A Die Steel Heat Treatment Performance Prediction System Based on Big Data

Abstract

The present invention provides a prediction system for the heat treatment performance of die steel based on big data, belonging to the field of intelligent prediction technology, including: a data acquisition module for obtaining detailed chemical composition data, production process setting data, and production process monitoring data of different batches of steel from die steel manufacturers; a determination module for determining the composition difference array and the affected array of chemical composition, process setting parameters, and process monitoring parameters based on the preprocessed data. At the same time, a first factor set affecting the heat treatment performance of each batch of steel in the historical actual production process is determined; a result prediction module for inputting the actual obtained parameters of the current die steel into the performance prediction model to determine the initial performance prediction result; a result optimization module for optimizing the initial performance prediction result based on the composition difference array, the affected array, and the first factor set to obtain the current performance prediction result. Ensure the accuracy of the prediction of the heat treatment performance of die steel.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent prediction, and particularly to a prediction system for the heat treatment performance of die steel based on big data. Background Art

[0002] The heat treatment of die steel is a process of heating, insulating and cooling die steel to change its organizational structure and performance to meet the requirements of die use. In the die manufacturing industry, the accurate control of the heat treatment performance of die steel plays a decisive role in product quality, production efficiency and cost control. The traditional method relying on experience and repeated tests is not only inefficient, but also difficult to meet the growing demand for high-precision and high-performance dies.

[0003] Therefore, the present invention proposes a prediction system for the heat treatment performance of die steel based on big data. Summary of the Invention

[0004] The present invention provides a prediction system for the heat treatment performance of die steel based on big data, which is used to optimize the initial performance prediction result by collecting chemical composition data, production process setting data and production process monitoring data to establish a composition difference array, an affected array and a combined factor set, so as to ensure the accuracy of the prediction of the heat treatment performance of die steel.

[0005] The present invention provides a prediction system for the heat treatment performance of die steel based on big data, comprising:

[0006] A data acquisition module, configured to obtain detailed chemical composition data, production process setting data and production process monitoring data of different batches of steel from die steel manufacturers, and perform data cleaning and preprocessing on the collected data;

[0007] A determination module, configured to determine a composition difference array, an affected array of chemical compositions, process setting parameters and process monitoring parameters based on the preprocessed data, and at the same time, determine a first factor set that affects the heat treatment performance of each batch of steel in the historical actual production process;

[0008] A result prediction module, configured to input the actual obtained parameters of the current die steel into a performance prediction model to determine an initial performance prediction result;

[0009] A result optimization module, configured to optimize the initial performance prediction result based on the composition difference array, the affected array and the first factor set to obtain the current performance prediction result.

[0010] Preferably, the determination module includes:

[0011] A comparative analysis unit, configured to perform a comparative analysis on the historical actual production process and the historical theoretical production process to determine abnormal factors corresponding to abnormal values;

[0012] A statistical unit for statistically analyzing all abnormal factors to obtain a first factor set.

[0013] Preferably, the determining module further includes:

[0014] A component determining unit for determining the production model of die steel, determining the production use based on the production model, and then obtaining the specified component data corresponding to the production model by acquiring the key analysis parameters based on the production use from a use - analysis comparison table, where the key analysis parameters are related to chemical components;

[0015] A process deviation unit for matching and dividing the production process monitoring data of each batch of die steel and the production process setting data according to production stages to determine the actual process deviation set of the second monitoring data , where represents the difference of the j - th process parameter of the corresponding die steel at the corresponding production stage; represents the actual value of the j - th process parameter of the corresponding die steel at the corresponding production stage; represents the standard value of the j - th process parameter of the corresponding die steel at the corresponding production stage; m2 is the total number of process parameters involved in the corresponding production stage;

[0016] A deviation impact unit for determining the deviation impact set of the first monitoring data on the standard process data at the corresponding production stage based on the actual process deviation set , where respectively represent the influence coefficients of the production environment temperature and production environment humidity involved in the corresponding production stage on the j - th process parameter;

[0017] An array construction unit for constructing an affected array of all process parameters involved in each production stage according to the deviation impact set;

[0018] A difference construction unit for extracting the standard component array at the corresponding production stage from the specified component data and comparing it with the historical component array of the corresponding production stage obtained by actual monitoring to obtain a component difference array.

[0019] Preferably, the deviation impact unit includes:

[0020] An array determination subunit for determining the initial array { , } of the first monitoring data at the corresponding production stage;

[0021]

[0022]

[0023]

[0024]

[0025] Among them, represents the judgment influence factor of all production environment temperatures on process parameters in the corresponding first monitoring data; represents the judgment influence factor of all production environment humidities on process parameters in the corresponding first monitoring data; represents the error judgment function of the i1-th production environment temperature in the corresponding production stage; represents the error judgment function of the i2-th production environment humidity in the corresponding production stage; represents the number of production environment temperatures involved in the corresponding production stage, and is the same as the number of production environment humidities; represents that the i1-th production environment temperature continuously stays at the current position in state or continuously stays in state or is continuously in state; represents that the i2-th production environment humidity continuously stays at the current position in state or continuously stays in state or is continuously in state; represents the i1-th production environment temperature; represents the i2-th production environment humidity; , respectively represent the temperature threshold and humidity threshold of the corresponding production stage; , respectively represent the influence amount of the parameter value of the i1-th production environment temperature based on , cases; , respectively represent the influence amount of the parameter value of the i2-th production environment humidity based on , cases.

[0026] Preferably, the deviation influence unit further includes:

[0027] An error adjustment sub-unit for systematically adjusting the difference of the j-th process parameter in the corresponding production stage, and respectively determining the first influence coefficient and the second influence coefficient of the production environment temperature and the production environment humidity on the adjusted difference in combination with the initial array { , }.

[0028] Preferably, the error adjustment sub-unit includes:

[0029] If , assign 1 to the first influence coefficient and the second influence coefficient in the corresponding production stage respectively, and calibrate them to the j-th process parameter, where represents the ratio threshold of the j-th process parameter based on temperature represents the ratio threshold of the j-th process parameter based on humidity represents the value after systematic error adjustment of the difference of the j-th process parameter in the corresponding production stage;

[0030] If , assign 1 to the first influence coefficient in the corresponding production stage, assign 0 to the second influence coefficient respectively, and calibrate them to the j-th process parameter;

[0031] If , assign 0 to the first influence coefficient in the corresponding production stage, assign 1 to the second influence coefficient respectively, and calibrate them to the j-th process parameter;

[0032] If , assign 0 to the first influence coefficient and the second influence coefficient in the corresponding production stage respectively, and calibrate them to the j-th process parameter.

[0033] Preferably, the result optimization module includes:

[0034] A coefficient determination unit, configured to input the composition difference array, the affected array, the first factor set, and the corresponding historical performance results into different performance index models, obtain the coefficients to be optimized of different performance indexes in different production stages, and extract the optimal coefficient and the first variance;

[0035] An optimization unit, configured to perform optimization adjustment on the initial performance values under each performance index according to the minimum coefficient respectively.

[0036] Preferably, the performance indexes include: hardness index, toughness index, and wear resistance index.

[0037] Compared with the prior art, the beneficial effects of the present application are as follows:

[0038] By collecting chemical composition data, production process setting data, and production process monitoring data to establish a composition difference array, an affected array, and combining with a factor set, the initial performance prediction result is optimized to ensure the accuracy of die steel heat treatment performance prediction. Description of the Drawings

[0039] To more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0040] Figure 1 It is a structural diagram of a mold steel heat treatment performance prediction system based on big data provided by an embodiment of the present invention. Detailed implementation manners

[0041] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0042] The present invention provides a mold steel heat treatment performance prediction system based on big data, as Figure 1 shown, including:

[0043] A data acquisition module, configured to obtain detailed chemical composition data, production process setting data, and production process monitoring data of different batches of steel from mold steel manufacturers, and perform data cleaning and preprocessing on the acquired data;

[0044] A determination module, configured to determine an ingredient difference array and an affected array of chemical composition, process setting parameters, and process monitoring parameters based on the preprocessed data. At the same time, determine a first factor set that affects the heat treatment performance of each batch of steel during the historical actual production process;

[0045] A result prediction module, configured to input the actually obtained parameters of the current mold steel into the performance prediction model to determine an initial performance prediction result;

[0046] A result optimization module, configured to optimize the initial performance prediction result based on the ingredient difference array, the affected array, and the first factor set to obtain the current performance prediction result.

[0047] In this embodiment, the chemical composition data includes the content of each trace element in the mold steel. For example, the content of elements such as carbon, chromium, molybdenum, and vanadium.

[0048] The production process setting data includes process parameters such as the theoretical temperature, theoretical time, and theoretical rate in the heating, heat preservation, and cooling stages;

[0049] The production process monitoring data includes process parameters such as the actual temperature, actual time, and actual rate during the heating, heat preservation, and cooling stages, and also includes environmental data, such as humidity data and temperature data of the production die steel at different production stages.

[0050] In this implementation, the performance prediction results are related to the hardness, toughness, wear resistance, etc. of the die steel.

[0051] In this embodiment, data cleaning and preprocessing use data cleaning algorithms to identify and correct error values, missing values, and duplicate values in the data. Standardize data from different sources and formats, unify data units and coding methods, and lay a foundation for subsequent analysis and modeling.

[0052] In this embodiment, the performance prediction model is obtained by training a neural network model with the composition of the new die steel and the proposed process parameters as input samples and the performance prediction values such as hardness, toughness, and wear resistance as output samples. Since environmental-related factors are not considered in this model, relevant composition difference arrays, affected arrays, and the first factor set need to be determined to improve the accuracy of performance result prediction.

[0053] In this embodiment, the heat treatment of die steel includes the following processes:

[0054] Annealing: Heat the steel to a certain temperature and hold for a period of time, then cool it slowly. The purpose is to eliminate tissue defects, improve the tissue to make the composition uniform, refine the grains, improve the mechanical properties of the steel, and reduce residual stress; at the same time, it can reduce hardness, increase plasticity and toughness, and improve machining performance.

[0055] Normalizing: Heat the steel above the critical temperature to transform the steel completely into uniform austenite, and then cool it naturally in the air. It can eliminate the network cementite in hypereutectoid steel. For hypoeutectoid steel, normalizing can refine the crystal lattice, improve the comprehensive mechanical properties, and it is more economical to use normalizing instead of annealing for parts with low requirements.

[0056] Quenching: Heat the steel above the critical temperature, hold for a period of time, and then quickly put it into a quenching agent to suddenly lower its temperature and cool it rapidly at a speed greater than the critical cooling rate to obtain an unbalanced structure mainly composed of martensite. Quenching can increase the strength and hardness of the steel, but reduce its plasticity.

[0057] Tempering: Reheat the quenched steel to a certain temperature and then cool it in a certain way. The purpose is to eliminate the internal stress generated by quenching, reduce hardness and brittleness, and obtain the expected mechanical properties. Tempering is divided into three categories: high-temperature tempering, medium-temperature tempering, and low-temperature tempering, and it is mostly used in combination with quenching and normalizing.

[0058] Surface heat treatment: It includes surface hardening and chemical heat treatment. Surface hardening is to rapidly heat the surface of a steel workpiece to above the critical temperature and then quickly cool it before the heat has time to reach the core, so that the outer layer is quenched into martensite structure while the core remains unchanged; Chemical heat treatment refers to the atoms of chemical elements entering the surface layer of the workpiece by virtue of the atomic diffusion ability at high temperature to change the chemical composition and structure of the surface layer of the workpiece, including carburizing, nitriding, cyaniding, and metal infiltration methods, etc.

[0059] It should be noted that for different types of die steels, such as cold work die steel, hot work die steel, etc., the specific heat treatment process parameters will be different, and reasonable selection and adjustment need to be made according to factors such as the type of steel and the usage requirements of the die.

[0060] The beneficial effects of the above technical solution are: By collecting chemical composition data, production process setting data, and production process monitoring data to establish a composition difference array, an affected array, and combining with a factor set, the initial performance prediction result is optimized to ensure the accuracy of die steel heat treatment performance prediction.

[0061] The present invention provides a system for predicting the heat treatment performance of die steel based on big data. The determination module includes:

[0062] A comparative analysis unit for comparing and analyzing the historical actual production process with the historical theoretical production process to determine the abnormal factors corresponding to the abnormal values;

[0063] A statistics unit for statistically analyzing all abnormal factors to obtain a first factor set.

[0064] In this embodiment, for example, when comparing the working parameters set in the process involved in the heat treatment of die steel with the actual parameters, if the difference between the two is too large, the parameter description of the corresponding set working parameters is regarded as an abnormal factor. For example, during the annealing process, the steel needs to be held at a certain temperature for 10 minutes, but the actual holding time is 8 minutes, resulting in an increase in hardness. At this time, the holding time involved in the annealing process is regarded as an abnormal factor.

[0065] In this embodiment, the first factor set = {all abnormal factors}.

[0066] The beneficial effects of the above technical solution are: By comparing the historical actual production process with the theoretical production process, abnormal factors are determined, providing a basis for optimizing the initial prediction performance result subsequently.

[0067] The present invention provides a system for predicting the heat treatment performance of die steel based on big data. The determination module further includes:

[0068] A composition determination unit, configured to determine the production model of the die steel, determine the production use based on the production model, and then obtain the key analysis parameters based on the production use from a use - analysis comparison table, so as to obtain the specified composition data corresponding to the production model, where the key analysis parameters are related to chemical components;

[0069] A process deviation unit, configured to match and divide the production process monitoring data of each batch of die steel and the production process setting data according to the production stage to determine the actual process deviation set of the second monitoring data , where represents the difference of the j - th process parameter of the corresponding die steel at the corresponding production stage; represents the actual value of the j - th process parameter of the corresponding die steel at the corresponding production stage; represents the standard value of the j - th process parameter of the corresponding die steel at the corresponding production stage; m2 is the total number of process parameters involved in the corresponding production stage;

[0070] A deviation impact unit, configured to determine the deviation impact set of the first monitoring data on the standard process data at the corresponding production stage based on the actual process deviation set , where respectively represent the influence coefficients of the production environment temperature and production environment humidity involved in the corresponding production stage on the j - th process parameter;

[0071] An array construction unit, configured to construct an affected array of all process parameters involved in each production stage according to the deviation impact set;

[0072] A difference construction unit, configured to extract the standard composition array at the corresponding production stage from the specified composition data and compare it with the historical composition array of the corresponding production stage obtained by actual monitoring to obtain a composition difference array.

[0073] In this embodiment, for example, the standard composition array extracted at production stage 1 is {u1, u2}, and at this time, the actually monitored historical composition array is {r1, r2}, and then the composition difference array is: {u1 - r1, u2 - r2}.

[0074] In this embodiment, the use - analysis comparison table contains parameters related to chemical components under different production uses. For example, for the steel material used for house building (production use), the carbon component is u1, the chromium component is u2, the molybdenum component is u3, the vanadium component is u4, and the remaining chemical components can be ignored (specified composition data), where the key analysis parameters are: carbon component, chromium component, molybdenum component, and vanadium component.

[0075] In this embodiment, the production model refers to the unique code of the corresponding die steel.

[0076] In this embodiment, since a batch of die steel production goes through different process flows, there are multiple production stages.

[0077] In this embodiment, for the production processes of different batches of die steel, there are corresponding standard values for the process parameters, which are preset and can be directly retrieved for use because the firing standards for different types of die steel are unified.

[0078] In this embodiment, the actual value refers to the value actually monitored during the historical process.

[0079] In this embodiment, the number of process parameters is at least greater than 3.

[0080] In this embodiment, They are the first influence coefficient and the second influence coefficient obtained subsequently.

[0081] In this embodiment, the affected array = {the deviation influence set under all process parameters in each production stage}.

[0082] The beneficial effects of the above technical solution are: determining the production model to obtain the specified composition data provides a comparison basis for obtaining the composition difference data, and constructing the affected array by determining the actual process deviation set and the deviation influence set on the standard process data. The combination of the two provides a basis for subsequent prediction and adjustment, ensuring the accuracy of the prediction.

[0083] The present invention provides a die steel heat treatment performance prediction system based on big data. The deviation influence unit includes:

[0084] An array determination subunit for determining the initial array of the first monitoring data corresponding to the production stage { , };

[0085]

[0086]

[0087]

[0088]

[0089] Among them, represents the judgment influence factor of all production environment temperatures on the process parameters in the corresponding first monitoring data; represents the judgment influence factor of all production environment humidities on the process parameters in the corresponding first monitoring data; represents the error judgment function of the i1th production environment temperature in the corresponding production stage; Denote the error evaluation function of the humidity of the i2-th production environment in the corresponding production stage; Denote the number of production environment temperatures involved in the corresponding production stage, which is the same as the number of production environment humidities; Denote that the i1-th production environment temperature continuously remains at the current position The continuous quantity of the state or continuously remains in The continuous quantity of the state or alternatively continuously remains in The continuous quantity of the state; Denote that the i2-th production environment humidity continuously remains at the current position The continuous quantity of the state or continuously remains in The continuous quantity of the state or alternatively continuously remains in The continuous quantity of the state; Denote the i1-th production environment temperature; Denote the i2-th production environment humidity; , Denote the temperature threshold and humidity threshold of the corresponding production stage respectively; , Denote the influence amount of the parameter value of the i1-th production environment temperature based on , The case of the influence amount; , Denote the influence amount of the parameter value of the i2-th production environment humidity based on , The case of the influence amount.

[0090] In this embodiment, for example, The moments are: moment 1, moment 2, moment 5, The moment of = 2.

[0091] The beneficial effects of the above technical solution are: starting from the environmental temperature and environmental humidity, determining the evaluation influence factors of the temperature and humidity in the production stage on the process parameters respectively, comparing and analyzing with the actual influence generated, further verifying the true and false influence of the temperature and humidity on the corresponding parameters in different production stages, and providing an analysis basis for subsequent prediction.

[0092] The present invention provides a die steel heat treatment performance prediction system based on big data. The deviation influence unit further includes:

[0093] An error adjustment sub-unit for performing systematic error adjustment on the difference of the j-th process parameter in the corresponding production stage, and combining with the initial array { , }Determine the first influence coefficient and the second influence coefficient of the production environment temperature and the production environment humidity on the adjusted difference respectively.

[0094] Preferably, the error adjustment subunit includes:

[0095] If , assign 1 to the first influence coefficient and the second influence coefficient in the corresponding production stage respectively, and calibrate them to the j-th process parameter, where represents the ratio threshold of the j-th process parameter based on temperature represents the ratio threshold of the j-th process parameter based on humidity represents the value after systematic error adjustment of the difference of the j-th process parameter in the corresponding production stage;

[0096] If , assign 1 to the first influence coefficient and 0 to the second influence coefficient in the corresponding production stage respectively, and calibrate them to the j-th process parameter;

[0097] If , assign 0 to the first influence coefficient and 1 to the second influence coefficient in the corresponding production stage respectively, and calibrate them to the j-th process parameter;

[0098] If , assign 0 to the first influence coefficient and the second influence coefficient in the corresponding production stage respectively, and calibrate them to the j-th process parameter.

[0099] In this embodiment, = / (1 - systematic error), where the systematic error is an inherent error and a fixed value that cannot be eliminated, where represents the difference of the j-th process parameter in the corresponding production stage; represents the value after systematic error adjustment of the difference of the j-th process parameter in the corresponding production stage.

[0100] The beneficial effects of the above technical solutions are: by calculating the ratios of temperature and humidity, influence coefficients based on temperature and humidity are assigned to process parameters, providing variables for constructing the affected array.

[0101] The present invention provides a die steel heat treatment performance prediction system based on big data. The result optimization module includes:

[0102] A coefficient determination unit, configured to input the composition difference array, the affected array, the first factor set, and the corresponding historical performance results into different performance index models, obtain the coefficients to be optimized of different performance indexes in different production stages, and extract the optimal coefficient and the first variance;

[0103] Optimization unit, configured to optimize and adjust the initial performance values under each performance index according to the respective minimum coefficients.

[0104] Preferably, the performance indexes include: hardness index, toughness index, and wear resistance index.

[0105] In this embodiment, if a complex non-linear prediction model is constructed using a neural network, through training with a large amount of historical data, learning the composition difference array, affected array, first factor set, and the prediction performance, actual performance, and coefficients to be optimized of relevant history among chemical composition, process parameters, and monitoring parameters, different performance index models can be obtained, and then the corresponding coefficients to be optimized can be directly obtained.

[0106] Since there is a coefficient to be optimized in each production stage, but to ensure the reliability of the calculation, the coefficient closest to 0 is selected and added to the first variance to optimize and adjust the initial performance, that is, the adjusted performance value = initial performance value × (1 + optimal coefficient + first variance). For example, if the obtained coefficients to be optimized are: -0.1, -0.05, 1, at this time, -0.05 is the closest to 0, so -0.05 is regarded as the optimal coefficient, and the first variance is the variance of the coefficients to be optimized in different production stages corresponding to the performance index.

[0107] The beneficial effects of the above technical solution are: by inputting the composition difference array, affected array, first factor set, and historical performance results into the model to obtain the optimal coefficient and the first variance for this index, optimization and adjustment are realized, ensuring the accuracy of performance result prediction.

[0108] 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 foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A die steel heat treatment performance prediction system based on big data, characterized in that: include: The data acquisition module is used to obtain detailed chemical composition data, production process setting data and production process monitoring data of different batches of steel from mold steel manufacturers, and to clean and preprocess the collected data; A determination module, used for determining the chemical composition, the composition difference array of the process setting parameters and the process monitoring parameters and the affected array based on the pre-processed data, and at the same time, determining the first factor set affecting the heat treatment performance of each batch of steel in the historical actual production process; The result prediction module is used to input the actual acquired parameters of the current mold steel into the performance prediction model to determine the initial performance prediction results; A result optimization module, configured to optimize the initial performance prediction result based on the component difference array, the affected array and the first factor set to obtain a current performance prediction result; The affected array is the deviation impact set of all process parameters in each production stage. ,in, They respectively represent the influence coefficients of the production environment temperature and the production environment humidity involved in the corresponding production stage on the jth process parameter; m2 is the total number of process parameters involved in the corresponding production stage.

2. The die steel heat treatment performance prediction system based on big data according to claim 1 is characterized in that: The determining module comprises: A comparison and analysis unit, used to compare and analyze the historical actual production process with the historical theoretical production process, and determine the abnormal factors corresponding to the abnormal values; The statistical unit is used to count all abnormal factors to obtain a first factor set.

3. The die steel heat treatment performance prediction system based on big data according to claim 1 is characterized in that: The determining module further includes: A composition determination unit is used to determine the production model of the die steel, and determine the production purpose based on the production model, and then obtain key analysis parameters based on the production purpose from the purpose-analysis comparison table to obtain the specified composition data corresponding to the production model, wherein the key analysis parameters are related to the chemical composition; The process deviation unit is used to match and divide the production process monitoring data of each batch of mold steel with the production process setting data according to the production stage to determine the actual process deviation set of the second monitoring data. ,in, It represents the difference of the jth process parameter of the corresponding mold steel at the corresponding production stage; Represents the actual value of the jth process parameter of the corresponding mold steel at the corresponding production stage; Indicates the standard value of the jth process parameter of the corresponding mold steel at the corresponding production stage; A deviation impact unit, configured to determine a deviation impact set of the first monitoring data on the standard process data in the corresponding production stage based on the actual process deviation set; An array construction unit, used to construct an affected array of all process parameters involved in each production stage according to the deviation impact set; The difference construction unit is used to extract the standard component array under the corresponding production stage from the specified component data to compare with the historical component array of the corresponding production stage obtained by actual monitoring to obtain a component difference array.

4. The die steel heat treatment performance prediction system based on big data according to claim 3 is characterized in that: The deviation influencing unit comprises: An array determination subunit, used to determine an initial array of the first monitoring data corresponding to the production stage { , }; in, Indicates the evaluation influence factor of all production environment temperatures on process parameters corresponding to the first monitoring data; Indicates the evaluation influence factor of all production environment humidity on process parameters corresponding to the first monitoring data; represents the error judgment function of the i1th production environment temperature in the corresponding production stage; represents the error judgment function of the humidity of the i2th production environment in the corresponding production stage; Indicates the number of production environment temperatures involved in the corresponding production stage, and is consistent with the number of production environment humidity; Indicates that the temperature of the i1th production environment is continuously at the current location The number of consecutive states or the duration of The number of consecutive states or the number of consecutive The number of consecutive states; Indicates that the humidity of the i2nd production environment is continuously at the current position The number of consecutive states or the duration of The number of consecutive states or the number of consecutive The number of consecutive states; Indicates the temperature of the i1th production environment; Indicates the humidity of the i2th production environment; , They represent the temperature threshold and humidity threshold of the corresponding production stage respectively; , Respectively represent the i1th production environment temperature based on , The influence of parameter values ​​in different situations; , Respectively represent the humidity of the i2th production environment based on , The parameter value affects the amount of influence in the case.

5. The die steel heat treatment performance prediction system based on big data according to claim 4 is characterized in that: The deviation influencing unit further includes: The error adjustment subunit is used to perform system error adjustment on the difference of the jth process parameter in the corresponding production stage, and combines the initial array { , }Respectively determine the first influence coefficient and the second influence coefficient of the production environment temperature and the production environment humidity on the adjusted difference.

6. The die steel heat treatment performance prediction system based on big data according to claim 5 is characterized in that: The error adjustment subunit comprises: like , assign 1 to the first influence coefficient and the second influence coefficient in the corresponding production stage respectively, and calibrate them to the jth process parameter, where, Indicates the ratio threshold of the jth process parameter based on temperature The adjustment coefficient of Indicates the ratio threshold of the jth process parameter based on humidity The adjustment coefficient of It represents the value after the system error adjustment of the difference of the jth process parameter in the corresponding production stage; like , assign 1 to the first influence coefficient and 0 to the second influence coefficient in the corresponding production stage, and calibrate them to the jth process parameter; like , assign 0 to the first influence coefficient and 1 to the second influence coefficient in the corresponding production stage, and calibrate them to the jth process parameter; like , assign 0 to the first influence coefficient and the second influence coefficient in the corresponding production stage respectively, and calibrate them to the jth process parameter.

7. The die steel heat treatment performance prediction system based on big data according to claim 1 is characterized in that: The result optimization module comprises: A coefficient determination unit, used for inputting the component difference array, the affected array, the first factor set and the corresponding historical performance results into different performance indicator models, obtaining coefficients to be optimized for different performance indicators at different production stages, and extracting the optimal coefficient and the first variance; The optimization unit is used to optimize and adjust the initial performance value under each performance indicator according to the optimal coefficient.

8. The die steel heat treatment performance prediction system based on big data according to claim 7 is characterized in that: The performance indicators include: hardness index, toughness index and wear resistance index.

Images