CN112712861A - Model construction method, device, equipment and computer readable medium - Google Patents
Model construction method, device, equipment and computer readable medium Download PDFInfo
- Publication number
- CN112712861A CN112712861A CN202110020202.2A CN202110020202A CN112712861A CN 112712861 A CN112712861 A CN 112712861A CN 202110020202 A CN202110020202 A CN 202110020202A CN 112712861 A CN112712861 A CN 112712861A
- Authority
- CN
- China
- Prior art keywords
- time
- process parameters
- feature
- features
- calcium oxide
- 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.)
- Withdrawn
Links
- 238000010276 construction Methods 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 167
- 230000008569 process Effects 0.000 claims abstract description 135
- BRPQOXSCLDDYGP-UHFFFAOYSA-N calcium oxide Chemical compound [O-2].[Ca+2] BRPQOXSCLDDYGP-UHFFFAOYSA-N 0.000 claims abstract description 77
- ODINCKMPIJJUCX-UHFFFAOYSA-N calcium oxide Inorganic materials [Ca]=O ODINCKMPIJJUCX-UHFFFAOYSA-N 0.000 claims abstract description 77
- 239000000292 calcium oxide Substances 0.000 claims abstract description 77
- 239000004568 cement Substances 0.000 claims abstract description 65
- 238000004519 manufacturing process Methods 0.000 claims abstract description 52
- 238000012549 training Methods 0.000 claims abstract description 35
- 238000007637 random forest analysis Methods 0.000 claims description 33
- 238000012216 screening Methods 0.000 claims description 29
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000004891 communication Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 230000036962 time dependent Effects 0.000 claims description 2
- 238000013441 quality evaluation Methods 0.000 abstract description 3
- 230000009471 action Effects 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000001354 calcination Methods 0.000 description 2
- 239000003245 coal Substances 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000003837 high-temperature calcination Methods 0.000 description 2
- 235000012054 meals Nutrition 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C10/00—Computational theoretical chemistry, i.e. ICT specially adapted for theoretical aspects of quantum chemistry, molecular mechanics, molecular dynamics or the like
Landscapes
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a model construction method, a model construction device, a model construction equipment and a computer readable medium. The method comprises the following steps: acquiring a plurality of process parameters used in the cement production process; extracting time period characteristics of each process parameter at different time, wherein all the time period characteristics are to-be-selected characteristics to be input into the prediction model to train the prediction model; determining target characteristics from the characteristics to be selected according to the time correlation relationship between the process parameters at different times and the free calcium oxide content, and inputting the target characteristics into a prediction model for training so that the prediction model predicts the free calcium oxide content according to the time correlation relationship between the process parameters and the free calcium oxide content. According to the method, the most relevant characteristics are found out to be used as the training input of the prediction model by analyzing the time correlation between the process parameters in the cement production process and the free calcium oxide content in the cement quality evaluation, so that the prediction accuracy of the prediction model is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a model building method, apparatus, device, and computer readable medium.
Background
The content of free calcium oxide (f-CaO) in cement clinker is an important index of the quality of the cement clinker, and in the cement production process, the content of the free calcium oxide needs to be controlled within a certain range, and the stability of the cement and the strength of the clinker are directly influenced by the content of the free calcium oxide. Various process parameters in the cement production process directly influence the content of free calcium oxide, the process parameters are given according to the experience of operators and technologists, the content of the free calcium oxide in the clinker cannot be accurately predicted, and unreasonable process parameters easily cause low clinker quality qualification rate. Therefore, the accurate prediction of the content of the free calcium oxide is significant for actual production control and quality optimization.
At present, in the related art, a model of the free calcium oxide content can be constructed based on feature screening of the feature importance of the tree model, including collecting the features of each process parameter and the cement clinker quality parameter (free calcium oxide content) in the cement manufacturing process. The characteristic parameters include raw meal composition parameters and process parameters during calcination of the clinker. And (3) sending the characteristic parameters into a tree model, such as a random forest model, a training model, sequencing all the characteristics from large to small according to the characteristic importance of the model, calling the values of the first n sequenced parameters in the characteristic parameters to form a characteristic set, sending the characteristic set into the prediction model for training, and finishing the training to obtain the prediction model of the free calcium oxide content of the clinker. However, the various process parameters in the cement manufacturing process actually represent the reaction environment parameters of the various processes in the cement manufacturing process, and the prediction model trained in the way is difficult to accurately and effectively predict the content of the free calcium oxide according to the process parameters in different periods.
Aiming at the problem of low prediction accuracy of the content of free calcium oxide, no effective solution is provided at present.
Disclosure of Invention
The application provides a model construction method, a model construction device, model construction equipment and a computer readable medium, which are used for constructing a more accurate free calcium oxide content prediction model and solving the technical problem of low prediction accuracy of the free calcium oxide content.
According to an aspect of an embodiment of the present application, there is provided a model building method including:
acquiring a plurality of process parameters used in the cement production process;
extracting time period characteristics of each process parameter at different time, wherein all the time period characteristics are to-be-selected characteristics to be input into the prediction model to train the prediction model;
determining target characteristics from the characteristics to be selected according to the time correlation relationship between the process parameters at different times and the free calcium oxide content, and inputting the target characteristics into a prediction model for training so that the prediction model predicts the free calcium oxide content according to the time correlation relationship between the process parameters and the free calcium oxide content.
Optionally, the extracting time period characteristics of each process parameter at different times includes:
constructing a time sliding window;
sliding a time sliding window in the process parameters according to a preset step length, wherein the length of the preset step length is the time length;
determining at least one of the average value, the variance and the standard deviation of the process parameters in the corresponding time period when the time sliding window is slid each time;
and taking at least one of the average value, the variance and the standard deviation of the process parameters in the corresponding time period as the time period characteristic of the corresponding time period.
Optionally, constructing the time sliding window comprises:
determining the window size of a time sliding window, wherein the window size is larger than or equal to the cement production time divided by the total process number;
determining the sliding time range of the time sliding window, wherein the sliding time range is greater than or equal to the cement production time;
a time sliding window is determined using the window size and the sliding time range.
Optionally, determining the target feature from the candidate features according to the time-dependent relationship between the process parameters and the free calcium oxide content at different times comprises at least one of the following ways:
determining the feature weights of all to-be-selected features of the process parameters by using a random forest model, and screening out a target number of to-be-selected features as target features according to the sequence of the feature weights from large to small;
determining linear correlation coefficients of various candidate characteristics of the process parameters and the content of free calcium oxide in the cement obtained by actual production, and screening a target number of candidate characteristics as target characteristics according to the sequence of the linear correlation coefficients from large to small, wherein the time correlation relationship comprises a relationship expressed by the linear correlation coefficients;
determining nonlinear correlation coefficients of various candidate characteristics of the process parameters and the content of free calcium oxide in the cement obtained by actual production, and screening a target number of candidate characteristics as target characteristics according to the sequence of the nonlinear correlation coefficients from large to small, wherein the time correlation relationship comprises a relationship expressed by the nonlinear correlation coefficients.
Optionally, the determining the target feature from the candidate features further includes:
extracting the features to be selected which are screened out according to the sequence of the feature weights from big to small;
determining a comprehensive correlation coefficient of the to-be-selected feature by using the extracted feature weight, the linear correlation coefficient and the nonlinear correlation coefficient of the to-be-selected feature;
and screening the candidate features corresponding to the maximum comprehensive correlation coefficient as target features according to the sequence of the maximum comprehensive correlation coefficient from large to small.
Optionally, determining the comprehensive correlation coefficient of the feature to be selected by using the extracted feature weight, the linear correlation coefficient and the nonlinear correlation coefficient of the feature to be selected includes:
acquiring the characteristic weight of each process parameter, the linear correlation coefficient and the calculation proportion of the nonlinear correlation coefficient in the comprehensive correlation coefficient;
and taking the sum of the product of the feature weight and the corresponding calculation proportion, the product of the linear correlation coefficient and the corresponding calculation proportion and the product of the nonlinear correlation coefficient and the corresponding calculation proportion as the comprehensive correlation coefficient of the feature to be selected.
Optionally, determining feature weights of all to-be-selected features of the process parameters by using the random forest model, and screening a target number of to-be-selected features as the target features according to a descending order of the feature weights includes:
all the characteristics to be selected of the process parameters are used as the input of a random forest model, the content of free calcium oxide in the cement obtained by actual production is used as the output of the random forest model, and the random forest model is trained to obtain the characteristic weight of each characteristic to be selected;
sequencing all the features to be selected according to the sequence of the feature weights from large to small;
and eliminating a preset number of to-be-selected features which are ranked backwards, taking the remaining to-be-selected features as new input of the random forest model, and recursively obtaining a target number of to-be-selected features as target features.
According to another aspect of the embodiments of the present application, there is provided a model building apparatus including:
the process parameter acquisition module is used for acquiring a plurality of process parameters used in the cement production process;
the time period characteristic extraction module is used for extracting time period characteristics of each process parameter at different time, and all the time period characteristics are to-be-selected characteristics to be input into the prediction model to train the prediction model;
and the characteristic screening and training module is used for determining target characteristics from the characteristics to be selected according to the time correlation relationship between the process parameters at different times and the free calcium oxide content, and inputting the target characteristics into a prediction model for training so that the prediction model predicts the free calcium oxide content according to the time correlation relationship between the process parameters and the free calcium oxide content.
According to another aspect of the embodiments of the present application, there is provided an electronic device, including a memory, a processor, a communication interface, and a communication bus, where the memory stores a computer program executable on the processor, and the memory and the processor communicate with each other through the communication bus and the communication interface, and the processor implements the steps of the method when executing the computer program.
According to another aspect of embodiments of the present application, there is also provided a computer readable medium having non-volatile program code executable by a processor, the program code causing the processor to perform the above-mentioned method.
Compared with the related art, the technical scheme provided by the embodiment of the application has the following advantages:
the technical scheme of the application is to obtain a plurality of process parameters used in the cement production process; extracting time period characteristics of each process parameter at different time, wherein all the time period characteristics are to-be-selected characteristics to be input into the prediction model to train the prediction model; determining target characteristics from the characteristics to be selected according to the time correlation relationship between the process parameters at different times and the free calcium oxide content, and inputting the target characteristics into a prediction model for training so that the prediction model predicts the free calcium oxide content according to the time correlation relationship between the process parameters and the free calcium oxide content. According to the method, the most relevant characteristics are found out to be used as the training input of the prediction model by analyzing the time correlation between the process parameters in the cement production process and the free calcium oxide content in the cement quality evaluation, so that the prediction accuracy of the prediction model is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the technical solutions in the embodiments or related technologies of the present application, the drawings needed to be used in the description of the embodiments or related technologies will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without any creative effort.
FIG. 1 is a schematic diagram of an alternative hardware environment for a model building method according to an embodiment of the present application;
FIG. 2 is a flow chart of an alternative model construction method provided in accordance with an embodiment of the present application;
FIG. 3 is a block diagram of an alternative model building apparatus according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an alternative electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. 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 application.
In the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for the convenience of description of the present application, and have no specific meaning in themselves. Thus, "module" and "component" may be used in a mixture.
In the related art, a model of the free calcium oxide content can be constructed based on feature screening of the significance of the tree model features, including collecting the features of each process parameter and the cement clinker quality parameter (free calcium oxide content) in the cement manufacturing process. The characteristic parameters include raw meal composition parameters and process parameters during calcination of the clinker. And (3) sending the characteristic parameters into a tree model, such as a random forest model, a training model, sequencing all the characteristics from large to small according to the characteristic importance of the model, calling the values of the first n sequenced parameters in the characteristic parameters to form a characteristic set, sending the characteristic set into the prediction model for training, and finishing the training to obtain the prediction model of the content of clinker free calcium oxide.
The various process parameters in the cement manufacturing process actually represent the reaction environment parameters of the various processes in the cement manufacturing process. The cement is manufactured through a series of process flows, the cement is preheated in a preheater, then enters a decomposing furnace for predecomposition, then enters a rotary kiln for high-temperature calcination, generates complex physical and chemical reaction with fire coal, slides to a grate cooler from a kiln tail to a kiln head, completes a strong air cooling process in the grate cooler, runs to an outlet of the grate cooler under the pushing action of a grate bed, and is crushed by a clinker crusher to form cement clinker. The different processes are carried out in different time periods in the whole process, and the influence time of the different processes on clinker free calcium oxide is different. In the related technology, analysis is only carried out from the model level, characteristics are screened by adopting characteristic importance, the fact that different working procedures in service have different action times and the correlation between the working procedures and the content of free calcium oxide in cement is different is not considered, and therefore the accuracy of the obtained prediction model is low.
To solve the problems mentioned in the background, according to an aspect of embodiments of the present application, an embodiment of a model construction method is provided. According to the model construction method, time correlation analysis is adopted for feature screening, time period features most relevant to the content of free calcium oxide are sent to the prediction model for training, and the finally obtained prediction model can be used for predicting the content of free calcium oxide in clinker more accurately.
Alternatively, in the embodiment of the present application, the model building method described above may be applied to a hardware environment formed by the terminal 101 and the server 103 as shown in fig. 1. As shown in fig. 1, a server 103 is connected to a terminal 101 through a network, which may be used to provide services for the terminal or a client installed on the terminal, and a database 105 may be provided on the server or separately from the server, and is used to provide data storage services for the server 103, and the network includes but is not limited to: wide area network, metropolitan area network, or local area network, and the terminal 101 includes but is not limited to a PC, a cell phone, a tablet computer, and the like.
A model building method in the embodiment of the present application may be executed by the server 103, or may be executed by both the server 103 and the terminal 101, as shown in fig. 2, the method may include the following steps:
step S202, a plurality of process parameters used in the cement production process are obtained.
In the embodiment of the application, cement manufacture is subjected to a series of process flows, the cement is preheated in a preheater, then enters a decomposing furnace for predecomposition, then enters a rotary kiln for high-temperature calcination, is subjected to complex physical and chemical reaction with fire coal, slides to a grate cooler from a kiln tail to a kiln head, completes a strong air cooling process in the grate cooler, runs to an outlet of the grate cooler under the pushing action of a grate bed, and is crushed by a clinker crusher to form cement clinker. The process parameters comprise various parameters in the process flow, such as kiln rotating speed, secondary air temperature and the like.
And S204, extracting time period characteristics of each process parameter at different time, wherein all the time period characteristics are to-be-selected characteristics to be input into the prediction model to train the prediction model.
In the embodiment of the application, different processes are in different time periods in the whole process, and the influence time of the different processes on clinker free calcium oxide is different, so in order to find the characteristics of the time period with the largest influence on the free calcium oxide, the time period characteristics of each process parameter in different time periods need to be extracted, all the time period characteristics are the candidate characteristics to be input into the prediction model to train the prediction model, and the found characteristics of the time period with the largest influence on the free calcium oxide are the process of finding the target characteristics from the candidate characteristics.
Optionally, the step S204 of extracting the time period characteristics of each process parameter at different times includes the following steps:
step 11, constructing a time sliding window;
step 12, sliding a time sliding window in the process parameters according to a preset step length, wherein the length of the preset step length is a time length;
step 13, determining at least one of the average value, the variance and the standard deviation of the process parameters in the corresponding time period when the time sliding window is slid each time;
and step 14, taking at least one of the average value, the variance and the standard deviation of the process parameters in the corresponding time period as the time period characteristic of the corresponding time period.
In the embodiment of the application, the whole process flow of cement production needs 2 to 3 hours, and for the produced clinker, only a certain period of time of a certain process parameter is related to the batch of clinker, so that a time sliding window can be slid in the process parameter according to a preset step length, and at least one of the average value, the variance and the standard deviation of the process parameter in the corresponding time period is determined when the time sliding window is slid every time, so that the time period characteristic of the process parameter in the time period is found through the time sliding window. The length of the preset step is a time length, such as 2 minutes, 5 minutes, and the like.
In the embodiment of the application, the process parameters are obtained by sampling, the sampling intervals of different process parameters are different, some process parameters may generate new values within several seconds, and the process parameters need to be sampled by using shorter sampling intervals.
Optionally, constructing the time sliding window comprises the steps of:
step 21, determining the window size of a time sliding window, wherein the window size is larger than or equal to the cement production time divided by the total process number;
step 22, determining the sliding time range of the time sliding window, wherein the sliding time range is greater than or equal to the cement production time;
step 23, determining a time sliding window using the window size and the sliding time range.
In the embodiment of the application, the window size of the time sliding window is larger than or equal to the cement production time divided by the total working procedure number, and the sliding time range of the time sliding window is larger than or equal to the cement production time.
Step S206, determining target characteristics from the characteristics to be selected according to the time correlation relationship between the process parameters at different times and the free calcium oxide content, and inputting the target characteristics into a prediction model for training so that the prediction model predicts the free calcium oxide content according to the time correlation relationship between the process parameters and the free calcium oxide content.
In the embodiment of the application, the most relevant characteristics are found out as the training input of the prediction model by analyzing the time correlation between the process parameters in the cement production process and the free calcium oxide content in the cement quality evaluation, so that the prediction accuracy of the prediction model is improved.
Optionally, in step S206, determining the target feature from the candidate features according to the time correlation between the process parameters at different times and the content of the free calcium oxide includes at least one of the following ways:
firstly, determining the feature weights of all the features to be selected of the process parameters by using a random forest model, and screening a target number of features to be selected as target features according to the sequence of the feature weights from large to small.
In the embodiment of the application, the importance of the influence of each time period characteristic in the process parameters on the content of free calcium oxide is calculated by using a random forest model, and the method specifically comprises the following steps:
step 31, taking all the characteristics to be selected of the process parameters as the input of a random forest model, taking the content of free calcium oxide in the cement obtained by actual production as the output of the random forest model, and training the random forest model to obtain the characteristic weight of each characteristic to be selected;
step 32, sequencing all the features to be selected according to the sequence of the feature weights from large to small;
and step 33, eliminating a preset number of to-be-selected features which are ranked backwards, taking the remaining to-be-selected features as new input of the random forest model, and recursively obtaining a target number of to-be-selected features as target features.
For example, assume that the process parameter a has a total of 50 time segment characteristics. Firstly, 50 time period characteristics X1, X2 and X3 … … X50 are used as input of a random forest model, the content of free calcium oxide in cement obtained by actual production is used as output of the random forest model, and the random forest model is trained to obtain the characteristic importance of 50 characteristics, namely characteristic weight. The 50 time period features are arranged according to the sequence of the feature weights from large to small, and the features with the minimum feature weights (the preset number of time period features which are ranked later) are removed. And then, taking the residual time period characteristics as new input of a random forest model, taking the content of free calcium oxide in the cement obtained by actual production as output of the random forest model, continuing training the random forest model to obtain the characteristic weight of the residual time period characteristics, removing the characteristics with the minimum characteristic weight again, and performing recursion in the way until the residual characteristic number meets the requirement, namely, only the target number of time period characteristics are left, wherein the target number can be set according to the actual situation.
In the embodiment of the application, because the calculation of each feature and parameter in the model training process is completely independent unlike the linear correlation coefficient and the nonlinear correlation coefficient, and each feature in one-time model training may affect each other, the features with weak importance (feature weight), similarity and negative influence on the model training are removed for many times through recursive training, so that the most desirable features are screened out step by step.
In the embodiment of the application, the random forest model can be replaced by other tree models.
Secondly, determining linear correlation coefficients of various candidate characteristics of the process parameters and the content of free calcium oxide in the cement obtained by actual production, and screening a target number of candidate characteristics as target characteristics according to the sequence of the linear correlation coefficients from large to small, wherein the time correlation relationship comprises a relationship expressed by the linear correlation coefficients.
In the embodiment of the present application, X represents the candidate features of the process parameter (i.e., the time period features at different times), and Y represents the content of free calcium oxide in the cement obtained through actual production, so that the linear Correlation Coefficient between each candidate feature of the process parameter and the content of free calcium oxide in the cement obtained through actual production can be obtained by calculating a Pearson Correlation Coefficient (Pearson Correlation Coefficient). Calculating the Pearson correlation coefficient rhoX,YThe formula of (1) is:
where cov denotes the covariance of X and Y, σ denotes the standard deviation, μ denotes the mean, and E denotes the expectation.
In the embodiment of the application, the linear correlation coefficient may be obtained by calculating a spearman correlation coefficient, a kender rank correlation coefficient, and the like.
Thirdly, determining nonlinear correlation coefficients of various candidate characteristics of the process parameters and the content of free calcium oxide in the cement obtained by actual production, and screening a target number of candidate characteristics as target characteristics according to the descending order of the nonlinear correlation coefficients, wherein the time correlation relationship comprises a relationship expressed by the nonlinear correlation coefficients.
In the embodiment of the present application, the nonlinear correlation Coefficient between each candidate feature of the process parameters and the content of free calcium oxide in the cement obtained by actual production can be obtained by calculating the maximum Mutual Information Coefficient (MIC). Mutual information is used to evaluate the amount of information that the occurrence of one event contributes to the occurrence of another event, and the calculation formula is as follows:
the maximum mutual information coefficient is:
wherein p (X, Y) is the joint probability between the characteristic X to be selected and the free calcium oxide content Y in the cement obtained by actual production.
In the embodiment of the application, the partial target characteristics with larger time correlation can be found by adopting the three modes. In order to further mine the time correlation, the determining the target feature from the candidate features may further include the following steps:
step 41, extracting the features to be selected, which are screened out according to the sequence of the feature weights from big to small;
step 42, determining a comprehensive correlation coefficient of the to-be-selected feature by using the extracted feature weight, linear correlation coefficient and nonlinear correlation coefficient of the to-be-selected feature;
and 43, screening the candidate features corresponding to the maximum comprehensive correlation coefficient as target features according to the sequence of the maximum comprehensive correlation coefficient from large to small.
In the embodiment of the application, the time correlation analysis can be further performed on the to-be-selected features with larger feature weights screened by using the random forest model, namely, the comprehensive correlation coefficient of each to-be-selected feature is calculated by using the feature weights, the linear correlation coefficients and the nonlinear correlation coefficients of the part of to-be-selected features. The comprehensive correlation coefficient can more comprehensively and truly reflect the time correlation between each feature to be selected and the content of free calcium oxide in the cement obtained by actual production, and finally, the most relevant target feature is found according to the arrangement sequence of the comprehensive correlation coefficient and is input into a prediction model for training as the final feature of the process parameter.
In the embodiment of the application, each process parameter is selected to correspond to the most relevant target characteristic and input to the prediction model for training, and the prediction model is trained by combining raw material data, fineness data and the like, so that the prediction model can more accurately predict the content of free calcium oxide in clinker.
Optionally, determining the comprehensive correlation coefficient of the feature to be selected by using the extracted feature weight, the linear correlation coefficient and the nonlinear correlation coefficient of the feature to be selected includes:
acquiring the characteristic weight of each process parameter, the linear correlation coefficient and the calculation proportion of the nonlinear correlation coefficient in the comprehensive correlation coefficient;
and taking the sum of the product of the feature weight and the corresponding calculation proportion, the product of the linear correlation coefficient and the corresponding calculation proportion and the product of the nonlinear correlation coefficient and the corresponding calculation proportion as the comprehensive correlation coefficient of the feature to be selected.
In the embodiment of the present application, when calculating the comprehensive correlation coefficient, the feature weight, the linear correlation coefficient and the nonlinear correlation coefficient correspondingly have respective calculation proportions, and if the linear correlation coefficient cor islinearIs calculated in a proportion of a, a nonlinear correlation coefficient cornonlinearThe calculation proportion of b, the calculation proportion of the feature weight import is (1-a-b), and then the comprehensive correlation coefficient of the candidate features is:
score＝a*abs(corlinear)+b*cornonlinear+(1-a-b)*importance
according to still another aspect of an embodiment of the present application, as shown in fig. 3, there is provided a model building apparatus including:
a process parameter obtaining module 301, configured to obtain a plurality of process parameters used in a cement production process;
the time period feature extraction module 303 is configured to extract time period features of each process parameter at different times, where all the time period features are to-be-selected features to be input into the prediction model to train the prediction model;
the feature screening and training module 305 is configured to determine a target feature from the features to be selected according to a time correlation between the process parameters at different times and the free calcium oxide content, and input the target feature into a prediction model for training, so that the prediction model predicts the free calcium oxide content according to the time correlation between the process parameters and the free calcium oxide content.
It should be noted that the process parameter obtaining module 301 in this embodiment may be configured to execute step S202 in this embodiment, the time period feature extracting module 303 in this embodiment may be configured to execute step S204 in this embodiment, and the feature screening and training module 305 in this embodiment may be configured to execute step S206 in this embodiment.
It should be noted here that the modules described above are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of the above embodiments. It should be noted that the modules described above as a part of the apparatus may operate in a hardware environment as shown in fig. 1, and may be implemented by software or hardware.
Optionally, the time period feature extraction module is specifically configured to:
constructing a time sliding window;
sliding a time sliding window in the process parameters according to a preset step length, wherein the length of the preset step length is the time length;
determining at least one of the average value, the variance and the standard deviation of the process parameters in the corresponding time period when the time sliding window is slid each time;
and taking at least one of the average value, the variance and the standard deviation of the process parameters in the corresponding time period as the time period characteristic of the corresponding time period.
Optionally, the time period feature extraction module is further configured to:
determining the window size of a time sliding window, wherein the window size is larger than or equal to the cement production time divided by the total process number;
determining the sliding time range of the time sliding window, wherein the sliding time range is greater than or equal to the cement production time;
a time sliding window is determined using the window size and the sliding time range.
Optionally, the feature screening and training module is specifically configured to:
determining the feature weights of all to-be-selected features of the process parameters by using a random forest model, and screening out a target number of to-be-selected features as target features according to the sequence of the feature weights from large to small;
determining linear correlation coefficients of various candidate characteristics of the process parameters and the content of free calcium oxide in the cement obtained by actual production, and screening a target number of candidate characteristics as target characteristics according to the sequence of the linear correlation coefficients from large to small, wherein the time correlation relationship comprises a relationship expressed by the linear correlation coefficients;
determining nonlinear correlation coefficients of various candidate characteristics of the process parameters and the content of free calcium oxide in the cement obtained by actual production, and screening a target number of candidate characteristics as target characteristics according to the sequence of the nonlinear correlation coefficients from large to small, wherein the time correlation relationship comprises a relationship expressed by the nonlinear correlation coefficients.
Optionally, the feature screening and training module is further configured to:
extracting the features to be selected which are screened out according to the sequence of the feature weights from big to small;
determining a comprehensive correlation coefficient of the to-be-selected feature by using the extracted feature weight, the linear correlation coefficient and the nonlinear correlation coefficient of the to-be-selected feature;
and screening the candidate features corresponding to the maximum comprehensive correlation coefficient as target features according to the sequence of the maximum comprehensive correlation coefficient from large to small.
Optionally, the feature screening and training module is further configured to:
acquiring the characteristic weight of each process parameter, the linear correlation coefficient and the calculation proportion of the nonlinear correlation coefficient in the comprehensive correlation coefficient;
and taking the sum of the product of the feature weight and the corresponding calculation proportion, the product of the linear correlation coefficient and the corresponding calculation proportion and the product of the nonlinear correlation coefficient and the corresponding calculation proportion as the comprehensive correlation coefficient of the feature to be selected.
Optionally, the feature screening and training module is further configured to:
all the characteristics to be selected of the process parameters are used as the input of a random forest model, the content of free calcium oxide in the cement obtained by actual production is used as the output of the random forest model, and the random forest model is trained to obtain the characteristic weight of each characteristic to be selected;
sequencing all the features to be selected according to the sequence of the feature weights from large to small;
and eliminating a preset number of to-be-selected features which are ranked backwards, taking the remaining to-be-selected features as new input of the random forest model, and recursively obtaining a target number of to-be-selected features as target features.
According to another aspect of the embodiments of the present application, there is provided an electronic device, as shown in fig. 4, including a memory 401, a processor 403, a communication interface 405, and a communication bus 407, where the memory 401 stores a computer program that is executable on the processor 403, the memory 401 and the processor 403 communicate with each other through the communication interface 405 and the communication bus 407, and the processor 403 implements the steps of the method when executing the computer program.
The memory and the processor in the electronic equipment are communicated with the communication interface through a communication bus. The communication bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
There is also provided, in accordance with yet another aspect of an embodiment of the present application, a computer-readable medium having non-volatile program code executable by a processor.
Optionally, in an embodiment of the present application, a computer readable medium is configured to store program code for the processor to perform the following steps:
acquiring a plurality of process parameters used in the cement production process;
extracting time period characteristics of each process parameter at different time, wherein all the time period characteristics are to-be-selected characteristics to be input into the prediction model to train the prediction model;
determining target characteristics from the characteristics to be selected according to the time correlation relationship between the process parameters at different times and the free calcium oxide content, and inputting the target characteristics into a prediction model for training so that the prediction model predicts the free calcium oxide content according to the time correlation relationship between the process parameters and the free calcium oxide content.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment is not described herein again.
When the embodiments of the present application are specifically implemented, reference may be made to the above embodiments, and corresponding technical effects are achieved.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the Processing units may be implemented within one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units configured to perform the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented by means of units performing the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present application, 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 modules is merely a logical division, and in actual implementation, there may be other divisions, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not implemented. 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 displayed as units may or may not be physical units, may be located in one place, 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 application 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 functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially implemented or make a contribution to the prior art, or may be implemented in the form of a software product stored in a storage medium and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk. It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is merely exemplary of the present application and is presented to enable those skilled in the art to understand and practice the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method of model construction, comprising:
acquiring a plurality of process parameters used in the cement production process;
extracting time period characteristics of each process parameter at different time, wherein all the time period characteristics are to-be-selected characteristics to be input into a prediction model to train the prediction model;
and determining target characteristics from the characteristics to be selected according to the time correlation relationship between the process parameters and the free calcium oxide content at different times, and inputting the target characteristics into the prediction model for training so that the prediction model predicts the free calcium oxide content according to the time correlation relationship between the process parameters and the free calcium oxide content.
2. The method of claim 1, wherein extracting time period characteristics of each of the process parameters at different times comprises:
constructing a time sliding window;
sliding the time sliding window in the process parameters according to a preset step length, wherein the length of the preset step length is a time length;
determining at least one of the mean, variance and standard deviation of the process parameters in the corresponding time period each time the time sliding window is slid;
and taking at least one of the average value, the variance and the standard deviation of the process parameters in the corresponding time period as the time period characteristic of the corresponding time period.
3. The method of claim 2, wherein constructing a time sliding window comprises:
determining a window size of the time sliding window, wherein the window size is greater than or equal to cement production time divided by the total number of processes;
determining a sliding time range of the time sliding window, wherein the sliding time range is greater than or equal to the cement production time;
determining the time sliding window using the window size and the sliding time range.
4. The method of any one of claims 1 to 3, wherein determining the target feature from the candidate features based on the time-dependent relationship of the process parameter and free calcium oxide content at different times comprises at least one of:
determining feature weights of all the features to be selected of the process parameters by using a random forest model, and screening a target number of the features to be selected as the target features according to the sequence of the feature weights from large to small;
determining linear correlation coefficients of the various candidate characteristics of the process parameters and the content of free calcium oxide in the cement obtained by actual production, and screening a target number of the candidate characteristics as the target characteristics according to the sequence of the linear correlation coefficients from large to small, wherein the time correlation relationship comprises a relationship expressed by the linear correlation coefficients;
and determining nonlinear correlation coefficients of the various candidate characteristics of the process parameters and the content of the free calcium oxide in the cement obtained by actual production, and screening a target number of the candidate characteristics as the target characteristics according to the descending order of the nonlinear correlation coefficients, wherein the time correlation relationship comprises a relationship expressed by the nonlinear correlation coefficients.
5. The method of claim 4, wherein determining a target feature from the candidate features further comprises:
extracting the features to be selected which are screened out according to the sequence of the feature weights from big to small;
determining a comprehensive correlation coefficient of the feature to be selected by using the extracted feature weight, the linear correlation coefficient and the nonlinear correlation coefficient of the feature to be selected;
and screening the candidate features corresponding to the maximum comprehensive correlation coefficient as the target features according to the descending order of the comprehensive correlation coefficients.
6. The method of claim 5, wherein determining a comprehensive correlation coefficient of the candidate feature by using the extracted feature weight, the linear correlation coefficient and the nonlinear correlation coefficient of the candidate feature comprises:
acquiring the calculation proportion of the characteristic weight, the linear correlation coefficient and the nonlinear correlation coefficient of each process parameter in the comprehensive correlation coefficient;
and taking the sum of the product of the feature weight and the corresponding calculation proportion, the product of the linear correlation coefficient and the corresponding calculation proportion and the product of the nonlinear correlation coefficient and the corresponding calculation proportion as the comprehensive correlation coefficient of the feature to be selected.
7. The method as claimed in claim 4, wherein determining feature weights of all the candidate features of the process parameters by using a random forest model, and screening a target number of the candidate features as the target features according to a descending order of the feature weights comprises:
all the features to be selected of the process parameters are used as input of a random forest model, the content of free calcium oxide in the cement obtained in actual production is used as output of the random forest model, and the random forest model is trained to obtain the feature weight of each feature to be selected;
sequencing all the features to be selected according to the sequence of the feature weights from large to small;
and eliminating a preset number of the to-be-selected features which are ranked backwards, taking the remaining to-be-selected features as new input of a random forest model, and recursively obtaining a target number of the to-be-selected features as the target features.
8. A model building apparatus, comprising:
the process parameter acquisition module is used for acquiring a plurality of process parameters used in the cement production process;
the time period characteristic extraction module is used for extracting time period characteristics of each process parameter at different time, wherein all the time period characteristics are to-be-selected characteristics to be input into a prediction model to train the prediction model;
and the characteristic screening and training module is used for determining target characteristics from the characteristics to be selected according to the time correlation relationship between the process parameters and the free calcium oxide content at different times, and inputting the target characteristics into the prediction model for training so that the prediction model predicts the free calcium oxide content according to the time correlation relationship between the process parameters and the free calcium oxide content.
9. An electronic device comprising a memory, a processor, a communication interface and a communication bus, wherein the memory stores a computer program operable on the processor, and the memory and the processor communicate via the communication bus and the communication interface, wherein the processor implements the steps of the method according to any of the claims 1 to 7 when executing the computer program.
10. A computer-readable medium having non-volatile program code executable by a processor, wherein the program code causes the processor to perform the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110020202.2A CN112712861A (en) | 2021-01-07 | 2021-01-07 | Model construction method, device, equipment and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110020202.2A CN112712861A (en) | 2021-01-07 | 2021-01-07 | Model construction method, device, equipment and computer readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112712861A true CN112712861A (en) | 2021-04-27 |
Family
ID=75548521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110020202.2A Withdrawn CN112712861A (en) | 2021-01-07 | 2021-01-07 | Model construction method, device, equipment and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112712861A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113033923A (en) * | 2021-04-30 | 2021-06-25 | 中国建筑材料科学研究总院有限公司 | Method, device and system for predicting, evaluating and optimizing performance of cement clinker |
| CN114236104A (en) * | 2021-10-28 | 2022-03-25 | 阿里云计算有限公司 | Method, device, equipment, medium and product for measuring free calcium oxide |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160350672A1 (en) * | 2015-05-26 | 2016-12-01 | Textio, Inc. | Using Machine Learning to Predict Outcomes for Documents |
| JP2017066026A (en) * | 2015-09-29 | 2017-04-06 | 太平洋セメント株式会社 | Method for predicting quality or manufacturing condition of cement |
| WO2018076403A1 (en) * | 2016-10-25 | 2018-05-03 | 浙江邦业科技股份有限公司 | One-dimensional simulation method for predicting quality of clinker in rotary cement kiln |
| CN109165798A (en) * | 2018-10-19 | 2019-01-08 | 燕山大学 | A kind of Free Calcium Oxide Contents in Cement Clinker on-line prediction method and system |
| CN109342703A (en) * | 2018-12-06 | 2019-02-15 | 燕山大学 | A kind of clinker free calcium levels measurement method and system |
| CN109446236A (en) * | 2018-10-18 | 2019-03-08 | 太原理工大学 | Cement-particle size distribution forecasting method based on random distribution |
| CN110763830A (en) * | 2019-12-04 | 2020-02-07 | 济南大学 | Method for predicting content of free calcium oxide in cement clinker |
| CN111160472A (en) * | 2019-12-30 | 2020-05-15 | 深圳集智数字科技有限公司 | Method and device for predicting target characteristic of object, storage medium and electronic equipment |
| AU2020101854A4 (en) * | 2020-08-17 | 2020-09-24 | China Communications Construction Co., Ltd. | A method for predicting concrete durability based on data mining and artificial intelligence algorithm |
| CN111832101A (en) * | 2020-06-18 | 2020-10-27 | 湖北博华自动化***工程有限公司 | Construction method of cement strength prediction model and cement strength prediction method |
| WO2020244202A1 (en) * | 2019-06-05 | 2020-12-10 | 北京极智嘉科技有限公司 | Order processing method, apparatus and device, and storage medium |
| CN112069567A (en) * | 2020-08-07 | 2020-12-11 | 湖北交投十巫高速公路有限公司 | Method for predicting compressive strength of concrete based on random forest and intelligent algorithm |
-
2021
- 2021-01-07 CN CN202110020202.2A patent/CN112712861A/en not_active Withdrawn
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160350672A1 (en) * | 2015-05-26 | 2016-12-01 | Textio, Inc. | Using Machine Learning to Predict Outcomes for Documents |
| JP2017066026A (en) * | 2015-09-29 | 2017-04-06 | 太平洋セメント株式会社 | Method for predicting quality or manufacturing condition of cement |
| WO2018076403A1 (en) * | 2016-10-25 | 2018-05-03 | 浙江邦业科技股份有限公司 | One-dimensional simulation method for predicting quality of clinker in rotary cement kiln |
| CN109446236A (en) * | 2018-10-18 | 2019-03-08 | 太原理工大学 | Cement-particle size distribution forecasting method based on random distribution |
| CN109165798A (en) * | 2018-10-19 | 2019-01-08 | 燕山大学 | A kind of Free Calcium Oxide Contents in Cement Clinker on-line prediction method and system |
| CN109342703A (en) * | 2018-12-06 | 2019-02-15 | 燕山大学 | A kind of clinker free calcium levels measurement method and system |
| WO2020244202A1 (en) * | 2019-06-05 | 2020-12-10 | 北京极智嘉科技有限公司 | Order processing method, apparatus and device, and storage medium |
| CN110763830A (en) * | 2019-12-04 | 2020-02-07 | 济南大学 | Method for predicting content of free calcium oxide in cement clinker |
| CN111160472A (en) * | 2019-12-30 | 2020-05-15 | 深圳集智数字科技有限公司 | Method and device for predicting target characteristic of object, storage medium and electronic equipment |
| CN111832101A (en) * | 2020-06-18 | 2020-10-27 | 湖北博华自动化***工程有限公司 | Construction method of cement strength prediction model and cement strength prediction method |
| CN112069567A (en) * | 2020-08-07 | 2020-12-11 | 湖北交投十巫高速公路有限公司 | Method for predicting compressive strength of concrete based on random forest and intelligent algorithm |
| AU2020101854A4 (en) * | 2020-08-17 | 2020-09-24 | China Communications Construction Co., Ltd. | A method for predicting concrete durability based on data mining and artificial intelligence algorithm |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113033923A (en) * | 2021-04-30 | 2021-06-25 | 中国建筑材料科学研究总院有限公司 | Method, device and system for predicting, evaluating and optimizing performance of cement clinker |
| CN113033923B (en) * | 2021-04-30 | 2024-05-14 | 中国建筑材料科学研究总院有限公司 | Method for predicting, evaluating and optimizing cement clinker performance, device and system thereof |
| CN114236104A (en) * | 2021-10-28 | 2022-03-25 | 阿里云计算有限公司 | Method, device, equipment, medium and product for measuring free calcium oxide |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gill et al. | Genotyping and interpretation of STR-DNA: low-template, mixtures and database matches—twenty years of research and development | |
| Stegehuis et al. | Predicting the long-term citation impact of recent publications | |
| CN112712861A (en) | Model construction method, device, equipment and computer readable medium | |
| Mapes et al. | Knowledge on DNA success rates to optimize the DNA analysis process: from crime scene to laboratory | |
| CN112506990A (en) | Hydrological data anomaly detection method based on spatiotemporal information | |
| JP2015032030A (en) | Document classification system, document classification method and document classification program | |
| Su et al. | Utility of characters evolving at diverse rates of evolution to resolve quartet trees with unequal branch lengths: analytical predictions of long-branch effects | |
| CN112785067A (en) | Data prediction method and device, equipment and storage medium | |
| CN111064719B (en) | Method and device for detecting abnormal downloading behavior of file | |
| Smolak et al. | The impact of human mobility data scales and processing on movement predictability | |
| CN114662772A (en) | Traffic noise early warning method, model training method, device, equipment and medium | |
| CN111241497A (en) | Open source code tracing detection method based on software multiplexing feature learning | |
| Tuoto | New proposal for linkage error estimation | |
| Porter et al. | METAWORKS: A flexible, scalable bioinformatic pipeline for multi-marker biodiversity assessments | |
| CN110910270B (en) | Treatment method, device and system for phosphoric acid production process | |
| CN109002983B (en) | Method and computer system for evaluating enterprise investment potential | |
| Lai | Fitting power law distributions to data | |
| Zhu et al. | A generalized dSpliceType framework to detect differential splicing and differential expression events using RNA-Seq | |
| de Oliveira et al. | Viability of the use of minimum water quality indices: a comparison of methods | |
| Che et al. | An efficient intrusion detection approach based on hidden markov model and rough set | |
| Turnbull et al. | OrthoFlow: phylogenomic analysis and diagnostics with one command | |
| CN116304825A (en) | Method, device, terminal and storage medium for predicting hardenability of steel tail end | |
| CN104636577A (en) | Statistical analysis system applying linear regression method | |
| Kumbier et al. | Signed iterative random forests to identify enhancer-associated transcription factor binding | |
| CN113612639B (en) | Method and device for analyzing and predicting file downloading behavior based on website access record |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210427 |