameter characteristic information comprises a missing value, the missing value processing is carried out on the operation parameter characteristic information;
judging whether the characteristic type belongs to a target type such as a label type (a data type), if so, performing characteristic coding processing on the operation parameter characteristic information;
when the number of the characteristics reaches a set threshold value, if the number of the characteristics reaches the set threshold value, performing selection processing or dimension reduction processing on the operation parameter characteristic information;
judging whether the number of the samples of different types belongs to unbalanced samples, if so, processing the operation parameter characteristic information by adopting an undersampling or oversampling method;
and when the operating parameter characteristic information comprises the characteristic value domain information, performing data standardization processing on the operating parameter characteristic information.
The processing priority of the different historical operating parameter characteristic information is determined according to practical experience.
The processing system also comprises an algorithm list recommending module 10 and a target algorithm selecting module 11;
the algorithm list recommending module 10 is used for recommending a modeling algorithm list;
the target algorithm selection module 11 is configured to select a target algorithm from the recommended modeling algorithm list, and invoke the model establishment module 6 to establish a state acquisition model using the target algorithm.
In addition, in this embodiment, after one step is executed, the next execution step is automatically recommended to the user until the process is built, that is, the recommendation is stopped when the user selects not to continue executing the subsequent process, or when the step recommendation cannot obtain any result.
In the embodiment, after historical operation parameter data of the industrial equipment is obtained, historical operation parameter characteristic information of the historical operation parameter data is extracted, data processing steps are sequentially recommended according to the historical operation parameter characteristic information, the operation parameter data are processed according to the recommended data processing steps, and an automatic analysis process of the operation parameter data is realized through the automatic recommendation analysis steps, namely, a user is guided to complete a self-service data analysis process, so that the model precision of a subsequently established model is improved, the prediction result of the model is improved, and the analysis accuracy of the industrial and industrial equipment is improved; meanwhile, the defect that the user needs to participate in analysis in the existing data analysis process is overcome, so that the user can be concentrated in the business problem, and the user experience is improved.
Example 6
As shown in fig. 6, the system for processing the operation data of the industrial equipment in this embodiment is a further improvement of embodiment 4, specifically:
the processing system further comprises a second execution list acquisition module 12 and a target execution list acquisition module 13.
The second execution list obtaining module 12 is configured to count, according to a historical workflow of the industrial device stored in the database, frequencies of other data processing steps that are immediately after one data processing step, and obtain a second step execution list according to the frequencies;
the target execution list acquisition module 13 is configured to integrate the first step execution list and the second step execution list to acquire a target step execution list;
wherein the processing priority for the data processing steps that occur in both the first-step execution list and the second-step execution list is highest;
the processing priority of the data processing steps appearing only in the first-step execution list is higher than the algorithm appearing only in the second-step execution list;
the higher the processing priority is, the higher the ranking position in the target recommendation list is;
the step recommending module 4 is configured to sequentially recommend data processing steps from front to back in the target step execution list, and call the data processing module to sequentially process the historical operating parameter data according to the recommended data processing steps.
The following is a detailed description with reference to examples:
taking a certain wind driven generator as an example, historical operation parameter data of the wind driven generator within historical set time, such as wind speed, wind direction, power, weather forecast and the like, are stored in a database, and are sequentially stored in the database according to a time sequence to form a corresponding time sequence; based on these historical operating parameter data, the user needs to solve the problem of wind power prediction for the wind turbine, and the specific processing procedure is as follows:
1) importing historical operation parameter data of the wind driven generator in historical set time;
2) performing characteristic analysis on the historical operating parameter data by adopting a data set characteristic analyzer to obtain historical operating parameter characteristic information corresponding to the historical operating parameter data;
3) when the historical operation parameter characteristic information contains a missing value, automatically recommending the next step in the execution list of the first step to process the missing value; meanwhile, in the second-step execution list, the data processing steps immediately after the relief of the imported data include processing missing values and encoding characteristic values, then the data processing steps recommended in the first-step execution list and the data processing steps recommended in the second-step execution list are integrated, and finally the data processing step of "processing missing values" is determined to be recommended, after the data processing step is completed, the next data processing step is continuously recommended, and the process of determining the recommended data processing step is similar to the above process, and is not repeated here.
The last step of setting the historical operating parameter characteristic information analysis processing is to carry out standardization processing on the historical operating parameter characteristic information by adopting a standardization algorithm, and further obtain the historical operating parameter characteristic information after the standardization processing, so that the accuracy of the subsequent model establishment is ensured.
4) Recommending a modeling algorithm list to a user, taking an algorithm selected by the user in the modeling algorithm list as a target algorithm, and establishing a state acquisition model according to the standardized historical operating parameter characteristic information by adopting the target algorithm;
5) acquiring target operation parameter data of the wind driven generator within target set time;
6) and inputting the target operation parameter data into the state acquisition model to predict the operation state of the wind driven generator.
In the embodiment, after the operation parameter data of the industrial equipment is obtained, the operation parameter characteristic information of the operation parameter data is extracted, then the data processing steps are sequentially recommended to the operation parameter characteristic information, the operation parameter data are processed according to the sequentially recommended data processing steps, and the automatic analysis process of the operation parameter data is realized through the automatic recommendation analysis step, namely, a user is guided to complete the self-service data analysis process, so that the model precision of a subsequently established model is improved, the prediction result of the model is improved, and the analysis accuracy of the industrial and industrial equipment is improved; meanwhile, the defect that the user needs to participate in analysis in the existing data analysis process is overcome, so that the user can be concentrated in the business problem, and the user experience is improved.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that these are by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (10)
1. A method for processing operational data of an industrial device, the method comprising:
acquiring historical operating parameter data of the industrial equipment within historical set time;
performing characteristic analysis processing on the historical operating parameter data to obtain historical operating parameter characteristic information, wherein different pieces of historical operating parameter characteristic information correspond to different processing priorities;
presetting data processing steps, wherein the data processing steps are arranged in a one-to-one correspondence manner with different historical operating parameter characteristic information;
sequencing the corresponding data processing steps in sequence according to the processing priorities of the different historical operating parameter characteristic information to form a first step execution list;
according to the historical workflow of the industrial equipment stored in the database, counting the frequency of other data processing steps which are immediately sequenced after one data processing step, and obtaining a second step execution list according to the frequency;
integrating the first step execution list and the second step execution list to obtain a target step execution list;
recommending the data processing steps in the target step execution list in sequence;
and processing the historical operating parameter data according to the recommended data processing step.
2. The method for processing operation data of an industrial device according to claim 1, wherein in the target step execution list, a processing priority for a data processing step that occurs in both the first step execution list and the second step execution list is highest;
the processing priority of the data processing steps appearing only in the first step execution list is higher than the algorithm appearing only in the second step execution list;
the higher the processing priority of the data processing step, the higher the ranking position in the target step execution list.
3. The method for processing the operation data of the industrial equipment according to claim 1, wherein when the historical operation parameter feature information includes a missing value, a feature type, a feature quantity, a sample quantity of different classes, and feature value range information, the processing priorities corresponding to the missing value, the feature type, the feature quantity, the sample quantity of different classes, and the feature value range information are sequentially lowered.
4. The method of processing operational data for an industrial plant of claim 1, wherein the step of processing the historical operational parameter data according to the recommended data processing step further comprises:
establishing a state acquisition model according to the processed historical operating parameter data;
acquiring target operation parameter data of the industrial equipment within target set time;
and inputting the target operation parameter data into the state acquisition model to acquire the operation state of the industrial equipment.
5. The method of processing operational data for an industrial plant of claim 4, wherein the step of building a state acquisition model based on the processed historical operational parameter data comprises:
recommending a modeling algorithm list;
and selecting a target algorithm from the recommended modeling algorithm list, and establishing the state acquisition model by adopting the target algorithm.
6. The processing system for the operation data of the industrial equipment is characterized by comprising a historical parameter acquisition module, a historical characteristic information acquisition module, a preset module, a first execution list acquisition module, a second execution list acquisition module, a target execution list acquisition module, a step recommendation module and a data processing module;
the historical parameter acquisition module is used for acquiring historical operating parameter data of the industrial equipment within historical set time;
the historical characteristic information acquisition module is used for carrying out characteristic analysis processing on the historical operating parameter data to acquire historical operating parameter characteristic information, wherein different pieces of historical operating parameter characteristic information correspond to different processing priorities;
the preset module is used for presetting data processing steps, wherein the data processing steps are arranged in a one-to-one correspondence manner with different historical operating parameter characteristic information;
the first execution list acquisition module is used for sequentially sequencing the corresponding data processing steps according to the different processing priorities of the historical operation parameter characteristic information to form a first step execution list;
the second execution list acquisition module is used for counting the frequency of other data processing steps which are sequenced immediately after one data processing step according to the historical workflow of the industrial equipment stored in the database, and obtaining a second step execution list according to the frequency;
the target execution list acquisition module is used for integrating the first step execution list and the second step execution list to acquire a target step execution list;
the step recommending module is used for sequentially recommending the data processing steps in the target step execution list;
and the data processing module is used for processing the historical operating parameter data according to the recommended data processing steps.
7. The system for processing operational data of an industrial plant according to claim 6,
processing priority for data processing steps that occur in both the first step execution list and the second step execution list is highest in the target step execution list;
the processing priority of the data processing steps appearing only in the first step execution list is higher than the algorithm appearing only in the second step execution list;
the higher the processing priority of the data processing step, the higher the ranking position in the target step execution list.
8. The system according to claim 6, wherein when the operation parameter feature information includes a missing value, a feature type, a feature quantity, a number of samples of different categories, and feature value range information, processing priorities corresponding to the missing value, the feature type, the feature quantity, the number of samples of different categories, and the feature value range information are sequentially lowered.
9. The system for processing operational data of an industrial device according to claim 6, wherein the processing system comprises a model building module, a target parameter acquisition module, and a state acquisition module;
the model establishing module is used for establishing a state obtaining model according to the processed historical operating parameter data;
the target parameter acquisition module is used for acquiring target operation parameter data of the industrial equipment within target set time;
the state acquisition module is used for inputting the target operation parameter data into the state acquisition model to acquire the operation state of the industrial equipment.
10. The system for processing operational data of an industrial device of claim 9, further comprising an algorithm list recommendation module and a target algorithm selection module;
the algorithm list recommending module is used for recommending a modeling algorithm list;
the target algorithm selection module is used for selecting a target algorithm from the recommended modeling algorithm list and calling the model establishment module to establish the state acquisition model by adopting the target algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910376599.1A CN110134040B (en) | 2019-05-07 | 2019-05-07 | Method and system for processing operation data of industrial equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910376599.1A CN110134040B (en) | 2019-05-07 | 2019-05-07 | Method and system for processing operation data of industrial equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110134040A CN110134040A (en) | 2019-08-16 |
| CN110134040B true CN110134040B (en) | 2021-09-24 |
Family
ID=67576593
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910376599.1A Active CN110134040B (en) | 2019-05-07 | 2019-05-07 | Method and system for processing operation data of industrial equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110134040B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826196B (en) * | 2019-10-21 | 2024-03-12 | 上海电气集团股份有限公司 | Industrial equipment operation data processing method and device |
| CN113777965B (en) * | 2020-05-21 | 2023-07-18 | 广东博智林机器人有限公司 | Spray quality control method, spray quality control device, computer equipment and storage medium |
| CN112668650A (en) * | 2020-12-30 | 2021-04-16 | 上海电气集团股份有限公司 | Industrial data model generation method, system, device and medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202261656U (en) * | 2011-12-20 | 2012-05-30 | 大连大学 | Automatic switchover encoding device |
| CN102855333A (en) * | 2012-09-27 | 2013-01-02 | 南京大学 | Service selection system based on group recommendation and selection method thereof |
| CN105825406A (en) * | 2016-03-28 | 2016-08-03 | 乐视控股（北京）有限公司 | Data processing method and device |
| CN106156092A (en) * | 2015-04-01 | 2016-11-23 | 阿里巴巴集团控股有限公司 | Data processing method and device |
| CN106294743A (en) * | 2016-08-10 | 2017-01-04 | 北京奇虎科技有限公司 | The recommendation method and device of application function |
| CN107203545A (en) * | 2016-03-17 | 2017-09-26 | 阿里巴巴集团控股有限公司 | A kind of data processing method and device |
| CN108229828A (en) * | 2018-01-04 | 2018-06-29 | 上海电气集团股份有限公司 | A kind of analysis system based on industrial data |
| CN108363738A (en) * | 2018-01-19 | 2018-08-03 | 上海电气集团股份有限公司 | A kind of recommendation method of industrial equipment data analysis algorithm |
| CN108363714A (en) * | 2017-12-21 | 2018-08-03 | 北京至信普林科技有限公司 | A kind of method and system for the ensemble machine learning for facilitating data analyst to use |
| CN109254990A (en) * | 2018-09-11 | 2019-01-22 | 北京唐冠天朗科技开发有限公司 | A kind of method and system of information source acquisition and dynamic analysis |
-
2019
- 2019-05-07 CN CN201910376599.1A patent/CN110134040B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202261656U (en) * | 2011-12-20 | 2012-05-30 | 大连大学 | Automatic switchover encoding device |
| CN102855333A (en) * | 2012-09-27 | 2013-01-02 | 南京大学 | Service selection system based on group recommendation and selection method thereof |
| CN106156092A (en) * | 2015-04-01 | 2016-11-23 | 阿里巴巴集团控股有限公司 | Data processing method and device |
| CN107203545A (en) * | 2016-03-17 | 2017-09-26 | 阿里巴巴集团控股有限公司 | A kind of data processing method and device |
| CN105825406A (en) * | 2016-03-28 | 2016-08-03 | 乐视控股（北京）有限公司 | Data processing method and device |
| CN106294743A (en) * | 2016-08-10 | 2017-01-04 | 北京奇虎科技有限公司 | The recommendation method and device of application function |
| CN108363714A (en) * | 2017-12-21 | 2018-08-03 | 北京至信普林科技有限公司 | A kind of method and system for the ensemble machine learning for facilitating data analyst to use |
| CN108229828A (en) * | 2018-01-04 | 2018-06-29 | 上海电气集团股份有限公司 | A kind of analysis system based on industrial data |
| CN108363738A (en) * | 2018-01-19 | 2018-08-03 | 上海电气集团股份有限公司 | A kind of recommendation method of industrial equipment data analysis algorithm |
| CN109254990A (en) * | 2018-09-11 | 2019-01-22 | 北京唐冠天朗科技开发有限公司 | A kind of method and system of information source acquisition and dynamic analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110134040A (en) | 2019-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110134040B (en) | Method and system for processing operation data of industrial equipment | |
| CN111191822A (en) | Steel parameter prediction method and terminal equipment | |
| CN112418921A (en) | Power demand prediction method, device, system and computer storage medium | |
| CN111597121B (en) | Precise test method based on historical test case mining | |
| CN109918690A (en) | Monitoring system, learning device, learning method, monitoring arrangement and monitoring method | |
| CN108663501A (en) | A kind of predicting model for dissolved gas in transformer oil method and system | |
| CN116991130A (en) | Intelligent automatic control system and method for petrochemical production | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN117060409A (en) | Automatic detection and analysis method and system for power line running state | |
| CN117218118B (en) | Slump monitoring method and device based on image sequence and readable medium | |
| CN110879820A (en) | Industrial data processing method and device | |
| CN111062827B (en) | Engineering supervision method based on artificial intelligence mode | |
| CN115883424B (en) | Method and system for predicting flow data between high-speed backbone networks | |
| CN110942319A (en) | Method and device for modeling analysis and prediction of product claim data | |
| CN116883184A (en) | Financial tax intelligent analysis method based on big data | |
| Housseman et al. | Smart dynamic sampling for wafer at risk reduction in semiconductor manufacturing | |
| CN114970311A (en) | Method for establishing remote module life prediction model and life prediction method | |
| CN112668249A (en) | Online construction method and system for major repair technical modification scheme of primary equipment of power grid | |
| CN117195083B (en) | Slump prediction method and device based on current curve and readable medium | |
| CN111829359A (en) | Centralized monitoring method and total system for metallurgical industrial furnace and kiln | |
| CN117473347B (en) | Ore dressing full-flow data processing method and system based on rule engine | |
| CN113890837B (en) | Method and system for predicting index degradation based on sliding window cross algorithm | |
| CN114418456B (en) | Machine learning progress control method based on working conditions and related device | |
| CN116797577B (en) | Method for predicting corrosion rate of natural gas pipeline | |
| CN115796307A (en) | Automatic learning method and device for artificial intelligence system of generator set and readable medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |