TWI697585B - Hot dip galvanizing product defect estimation system and method thereof - Google Patents

Abstract

A hot dip galvanizing product defect estimation system and a hot dip galvanizing product defect estimation method are provided. The hot dip galvanizing product defect estimation method comprises the steps of: collecting a historical production information of a plurality of pre-galvanized products, wherein each historical production information records at least one process experienced by the pre-galvanized product, wherein the process has a plurality of process conditions; processing the process and the process conditions to form a plurality of variable arrays; selecting at least one of the variable arrays as a pre-established classification model by using a gene algorithm; using the pre-established classification model and a historical production information of the pre-galvanized product to generate a prediction information; and estimating whether the defect is generated and generating a suggestion information based on the predicted information.

Description

Hot-dip galvanized product defect estimation system and method

The invention relates to a defect estimation system, in particular to a defect estimation system and method for hot-dip galvanized products.

Hot-dip galvanized products often have defects, such as bulging, on the surface of the galvanized product, and such problems often occur on thin plates or thick galvanized products. Before hot-dip galvanizing with current industry technology, various products may go through processes such as hot rolling, pickling, and cold rolling. At present, the evaluation before the hot-dip galvanizing process or the adjustment of the process conditions in the hot-dip galvanizing process is mostly estimated and adjusted based on the accumulated experience of the operators themselves, and the basis of each operator's estimation is not It is the same, and it is impossible to systematically accumulate relevant experience, which makes it difficult to establish a systematic estimation model.

Therefore, it is necessary to provide a defect estimation system and method for hot-dip galvanized products to solve the problems of conventional technologies.

The main purpose of the present invention is to provide a hot-dip galvanized product defect estimation system and method, which can estimate whether it is a defect (bulging) risk group through historical production information of an object before hot-dip galvanizing.

Another object of the present invention is to provide early warning to the production line for the products of the estimated defect (bulging) risk group, so as to adjust the process conditions or transfer orders, thereby reducing the probability of product defects and reducing the customer complaint rate.

In order to achieve the above-mentioned object, the present invention provides a hot-dip galvanized product defect estimation system for predicting whether a defect occurs in a pre-galvanized object after a hot-dip galvanizing process, which includes: a historical production data database To store multiple production information; a forecasting module, It establishes a pre-built classification model and uses a piece of historical production information of the object before galvanization from the historical production data database to generate forecast information, wherein the historical production information records at least the experience of the object before galvanization A process, wherein the process has a plurality of process conditions, wherein forming the pre-built classification model includes the steps of: collecting the historical production information of a plurality of the objects before galvanizing; processing the processes and the process conditions to form a plurality of An independent variable array; and using a genetic algorithm to select at least one of the independent variable arrays as the pre-built classification model; an evaluation module connected to the prediction module, and the evaluation module estimates the defect based on the prediction information Whether to generate and generate a recommendation information; and a production module, connected to the evaluation module, and process the object before galvanization according to the recommendation information, and generate a galvanization production information, wherein the galvanization production information is stored in the history Production data database.

In an embodiment of the present invention, the prediction module uses the genetic algorithm to select C of the independent variable arrays as the pre-built classification model, wherein the C value is determined by the genetic algorithm and the C value is greater than 1.

In an embodiment of the present invention, the prediction module uses a minority sample synthesis technique to increase a sample number, where the sample number is (1+N/100) times an original sample number, and the range of N value is Between 0 and 17, and use the genetic algorithm to select the N value.

In an embodiment of the present invention, the prediction module converts the processes and the process conditions into a plurality of values, normalizes the values, and excludes an average value of the values plus or minus n times the standard deviation range The range of n is between 2 and 6.

The present invention also provides a hot-dip galvanized product defect estimation method for predicting whether a defect occurs in a pre-galvanized object after a hot-dip galvanizing process, which includes the step of collecting a history of a plurality of pre-galvanized objects Production information, wherein each of the historical production information records at least one process that the object has gone through before galvanizing, wherein the process has a plurality of process conditions; the process and the process conditions are processed to form a plurality of independent variable arrays; Use a genetic algorithm to select at least one of the independent variable arrays as a pre-built classification model; use the pre-built classification model and a piece of historical production information of the pre-galvanized object to generate prediction information; and based on the prediction The information estimates whether the defect is generated and generates a suggestion information.

In an embodiment of the present invention, processing the processes and the process conditions further includes: converting the processes and the process conditions into a parameter condition comparison table, the parameter bar The comparison table has multiple fields and multiple values corresponding to these fields; normalizes these values between 0 and 1; and excludes an average value of the values in each field plus minus n times the standard deviation For these values outside the range, the range of n is between 2-6.

In an embodiment of the present invention, the method for estimating defects of hot-dip galvanized products further includes: using the genetic algorithm to select C of the independent variable arrays as the pre-built classification model, wherein the C value is determined by the The genetic algorithm determines and the C value is greater than 1.

In an embodiment of the present invention, it further includes: using a Synthetic Minority Over-sampling Technique (SMOTE) to increase a sampling quantity, wherein the sampling quantity is (1+N) of the original sampling quantity. /100) times, where the value of N ranges from 0 to 17.

In an embodiment of the present invention, the method for estimating defects of hot-dip galvanized products further includes: using the genetic algorithm to select the N value.

In an embodiment of the present invention, the method for estimating defects of hot-dip galvanized products further includes: processing the object before galvanizing according to the suggestion information, and generating a galvanized production information.

As mentioned above, the present invention builds an estimated classification model by concatenating historical production information of the object before galvanizing, combined with machine learning algorithms such as genetic algorithms, and using the estimated classification model established by automated calculations. It can save time and systematically estimate whether the product will produce defects after hot-dip galvanizing. In addition, the present invention can also provide early warning for dangerous groups that may produce defects, such as adjusting the process conditions of hot-dip galvanizing to reduce the probability of product defects, or for example, stop working on dangerous groups or transfer orders to avoid unnecessary production capacity. Consumption.

100‧‧‧Defect estimation system for hot dip galvanized products

110‧‧‧Historical production data database

112‧‧‧Production Information

120‧‧‧Prediction Module

122‧‧‧Pre-built classification model

124‧‧‧Forecast Information

130‧‧‧Evaluation Module

132‧‧‧Recommended information

140‧‧‧Production Module

142‧‧‧Zinc Plating Production Information

310‧‧‧Hot rolling process

311‧‧‧Steel grade

312‧‧‧Hot rolling pressure

313‧‧‧Hot rolling temperature

320‧‧‧Cold rolling process

321‧‧‧Steel grade

322‧‧‧Cold rolling pressure

323‧‧‧cold rolling temperature

400‧‧‧Parameter condition comparison table

411‧‧‧Column

412‧‧‧ columns

413‧‧‧ columns

421‧‧‧line

422‧‧‧line

423‧‧‧line

424‧‧‧line

425‧‧‧line

S110~S150‧‧‧Step

Figure 1 is a schematic diagram of a defect estimation system for hot-dip galvanized products of the present invention.

Figure 2 is a flowchart of an embodiment of a method for estimating defects of hot-dip galvanized products of the present invention.

Figures 3A to 3C are an embodiment of the conversion process and process conditions into a parameter condition comparison table in the present invention.

In order to make the above and other objectives, features, and advantages of the present invention more obvious Understand, the preferred embodiments of the present invention will be specifically cited below, and detailed descriptions will be made as follows in conjunction with the drawings. Furthermore, the directional terms mentioned in the present invention, such as up, down, top, bottom, front, back, left, right, inside, outside, side, surrounding, center, horizontal, horizontal, vertical, vertical, axial, The radial direction, the uppermost layer or the lowermost layer, etc., are only the direction of reference to the attached drawings. Therefore, the directional terms used are used to describe and understand the present invention, rather than to limit the present invention.

Please refer to Fig. 1. Fig. 1 is a schematic diagram of a defect estimation system for hot-dip galvanized products of the present invention. The present invention provides a hot-dip galvanized product defect estimation system 100, which is used to predict whether a defect occurs after a hot-dip galvanizing process of an object before galvanizing, which includes: a historical production data database 110, a prediction model Group 120, an evaluation module 130 and a production module 140. The defect is, for example, bulging or depression of the product surface after hot-dip galvanizing.

The historical production data database 110 is used to store a plurality of production information 112. The production information 112 may be various production information of various products before/after hot-dip galvanizing, such as historical production information before galvanizing or galvanizing production information. All kinds of products can be steel coils, steel bars or other products that require hot-dip galvanizing, and all kinds of products have undergone at least one process before the hot-dip galvanizing process.

The prediction module 120 establishes a pre-built classification model 122, and uses a historical production information 112 of the pre-galvanized object from the historical production data database 110 to generate a forecast information 124, wherein the historical production information 112 records At least one process that the object has gone through before galvanizing, wherein the process has a plurality of process conditions. The prediction module 120 forming the pre-built classification model 122 includes the step of collecting the historical production information 122 of a plurality of the objects before galvanizing.

The processes and the process conditions are processed to form a plurality of independent variable arrays.

A genetic algorithm is used to select at least one of the independent variable arrays as the pre-built classification model 122.

The prediction module 120 converts the processes and the process conditions into a plurality of numerical values, normalizes the numerical values, and excludes the numerical values outside the range of an average value of the numerical values plus or minus n times the standard deviation, where n The range is between 2 and 6. In this way, some outliers/deviations are filtered, and the outliers/deviations are prevented from affecting the pre-established classification model 122.

The prediction module 120 uses the genetic algorithm to select the C independent variable groups are used as the pre-built classification model 122, where the C value is determined by the genetic algorithm and the C value is greater than one. That is, the prediction module 120 can determine one, five or more independent variable groups as the pre-built classification model 122 through the genetic algorithm.

However, when the amount of production information in the historical production data database 110 is too small (too few samples). The prediction module 120 can use a minority sample synthesis technique to increase a sample number, where the sample number is (1+N/100) times an original sample number, and the value of N ranges from 0 to 17, and Use the genetic algorithm to select/determine the N value. In this way, it is avoided that the accuracy of the pre-built classification model 122 is affected because the amount of production information is too small (too few samples).

The prediction information 124 generated by the prediction module 120 indicates whether the object before hot-dip galvanizing is a defect (bulging) danger group.

The evaluation module 130 is connected to the prediction module 120, and the evaluation module 130 estimates whether the defect occurs according to the prediction information 124 and generates a recommendation information 132. The suggestion information 132 may include suggestions for the adjustment/fine-tuning of the process conditions in the hot-dip galvanizing process, and not to perform the hot-dip galvanizing process (that is, transfer orders).

The production module 140 is connected to the evaluation module 130, and processes the pre-galvanized object according to the suggested information 132, and generates a galvanized production information 142, wherein the galvanized production information 142 is stored in the historical production data database 110 . That is to say, the production module 140 receives the transfer order and suggests that it should be used to avoid the production and energy costs on the objects that will inevitably produce defects (bulging). Alternatively, the production module 140 can reduce the probability of defects (bulging) in the hot-dip galvanizing process by adjusting/fine-tuning the process conditions in the hot-dip galvanizing process. The fine-tuned process conditions are included in the zinc plating production information 142 and stored in the historical production data database 110, which can be used as a basis for processing similar objects in the future.

Please refer to Fig. 2 and Figs. 3A to 3C. Fig. 2 is a flowchart of an embodiment of a method for estimating defects of hot-dip galvanized products of the present invention. Figures 3A to 3C are an embodiment of the conversion process and process conditions into a parameter condition comparison table in the present invention. The present invention also provides a method for estimating defects of hot-dip galvanized products, which is used to predict whether a defect occurs after a hot-dip galvanizing process of an object before galvanizing, including:

Step S110, collecting historical production information of a plurality of objects before galvanizing, which Each of the historical production information records at least one process experienced by the object before galvanizing, and each of the processes has a plurality of process conditions.

In step S120, the processes and the process conditions are processed to form a plurality of independent variable arrays. The combination of these independent variable arrays can form a pre-built classification model. And step S120 can also include step S122, step S124, and step S126.

In step S122, the processes and the process conditions are converted into a parameter condition comparison table 400. The parameter condition comparison table 400 may have a plurality of fields and a plurality of values corresponding to the fields. Step S122 is used to convert the production information into a plurality of values.

Step S124, normalize these values between 0 and 1. That is, these values are normalized, so as to prevent the production information with larger values from affecting the presentation of the model.

Step S126, excluding the values outside the range of an average value plus or minus n times the standard deviation of the values in each field, where the range of n is between 2 and 6, to filter out outliers. Taking n=3 as an example, it means to exclude the values outside the range of standard deviation by the plus or minus 3 of the field data. These excessively large values may be caused by errors in the acquisition or other factors, which can avoid distortion of the pre-built classification model. The calculation formula for normalization in step S126 is as follows:

Take the example shown in Figs. 3A to 3C for illustration. As shown in Fig. 3A, the historical production information record of the object before galvanizing may include, for example, the hot rolling process 310 and the cold rolling process 320, while the hot rolling process 310 contains Steel grade 311, hot rolling pressure 312, hot rolling temperature 313 and other process conditions, while cold rolling process 320 includes steel grade 321, cold rolling pressure 322, cold rolling temperature 323 and other process conditions. As shown in FIG. 3B, the process conditions of the hot rolling process 310 and the cold rolling process 320 are converted into a parameter condition comparison table 400, that is, multiple process conditions that the object may experience before galvanizing are connected in series. For example, column 411 in the parameter condition comparison table 400 is filled with production information 1, and production information 1 records the historical production information of object 1, such as steel type 1, hot rolling pressure of 10 Gpa, hot rolling temperature of 1100 ℃, and object 1 does not After the cold rolling process, the cold rolling pressure and the cold rolling temperature are each 0, and they are respectively filled in the columns corresponding to rows 421, 422, 423, 424, and 425. In the same way, column 412 records the production information 2 and the production information 2 records the historical production information of the object 2. For example, the steel type is 2, the hot rolling pressure is 10Gpa, the hot rolling temperature is 1100℃, and the cold rolling pressure is 5Gpa. And the cold rolling temperature is 30°C, and fill in the fields corresponding to row 421, row 422, row 423, row 424, and row 425, respectively. In the same way, column 413 is filled with production information 3, and production information 3 records the historical production information of object 3. For example, steel type is 3, hot rolling pressure is 12Gpa, hot rolling temperature is 800℃, cold rolling pressure is 10Gpa and cold rolling The temperature is 80°C, and fill in the columns corresponding to row 421, row 422, row 423, row 424, and row 425, respectively.

Since the values of the hot rolling temperature and the cold rolling temperature are 1100 and 30, respectively, the large difference between the values in the model (for example, after graphing) cannot clearly show their respective effects. In order to avoid such problems, as shown in Figure 3C, normalize the value of each field (each process condition) so that the value of each field is between 0 and 1, so that the influence of each process condition can be clearly displayed. To facilitate subsequent interpretation. The fields are the independent variable arrays.

Step S130, using a genetic algorithm to select at least one of the independent variable arrays as a pre-built classification model. Step S130 further includes: step S132, step S134, and step S136.

Step S132, using the genetic algorithm to select C independent variable groups among the independent variable groups as the pre-built classification model, wherein the C value is determined by the genetic algorithm and the C value is greater than 1. Take the 5 independent variable arrays (process parameters) in Figure 3C as an example. You can choose one, two, three, four, or five among the five. Combine as a pre-built classification model. That is, according to the C value, the pre-built classification model has at least one combination of independent variables. For example, 5 independent variable arrays and a C value of 5 is a combination of independent variable arrays. If there are 5 independent variable arrays and a C value of 4, there are 5 independent variable array combinations. Therefore, the number of combinations of the independent variable array can be obtained by the following formula:

Step S134, using a minority sample synthesis technique to increase a sample number, where the sample number is (1+N/100) times an original sample number, and the value of N ranges from 0 to 17. In addition, step S134 can also use the genetic algorithm to select the N value. In this way, the problem of the unbalance between the defective (bulging) data amount and the normal data amount in the initial stage of data creation can be solved.

Step S136, selecting a pre-built classification model. The C value selected in step S132 4 to illustrate, there will be 5 kinds of independent variable array combinations. Step S136 is to select one of the five independent variable array combinations as the pre-built classification model.

Step S140, using the pre-built classification model and a piece of historical production information of the pre-galvanized object to generate a piece of prediction information. The prediction information at least indicates whether the object before hot-dip galvanizing is a defect (bulging) danger group.

In step S150, it is estimated whether the defect is generated according to the prediction information and a suggestion information is generated. The suggestion information may include suggestions for the adjustment/fine-tuning of the process conditions in the hot-dip galvanizing process, and not to perform the hot-dip galvanizing process (that is, the transfer order).

As mentioned above, the present invention builds an estimated classification model by concatenating historical production information of the object before galvanizing, combined with machine learning algorithms such as genetic algorithms, and using the estimated classification model established by automated calculations. It can save time and systematically estimate whether the product will produce defects after hot-dip galvanizing. In addition, the present invention can also provide early warning for dangerous groups that may produce defects, such as adjusting the process conditions of hot-dip galvanizing to reduce the probability of product defects, or for example, stop working or transferring orders to defect dangerous groups to avoid unnecessary uselessness. Capacity consumption.

Although the present invention has been disclosed in preferred embodiments, it is not intended to limit the present invention. Anyone who is familiar with the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the present invention The scope of protection shall be subject to the scope of the attached patent application.

100‧‧‧Defect estimation system for hot dip galvanized products

110‧‧‧Historical production data database

112‧‧‧Production Information

120‧‧‧Prediction Module

122‧‧‧Pre-built classification model

124‧‧‧Forecast Information

130‧‧‧Evaluation Module

132‧‧‧Recommended information

140‧‧‧Production Module

142‧‧‧Zinc Plating Production Information

Claims (10)

A hot-dip galvanized product defect estimation system for predicting whether a defect will occur after a hot-dip galvanizing process on an object before galvanizing, which includes: a historical production data database for storing multiple production information; A prediction module that creates a pre-built classification model and uses historical production information of the pre-galvanized object from the historical production data database to generate prediction information, wherein the historical production information records the pre-galvanized object At least one process that has been experienced, wherein the process has a plurality of process conditions, wherein forming the pre-built classification model includes the steps of: collecting the historical production information of a plurality of the objects before galvanizing; processing the processes and the process conditions , To form a plurality of independent variable arrays; and use a genetic algorithm to select at least one of the independent variable arrays as the pre-built classification model; an evaluation module connected to the prediction module, and the evaluation module is based on the prediction The information estimates whether the defect is generated and generates a recommendation information; and a production module is connected to the evaluation module, and the object before galvanization is processed according to the recommendation information, and a zinc plating production information is generated, wherein the zinc plating production The information is stored in the historical production data database. The hot-dip galvanized product defect estimation system described in item 1 of the scope of patent application, wherein the prediction module uses the genetic algorithm to select C of the independent variable arrays as the pre-built classification model, wherein the C value Determined by the genetic algorithm and the C value is greater than 1. Defect estimation system for hot-dip galvanized products as described in item 1 of the scope of patent application System, where the prediction module uses a minority sample synthesis technique to increase a sample number, where the sample number is (1+N/100) times an original sample number, and the value of N ranges from 0 to 17, And use the genetic algorithm to select the N value. For the hot-dip galvanized product defect estimation system described in item 1 of the scope of patent application, the prediction module converts the processes and the process conditions into a plurality of values, normalizes the values, and excludes the An average value of the values plus or minus the values outside the range of n times the standard deviation, wherein the range of n is between 2-6. A method for estimating defects of hot-dip galvanized products is used to predict whether a defect occurs after a hot-dip galvanizing process of an object before galvanizing. Each of the historical production information records at least one process that the object has gone through before galvanizing, wherein the process has a plurality of process conditions; the process and the process conditions are processed to form a plurality of independent variable arrays; a genetic algorithm is used Method selects at least one of the independent variable arrays as a pre-built classification model; uses the pre-built classification model and a piece of historical production information of the object before galvanizing to generate a prediction information; and estimates the prediction information based on the prediction information Whether the defect is generated and a suggestion information is generated. For example, the hot-dip galvanized product defect estimation method described in item 5 of the scope of patent application, wherein processing the processes and the process conditions further includes: converting the processes and the process conditions into a parameter condition comparison table, The The parameter condition comparison table has multiple fields and multiple values corresponding to these fields; normalizes these values between 0 and 1; and excludes an average value of the values in each field plus or minus n times the standard For these values outside the difference range, the range of n is between 2 and 6. For example, the hot-dip galvanized product defect estimation method described in item 6 of the scope of patent application further includes: using the genetic algorithm to select C of the independent variable arrays as the pre-built classification model, wherein the C value is determined by the The genetic algorithm determines and the C value is greater than 1. As described in item 6 of the scope of patent application, the defect estimation method of hot-dip galvanized products further includes: using a small number of sample synthesis technology to increase a sampling quantity, where the sampling quantity is (1+N/ 100) times, where the value of N ranges from 0 to 17. The method for estimating defects of hot-dip galvanized products described in item 8 of the scope of patent application further includes: using the genetic algorithm to select the N value. The method for estimating defects of hot-dip galvanized products as described in item 5 of the scope of patent application further includes: processing the object before galvanizing according to the suggested information, and generating a galvanized production information.

Images