CN113505539A - Industrial mechanism model testing method, device and storage medium - Google Patents
Industrial mechanism model testing method, device and storage medium Download PDFInfo
- Publication number
- CN113505539A CN113505539A CN202110877983.7A CN202110877983A CN113505539A CN 113505539 A CN113505539 A CN 113505539A CN 202110877983 A CN202110877983 A CN 202110877983A CN 113505539 A CN113505539 A CN 113505539A
- Authority
- CN
- China
- Prior art keywords
- target
- data
- mechanism model
- industrial
- industrial mechanism
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007246 mechanism Effects 0.000 title claims abstract description 194
- 238000012360 testing method Methods 0.000 title claims abstract description 178
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims description 80
- 238000012545 processing Methods 0.000 claims description 45
- 238000000034 method Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 19
- 238000004140 cleaning Methods 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 13
- 238000010946 mechanistic model Methods 0.000 claims 4
- 238000010586 diagram Methods 0.000 description 16
- 230000009286 beneficial effect Effects 0.000 description 8
- 238000013473 artificial intelligence Methods 0.000 description 7
- 238000009776 industrial production Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008676 import Effects 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000012824 chemical production Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Prevention of errors by analysis, debugging or testing of software
- G06F11/3668—Testing of software
- G06F11/3672—Test management
- G06F11/3688—Test management for test execution, e.g. scheduling of test suites
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an industrial mechanism model testing method, device and storage medium, which are used for acquiring user input testing data and an industrial mechanism model to be detected; training an industrial mechanism model to be detected to obtain a target industrial mechanism model, and acquiring target data output by the target industrial mechanism model; testing the target industrial mechanism model according to the test data and the target data to obtain a test result; and outputting a test result. The target industrial mechanism model obtained by the technical scheme provided by the invention has higher accuracy, and the target industrial mechanism model is tested by the test data and the data output by the target industrial mechanism model, so that the accuracy of the target industrial mechanism model is further improved.
Description
Technical Field
The embodiment of the invention belongs to the technical field of model detection, and particularly relates to an industrial mechanism model testing method, an industrial mechanism model testing device and a storage medium.
Background
The mechanism model is an accurate mathematical model established according to the object, the internal mechanism of the production process or the transfer mechanism of the material flow. The mechanism model can be widely applied to industrial production or management, and the industrial mechanism model becomes the core of industrial production.
In industrial production or management, a large number of unquantized influence factors may exist, such as human factors, environmental factors or various random events, and during the use of the mechanism model, deviation between data output by the mechanism model and real data may occur, so that the accuracy of the mechanism model is low.
Disclosure of Invention
In order to solve the above problem in the prior art, that is, to solve the problem of low accuracy of the existing mechanism model, embodiments of the present invention provide an industrial mechanism model testing method, apparatus, and storage medium.
The embodiment of the invention provides an industrial mechanism model testing method, which comprises the following steps:
and acquiring user input test data and an industrial mechanism model to be detected.
And training the industrial mechanism model to be detected to obtain a target industrial mechanism model, and acquiring target data output by the target industrial mechanism model.
And testing the target industrial mechanism model according to the test data and the target data to obtain a test result.
And outputting the test result.
Optionally, the training the to-be-detected industrial mechanism model to obtain a target industrial mechanism model includes:
and acquiring target sample data.
And selecting at least one first algorithm from a preset algorithm library according to the target sample data and/or the requirement information of the user.
And training the industrial mechanism model to be detected according to the target sample data and the first algorithm to obtain a target industrial mechanism model.
Optionally, the obtaining target sample data includes:
and acquiring initial sample data.
And carrying out data cleaning processing on the initial sample data to obtain the cleaned sample data.
And performing feature extraction processing on the cleaned sample data to obtain target sample data.
Optionally, the selecting at least one first algorithm from a preset algorithm library according to the target sample data includes:
and extracting target data characteristics in the target sample data.
And determining the at least one first algorithm corresponding to the target data characteristic according to a preset relation between preset data characteristics and algorithms.
Optionally, the testing the target industrial mechanism model according to the test data and the target data to obtain a test result includes:
and preprocessing the test data to obtain target test data, wherein the preprocessing comprises data cleaning processing and/or feature extraction processing.
And comparing the target test data with the target data, and testing the target industrial mechanism model to obtain the test result.
Optionally, the outputting the test result includes:
and displaying the test result, and/or generating a target file, wherein the target file comprises the test result.
The embodiment of the invention also provides an industrial mechanism model testing device, which comprises:
and the acquisition unit is used for acquiring the test data input by the user and the industrial mechanism model to be detected.
And the processing unit is used for training the industrial mechanism model to be detected to obtain a target industrial mechanism model and acquiring target data output by the target industrial mechanism model.
And the processing unit is used for testing the target industrial mechanism model according to the test data and the target data to obtain a test result.
And the output unit is used for outputting the test result.
Optionally, the processing unit is specifically configured to obtain target sample data; selecting at least one first algorithm from a preset algorithm library according to the target sample data and/or the requirement information of the user; and training the industrial mechanism model to be detected according to the target sample data and the first algorithm to obtain a target industrial mechanism model.
Optionally, the processing unit is specifically configured to obtain initial sample data; performing data cleaning processing on the initial sample data to obtain cleaned sample data; and performing feature extraction processing on the cleaned sample data to obtain target sample data.
Optionally, the processing unit is specifically configured to extract a target data feature in the target sample data; and determining the at least one first algorithm corresponding to the target data characteristic according to a preset relation between preset data characteristics and algorithms.
Optionally, the processing unit is specifically configured to perform preprocessing on the test data to obtain target test data, where the preprocessing includes data cleaning processing and/or feature extraction processing; and comparing the target test data with the target data, and testing the target industrial mechanism model to obtain the test result.
Optionally, the output unit is specifically configured to display the test result, and/or generate a target file, where the target file includes the test result.
The embodiment of the invention also provides an industrial mechanism model testing device, which comprises:
the memory is used for storing the computer program.
The processor is configured to read the computer program stored in the memory, and execute the industrial mechanism model testing method in any one of the above preferred technical solutions according to the computer program in the memory.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer execution instruction is stored in the computer-readable storage medium, and when a processor executes the computer execution instruction, the industrial mechanism model testing method in any of the above preferred technical solutions is implemented.
The embodiment of the present invention further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the industrial mechanism model testing method in any of the above preferred technical solutions is implemented.
Those skilled in the art can understand that, the industrial mechanism model testing method, the device and the storage medium provided by the embodiment of the invention obtain the user input test data and the industrial mechanism model to be detected; training an industrial mechanism model to be detected to obtain a target industrial mechanism model, and acquiring target data output by the target industrial mechanism model; testing the target industrial mechanism model according to the test data and the target data to obtain a test result; and outputting a test result. According to the technical scheme provided by the invention, the target industrial mechanism model is obtained after the industrial mechanism model to be detected is trained, so that the obtained mechanism model is more accurate, and the target industrial mechanism model is tested according to the test data and the data output by the target industrial mechanism model, so that the accuracy of the determined target industrial mechanism model is further improved.
Drawings
Fig. 1 is a scene schematic diagram of an industrial mechanism model testing method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an interface for inputting real data according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a method for testing an industrial mechanical model according to an embodiment of the present invention;
FIG. 4 is a block diagram of a method for testing an industrial mechanical model according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an interface for industrial mechanical model testing according to an embodiment of the present invention;
FIG. 6 is a schematic interface diagram of an algorithm display according to an embodiment of the present invention;
FIG. 7 is a schematic diagram illustrating a test result according to an embodiment of the present invention;
FIG. 8 is a schematic structural diagram of an industrial mechanical model testing apparatus according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of another industrial mechanical model testing apparatus according to an embodiment of the present invention.
Detailed Description
First, it should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention. And can be adjusted as needed by those skilled in the art to suit particular applications.
Next, it should be noted that in the description of the embodiments of the present invention, the terms of direction or positional relationship indicated by the terms "inside", "outside", and the like are based on the directions or positional relationships shown in the drawings, which are merely for convenience of description, and do not indicate or imply that the device or member must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The technical scheme provided by the embodiment of the invention can be applied to a detection scene of a mechanism model. For example, defect detection classification, yield root cause analysis, and detection of micro-mark defects with high accuracy for a panel.
At present, theoretical guidance can be provided for industrial production or enterprise management and the like through data output by a mechanism model, and various data generated in the industrial production or enterprise management can be influenced by factors such as human factors or environmental factors, so that the data output by the mechanism model can deviate from real data, and the accuracy of the mechanism model is low.
In order to solve the problem of low accuracy of the mechanism model, the initial mechanism model can be trained to obtain the mechanism model with high accuracy, and the mechanism model is tested by using data output by the trained mechanism model and test data, so that the accuracy of the mechanism model is further improved.
Fig. 1 is a scene schematic diagram of an industrial mechanism model testing method according to an embodiment of the present invention. As shown in fig. 1, an artificial intelligence platform for detecting an industrial mechanism model exists on the server 102, and the artificial intelligence platform in the server 102 may provide an interface for the terminal device 101 of the user, so that the terminal device 101 of the user can establish a connection with the server 102 to detect the industrial mechanism model on the artificial intelligence platform. After the terminal device 101 and the server 102 are connected, a user can input real data and an industrial mechanism model to be detected on the terminal device 101, and train the model to be detected through a large amount of sample data and an algorithm library stored in the server 102 to obtain a target industrial mechanism model. The target industrial mechanism model is obtained by training the model to be detected, so that the accuracy of the target industrial mechanism model is higher.
Further, for the server 102, when the target industrial mechanism model is obtained, data output by the target industrial mechanism model is obtained at the same time, and the data output by the target industrial mechanism model is compared with real data input by a user, so that the target industrial mechanism model is tested, and a test result is output on the terminal device 101. The accuracy of the target industrial mechanism model can be tested according to the output test result, so that the accuracy of the finally obtained target industrial mechanism model can be improved.
For example, when a user inputs real data into the terminal 101, a display interface of the terminal 101 may be as shown in fig. 2, where fig. 2 is a schematic diagram of an interface for inputting real data according to an embodiment of the present invention. According to fig. 2, the user may import the real data stored in the database of the terminal device 101 by means of data import, so as to transmit the real data to the server 102. Specifically, the user may create a new database on the data source interface displayed by the terminal device 101, import the real data into the new database, and create the new database containing the real data by clicking the creation control. The user can independently select the imported data, and the data can be prevented from being leaked. The embodiment of the invention is described by taking the display interface shown in fig. 2 as an example, but the embodiment of the invention is not limited thereto. It can be understood that the user has unique management right and control right for the input real data, so that the real data input by the user is ensured not to be leaked, and the privacy of the user is protected.
Hereinafter, the industrial mechanism model test method provided by the present invention will be described in detail by specific examples. It is to be understood that the following detailed description may be combined with other embodiments, and that the same or similar concepts or processes may not be repeated in some embodiments.
Fig. 3 is a schematic flow chart of an industrial mechanism model testing method according to an embodiment of the present invention. The industrial mechanism model testing method can be executed by software and/or hardware device, for example, the hardware device can be an electronic device, and the electronic device can be a terminal or a processing chip in the terminal. For example, referring to fig. 3, the industrial mechanism model testing method may include:
s301, obtaining user input test data and the industrial mechanism model to be detected.
In the embodiment of the invention, the test data is real data, and can be real data generated in industrial production or enterprise management. The industrial mechanism model to be detected can be an initial industrial mechanism model obtained by a user according to requirements, or an industrial mechanism model with low accuracy obviously in the use process, for example, in chemical production, when the production of chemicals is carried out according to data output by the industrial mechanism model, a certain error exists between the obtained chemicals and an expected chemicals, so that the accuracy of the industrial mechanism model is low, and the industrial mechanism model needs to be tested. The embodiment of the invention does not limit the input test data and the industrial mechanism model to be detected.
S302, training the industrial mechanism model to be detected to obtain a target industrial mechanism model, and acquiring target data output by the target industrial mechanism model.
When the industrial mechanism model to be detected is trained to obtain a target industrial mechanism model, target sample data can be obtained; selecting at least one first algorithm from a preset algorithm library according to target sample data and/or user requirement information; and training the industrial mechanism model to be detected according to the target sample data and the first algorithm to obtain the target industrial mechanism model.
In an example, the preset algorithm library includes a large number of algorithms, including basic machine learning algorithms such as two-class and multi-class problems, cluster analysis, time series analysis, regression analysis, and the like, and further provides frames such as a deep learning algorithm, text analysis, natural language processing, network analysis, association rule analysis, and the like. The method provided by the embodiment of the application can realize artificial intelligence through the algorithm. The embodiment of the present invention is described by taking the above as an example, but the embodiment of the present invention is not limited thereto.
In a possible implementation manner, at least one first algorithm may be selected from a preset algorithm library according to target sample data. For example, at least one first algorithm may be selected from a preset algorithm library according to characteristics of the target sample data.
In a possible implementation manner, at least one first algorithm may be selected from a preset algorithm library according to the requirement information of the user. For example, the user may access a preset algorithm library on the terminal device, and select at least one first algorithm from the preset algorithm library by performing a corresponding operation. For example, a user may drag at least one algorithm in the preset algorithm library to a preset area as a first algorithm according to a requirement; or, the user may select at least one first algorithm by clicking a control corresponding to the algorithm, which is only described once in the embodiment of the present invention, but the embodiment of the present invention is not limited thereto. The user selects at least one first algorithm according to the requirement information, so that the accuracy of the selected first algorithm can be improved, and the requirement of the user can be met better.
In another possible implementation manner, at least one first algorithm may be selected from a preset algorithm library according to the target sample data and the requirement information of the user. For example, a user may input requirement information on the terminal device, so that the target sample can be processed according to the requirement information, and the accuracy of the selected first algorithm can be further improved by selecting at least one first algorithm according to the user information and the target sample.
According to the above several possible implementations, it can be known that when selecting the at least one first algorithm, the selection may be performed automatically or manually by a user, for example, the user selects the at least one first algorithm by clicking. User coding algorithm code is avoided, thereby improving the efficiency of determining the at least one first method.
In the embodiment of the invention, the industrial mechanism model to be detected is trained according to the target sample data and the first algorithm to obtain the target industrial mechanism model, the target sample data can simulate real data to a great extent, and the first algorithm is determined according to the target sample data and/or user demand information, so that the determined target industrial mechanism model can better meet the demand of a user, and the accuracy of the target industrial mechanism model is improved.
For example, when target sample data is acquired, initial sample data may be acquired; carrying out data cleaning processing on the initial sample data to obtain the cleaned sample data; and performing feature extraction processing on the cleaned sample data to obtain target sample data.
Wherein, the data cleaning is used as the last procedure for finding and correcting recognizable errors in the data file, and comprises the steps of checking the consistency of the data, processing invalid values and missing values and the like.
For example, when initial sample data is obtained, data on Internet of Things (IOT) equipment may be collected as the initial sample data, and the initial sample data may be stored on a big data platform, or the initial sample data may be imported into an artificial intelligence platform, so that the artificial intelligence platform may directly train a model to be detected by using the initial sample data. The embodiment of the present invention is described by taking an example of importing an artificial intelligence platform, but the embodiment of the present invention is not limited thereto.
For example, when initial sample data is acquired and data cleaning and feature extraction are performed on the initial sample data, data can be processed in a distributed parallelization manner, so that the operation speed of the data can be increased, and effective real-time decision making can be realized.
In the embodiment of the invention, by cleaning the initial sample data, partial invalid values or missing values and the like in the initial sample data can be removed, and by extracting the characteristic values of the cleaned data, the conformity of the obtained target sample data and the real data is higher, so that the accuracy of the obtained target industrial mechanism model is further improved.
When at least one first algorithm is selected from a preset algorithm library according to target sample data, target data characteristics in the target sample data can be extracted; and determining at least one first algorithm corresponding to the target data characteristic according to a preset relation between the preset data characteristic and the algorithm.
For example, the preset relationship between the preset data characteristics and the algorithm may be determined by repeatedly processing a large amount of data, wherein the preset relationship includes corresponding relationships between different types of data and algorithms, for example, an algorithm corresponding to sales data is determined by processing sales and repeatedly trial and error during sales of a certain product. Sales data and corresponding algorithms over a period of time. Therefore, the first algorithm can be accurately determined according to the preset relationship between the preset data characteristics and the algorithm.
In the embodiment of the invention, at least one first algorithm is determined according to the preset relation between the preset data characteristics and the algorithms, so that the determined at least one first algorithm is more accurate, and the accuracy of the target industrial mechanism model can be improved when the industrial mechanism model to be detected is trained according to the first algorithm to generate the target industrial mechanism model.
And S303, testing the target industrial mechanism model according to the test data and the target data to obtain a test result.
When the target industrial mechanism model is tested according to the test data and the target data to obtain a test result, the test data can be preprocessed to obtain target test data, and the preprocessing comprises data cleaning processing and/or feature extraction processing; and comparing the target test data with the target data, and testing the target industrial mechanism model to obtain a test result.
For example, the method for preprocessing the test data may be described in the above embodiments, and details of the embodiment of the present invention are not repeated.
In the embodiment of the invention, the data cleaning processing and/or the characteristic extraction data are carried out on the test data, so that the obtained target test data is more accurate, and the accuracy of the test result obtained by testing the target industrial mechanism model is improved.
And S304, outputting the test result.
When the test result is output, the test result may be displayed and/or a target file may be generated, the target file containing the test result. The test result can be displayed on the terminal equipment of the user side, so that the user can know the test result in time to execute corresponding measures, and the specific test result can be set according to the actual situation.
For example, the output test result may be output in a table manner, may be output in a graph manner, or in other manners. Specifically, the setting may be performed according to actual conditions, and the embodiment of the present invention is not limited in this respect.
For example, the target file may also be directly generated and stored in the terminal device of the user, and the form of the test result in the target file may be various, for example, a form, a line graph, a bar graph, a pie graph, or a character string form, which is not limited in this embodiment of the present invention.
In the embodiment of the invention, the user can visually see the detection result of the target industrial mechanism model by outputting the test result, so that the target industrial mechanism model is determined.
Therefore, the industrial mechanism model testing method, the device and the storage medium provided by the embodiment of the invention can obtain the user input testing data and the industrial mechanism model to be detected; training an industrial mechanism model to be detected to obtain a target industrial mechanism model, and acquiring target data output by the target industrial mechanism model; testing the target industrial mechanism model according to the test data and the target data to obtain a test result; and outputting a test result. According to the technical scheme, the target industrial mechanism model is obtained by training the industrial mechanism model to be detected, and the target industrial mechanism model is tested, so that the accuracy of the determined target industrial mechanism model is improved.
For example, after the test result is output, the target excitation model can be evaluated according to the test result, and if the evaluation result of the target industrial mechanism model is qualified, the target industrial mechanism model can be output; if the evaluation result of the target industrial mechanism model is unqualified, the method described in the above embodiment may be performed until the evaluation result of the target industrial mechanism model is qualified, so that the accuracy of the finally determined target industrial mechanism model may be improved.
In order to facilitate understanding of the industrial mechanism model testing method provided by the embodiment of the present invention, the following will describe in detail the technical solution provided by the embodiment of the present invention through a specific example, specifically refer to fig. 4, where fig. 4 is a schematic frame diagram of an industrial mechanism model testing method provided by the embodiment of the present invention.
As shown in fig. 4, the training data and the test data are both subjected to data preprocessing, and the data preprocessing manner may include data cleaning processing and/or feature extraction processing, which is the same as the method for processing the initial sample data in the above embodiment, and reference may be made to the above embodiment, which is not described herein again in the embodiment of the present invention. For example, data preprocessing may identify and fill in missing data, remove missing records, remove attributes whose attribute values are all constant, randomize the data, etc., resulting in higher accuracy of the resulting data. The training data is sample data, the training data includes the industrial mechanism model to be detected, the sample data can be stored in the server or uploaded by the user, and the embodiment of the invention does not limit the sample data. The test data is real data uploaded by the user through the terminal equipment.
In the embodiment of the present invention, an industrial mechanism model testing process may be executed through the interface shown in fig. 5, and fig. 5 is an interface schematic diagram of an industrial mechanism model testing provided in the embodiment of the present invention. The display interface shown in fig. 5 includes preprocessing, feature processing, regression function, data classification, clustering, estimation, evaluation function, intuitive function, and output control, and when a user clicks the corresponding control of the interface, the user can perform corresponding operation, thereby outputting a result. For example, when the user clicks the preprocessing control, the data is preprocessed and the processed data is displayed, or when the user clicks the output control, the processed data is output to the terminal device of the user. In addition, the interface can also display the industrial mechanism model testing process, so that a user can visually see the process of the industrial mechanism model testing. The embodiment of the present invention is illustrated by using fig. 5 as an example, but the embodiment of the present invention is not limited thereto.
Further, after the training data is preprocessed, the model training of the industrial mechanism model to be detected can be performed according to the preprocessed data selection algorithm, the trained industrial mechanism model is obtained, and the data output by the trained industrial mechanism model is obtained. For a specific model training process, reference may be made to the above embodiments, which are not described in detail herein. For example, when an algorithm is selected, refer to fig. 6, where fig. 6 is a schematic interface diagram of an algorithm display provided by an embodiment of the present invention. The algorithm shown in fig. 6 is an algorithm in an algorithm library, and a user can select an algorithm autonomously to train a model to be detected. The embodiment of the present invention is illustrated by using fig. 6 as an example, but the embodiment of the present invention is not limited thereto.
And further, inputting data output by the trained industrial mechanism model and the preprocessed training data into a scoring model, and detecting the target model by comparing the two data by the scoring model. The scoring model sends the output data to the evaluation model, and the data is evaluated to obtain a test result. For example, the obtained test result can be seen in fig. 7, and fig. 7 is a schematic display diagram of a test result provided by an embodiment of the present invention. According to fig. 7, the test result can be represented by an error histogram, and the relative square error between the data output by the trained industrial mechanism model and the pre-processed training data is 0.181, the relative absolute error is 0.449, the coefficient of determination is 0.819, the root mean square error is 72115.699, and the average absolute error is 56997.667. It can be understood that the error histogram may be directly displayed on a display interface of the user terminal device, or the error histogram may be stored in the user terminal device.
In summary, the industrial mechanism model testing method provided by the embodiment of the invention can perform model training on the industrial mechanism model to be detected to generate the target industrial mechanism model, so that the generated target industrial mechanism model has higher accuracy. In addition, the method can realize the fusion of an industrial mechanism and big data.
In another embodiment of the present invention, the industrial mechanism model testing method provided by the embodiment of the present invention can match the typical organization architecture in the industry, i.e., the total plant, the factory floor, the workshop and the production line. For example, in the intelligent practice of the household appliance industry, the device can be adapted to the existing equipment and control system in a plug-and-play mode under the condition of continuous production. The delay requirement of the industrial operation environment is matched, various deployment modes are provided, the consumption of the model on the calculation space and time is reduced to the maximum extent through technologies such as model compression, and the delay requirement of factory production is met.
Fig. 8 is a schematic structural diagram of an industrial mechanical model testing apparatus 80 according to an embodiment of the present invention, for example, referring to fig. 8, the industrial mechanical model testing apparatus 80 may include:
the obtaining unit 801 is configured to obtain user input test data and an industrial mechanism model to be detected.
The processing unit 802 is configured to train the industrial mechanism model to be detected to obtain a target industrial mechanism model, and obtain target data output by the target industrial mechanism model.
And the processing unit 802 is configured to test the target industrial mechanism model according to the test data and the target data to obtain a test result.
And an output unit 803 for outputting the test result.
Optionally, the processing unit 802 is specifically configured to obtain target sample data; selecting at least one first algorithm from a preset algorithm library according to target sample data and/or user requirement information; and training the industrial mechanism model to be detected according to the target sample data and the first algorithm to obtain the target industrial mechanism model.
Optionally, the processing unit 802 is specifically configured to obtain initial sample data; carrying out data cleaning processing on the initial sample data to obtain the cleaned sample data; and performing feature extraction processing on the cleaned sample data to obtain target sample data.
Optionally, the processing unit 802 is specifically configured to extract target data features in the target sample data; and determining at least one first algorithm corresponding to the target data characteristic according to a preset relation between the preset data characteristic and the algorithm.
Optionally, the processing unit 802 is specifically configured to perform preprocessing on the test data to obtain target test data, where the preprocessing includes data cleaning processing and/or feature extraction processing; and comparing the target test data with the target data, and testing the target industrial mechanism model to obtain a test result.
Optionally, the output unit 803 is specifically configured to display the test result, and/or generate a target file, where the target file includes the test result.
The industrial mechanism model testing device provided by the embodiment of the invention can execute the technical scheme of the industrial mechanism model testing method in any embodiment, the implementation principle and the beneficial effect of the industrial mechanism model testing device are similar to those of the industrial mechanism model testing method, and the implementation principle and the beneficial effect of the industrial mechanism model testing method can be referred to, and are not described herein again.
Fig. 9 is a schematic structural diagram of another industrial mechanical model testing device 90 according to an embodiment of the present invention, for example, referring to fig. 9, the industrial mechanical model testing device 90 may include a processor 901 and a memory 902; wherein,
the memory 902 is used for storing computer programs.
The processor 901 is configured to read the computer program stored in the memory 902, and execute the technical solution of the industrial mechanism model testing method in any of the embodiments according to the computer program in the memory 902.
Alternatively, the memory 902 may be separate or integrated with the processor 901. When the memory 902 is a device independent from the processor 901, the industrial mechanism model test apparatus 90 may further include: a bus for connecting the memory 902 and the processor 901.
Optionally, this embodiment further includes: a communication interface that may be connected to the processor 901 via a bus. The processor 901 may control the communication interface to implement the functions of receiving and transmitting of the industrial mechanical model test device 90 described above.
The industrial mechanism model testing device 90 shown in the embodiment of the present invention can execute the technical solution of the industrial mechanism model testing method in any embodiment, and the implementation principle and the beneficial effect thereof are similar to those of the industrial mechanism model testing method, and reference may be made to the implementation principle and the beneficial effect of the industrial mechanism model testing method, which are not described herein again.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer execution instruction is stored in the computer-readable storage medium, and when a processor executes the computer execution instruction, the technical solution of the industrial mechanism model testing method in any of the above embodiments is implemented, and an implementation principle and beneficial effects of the technical solution are similar to those of the industrial mechanism model testing method, which can be referred to as the implementation principle and beneficial effects of the industrial mechanism model testing method, and are not described herein again.
The embodiment of the present invention further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the technical solution of the industrial mechanism model testing method in any of the above embodiments is implemented, and the implementation principle and the beneficial effect of the computer program are similar to those of the industrial mechanism model testing method, which can be referred to as the implementation principle and the beneficial effect of the industrial mechanism model testing method, and are not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts shown as units may or may not be physical units, may be located in one position, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated module implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention.
It should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
The memory may comprise a high-speed RAM memory, and may further comprise a non-volatile storage NVM, such as at least one disk memory, and may also be a usb disk, a removable hard disk, a read-only memory, a magnetic or optical disk, etc.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present invention are not limited to only one bus or one type of bus.
The computer-readable storage medium may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An industrial mechanistic model testing method, comprising:
acquiring user input test data and an industrial mechanism model to be detected;
training the industrial mechanism model to be detected to obtain a target industrial mechanism model, and acquiring target data output by the target industrial mechanism model;
testing the target industrial mechanism model according to the test data and the target data to obtain a test result;
and outputting the test result.
2. The method according to claim 1, wherein the training of the industrial mechanism model to be detected to obtain a target industrial mechanism model comprises:
acquiring target sample data;
selecting at least one first algorithm from a preset algorithm library according to the target sample data and/or the requirement information of the user;
and training the industrial mechanism model to be detected according to the target sample data and the first algorithm to obtain a target industrial mechanism model.
3. The method of claim 2, wherein said obtaining target sample data comprises:
acquiring initial sample data;
performing data cleaning processing on the initial sample data to obtain cleaned sample data;
and performing feature extraction processing on the cleaned sample data to obtain target sample data.
4. The method according to claim 2 or 3, wherein said selecting at least one first algorithm from a preset algorithm library according to the target sample data comprises:
extracting target data characteristics in the target sample data;
and determining the at least one first algorithm corresponding to the target data characteristic according to a preset relation between preset data characteristics and algorithms.
5. The method according to any one of claims 1-3, wherein said testing said target industrial mechanistic model based on said test data and said target data to obtain a test result comprises:
preprocessing the test data to obtain target test data, wherein the preprocessing comprises data cleaning processing and/or feature extraction processing;
and comparing the target test data with the target data, and testing the target industrial mechanism model to obtain the test result.
6. The method of claim 1, wherein outputting the test result comprises:
and displaying the test result, and/or generating a target file, wherein the target file comprises the test result.
7. An industrial mechanism model testing apparatus, comprising:
the acquisition unit is used for acquiring user input test data and an industrial mechanism model to be detected;
the processing unit is used for training the industrial mechanism model to be detected to obtain a target industrial mechanism model and acquiring target data output by the target industrial mechanism model;
the processing unit is further used for testing the target industrial mechanism model according to the test data and the target data to obtain a test result;
and the output unit is used for outputting the test result.
8. An industrial mechanism model testing device is characterized by comprising a memory and a processor; wherein,
the memory for storing a computer program;
the processor is used for reading the computer program stored in the memory and executing the industrial mechanism model testing method of any one of the claims 1-6 according to the computer program in the memory.
9. A computer-readable storage medium having computer-executable instructions stored thereon which, when executed by a processor, implement an industrial mechanistic model testing method as recited in any one of claims 1-6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, carries out a method for industrial mechanistic model testing according to any one of the preceding claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110877983.7A CN113505539A (en) | 2021-07-30 | 2021-07-30 | Industrial mechanism model testing method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110877983.7A CN113505539A (en) | 2021-07-30 | 2021-07-30 | Industrial mechanism model testing method, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113505539A true CN113505539A (en) | 2021-10-15 |
Family
ID=78014825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110877983.7A Pending CN113505539A (en) | 2021-07-30 | 2021-07-30 | Industrial mechanism model testing method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113505539A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190005168A1 (en) * | 2017-06-30 | 2019-01-03 | Siemens Aktiengesellschaft | Performance testing method and apparatus for industrial system deployed on cloud |
| CN109754014A (en) * | 2018-12-29 | 2019-05-14 | 北京航天数据股份有限公司 | Industry pattern training method, device, equipment and medium |
| CN110427998A (en) * | 2019-07-26 | 2019-11-08 | 上海商汤智能科技有限公司 | Model training, object detection method and device, electronic equipment, 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 |
| CN113065843A (en) * | 2021-03-15 | 2021-07-02 | 腾讯科技（深圳）有限公司 | Model processing method and device, electronic equipment and storage medium |
-
2021
- 2021-07-30 CN CN202110877983.7A patent/CN113505539A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190005168A1 (en) * | 2017-06-30 | 2019-01-03 | Siemens Aktiengesellschaft | Performance testing method and apparatus for industrial system deployed on cloud |
| CN109754014A (en) * | 2018-12-29 | 2019-05-14 | 北京航天数据股份有限公司 | Industry pattern training method, device, equipment and medium |
| CN110427998A (en) * | 2019-07-26 | 2019-11-08 | 上海商汤智能科技有限公司 | Model training, object detection method and device, electronic equipment, 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 |
| CN113065843A (en) * | 2021-03-15 | 2021-07-02 | 腾讯科技（深圳）有限公司 | Model processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112884092B (en) | AI model generation method, electronic device, and storage medium | |
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| CN110222087B (en) | Feature extraction method, device and computer readable storage medium | |
| CN113449703B (en) | Quality control method and device for environment online monitoring data, storage medium and equipment | |
| CN109872026A (en) | Evaluation result generation method, device, equipment and computer readable storage medium | |
| CN111506798A (en) | User screening method, device, device and storage medium | |
| CN114066848A (en) | FPCA appearance defect visual inspection system | |
| CN112766387A (en) | Error correction method, device, equipment and storage medium for training data | |
| CN112613425B (en) | A target recognition system for small sample underwater images | |
| CN113110961B (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
| CN113918471A (en) | Test case processing method and device and computer readable storage medium | |
| CN114003493A (en) | Test data processing method, device, equipment and storage medium | |
| CN110083540B (en) | Interface testing method and device | |
| CN113505539A (en) | Industrial mechanism model testing method, device and storage medium | |
| CN118070280A (en) | Malicious webpage file detection method and device, electronic equipment and storage medium | |
| CN110837459A (en) | Big data-based operation performance analysis method and system | |
| CN115344495A (en) | Data analysis method and device for batch task test, computer equipment and medium | |
| CN116662186A (en) | Log playback assertion method and device based on logistic regression and electronic equipment | |
| CN112505337B (en) | Data processing method for assisting analysis of sample | |
| CN115905016A (en) | BIOS Setup search function test method and device, electronic equipment and storage medium | |
| CN115829925A (en) | Appearance defect detection method and device, computer equipment and storage medium | |
| CN114066132A (en) | Quality evaluation method and evaluation device for agricultural products | |
| CN113569879A (en) | Training method of abnormal recognition model, abnormal account recognition method and related device | |
| KR101513071B1 (en) | Amount calcuration apparatus and method using drawing and recording medium | |
| CN114580982B (en) | Method, device and equipment for evaluating data quality of industrial 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 |