WO2021004198A1 - 一种板材性能的预测方法及装置 - Google Patents
一种板材性能的预测方法及装置 Download PDFInfo
- Publication number
- WO2021004198A1 WO2021004198A1 PCT/CN2020/093942 CN2020093942W WO2021004198A1 WO 2021004198 A1 WO2021004198 A1 WO 2021004198A1 CN 2020093942 W CN2020093942 W CN 2020093942W WO 2021004198 A1 WO2021004198 A1 WO 2021004198A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- model
- type
- performance
- prediction
- data
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/24—Sheet material
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Definitions
- This application relates to the technical field of sheet material quality, and in particular to a method and device for predicting sheet properties.
- the physical metallurgy model is composed of sub-models such as temperature field, recrystallization, flow stress, precipitation and phase change, and can perform qualitative analysis on the chemical composition, process parameters, microstructure and mechanical properties of steel sheets.
- the accuracy rate continues to decrease, which makes it more and more difficult to control the quality of steel sheets.
- the present application provides a method and device for predicting sheet performance, which can be used to solve the technical problem that the use of physical metallurgy models to predict the performance data of steel sheets in the prior art leads to low accuracy.
- an embodiment of the present application provides a method for predicting the performance of a board, and the method includes:
- a plurality of candidate prediction models are determined according to the type of the performance index and the correspondence between the type of the performance index stored in advance and the prediction model;
- the prediction model and the weight values of the preset candidate prediction models are determined to determine the combined model;
- the production data of the board to be predicted is input into the combined model to obtain the predicted performance data of the board to be predicted on the performance index.
- the candidate prediction model includes an output layer, and the combined model includes an input layer;
- determining the combined model includes:
- the output layers of the multiple candidate prediction models are respectively multiplied by the preset weight values of the candidate prediction models, they are used as the input layer of the combined model to determine the combined model.
- inputting the production data of the plate to be predicted into the combined model to obtain the predicted performance data of the plate to be predicted on the performance index includes:
- the input data is input into the input layer of the combined model to obtain the predicted performance data of the board to be predicted on the performance index.
- the corresponding relationship between the type of the performance indicator and the prediction model is determined in the following manner:
- the training data set including training production data of a plurality of plates to be trained and actual performance data corresponding to multiple types of performance indicators in the plates to be trained;
- the first type of performance indicators input the training production data into multiple initial prediction models to obtain prediction results corresponding to the initial prediction models; the first type of performance indicators are multiple types of performance Any one of the indicators;
- reverse training is performed to generate a plurality of prediction models of the first type; the first type of prediction The model is used to predict the performance data corresponding to the first type of performance index;
- any prediction model of the first type input the training production data into the prediction model of the first type to obtain a prediction result corresponding to the prediction model of the first type;
- the prediction model includes a polynomial regression model, a ridge regression model, a Kernel Ridge Regression (KRR) model, a Support Vector Machine (SVM) model, and a neighboring algorithm (K-Nearest Neighbor, KNN) Model, Random Forest Model, Gradient Boost Regression Tree (GBRT) model, Extreme Gradient Boosting (XGboost) model, Distributed Gradient Boosting Machine (LightGBM) model and iterative algorithm ( Adaboost) any one of the model.
- KRR Kernel Ridge Regression
- SVM Support Vector Machine
- the step of inputting the training production data into a plurality of initial prediction models for the first type of performance indicators includes:
- an embodiment of the present application provides a method for predicting the performance of a board, the method including:
- an embodiment of the present application provides a device for predicting the performance of a board, and the device includes:
- An obtaining unit for obtaining production data of the plate to be predicted the production data including at least one of the chemical composition, process parameters, and laboratory data of the plate to be predicted;
- the processing unit is configured to determine a plurality of candidate prediction models according to the type of the performance index and the correspondence between the type of the performance index stored in advance and the prediction model for any type of performance index of the board to be predicted;
- the multiple candidate prediction models and the weight values of the preset candidate prediction models are determined to determine the combined model;
- the production data of the board to be predicted is input into the combined model to obtain the performance index of the board to be predicted Predictive performance data.
- the candidate prediction model includes an output layer, and the combined model includes an input layer;
- the processing unit is specifically used for:
- the output layers of the multiple candidate prediction models are respectively multiplied by the preset weight values of the candidate prediction models, they are used as the input layer of the combined model to determine the combined model.
- processing unit is specifically configured to:
- the corresponding relationship between the type of the performance indicator and the prediction model is determined in the following manner:
- the training data set including training production data of a plurality of plates to be trained and actual performance data corresponding to multiple types of performance indicators in the plates to be trained;
- the first type of performance indicators input the training production data into multiple initial prediction models to obtain prediction results corresponding to the initial prediction models; the first type of performance indicators are multiple types of performance Any one of the indicators;
- reverse training is performed to generate a plurality of prediction models of the first type; the first type of prediction The model is used to predict the performance data corresponding to the first type of performance index;
- any prediction model of the first type input the training production data into the prediction model of the first type to obtain a prediction result corresponding to the prediction model of the first type;
- the prediction model includes polynomial regression model, ridge regression model, kernel ridge regression KRR model, support vector machine SVM model, proximity algorithm KNN model, random forest model, progressive gradient regression tree GBRT model, extreme gradient boost XGboost Any one of the model, the distributed gradient boosting framework LightGBM model and the iterative algorithm Adaboost model.
- the step of inputting the training production data into a plurality of initial prediction models for the first type of performance indicators includes:
- the preprocessing unit performs preprocessing on the training data set.
- the embodiments of the present application can predict the performance of the plate based on the chemical composition, process parameters and laboratory data.
- the combination model is used in the embodiments of the present application to predict the performance data of the plate, because the combination model It is determined by combining multiple candidate prediction models. Therefore, the method comprehensively considers multiple prediction models, which can further improve the prediction accuracy of sheet performance.
- FIG. 1 is a schematic diagram of a process corresponding to a method for predicting sheet performance provided by an embodiment of the application;
- FIG. 2 is a schematic flowchart of a method for determining the correspondence between the type of performance indicator and the prediction model provided by an embodiment of the application;
- FIG. 3 is a schematic structural diagram of a prediction device for sheet performance provided by an embodiment of the application.
- FIG. 5 is a schematic diagram of the calculation result of the error rate of the SVM model provided by an embodiment of the application.
- FIG. 6 is a schematic diagram of a calculation result of a random forest model error rate provided by an embodiment of the application.
- FIG. 7 is a schematic diagram of a calculation result of a LightGBM model error rate provided by an embodiment of the application.
- FIG. 8 is a schematic diagram of the calculation result of the error rate of the XGboost model provided by an embodiment of the application.
- FIG. 9 is a schematic diagram of the error rate calculation result of the Adaboost model provided by an embodiment of the application.
- the board performance prediction method of the present application uses a combination model algorithm to predict the performance indicators of the board according to the given board production data.
- the precision method of root mean square error is used for comparative analysis.
- Fig. 1 exemplarily shows a schematic diagram of a process corresponding to a method for predicting sheet performance provided by an embodiment of the present application. As shown in Figure 1, it specifically includes the following steps:
- Step 101 Obtain the production data of the plate to be predicted.
- Step 102 For any type of performance index of the plate to be predicted, a plurality of candidate prediction models are determined according to the type of the performance index and the correspondence between the type of the performance index stored in advance and the prediction model.
- Step 103 Determine a combined model according to the multiple candidate prediction models and preset weight values of the candidate prediction models.
- Step 104 Input the production data of the plate to be predicted into the combined model to obtain predicted performance data of the plate to be predicted on the performance index.
- the embodiments of the present application can predict the performance of the plate based on the chemical composition, process parameters and laboratory data.
- the combination model is used in the embodiments of the present application to predict the performance data of the plate, because the combination model It is determined by combining multiple candidate prediction models. Therefore, the method comprehensively considers multiple prediction models, which can further improve the prediction accuracy of sheet performance.
- the combined model in this application is determined by combining multiple candidate prediction models.
- a single machine learning algorithm is selected (the most basic method of machine learning is to use algorithms to parse data, learn from it, and then make changes to events in the real world. Decision-making and prediction. Unlike traditional software programs that are hard-coded to solve specific tasks, machine learning uses a large amount of data to "train” and learns how to complete tasks from the data through various algorithms.), including polynomial regression models, Ridge regression model, KRR model, SVM model, KNN model, random forest model, GBRT model, XGboost model, LightGBM model and Adaboost model are trained on the training set, and a single model is obtained through continuous tuning and optimization. The best parameters on the set.
- the production data may include at least one of the chemical composition, process parameters, and laboratory data of the plate to be predicted.
- the chemical composition may include chemical elements such as carbon, silicon, manganese, chromium, nickel, and copper.
- the process parameters can refer to the processing process parameters of the steel plate, and can include parameters such as plate thickness, plate width, rolling pressure parameters, and quenching temperature.
- Laboratory data can refer to the content percentage of each chemical component.
- the prediction model may include any one of polynomial regression model, ridge regression model, KRR model, SVM model, KNN model, random forest model, GBRT model, XGboost model, LightGBM model, and Adaboost model.
- the corresponding relationship between the type of performance indicator and the prediction model can be determined in multiple ways.
- a possible implementation is, as shown in FIG. 2, the corresponding relationship between the type of performance indicator and the prediction model provided in this embodiment of the application.
- the schematic diagram of the process corresponding to the method of determining includes the following steps:
- Step 201 Obtain a training data set.
- the training data set may include training production data of multiple plates to be trained and actual performance data corresponding to multiple types of performance indicators in the plates to be trained.
- the training production data may refer to the production data used to train the model, and the specific data included in the training production data may be consistent with the specific data included in the production data described above.
- the way to obtain the training data set can be through ERP, MES and other office systems to obtain production data such as chemical composition, process parameters, and laboratory data, and then perform data integration on these data.
- production data such as chemical composition, process parameters, and laboratory data
- the stored production data may be in the form of a data table.
- Step 202 Regarding the first type of performance indicators, input training production data into multiple initial prediction models, respectively, to obtain prediction results corresponding to the initial prediction models.
- the first type of performance indicator is any one of multiple types of performance indicators.
- the first type of performance index can be any one of yield strength, tensile strength, elongation and impact energy.
- data preprocessing may be performed on the training data set.
- data cleaning can be performed on the stored production data, including processing of null values and abnormal values, vectorization of category variables, data deduplication, and data de-drying.
- the preprocessing of the training data set in this application can not only provide data of specifications for the input of multiple initial prediction models, but also avoid the interference of erroneous data and abnormal values through the preprocessed data, thereby improving the efficiency of data processing .
- the data preprocessing in this application has specific application scenarios.
- the preprocessing step is performed after the training data set is obtained.
- Our training data set is the training production data of multiple plates to be trained and the plates to be trained. Multiple types of performance indicators correspond to actual performance data. Therefore, the pre-processing process arrangement has a specific role in a specific link. The specific description is as follows:
- ETL is the process of data extraction (Extract), transformation (Transform), and loading (Load).
- Catalog is used for data. Operations such as transfer in and out, but based on these two commonly used methods, basically only complete operations such as the removal of null values and outliers of the data, which can meet the needs of daily work applications.
- the training data set is preprocessed.
- the preprocessing includes many aspects. For example, one includes the processing of incomplete data, for example, the processing of missing certain attribute values of interest; One includes the processing of inconsistent data, such as the difference processing for codes or names; also includes the processing of errors or data with outliers, etc.
- the data set often comes from multiple heterogeneous data sources, so it is solved by preprocessing The problem in the specific scenario above.
- data preprocessing includes data cleaning, data integration, data specification, and data transformation.
- the pre-processed data can not only meet the requirement of "input multiple initial prediction models", but also has the following effects: the training data set is preprocessed to greatly avoid the interference of junk data, and can affect the data set.
- Step 203 Perform reverse training according to the prediction result corresponding to the initial prediction model and the actual performance data corresponding to the performance index of the first type to generate multiple prediction models of the first type.
- the prediction model of the first type may be used to predict the performance data corresponding to the performance index of the first type.
- Step 204 For any prediction model of the first type, input the training production data into the prediction model of the first type to obtain a prediction result corresponding to the prediction model of the first type.
- Step 205 Determine the error rate of the first type of prediction model according to the prediction result corresponding to the first type of prediction model and the actual performance data corresponding to the first type of performance index.
- the error rate of the first type of prediction model can be calculated by using the root mean square error, and the specific calculation method can refer to formula (1).
- RMSE is the error rate of the first type of prediction model
- N is the number of samples in the training data set to be trained, N is an integer greater than 1
- y i is the true value of the i-th sample in the training data set
- It is the prediction result of the first type of prediction model on the i-th sample in the training data set.
- the formula (1) is the error rate of the first type of prediction model.
- the example of this application is the root mean square error, and the root mean square error represents the magnitude of the error between the predicted value of the model and the true value. The smaller the root mean square error, the closer the model prediction value is to the true value.
- the performance prediction of yield strength as an example, machine learning algorithms are used to train and test on the training data set of the plate to be trained. The calculation results of some prediction models are listed here, and the results are only examples. See Figure 4-9. Specifically:
- FIG. 4 is a schematic diagram of the calculation result of the ridge regression model error rate provided by an embodiment of the application, and it can be seen that the calculation result of the ridge regression model error rate is 17.202095;
- FIG. 5 is a schematic diagram of the calculation result of the SVM model error rate provided by an embodiment of the application, and it can be seen that the calculation result of the SVM model error rate is 19.115036;
- FIG. 6 is a schematic diagram of the error rate calculation result of the random forest model provided by the embodiment of the application, and it can be seen that the error rate calculation result of the random forest model is 13.790967;
- FIG. 7 is a schematic diagram of the calculation result of the LightGBM model error rate provided by an embodiment of the application, and it can be seen that the calculation result of the LightGBM model error rate is 7.044598;
- FIG. 8 is a schematic diagram of the calculation result of the error rate of the XGboost model provided by an embodiment of the application, and it can be seen that the calculation result of the error rate of the XGboost model is 14.185270;
- FIG. 9 is a schematic diagram of the calculation result of the Adaboost model error rate provided by the embodiment of the application, and it can be seen that the calculation result of the Adaboost model error rate is 17.617467.
- black and gray represent the true value of the training data set of the plate to be trained (the yield strength is taken as an example in this embodiment), and black represents the training data set of the plate to be trained (the yield strength is taken as an example in this embodiment)
- the idea of the combined model is to select the above-mentioned well-performing models for weighted combination.
- the combined model comprehensively considers multiple prediction models, which can further improve the prediction accuracy of sheet performance.
- formula (1) is only one possible calculation method, and those skilled in the art can also select other error calculation methods based on experience and actual conditions, and the specifics are not limited.
- Step 206 Determine a candidate prediction model from a plurality of prediction models of the first type according to the error rate of each prediction model of the first type.
- the error rate can be ranked from small to large, and then the top M prediction models can be used as Candidate prediction model, where M is an integer greater than 1.
- a prediction model with an error rate less than a preset threshold may be used as a candidate prediction model, where the preset threshold may be determined by those skilled in the art based on experience and actual conditions, and is not specifically limited.
- Table 1 it is an example of the error rate of the first type of prediction model.
- the specific content can refer to the content listed in Table 1, which will not be described here.
- Table 1 An example of the error rate of the first type of prediction model
- RMSE Error rate
- the first column of Table 1 is the prediction model of the first type
- the second column of Table 1 is the corresponding error rate corresponding to the specific category of the first type of prediction model, that is, for the different prediction models in the first column Corresponding values of different error rates. Table 1 clearly lists the specific error rate of each model. Based on this, the candidate prediction model is determined from multiple first-type prediction models.
- the candidate prediction models include random forest model, KNN model, GBRT model, XGboost model and LightGBM model.
- Step 207 Establish a correspondence between the first type of performance index and the candidate prediction model.
- the corresponding relationship between the type of performance index and the prediction model may also be determined by a person skilled in the art based on experience or actual conditions, and is not specifically limited.
- Step 101 is mainly for data collection, selecting data that has an impact on model performance, and using these data for model training;
- step 102 is mainly for selecting which models to fuse, and performing operations such as data integration and data preprocessing through the data provided in step 101 Obtain a training data set, and use the obtained data set to train multiple models to evaluate the accuracy of each model.
- the weight value of the candidate prediction model can be determined according to the error rate of the candidate prediction model. For example, the smaller the error rate of the candidate prediction model, the corresponding The higher the weight value.
- the weight value of the candidate prediction model can also be determined by those skilled in the art based on experience and actual conditions. For example, if the importance of the random forest model is higher by those skilled in the art based on experience tasks, it can be random. The forest model sets a higher weight value.
- the candidate prediction model may include an output layer
- the combined model may include an input layer.
- Manner 1 The output layers of multiple candidate prediction models can be respectively multiplied by the preset weight values of the candidate prediction models and used as the input layer of the combined model to determine the combined model.
- Method 2 The candidate prediction model can be used as a sub-model. After the sub-model is multiplied by the preset weight value of the candidate prediction model, the large model obtained can be regarded as a combined model.
- step 104 taking the combination model determination method as the above-mentioned method 1 as an example, the production data of the plate to be predicted can be input into the candidate prediction model to obtain the candidate prediction result; then, the candidate prediction result can be obtained according to the candidate prediction result and the preset candidate prediction The weight value corresponding to the model determines the input data corresponding to the input layer of the combined model; finally, the input data can be input into the input layer of the combined model to obtain the predicted performance data of the sheet to be predicted on the performance index.
- the following are device embodiments of this application, which can be used to implement the method embodiments of this application. For details not disclosed in the device embodiment of this application, please refer to the method embodiment of this application.
- Fig. 3 exemplarily shows a schematic structural diagram of a device for predicting sheet performance provided by an embodiment of the application.
- the device has the function of realizing the above prediction method of sheet performance, and the function can be realized by hardware, or by hardware executing corresponding software.
- the device may include: an acquiring unit 301 and a processing unit 302.
- the obtaining unit 301 is configured to obtain production data of the plate to be predicted, the production data including at least one of the chemical composition, process parameters, and laboratory data of the plate to be predicted;
- the processing unit 302 is configured to determine multiple candidate prediction models according to the type of the performance index and the corresponding relationship between the type of the performance index and the prediction model stored in advance for any type of performance index of the plate to be predicted; Determine the combined model according to the multiple candidate prediction models and the weight values of the preset candidate prediction models; input the production data of the to-be-predicted board into the combined model to obtain the performance index of the to-be-predicted board Predictive performance data on
- the candidate prediction model includes an output layer, and the combined model includes an input layer;
- the processing unit 302 is specifically configured to:
- the output layers of the multiple candidate prediction models are respectively multiplied by the preset weight values of the candidate prediction models, they are used as the input layer of the combined model to determine the combined model.
- processing unit 302 is specifically configured to:
- the corresponding relationship between the type of the performance indicator and the prediction model is determined in the following manner:
- the training data set including training production data of a plurality of plates to be trained and actual performance data corresponding to multiple types of performance indicators in the plates to be trained;
- the first type of performance indicators input the training production data into multiple initial prediction models to obtain prediction results corresponding to the initial prediction models; the first type of performance indicators are multiple types of performance Any one of the indicators;
- reverse training is performed to generate a plurality of prediction models of the first type; the first type of prediction The model is used to predict the performance data corresponding to the first type of performance index;
- any prediction model of the first type input the training production data into the prediction model of the first type to obtain a prediction result corresponding to the prediction model of the first type;
- the prediction model includes polynomial regression model, ridge regression model, kernel ridge regression KRR model, support vector machine SVM model, proximity algorithm KNN model, random forest model, progressive gradient regression tree GBRT model, extreme gradient boost XGboost Any one of the model, the distributed gradient boosting framework LightGBM model and the iterative algorithm Adaboost model.
- the step of inputting the training production data into a plurality of initial prediction models for the first type of performance indicators includes:
- the preprocessing unit performs preprocessing on the training data set.
- a computer-readable storage medium stores a computer program or smart contract, and the computer program or smart contract is loaded and executed by a node to implement the above-mentioned embodiments.
- Transaction processing method may be a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. .
- the technology in the embodiments of the present application can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solutions in the embodiments of the present application can be embodied in the form of a software product in essence or a part that contributes to the prior art.
- the computer software product can be stored in a storage medium, such as ROM/RAM , Magnetic disks, optical disks, etc., including a number of instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the application or some parts of the embodiment.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
一种板材性能的预测方法及装置。所述方法包括:获取待预测板材的生产数据(S101),针对任一类型的性能指标,根据性能指标的类型,以及预先存储的性能指标的类型与预测模型的对应关系,确定多个候选预测模型(S102),进而根据多个候选预测模型以及预先设置的候选预测模型的权重值,确定组合模型(S103),以及将待预测板材的生产数据输入组合模型中,得到性能指标对应的预测性能数据(S104)。采用上述方法对板材进行性能预测时,一方面能够减少频繁取样的操作步骤,缩短等待性能检测的时间,进而可以加快生产节奏,提高生产效率;另一方面,该方法综合考虑了多个预测模型,从而能够进一步提高板材性能的预测准确率。
Description
本申请要求在2019年7月10日提交中国专利局、申请号为201910626875.5、发明名称为“一种板材性能的预测方法及装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及板材质量技术领域,特别涉及一种板材性能的预测方法及装置。
随着人工智能技术的普及,智能制造的理念深入各行各业,对传统制造业产生了巨大的影响。例如,对钢铁行业来说,其生产流程包括从铁矿石到钢水、连铸坯、再到热轧、冷轧等一系列的步骤,是一个极度复杂的流程。在这个复杂的生产流程中,对钢铁板材的质量控制始终是重中之重。
现有技术通常采用物理冶金模型来预测钢铁板材的性能数据,进而控制钢铁板材的质量。物理冶金模型由温度场、再结晶、流变应力、析出和相变等子模型构成,可以对钢铁板材的化学成分、工艺参数、微观组织以及力学性能进行定性分析。然而,随着工艺要求的多样化和产品定制的多元化,依赖物理冶金模型预测钢铁板材的性能数据的方法,准确率不断降低,进而使得控制钢铁板材的质量变得越来越困难。
基于此,目前亟需一种板材性能的预测方法,用于解决现有技术中采用物理冶金模型来预测钢铁板材的性能数据导致准确率较低的问题。
发明内容
本申请提供了一种板材性能的预测方法及装置,可用于解决在现有技术中采用物理冶金模型来预测钢铁板材的性能数据导致准确率较低的技术问题。
第一方面,本申请实施例提供一种板材性能的预测方法,所述方法包括:
获取待预测板材的生产数据,所述生产数据包括所述待预测板材的化学成分、工艺参数和化验数据中的至少一项;
针对所述待预测板材的任一类型的性能指标,根据所述性能指标的类型,以及预先存储的性能指标的类型与预测模型的对应关系,确定多个候选预测模型;根据所述多个候选预测模型以及预先设置的候选预测模型的权重值,确定组合模型;将所述待预测板材的生产数据输入所述组合模型中,得到所述待预测板材在所述性能指标上的预测性能数据。
可选地,所述候选预测模型包括输出层,所述组合模型包括输入层;
根据所述多个候选预测模型以及预先设置的候选预测模型的权重值,确定组合模型,包括:
将所述多个候选预测模型的输出层分别与所述预先设置的候选预测模型的权重值相乘后,作为所述组合模型的输入层,确定所述组合模型。
可选地,将所述待预测板材的生产数据输入所述组合模型中,得到所述待预测板材在所述性能指标上的预测性能数据,包括:
将所述待预测板材的生产数据输入所述候选预测模型中,得到候选预测结果;
根据所述候选预测结果,以及预先设置的候选预测模型对应的权重值,确定所述组合模型的输入层对应的输入数据;
将所述输入数据输入所述组合模型的输入层,得到所述待预测板材在所述性能指标上的预测性能数据。
可选地,所述性能指标的类型与预测模型的对应关系通过以下方式确定:
获取训练数据集,所述训练数据集包括多个待训练板材的训练生产数据及所述待训练板材中多个类型的性能指标分别对应的实际性能数据;
针对第一类型的性能指标,将所述训练生产数据分别输入多个初始的预测模型,得到所述初始的预测模型所对应的预测结果;所述第一类型的性能指标为多个类型的性能指标中的任意一个类型;
根据所述初始的预测模型所对应的预测结果以及所述第一类型的性能指标所对应的实际性能数据,进行反向训练,生成多个第一类型的预测模型;所述第一类型的预测模型用于预测所述第一类型的性能指标对应的性能数据;
针对任意一个第一类型的预测模型,将所述训练生产数据输入所述第一类型的预测模型,得到所述第一类型的预测模型所对应的预测结果;
根据所述第一类型的预测模型所对应的预测结果以及所述第一类型的性能指标对应的实际性能数据,确定所述第一类型的预测模型的误差率;
根据每个第一类型的预测模型的误差率,从所述多个第一类型的预测模型中确定候选预测模型;
建立所述第一类型的性能指标与所述候选预测模型之间的对应关系。
可选地,所述预测模型包括多项式回归模型、岭回归模型、核岭回归(Kernel Ridge Regression,KRR)模型、支持向量机(Support Vector Machine,SVM)模型、邻近算法(K-NearestNeighbor,KNN)模型、随机森林模型、渐进梯度回归树(Gradient BoostRegression Tree,GBRT)模型、极端梯度助推(Extreme Gradient Boosting,XGboost)模型、分布式梯度提升框架(Light Gradient Boosting Machine,LightGBM)模型和迭代算法(Adaboost)模型中的任意一项。
可选地,所述针对第一类型的性能指标,将所述训练生产数据分别输入多个初始的预测模型步骤之前,包括:
对所述训练数据集进行预处理。
第二方面,本申请实施例提供一种板材性能的预测方法,所述方法包括:
获取待预测板材的生产数据;
将所述待预测板材的生产数据输入候选预测模型中,得到候选预测结果;
根据所述候选预测结果以及预先设置的候选预测模型对应的权重值,确定组合模型的输入层对应的输入数据;
将所述输入数据输入所述组合模型的输入层,得到待预测板材在该性能指标上的预测性能数据。第三方面,本申请实施例提供一种板材性能的预测装置,所述装置包 括:
获取单元,用于获取待预测板材的生产数据,所述生产数据包括所述待预测板材的化学成分、工艺参数和化验数据中的至少一项;
处理单元,用于针对所述待预测板材的任一类型的性能指标,根据所述性能指标的类型,以及预先存储的性能指标的类型与预测模型的对应关系,确定多个候选预测模型;根据所述多个候选预测模型以及预先设置的候选预测模型的权重值,确定组合模型;将所述待预测板材的生产数据输入所述组合模型中,得到所述待预测板材在所述性能指标上的预测性能数据。
可选地,所述候选预测模型包括输出层,所述组合模型包括输入层;
所述处理单元具体用于:
将所述多个候选预测模型的输出层分别与所述预先设置的候选预测模型的权重值相乘后,作为所述组合模型的输入层,确定所述组合模型。
可选地,所述处理单元具体用于:
将所述待预测板材的生产数据输入所述候选预测模型中,得到候选预测结果;以及,根据所述候选预测结果,以及预先设置的候选预测模型对应的权重值,确定所述组合模型的输入层对应的输入数据;以及,将所述输入数据输入所述组合模型的输入层,得到所述待预测板材在所述性能指标上的预测性能数据。
可选地,所述性能指标的类型与预测模型的对应关系通过以下方式确定:
获取训练数据集,所述训练数据集包括多个待训练板材的训练生产数据及所述待训练板材中多个类型的性能指标分别对应的实际性能数据;
针对第一类型的性能指标,将所述训练生产数据分别输入多个初始的预测模型,得到所述初始的预测模型所对应的预测结果;所述第一类型的性能指标为多个类型的性能指标中的任意一个类型;
根据所述初始的预测模型所对应的预测结果以及所述第一类型的性能指标所对应的实际性能数据,进行反向训练,生成多个第一类型的预测模型;所述第一类型的预测模型用于预测所述第一类型的性能指标对应的性能数据;
针对任意一个第一类型的预测模型,将所述训练生产数据输入所述第一类型的预测模型,得到所述第一类型的预测模型所对应的预测结果;
根据所述第一类型的预测模型所对应的预测结果以及所述第一类型的性能指标对应的实际性能数据,确定所述第一类型的预测模型的误差率;
根据每个第一类型的预测模型的误差率,从所述多个第一类型的预测模型中确定候选预测模型;
建立所述第一类型的性能指标与所述候选预测模型之间的对应关系。
可选地,所述预测模型包括多项式回归模型、岭回归模型、核岭回归KRR模型、支持向量机SVM模型、邻近算法KNN模型、随机森林模型、渐进梯度回归树GBRT模型、极端梯度助推XGboost模型、分布式梯度提升框架LightGBM模型和迭代算法Adaboost模型中的任意一项。
可选地,所述针对第一类型的性能指标,将所述训练生产数据分别输入多个初始的预测模型步骤之前,包括:
预处理单元,对所述训练数据集进行预处理。
采用上述方法,一方面,相对于现有技术中采用物理冶金模型的方式而言,本申请实施例可以根据化学成分、工艺参数和化验数据来预测板材的性能,在对板材进行性能预测时,能够减少频繁取样的操作步骤,缩短等待性能检测的时间,进而可以加快生产节奏,提高生产效率;另一方面,本申请实施例中采用了组合模型的方式来预测板材的性能数据,由于组合模型是结合多个候选预测模型确定的,因此,该方法综合考虑了多个预测模型,从而能够进一步提高板材性能的预测准确率。
图1为本申请实施例提供的一种板材性能的预测方法所对应的流程示意图;
图2为本申请实施例提供的一种性能指标的类型与预测模型的对应关系的确定方式所对应的流程示意图;
图3为本申请实施例提供的一种板材性能的预测装置的结构示意图;
图4为本申请实施例提供的岭回归模型误差率计算结果示意图;
图5为本申请实施例提供的SVM模型误差率计算结果示意图;
图6为本申请实施例提供的随机森林模型误差率计算结果示意图;
图7为本申请实施例提供的LightGBM模型误差率计算结果示意图;
图8为本申请实施例提供的XGboost模型误差率计算结果示意图;
图9为本申请实施例提供的Adaboost模型误差率计算结果示意图。
为使本申请的目的、技术方案和优点更加清楚,下面将结合附图对本申请实施方式作进一步地详细描述。
本申请的板材性能预测方法根据给定的板材生产数据,利用组合模型算法对板材的性能指标进行预测。为了验证组合模型预测的效果,采用均方根误差的精度方式进行对比分析。
图1示例性示出了本申请实施例提供的一种板材性能的预测方法所对应的流程示意图。如图1所示,具体包括如下步骤:
步骤101,获取待预测板材的生产数据。
步骤102,针对待预测板材的任一类型的性能指标,根据所述性能指标的类型,以及预先存储的性能指标的类型与预测模型的对应关系,确定多个候选预测模型。
步骤103,根据所述多个候选预测模型以及预先设置的候选预测模型的权重值,确定组合模型。
步骤104,将所述待预测板材的生产数据输入所述组合模型中,得到所述待预测板材在所述性能指标上的预测性能数据。
采用上述方法,一方面,相对于现有技术中采用物理冶金模型的方式而言,本申请实施例可以根据化学成分、工艺参数和化验数据来预测板材的性能,在对板材进行性能预测时,能够减少频繁取样的操作步骤,缩短等待性能检测的时间,进而可以加快生产节奏,提高生产效率;另一方面,本申请实施例中采用了组合模型的方式来预测板材的性能数据,由于组合模型是结合多个候选预测模型确定的,因此,该方法综 合考虑了多个预测模型,从而能够进一步提高板材性能的预测准确率。
本申请中的组合模型是结合多个候选预测模型确定的,首先选择单一的机器学习算法(机器学习最基本的做法,是使用算法来解析数据、从中学习,然后对真实世界中的事件做出决策和预测。与传统的为解决特定任务、硬编码的软件程序不同,机器学习是用大量的数据来“训练”,通过各种算法从数据中学习如何完成任务。),包括多项式回归模型、岭回归模型、KRR模型、SVM模型、KNN模型、随机森林模型、GBRT模型、XGboost模型、LightGBM模型和Adaboost模型等算法分别在训练集上进行训练,通过不断地调参优化得到单个模型分别在训练集上最好的参数。此时,各个单一模型在训练集上预测能力已达到上限,通过再训练优化很难得到更好地效果。针对单一算法模型对板材性能预测难以改善的问题,我们将选择几种单一的模型进行组合,将单一模型的预测结果进行加权组合形成更强的分类器,此时的单一模型已达到最优参数,对组合模型来说相当于模型已经预训练,我们利用组合模型再次在训练集上不断地训练,从而得到组合模型的最优参数。
具体来说,步骤101中,生产数据可以包括待预测板材的化学成分、工艺参数和化验数据中的至少一项。其中,以钢铁板材为例,化学成分可以包括碳、硅、锰、铬、镍和铜等化学元素。工艺参数可以是指钢板的加工工艺参数,可以包括板材厚度、板材幅面尺寸、轧制压力参数和淬火温度等参数。化验数据可以是指各化学成分的含量百分比。步骤102中,待预测板材的性能指标的类型有多种,以钢铁板材为例,性能指标的类型可以包括屈服强度、抗拉强度、延伸率和冲击功中的至少一项。
预测模型可以包括多项式回归模型、岭回归模型、KRR模型、SVM模型、KNN模型、随机森林模型、GBRT模型、XGboost模型、LightGBM模型和Adaboost模型中的任意一项。
性能指标的类型与预测模型的对应关系可以通过多种方式确定,一种可能的实现方式为,如图2所示,为本申请实施例提供的一种性能指标的类型与预测模型的对应关系的确定方式所对应的流程示意图,具体包括如下步骤:
步骤201,获取训练数据集。
其中,训练数据集可以包括多个待训练板材的训练生产数据及待训练板材中多个类型的性能指标分别对应的实际性能数据。训练生产数据可以是指用于训练模型的生产数据,训练生产数据包括的具体数据与上文所描述的生产数据所包括的具体数据可以一致。
进一步地,训练数据集的获取方式可以通过ERP、MES等办公***得到化学成分、工艺参数和化验数据等生产数据,然后对这些数据进行数据整合,比如可以使用数据抽取ETL的相关技术将生产数据存储到指定的数据库。其中,存储的生产数据可以是数据表的形式。
步骤202,针对第一类型的性能指标,将训练生产数据分别输入多个初始的预测模型,得到初始的预测模型所对应的预测结果。
其中,第一类型的性能指标为多个类型的性能指标中的任意一个类型。以钢铁板材为例,第一类型的性能指标可以是屈服强度、抗拉强度、延伸率和冲击功中的任意一项。
需要说明的是,在执行上述步骤202之前,可以对训练数据集进行数据预处理。具体地,可以对存储的生产数据进行数据清洗,包括对空值和异常值的处理,类别变量的向量化,数据去重和数据去燥处理等操作。
本申请中的对训练数据集进行预处理,不仅能够为输入多个初始的预测模型提供规格规范的数据,而且通过预处理后的数据避免了错误数据及异常值的干扰,进而提高数据处理效率。同时,本申请中数据预处理是有特定的应用场景的,预处理步骤是在获取训练数据集之后才执行,而我们的训练数据集是多个待训练板材的训练生产数据及待训练板材中多个类型的性能指标分别对应的实际性能数据,所以,预处理过程安排在特定环节也有特定的作用,具体描述如下:
在此值得说明的是,本申请的数据预处理方法并不是容易想到的,而且不同于普通的数据处理方法。首先,日常工作应用中,一般数据处理大多数单纯的采用ETL或catalog进行简单处理,例如,ETL即数据抽取(Extract)、转换(Transform)、装载(Load)的过程,catalog即用于数据的转入转出等操作,但基于这两种常用的方式,基本上只完成对数据的空值和异常值去除等操作,即可满足日常工作应用需求。
但本申请中对训练数据集是采用了预处理的操作,预处理包括很多方面,举例说明,一种包括对不完整的数据的处理,例如,对缺少某些感兴趣的属性值的处理;一种包含对不一致数据的处理,例如针对代码或者名称的差异处理;还有包括对错误或带有异常值的数据处理等,数据集经常来自多个异种数据源,所以用预处理的方法解决上述特定场景下的问题。具体的,数据预处理包括数据清洗、数据集成、数据规约、数据变换等。本申请中,经过预处理后的数据除了能够满足“输入多个初始的预测模型”外,还有如下效果:训练数据集经过预处理后极大的避免垃圾数据的干扰,且能够对数据集进行压缩,例如由原来的2G变为500M,这样大大提高数据运行效率,进而提高工作效率。步骤203,根据初始的预测模型所对应的预测结果以及第一类型的性能指标所对应的实际性能数据,进行反向训练,生成多个第一类型的预测模型。
其中,第一类型的预测模型可以用于预测所述第一类型的性能指标对应的性能数据。
步骤204,针对任意一个第一类型的预测模型,将训练生产数据输入第一类型的预测模型,得到第一类型的预测模型所对应的预测结果。
步骤205,根据第一类型的预测模型所对应的预测结果以及第一类型的性能指标对应的实际性能数据,确定第一类型的预测模型的误差率。
具体来说,第一类型的预测模型的误差率可以采用均方根误差来计算,具体的计算方式可以参考公式(1)。
公式(1)中,RMSE为第一类型的预测模型的误差率;N为训练数据集中待训练板材的样本数目,N为大于1的整数;y
i为训练数据集中第i个样本的真实值;
为第一类型的预测模型对训练数据集中第i个样本的预测结果。
公式(1)为第一类型的预测模型的误差率,本申请示例的为均方根误差,均方根 误差表示模型的预测值和真实值之间的误差大小。均方根误差越小,说明模型预测值越接近真实值。以屈服强度的性能预测为例,利用机器学习算法在待训练板材训练数据集上进行训练,并进行测试,此处列举部分预测模型的计算结果,结果仅为示例,参见图4-图9,具体为:
图4为本申请实施例提供的岭回归模型误差率计算结果示意图,可见岭回归模型误差率计算结果为17.202095;
图5为本申请实施例提供的SVM模型误差率计算结果示意图,可见SVM模型误差率计算结果为19.115036;
图6为本申请实施例提供的随机森林模型误差率计算结果示意图,可见随机森林模型误差率计算结果为13.790967;
图7为本申请实施例提供的LightGBM模型误差率计算结果示意图,可见LightGBM模型误差率计算结果为7.044598;
图8为本申请实施例提供的XGboost模型误差率计算结果示意图,可见XGboost模型误差率计算结果为14.185270;
图9为本申请实施例提供的Adaboost模型误差率计算结果示意图,可见Adaboost模型误差率计算结果为17.617467。
其中,图4-图9中,黑灰色代表待训练板材训练数据集(本实施例以屈服强度为例)的真实值,黑色代表待训练板材训练数据集(本实施例以屈服强度为例)的预测值,组合模型的思想就是选择上述表现好的模型进行加权组合,组合模型综合考虑了多个预测模型,从而能够进一步提高板材性能的预测准确率。
需要说明的是,公式(1)仅为一种可能的计算方法,本领域技术人员也可以根据经验和实际情况选取其他误差计算方法,具体不做限定。
步骤206,根据每个第一类型的预测模型的误差率,从多个第一类型的预测模型中确定候选预测模型。
具体来说,从多个第一类型的预测模型中确定候选预测模型的方式可以有多种,一个示例中,可以将误差率按从小到大进行排名,然后将排名前M位的预测模型作为候选预测模型,其中,M为大于1的整数。另一个示例中,可以将误差率小于预设阈值的预测模型作为候选预测模型,其中,预设阈值可以是本领域技术人员根据经验和实际情况确定的,具体不做限定。
举个例子,如表1所示,为第一类型的预测模型的误差率的一种示例。具体内容可以参考表1中所列举的内容,此处不再一一描述。
表1:第一类型的预测模型的误差率的一种示例
第一类型的预测模型 | 误差率(RMSE) |
多项式回归模型 | 17.203 |
岭回归模型 | 17.202 |
KRR模型 | 15.085 |
SVM模型 | 19.115 |
KNN模型 | 13.794 |
随机森林模型 | 13.791 |
GBRT模型 | 7.045 |
XGboost模型 | 11.976 |
LightGBM模型 | 14.185 |
Adaboost模型 | 17.617 |
其中,表1的第一列为第一类型的预测模型,表1的第二列为第一类型的预测模型具体类别所对应的相应误差率,也即,针对第一列中不同的预测模型所对应的不同误差率的值。表1中清晰的列出了各个模型的具体误差率,以此为依据,从多个第一类型的预测模型中确定候选预测模型。
进一步地,根据表1示出的内容,结合上述提供的将排名前M位的预测模型作为候选预测模型的方法,假设M=5,则候选预测模型包括随机森林模型、KNN模型、GBRT模型、XGboost模型和LightGBM模型。
上述候选预测模型的确认方式即为,假设M=5,将误差率按从小到大进行排名,然后将排名前5位的预测模型作为候选预测模型。
步骤207,建立第一类型的性能指标与候选预测模型之间的对应关系。
需要说明的是,在其它可能的实现方式为,性能指标的类型与预测模型的对应关系也可以是本领域技术人员根据经验或实际情况确定的,具体不做限定。
步骤101主要是数据收集工作,选择对模型性能有影响的数据,使用这些数据进行模型训练;步骤102主要是选择哪些模型进行融合,通过步骤101提供的数据,进行数据整合、数据预处理等操作得到训练数据集,并用得到的数据集对多个模型进行训练,评估各个模型的精度。
步骤103中,候选预测模型的权重值的设置方式有多种,一个示例中,候选预测模型的权重值可以根据候选预测模型的误差率确定,比如,候选预测模型的误差率越小,对应的权重值越高。
在其它可能的示例中,候选预测模型的权重值也可以是本领域技术人员根据经验和实际情况确定的,比如,本领域技术人员根据经验任务随机森林模型的重要度更高,则可以为随机森林模型设置更高的权重值。
进一步地,候选预测模型可以包括输出层,组合模型可以包括输入层。具体来说,组合模型的确定方式可以有多种,下面描述两种可能的方式。
方式一:可以将多个候选预测模型的输出层分别与预先设置的候选预测模型的权重值相乘后,作为组合模型的输入层,确定组合模型。
方式二:可以将候选预测模型作为一个子模型,该子模型与预先设置的候选预测模型的权重值相乘后,得到的大模型可以看做是组合模型。步骤104中,以组合模型的确定方式为上述方式一为例,具体可以将待预测板材的生产数据输入候选预测模型中,得到候选预测结果;然后可以根据候选预测结果,以及预先设置的候选预测模型对应的权重值,确定组合模型的输入层对应的输入数据;最后可以将输入数据输入组合模型的输入层,得到待预测板材在该性能指标上的预测性能数据。下述为本申请装 置实施例,可以用于执行本申请方法实施例。对于本申请装置实施例中未披露的细节,请参照本申请方法实施例。
图3示例性示出了本申请实施例提供的一种板材性能的预测装置的结构示意图。如图3所示,该装置具有实现上述板材性能的预测方法的功能,所述功能可以由硬件实现,也可以由硬件执行相应的软件实现。该装置可以包括:获取单元301和处理单元302。
获取单元301,用于获取待预测板材的生产数据,所述生产数据包括所述待预测板材的化学成分、工艺参数和化验数据中的至少一项;
处理单元302,用于针对所述待预测板材的任一类型的性能指标,根据所述性能指标的类型,以及预先存储的性能指标的类型与预测模型的对应关系,确定多个候选预测模型;根据所述多个候选预测模型以及预先设置的候选预测模型的权重值,确定组合模型;将所述待预测板材的生产数据输入所述组合模型中,得到所述待预测板材在所述性能指标上的预测性能数据。
可选地,所述候选预测模型包括输出层,所述组合模型包括输入层;
所述处理单元302具体用于:
将所述多个候选预测模型的输出层分别与所述预先设置的候选预测模型的权重值相乘后,作为所述组合模型的输入层,确定所述组合模型。
可选地,所述处理单元302具体用于:
将所述待预测板材的生产数据输入所述候选预测模型中,得到候选预测结果;以及,根据所述候选预测结果,以及预先设置的候选预测模型对应的权重值,确定所述组合模型的输入层对应的输入数据;以及,将所述输入数据输入所述组合模型的输入层,得到所述待预测板材在所述性能指标上的预测性能数据。
可选地,所述性能指标的类型与预测模型的对应关系通过以下方式确定:
获取训练数据集,所述训练数据集包括多个待训练板材的训练生产数据及所述待训练板材中多个类型的性能指标分别对应的实际性能数据;
针对第一类型的性能指标,将所述训练生产数据分别输入多个初始的预测模型,得到所述初始的预测模型所对应的预测结果;所述第一类型的性能指标为多个类型的性能指标中的任意一个类型;
根据所述初始的预测模型所对应的预测结果以及所述第一类型的性能指标所对应的实际性能数据,进行反向训练,生成多个第一类型的预测模型;所述第一类型的预测模型用于预测所述第一类型的性能指标对应的性能数据;
针对任意一个第一类型的预测模型,将所述训练生产数据输入所述第一类型的预测模型,得到所述第一类型的预测模型所对应的预测结果;
根据所述第一类型的预测模型所对应的预测结果以及所述第一类型的性能指标对应的实际性能数据,确定所述第一类型的预测模型的误差率;
根据每个第一类型的预测模型的误差率,从所述多个第一类型的预测模型中确定候选预测模型;
建立所述第一类型的性能指标与所述候选预测模型之间的对应关系。
可选地,所述预测模型包括多项式回归模型、岭回归模型、核岭回归KRR模型、 支持向量机SVM模型、邻近算法KNN模型、随机森林模型、渐进梯度回归树GBRT模型、极端梯度助推XGboost模型、分布式梯度提升框架LightGBM模型和迭代算法Adaboost模型中的任意一项。
可选地,所述针对第一类型的性能指标,将所述训练生产数据分别输入多个初始的预测模型步骤之前,包括:
预处理单元,对所述训练数据集进行预处理。
在示例性实施例中,还提供了一种计算机可读存储介质,所述存储介质中存储有计算机程序或智能合约,所述计算机程序或智能合约被节点加载并执行以实现上述实施例提供的事务处理方法。可选地,上述计算机可读存储介质可以是只读存储记忆体(Read-Only Memory,ROM)、随机存储记忆体(Random Access Memory,RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
本领域的技术人员可以清楚地了解到本申请实施例中的技术可借助软件加必需的通用硬件平台的方式来实现。基于这样的理解,本申请实施例中的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品可以存储在存储介质中,如ROM/RAM、磁碟、光盘等,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本申请各个实施例或者实施例的某些部分所述的方法。
本领域技术人员在考虑说明书及实践这里公开的发明后,将容易想到本公开的其它实施方案。本申请旨在涵盖本公开的任何变型、用途或者适应性变化,这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的,本公开的真正范围和精神由下面的权利要求指出。
应当理解的是,本公开并不局限于上面已经描述并在附图中示出的精确结构,并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。
Claims (13)
- 一种板材性能的预测方法,其特征在于,所述方法包括:获取待预测板材的生产数据,所述生产数据包括所述待预测板材的化学成分、工艺参数和化验数据中的至少一项;针对所述待预测板材的任一类型的性能指标,根据所述性能指标的类型,以及预先存储的性能指标的类型与预测模型的对应关系,确定多个候选预测模型;根据所述多个候选预测模型以及预先设置的候选预测模型的权重值,确定组合模型;将所述待预测板材的生产数据输入所述组合模型中,得到所述待预测板材在所述性能指标上的预测性能数据。
- 根据权利要求1所述的方法,其特征在于,所述候选预测模型包括输出层,所述组合模型包括输入层;根据所述多个候选预测模型以及预先设置的候选预测模型的权重值,确定组合模型,包括:将所述多个候选预测模型的输出层分别与所述预先设置的候选预测模型的权重值相乘后,作为所述组合模型的输入层,确定所述组合模型。
- 根据权利要求2所述的方法,其特征在于,将所述待预测板材的生产数据输入所述组合模型中,得到所述待预测板材在所述性能指标上的预测性能数据,包括:将所述待预测板材的生产数据输入所述候选预测模型中,得到候选预测结果;根据所述候选预测结果,以及预先设置的候选预测模型对应的权重值,确定所述组合模型的输入层对应的输入数据;将所述输入数据输入所述组合模型的输入层,得到所述待预测板材在所述性能指标上的预测性能数据。
- 根据权利要求1所述的方法,其特征在于,所述性能指标的类型与预测模型的对应关系通过以下方式确定:获取训练数据集,所述训练数据集包括多个待训练板材的训练生产数据及所述待训练板材中多个类型的性能指标分别对应的实际性能数据;针对第一类型的性能指标,将所述训练生产数据分别输入多个初始的预测模型,得到所述初始的预测模型所对应的预测结果;所述第一类型的性能指标为多个类型的性能指标中的任意一个类型;根据所述初始的预测模型所对应的预测结果以及所述第一类型的性能指标所对应的实际性能数据,进行反向训练,生成多个第一类型的预测模型;所述第一类型的预测模型用于预测所述第一类型的性能指标对应的性能数据;针对任意一个第一类型的预测模型,将所述训练生产数据输入所述第一类型的预测模型,得到所述第一类型的预测模型所对应的预测结果;根据所述第一类型的预测模型所对应的预测结果以及所述第一类型的性能指标对应的实际性能数据,确定所述第一类型的预测模型的误差率;根据每个第一类型的预测模型的误差率,从所述多个第一类型的预测模型中确定候选预测模型;建立所述第一类型的性能指标与所述候选预测模型之间的对应关系。
- 根据权利要求1所述的方法,其特征在于,所述预测模型包括多项式回归模型、岭回归模型、核岭回归KRR模型、支持向量机SVM模型、邻近算法KNN模型、随机森林模型、渐进梯度回归树GBRT模型、极端梯度助推XGboost模型、分布式梯度提升框架LightGBM模型和迭代算法Adaboost模型中的任意一项。
- 根据权利要求4所述的方法,其特征在于,所述针对第一类型的性能指标,将所述训练生产数据分别输入多个初始的预测模型步骤之前,包括:对所述训练数据集进行预处理。
- 一种板材性能的预测方法,其特征在于,所述方法包括:获取待预测板材的生产数据;将所述待预测板材的生产数据输入候选预测模型中,得到候选预测结果;根据所述候选预测结果以及预先设置的候选预测模型对应的权重值,确定组合模型的输入层对应的输入数据;将所述输入数据输入所述组合模型的输入层,得到待预测板材在该性能指标上的预测性能数据。
- 一种板材性能的预测装置,其特征在于,所述装置包括:获取单元,用于获取待预测板材的生产数据,所述生产数据包括所述待预测板材的化学成分、工艺参数和化验数据中的至少一项;处理单元,用于针对所述待预测板材的任一类型的性能指标,根据所述性能指标的类型,以及预先存储的性能指标的类型与预测模型的对应关系,确定多个候选预测模型;根据所述多个候选预测模型以及预先设置的候选预测模型的权重值,确定组合模型;将所述待预测板材的生产数据输入所述组合模型中,得到所述待预测板材在所述性能指标上的预测性能数据。
- 根据权利要求8所述的装置,其特征在于,所述候选预测模型包括输出层,所述组合模型包括输入层;所述处理单元具体用于:将所述多个候选预测模型的输出层分别与所述预先设置的候选预测模型的权重值相乘后,作为所述组合模型的输入层,确定所述组合模型。
- 根据权利要求9所述的装置,其特征在于,所述处理单元具体用于:将所述待预测板材的生产数据输入所述候选预测模型中,得到候选预测结果;以及,根据所述候选预测结果,以及预先设置的候选预测模型对应的权重值,确定所述组合模型的输入层对应的输入数据;以及,将所述输入数据输入所述组合模型的输入层,得到所述待预测板材在所述性能指标上的预测性能数据。
- 根据权利要求8所述的装置,其特征在于,所述性能指标的类型与预测模型的对应关系通过以下方式确定:获取训练数据集,所述训练数据集包括多个待训练板材的训练生产数据及所述待训练板材中多个类型的性能指标分别对应的实际性能数据;针对第一类型的性能指标,将所述训练生产数据分别输入多个初始的预测模型,得到所述初始的预测模型所对应的预测结果;所述第一类型的性能指标为多个类型的性能指标中的任意一个类型;根据所述初始的预测模型所对应的预测结果以及所述第一类型的性能指标所对应的实际性能数据,进行反向训练,生成多个第一类型的预测模型;所述第一类型的预测模型用于预测所述第一类型的性能指标对应的性能数据;针对任意一个第一类型的预测模型,将所述训练生产数据输入所述第一类型的预测模型,得到所述第一类型的预测模型所对应的预测结果;根据所述第一类型的预测模型所对应的预测结果以及所述第一类型的性能指标对应的实际性能数据,确定所述第一类型的预测模型的误差率;根据每个第一类型的预测模型的误差率,从所述多个第一类型的预测模型中确定候选预测模型;建立所述第一类型的性能指标与所述候选预测模型之间的对应关系。
- 根据权利要求8所述的装置,其特征在于,所述预测模型包括多项式回归模型、岭回归模型、核岭回归KRR模型、支持向量机SVM模型、邻近算法KNN模型、随机森林模型、渐进梯度回归树GBRT模型、极端梯度助推XGboost模型、分布式梯度提升框架LightGBM模型和迭代算法Adaboost模型中的任意一项。
- 根据权利要求8所述的装置,其特征在于,所述装置还包括:预处理单元,对所述训练数据集进行预处理。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
GB2110100.1A GB2600213B (en) | 2019-07-10 | 2020-06-02 | Method and apparatus for predicitng plate performance |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910626875.5 | 2019-07-10 | ||
CN201910626875.5A CN110321658B (zh) | 2019-07-10 | 2019-07-10 | 一种板材性能的预测方法及装置 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021004198A1 true WO2021004198A1 (zh) | 2021-01-14 |
Family
ID=68123233
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/093942 WO2021004198A1 (zh) | 2019-07-10 | 2020-06-02 | 一种板材性能的预测方法及装置 |
Country Status (3)
Country | Link |
---|---|
CN (1) | CN110321658B (zh) |
GB (1) | GB2600213B (zh) |
WO (1) | WO2021004198A1 (zh) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113657490A (zh) * | 2021-08-16 | 2021-11-16 | 沭阳县源美装饰材料有限公司 | 一种基于人工智能的门窗静音检测方法 |
CN114219175A (zh) * | 2021-12-28 | 2022-03-22 | 鞍钢集团自动化有限公司 | 一种集装箱卷板的力学性能预测方法 |
CN114386325A (zh) * | 2021-12-27 | 2022-04-22 | 北京科技大学 | 一种基于规则寻优的带钢力学性能预报方法 |
CN114896860A (zh) * | 2022-03-29 | 2022-08-12 | 武汉纺织大学 | 基于LightGBM和XGBoost组合模型的飞灰含碳量软测量方法 |
CN117976094A (zh) * | 2024-01-19 | 2024-05-03 | 一半科技(江苏)有限公司 | 一种配方检测指标预测方法、***、介质及设备 |
CN118039031A (zh) * | 2023-12-05 | 2024-05-14 | 中国地质大学(北京) | 一种基于磷灰石成分的机器学习判别区域成矿潜力的方法 |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110321658B (zh) * | 2019-07-10 | 2023-09-01 | 江苏金恒信息科技股份有限公司 | 一种板材性能的预测方法及装置 |
CN117265214B (zh) * | 2023-11-22 | 2024-04-02 | 张家港广大特材股份有限公司 | 一种特种钢生产的优化控制方法及*** |
CN117732886B (zh) * | 2024-02-07 | 2024-04-30 | 东北大学 | 一种基于级联智能诊断的热轧质量预控制方法 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104517162A (zh) * | 2014-12-30 | 2015-04-15 | 东北大学 | 一种连续退火产品硬度在线集成学习预报方法 |
CN104657602A (zh) * | 2015-02-02 | 2015-05-27 | 北京科技大学 | 一种热连轧生产过程中带钢厚度预测方法及*** |
CN105929812A (zh) * | 2016-04-18 | 2016-09-07 | 北京科技大学 | 带钢热连轧质量的故障诊断方法及装置 |
CN109657799A (zh) * | 2018-11-20 | 2019-04-19 | 北京首钢自动化信息技术有限公司 | 一种基于场景适配的模型调优方法和装置 |
CN110321658A (zh) * | 2019-07-10 | 2019-10-11 | 江苏金恒信息科技股份有限公司 | 一种板材性能的预测方法及装置 |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102620980B (zh) * | 2012-02-14 | 2014-01-22 | 天津理工大学 | 一种利用神经网络预报板材成形性能的方法 |
JP6889173B2 (ja) * | 2016-09-30 | 2021-06-18 | 株式会社Uacj | アルミニウム製品の特性予測装置、アルミニウム製品の特性予測方法、制御プログラム、および記録媒体 |
US20190102693A1 (en) * | 2017-09-29 | 2019-04-04 | Facebook, Inc. | Optimizing parameters for machine learning models |
-
2019
- 2019-07-10 CN CN201910626875.5A patent/CN110321658B/zh active Active
-
2020
- 2020-06-02 WO PCT/CN2020/093942 patent/WO2021004198A1/zh active Application Filing
- 2020-06-02 GB GB2110100.1A patent/GB2600213B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104517162A (zh) * | 2014-12-30 | 2015-04-15 | 东北大学 | 一种连续退火产品硬度在线集成学习预报方法 |
CN104657602A (zh) * | 2015-02-02 | 2015-05-27 | 北京科技大学 | 一种热连轧生产过程中带钢厚度预测方法及*** |
CN105929812A (zh) * | 2016-04-18 | 2016-09-07 | 北京科技大学 | 带钢热连轧质量的故障诊断方法及装置 |
CN109657799A (zh) * | 2018-11-20 | 2019-04-19 | 北京首钢自动化信息技术有限公司 | 一种基于场景适配的模型调优方法和装置 |
CN110321658A (zh) * | 2019-07-10 | 2019-10-11 | 江苏金恒信息科技股份有限公司 | 一种板材性能的预测方法及装置 |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113657490A (zh) * | 2021-08-16 | 2021-11-16 | 沭阳县源美装饰材料有限公司 | 一种基于人工智能的门窗静音检测方法 |
CN113657490B (zh) * | 2021-08-16 | 2022-05-31 | 沭阳县源美装饰材料有限公司 | 一种基于人工智能的门窗静音检测方法 |
CN114386325A (zh) * | 2021-12-27 | 2022-04-22 | 北京科技大学 | 一种基于规则寻优的带钢力学性能预报方法 |
CN114219175A (zh) * | 2021-12-28 | 2022-03-22 | 鞍钢集团自动化有限公司 | 一种集装箱卷板的力学性能预测方法 |
CN114219175B (zh) * | 2021-12-28 | 2024-07-19 | 鞍钢集团自动化有限公司 | 一种集装箱卷板的力学性能预测方法 |
CN114896860A (zh) * | 2022-03-29 | 2022-08-12 | 武汉纺织大学 | 基于LightGBM和XGBoost组合模型的飞灰含碳量软测量方法 |
CN114896860B (zh) * | 2022-03-29 | 2024-05-14 | 武汉纺织大学 | 基于LightGBM和XGBoost组合模型的飞灰含碳量软测量方法 |
CN118039031A (zh) * | 2023-12-05 | 2024-05-14 | 中国地质大学(北京) | 一种基于磷灰石成分的机器学习判别区域成矿潜力的方法 |
CN117976094A (zh) * | 2024-01-19 | 2024-05-03 | 一半科技(江苏)有限公司 | 一种配方检测指标预测方法、***、介质及设备 |
Also Published As
Publication number | Publication date |
---|---|
GB202110100D0 (en) | 2021-08-25 |
CN110321658B (zh) | 2023-09-01 |
GB2600213A (en) | 2022-04-27 |
GB2600213B (en) | 2023-06-14 |
CN110321658A (zh) | 2019-10-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021004198A1 (zh) | 一种板材性能的预测方法及装置 | |
WO2019165673A1 (zh) | 一种报销单风险预测方法、装置、终端设备及存储介质 | |
CN111563706A (zh) | 一种基于lstm网络的多变量物流货运量预测方法 | |
JP2022500769A (ja) | 電力システム熱負荷の予測方法及び予測装置 | |
US10592777B2 (en) | Systems and methods for slate optimization with recurrent neural networks | |
JP2020500420A (ja) | マシンラーニング基盤の半導体製造の収率予測システム及び方法 | |
CN111738532B (zh) | 一种事件对对象影响度的获取方法和*** | |
CN108062331A (zh) | 基于终生学习的增量式朴素贝叶斯文本分类方法 | |
Shie et al. | Prediction of corporate financial distress: an application of the America banking industry | |
CN114678080B (zh) | 转炉终点磷含量预测模型及构建方法、磷含量预测方法 | |
Li et al. | A soft sensing scheme of gas utilization ratio prediction for blast furnace via improved extreme learning machine | |
CN110930038A (zh) | 一种贷款需求识别方法、装置、终端及存储介质 | |
CN113032367A (zh) | 面向动态负载场景的大数据***跨层配置参数协同调优方法和*** | |
CN112634992A (zh) | 分子性质预测方法及其模型的训练方法及相关装置、设备 | |
CN110533249B (zh) | 一种基于集成长短期记忆网络的冶金企业能耗预测方法 | |
Zhao et al. | Prediction of mechanical properties of cold rolled strip based on improved extreme random tree | |
Li et al. | Physical metallurgy guided industrial big data analysis system with data classification and property prediction | |
CN110880044A (zh) | 一种基于马尔科夫链的负荷预测方法 | |
Liu et al. | End-point prediction of 260 tons basic oxygen furnace (BOF) steelmaking based on WNPSVR and WOA | |
CN114037139A (zh) | 一种基于注意力机制的货运车辆仓库逗留时长预测方法 | |
CN112488188A (zh) | 一种基于深度强化学习的特征选择方法 | |
CN112418522A (zh) | 一种基于三支集成预测模型的工业加热炉钢温预测方法 | |
CN115809346A (zh) | 一种基于多视图语义增强的小样本知识图谱补全方法 | |
CN111680720A (zh) | 基于改进cs-svr模型的高炉铁水硅含量预测方法 | |
JP2019159988A (ja) | ニューラルネットワーク装置及びプログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20836497 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 202110100 Country of ref document: GB Kind code of ref document: A Free format text: PCT FILING DATE = 20200602 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20836497 Country of ref document: EP Kind code of ref document: A1 |