Special steel performance evaluation method

Abstract

The invention discloses a special steel performance evaluation method. The method comprises the following steps: 1, collecting alloy composition, preparation process and performance detection data information of different types of special steel, and establishing a database; 2, processing and analyzing the information of the database through a data analysis model; 3, 1000 sets of special steel of different models are selected, alloy composition and performance of the special steel are detected, and meanwhile the preparation technology of the special steel is recorded; then alloy composition and preparation process data are input into the data analysis model for training, and performance detection data obtained after training and actual performance detection data are subjected to error comparison analysis, so that the error rate of an obtained result is judged; and finally, a data analysis model with a low error rate is obtained, so that the performance of the special steel can be conveniently evaluated. According to the method, the performance of the special steel can be preliminarily judged through the alloy composition of the to-be-detected special steel and the preparation process, and the error rate of performance evaluation does not exceed 1%, so that the performance detection efficiency of the special steel is effectively improved.

Description

Technical Field

[0001] The invention belongs to the field of special steel performance evaluation, in particular to a special steel performance evaluation method. Background Art

[0002] Special steel is the abbreviation of special steel, that is, steel that needs to be used in special environments, steel that needs to have high requirements in one or all properties, such as high temperature resistance, low temperature resistance, hardness, toughness, compressive strength, tensile strength, etc. Therefore, due to the high performance requirements of special steel, the testing of its performance also requires high standards and strict requirements. At present, the performance testing of special steel requires multiple tests to ensure its performance is accurate, so the detection efficiency is low. At present, there is a lack of a method for evaluating the performance of special steel to make a preliminary judgment on the performance of special steel. Summary of the invention

[0003] The invention provides a special steel performance evaluation method to solve the defects in the prior art.

[0004] The present invention is achieved through the following technical solutions:

[0005] A special steel performance evaluation method comprises the following steps:

[0006] Step 1: Collect the alloy composition, preparation process and corresponding performance test data information of different types of special steel issued by authoritative institutions corresponding to different types of alloys and establish a database;

[0007] Step 2: Process and analyze the information in the database through the data analysis model, divide the data information into alloy composition, preparation process and performance test data, and use the text recognition module to perform feature keyword recognition and extraction training on professional terms, so as to realize the data analysis model for keyword recognition and key information extraction of alloy composition, preparation process and performance test results;

[0008] Step 3: Select 1,000 groups of special steels of different types to test their alloy composition and performance while recording their preparation process. Then input the alloy composition and preparation process data into the data analysis model for training. Perform an error comparison analysis between the performance test data obtained after training and the actual performance test data to determine the error rate of the results. Finally, a data analysis model with a low error rate is obtained, which can easily complete the evaluation of special steel performance.

[0009] In the special steel performance evaluation method as described above, the text recognition module of the data analysis model can identify the element symbol and its corresponding Chinese character as the same characteristic keyword when performing keyword recognition, and at the same time, the text descriptions of Arabic numerals and mathematical symbols and Chinese numerals and Chinese mathematical symbols correspond one to one to avoid recognition errors.

[0010] In the special steel performance evaluation method as described above, the text recognition module of the data analysis model identifies characteristic keywords and corresponding values ​​in the alloy composition, preparation process and performance test data, and judges the rationality of the corresponding values. The specific values ​​of each metal element and each collective parameter of each operation can be judged to avoid errors in the actual evaluation process and reduce the error rate.

[0011] In the special steel performance evaluation method as described above, the data analysis model can judge the alloy composition according to the percentage in actual use. When the percentage is lower than 0.2%, it is determined that ±0.02% can be determined within the same range; when the percentage is higher than 0.2% and lower than 0.5%, it is determined that ±0.05% can be determined within the same range; when the percentage is higher than 0.5% and lower than 1.0%, it is determined that ±0.1% can be determined within the same range; when the percentage is higher than 1.0% and lower than 2.0%, it is determined that ±0.15% can be determined within the same range; when the percentage is higher than 2.0% and lower than 4.0%, it is determined that ±0.2% can be determined within the same range; when the percentage is higher than 4.0%, it is determined that ±0.3% can be determined within the same range.

[0012] As described above, in a special steel performance evaluation method, the data analysis model can determine that the casting, rolling initial temperature, rolling termination temperature, tempering temperature, annealing temperature, aging temperature, solution temperature, normalizing temperature, and quenching temperature in the preparation process are within the same range of ±20°C during actual use.

[0013] As described above, a special steel performance evaluation method, the data analysis model can determine that the tempering time, annealing time, aging time, solution hardening time, normalizing time and quenching time are within the same range of ±30min during actual use.

[0014] In the special steel performance evaluation method as described above, the data analysis model can compare three groups of data: alloy composition, preparation process and performance test data, and the impact of single alloy differences in alloy composition and single operation differences in preparation process on special steel performance. In this way, when the alloy composition or preparation process cannot match the information in the database, the performance change can be estimated based on the difference data to ensure the accuracy of the performance evaluation.

[0015] In the special steel performance evaluation method described above, the alloy composition and preparation process of the different types of special steels selected in step 1 cover all metal elements and preparation operations involved in the current special steel production.

[0016] In the special steel performance evaluation method as described above, the alloy compositions of the 1000 groups of special steels of different types selected in step 3 and their preparation processes try to cover all metal elements and preparation operations involved in current special steel production.

[0017] In the special steel performance evaluation method described above, in the step three, the performance data obtained after the data analysis model training is compared with the actual performance data, and the performance difference rate of a single group is less than 1%.

[0018] The advantages of the present invention are as follows: the present invention can make a preliminary judgment on the performance of special steel by the alloy composition and preparation process of the special steel to be tested, and the error rate of the performance evaluation of the present invention does not exceed 1%. For products that may have performance differences, multiple tests are performed to determine whether their performance meets the standards, and for products that are preliminarily judged to be qualified, only normal tests are required to determine whether the performance meets the standards, thereby effectively improving the performance testing efficiency of special steels. In special circumstances where performance testing cannot be performed and continuous operation is required, the performance of special steels can also be evaluated to ensure the performance of production products. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described in combination with the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] A special steel performance evaluation method comprises the following steps:

[0021] Step 1: Collect the alloy composition, preparation process and corresponding performance test data information of different types of special steel issued by authoritative institutions corresponding to different types of alloys and establish a database;

[0022] Step 2: Process and analyze the information in the database through the data analysis model, divide the data information into alloy composition, preparation process and performance test data, and use the text recognition module to perform feature keyword recognition and extraction training on professional terms, so as to realize the data analysis model for keyword recognition and key information extraction of alloy composition, preparation process and performance test results;

[0023] Step 3: Select 1,000 groups of special steels of different types to test their alloy composition and performance while recording their preparation process. Then input the alloy composition and preparation process data into the data analysis model for training. Perform an error comparison analysis between the performance test data obtained after training and the actual performance test data to determine the error rate of the results. Finally, a data analysis model with a low error rate is obtained, which can easily complete the evaluation of special steel performance.

[0024] Specifically, in the text recognition module of the data analysis model described in this embodiment, when performing keyword recognition, the element symbol and its corresponding Chinese character can be recognized as the same feature keyword, and the text descriptions of Arabic numerals and mathematical symbols and Chinese numerals and Chinese mathematical symbols are matched one by one to avoid recognition errors.

[0025] Specifically, the text recognition module of the data analysis model described in this embodiment identifies characteristic keywords and corresponding values ​​in alloy composition, preparation process and performance test data, and judges the rationality of the corresponding values. It can judge the specific values ​​of each metal element and each collective parameter of each operation to avoid errors in the actual evaluation process and reduce the error rate.

[0026] More specifically, the data analysis model described in this embodiment can judge the alloy composition according to the percentage during actual use. When the percentage is lower than 0.2%, it is determined that ±0.02% can be determined within the same range; when the percentage is higher than 0.2% and lower than 0.5%, it is determined that ±0.05% can be determined within the same range; when the percentage is higher than 0.5% and lower than 1.0%, it is determined that ±0.1% can be determined within the same range; when the percentage is higher than 1.0% and lower than 2.0%, it is determined that ±0.15% can be determined within the same range; when the percentage is higher than 2.0% and lower than 4.0%, it is determined that ±0.2% can be determined within the same range; when the percentage is higher than 4.0%, it is determined that ±0.3% can be determined within the same range.

[0027] More specifically, the data analysis model described in this embodiment can determine that the casting, initial rolling temperature, rolling termination temperature, tempering temperature, annealing temperature, aging temperature, solution temperature, normalizing temperature, and quenching temperature in the preparation process are within the same range of ±20°C during actual use.

[0028] More specifically, the data analysis model described in this embodiment can determine that the tempering time, annealing time, aging time, solution hardening time, normalizing time, and quenching time are within the same range of ±30 min during actual use.

[0029] Furthermore, the data analysis model described in this embodiment can compare three groups of data: alloy composition, preparation process and performance test data, and the impact of single alloy differences in alloy composition and single operation differences in the preparation process on special steel performance. Therefore, when the alloy composition or preparation process cannot match the information in the database, the performance change can be estimated based on the difference data to ensure the accuracy of the performance evaluation.

[0030] Furthermore, the alloy composition and preparation process of the different types of special steel selected in step 1 described in this embodiment cover all metal elements and preparation operations involved in the current special steel production.

[0031] Furthermore, the alloy compositions of the 1000 groups of different types of special steels selected in step three of this embodiment and their preparation processes try to cover all metal elements and preparation operations involved in the current special steel production.

[0032] Furthermore, the performance data obtained after the data analysis model training in step three of this embodiment is compared with the actual performance data, and the single-group performance difference rate is less than 1%.

[0033] After actual use, the present invention has been used to evaluate the performance of special steel nearly 5,000 times, among which the maximum single performance error rate is 0.76%, and 90% of the single performance error rates are lower than 0.5%, thus proving that the present invention can perform a relatively accurate evaluation of the performance of special steel and ensure the accuracy of the special steel performance evaluation.

[0034] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating special steel performance, characterized in that: The steps include: Step 1: Collect the alloy composition, preparation process and corresponding performance test data information of different types of special steel issued by authoritative institutions corresponding to different types of alloys and establish a database; Step 2: Process and analyze the information in the database through the data analysis model, divide the data information into alloy composition, preparation process and performance test data, and use the text recognition module to perform feature keyword recognition and extraction training on professional terms, so as to realize the data analysis model for keyword recognition and key information extraction of alloy composition, preparation process and performance test results; Step 3: Select 1,000 groups of special steels of different types to test their alloy composition and performance while recording their preparation process. Then input the alloy composition and preparation process data into the data analysis model for training. Perform an error comparison analysis between the performance test data obtained after training and the actual performance test data to determine the error rate of the results. Finally, a data analysis model with a low error rate is obtained, which can easily complete the evaluation of special steel performance.

2. A special steel performance evaluation method according to claim 1, characterized in that: In the text recognition module of the data analysis model, element symbols and their corresponding Chinese characters can be identified as the same feature keyword when performing keyword recognition. At the same time, the text descriptions of Arabic numerals and mathematical symbols and Chinese numerals and Chinese mathematical symbols are matched one by one to avoid recognition errors.

3. A special steel performance evaluation method according to claim 1, characterized in that: The text recognition module of the data analysis model can identify characteristic keywords and corresponding values ​​in alloy composition, preparation process and performance test data, and judge the rationality of the corresponding values. It can judge the specific values ​​of each metal element and each collective parameter of each operation to avoid errors in the actual evaluation process and reduce the error rate.

4. A special steel performance evaluation method according to claim 1, characterized in that: The data analysis model can judge the alloy composition according to the percentage in actual use. When the percentage is lower than 0.2%, it is determined that ±0.02% can be determined within the same range; when the percentage is higher than 0.2% and lower than 0.5%, it is determined that ±0.05% can be determined within the same range; when the percentage is higher than 0.5% and lower than 1.0%, it is determined that ±0.1% can be determined within the same range; when the percentage is higher than 1.0% and lower than 2.0%, it is determined that ±0.15% can be determined within the same range; when the percentage is higher than 2.0% and lower than 4.0%, it is determined that ±0.2% can be determined within the same range; when the percentage is higher than 4.0%, it is determined that ±0.3% can be determined within the same range.

5. A special steel performance evaluation method according to claim 1, characterized in that: The data analysis model can determine that the casting, rolling initial temperature, rolling end temperature, tempering temperature, annealing temperature, aging temperature, solution temperature, normalizing temperature and quenching temperature in the preparation process are within the same range of ±20°C during actual use.

6. A special steel performance evaluation method according to claim 1, characterized in that: The data analysis model can determine that the tempering time, annealing time, aging time, solution hardening time, normalizing time and quenching time are within the same range of ±30min during actual use.

7. A special steel performance evaluation method according to claim 1, characterized in that: The data analysis model can compare three groups of data: alloy composition, preparation process and performance test data, and the impact of single alloy differences in alloy composition and single operation differences in preparation process on special steel performance. In this way, when the alloy composition or preparation process cannot match the information in the database, the performance change can be estimated based on the difference data to ensure the accuracy of the performance evaluation.

8. A special steel performance evaluation method according to claim 1, characterized in that: The alloy compositions and preparation processes of the different types of special steels selected in step 1 cover all metal elements and preparation operations involved in current special steel production.

9. A special steel performance evaluation method according to claim 1, characterized in that: The alloy compositions of the 1000 groups of special steels of different types and their preparation processes selected in step 3 try to cover all metal elements and preparation operations involved in current special steel production.

10. A special steel performance evaluation method according to claim 1, characterized in that: The performance data obtained after the data analysis model training in step three is compared with the actual performance data, and the performance difference rate of a single group is less than 1%.