Aluminum smelting product quality monitoring and traceability method and system based on big data modeling

Abstract

The invention discloses a method and system for monitoring and tracing the quality of aluminum smelting products based on big data modeling, and belongs to the technical field of quality monitoring and data tracing. The method specifically comprises: collecting key parameter data in the aluminum smelting process in real time through a sensor network, including temperature, pressure, component concentration and cooling rate, preprocessing the collected key parameter data in the aluminum smelting process, establishing a big data model for aluminum smelting products, detecting and analyzing the quality of aluminum smelting products in real time, setting a quality threshold, and determining that the quality of the aluminum smelting products is unqualified when the detection and analysis results exceed the quality threshold, performing traceability analysis based on historical data in the big data model for aluminum smelting products, analyzing the reasons for the unqualified quality of aluminum smelting products, and tracing back to specific process links, optimizing the key parameters in the traced process links based on the traceability results, tracing back the key factors affecting product quality, thereby improving product quality.

Description

Technical Field

[0001] The present invention belongs to the technical field of quality monitoring and data traceability, and specifically is a method and system for quality monitoring and traceability of aluminum smelting products based on big data modeling. Background Art

[0002] The existing quality monitoring and traceability methods for aluminum smelting products mainly rely on manual inspection and recording. This method has problems such as limited data volume, poor real-time performance, and difficulty in comprehensive coverage. It cannot meet the efficient and refined management needs of modern aluminum smelting processes. With the development of big data technology, the use of big data modeling technology to conduct comprehensive and real-time monitoring and traceability of the aluminum smelting process has become a research focus. However, there are still some defects in the comprehensive and real-time monitoring and traceability of the aluminum smelting process.

[0003] For example, a Chinese patent with authorization announcement number CN112101439B discloses a method for diagnosing and tracing the quality defects of high-speed wire rods based on a distributed Bayesian network. This method first collects the normal operating data of the steel high-speed wire rolling process, combines the process mechanism and the production process big data, decomposes the entire production process into several sections, and then constructs a distributed Bayesian network with a multi-layer structure based on data characteristics and process knowledge, and constructs local monitoring statistics, global monitoring statistics, local contribution and global contribution, and finally realizes the diagnosis and tracing of high-speed wire rod quality defects through information fusion. The application of this invention can realize the deep-level quality anomaly tracing, propagation path analysis and root cause location of the high-speed wire rolling process, and ensure the safe and stable operation of the high-speed wire rolling process.

[0004] For example, the Chinese patent with publication number CN118195641A discloses a blockchain-based full-process traceability method for the field of intelligent manufacturing. This method obtains the smoothed independent components of each independent component of the monitoring data sequence to be processed at different smoothness levels, and determines the optimal smoothness of each independent component according to the smoothing rationality of each independent component at different smoothness levels, the non-abnormal degree of each data point in the smoothed independent component at different smoothness levels, and the distribution difference between the independent component at different smoothness levels and the corresponding independent component, and obtains the processed monitoring data sequence for production traceability. This invention effectively improves the accuracy of production traceability by improving the quality of monitoring data.

[0005] The defects of the above patent: there may be larger or smaller fluctuations between the normal operating data, and it is impossible to make a judgment under special circumstances, resulting in the inability to trace the aluminum smelting back to a certain parameter in a specific production link. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention proposes an aluminum smelting product quality monitoring and traceability method and system based on big data modeling. Key parameter data of the aluminum smelting process are collected in real time through a sensor network, including temperature, pressure, component concentration and cooling rate. The collected key parameter data of the aluminum smelting process are preprocessed, and a big data model of aluminum smelting products is established. The quality of aluminum smelting products is detected and analyzed in real time, and a quality threshold is set. When the detection and analysis results exceed the quality threshold, the quality of the aluminum smelting products is determined to be unqualified. Tracing analysis is performed based on historical data in the big data model of aluminum smelting products, the reasons for the unqualified quality of aluminum smelting products are analyzed, and the data are traced back to specific process links. Based on the traceability results, the key parameters in the traced process links are optimized.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] Aluminum smelting product quality monitoring and traceability method based on big data modeling, including:

[0009] The sensor network collects real-time data on key parameters in the aluminum smelting process, including temperature, pressure, component concentration and cooling rate;

[0010] Pre-process the collected data of key parameters in the aluminum smelting process;

[0011] Establish a big data model for aluminum smelting products to conduct real-time detection and analysis of the quality of aluminum smelting products;

[0012] Set a quality threshold. When the test and analysis results exceed the quality threshold, the aluminum smelting product is judged to be unqualified. According to the historical data in the big data model of aluminum smelting products, traceability analysis is carried out to analyze the reasons for the unqualified quality of aluminum smelting products and trace them back to specific process links;

[0013] Based on the traceability results, key parameters in the traceable process are optimized.

[0014] Specifically, the establishment of a big data model for aluminum smelting products to perform real-time detection and analysis of the quality of aluminum smelting products includes:

[0015] Set the collected aluminum smelting furnace temperature set as T, the aluminum smelting furnace pressure set as P, the aluminum smelting product chemical composition set as C, and the aluminum smelting product cooling rate as v;

[0016] A big data model for aluminum smelting products is established to evaluate the quality of aluminum smelting products. The specific formula of the big data model for aluminum smelting products is:

[0017] ,

[0018] Among them, Q represents the big data model of aluminum smelting products, that is, the quality of aluminum smelting products smelted by the s-th aluminum smelting furnace, represents the intercept term, which is a constant term, and n represents the total number of the sth aluminum smelting furnace temperature power terms. represents the ith power of the sth aluminum smelting furnace temperature, represents the coefficient of the sth aluminum smelting furnace temperature i-th power, m represents the total number of pressure power items of the sth aluminum smelting furnace, represents the jth power of the pressure of the sth aluminum smelting furnace, represents the coefficient of the jth power of the pressure of the sth aluminum smelting furnace, q represents the total number of chemical components of the aluminum smelting product smelted by the sth aluminum smelting furnace, It represents the content of the kth item of chemical composition of the aluminum smelting product smelted by the sth aluminum smelting furnace. Indicates chemical composition The coefficient of The coefficient representing the cooling rate of the aluminum smelting product smelted by the s-th aluminum smelting furnace, The coefficient that represents the interaction between temperature, pressure and chemical composition in the aluminum smelting process. represents the error term.

[0019] Specifically, the influence coefficient of the interaction between temperature, pressure and chemical composition in the aluminum smelting process is The specific formula is:

[0020] ,

[0021] in, It represents the interaction coefficient of temperature, pressure and chemical composition in the aluminum smelting process.

[0022] Specifically, the traceability analysis based on the historical data in the big data model of aluminum smelting products includes:

[0023] Set the quality threshold to Q yz , when the quality of aluminum smelting product a after smelting is less than the quality threshold Q yz When the aluminum smelting product a is judged to be unqualified in quality;

[0024] Assume that the aluminum smelting product set is A, and the key parameter set when the aluminum smelting product is completed is S. A , calculate the set of key parameters S when the aluminum smelting product set A is completed A The correlation between each parameter and product quality is calculated as follows:

[0025] ,

[0026] Among them, r xy The set S represents the key parameters of the aluminum smelting product set A when smelting is completed. AThe correlation between each parameter and product quality, x ef Indicates S A The fth parameter value of the eth aluminum smelting product in, Indicates S A The average value of the fth parameter in Q e represents the quality of the e-th aluminum smelting product, It represents the mean value of the quality of aluminum smelting products;

[0027] Trace the unqualified aluminum smelting products and establish a time series model. The specific formula is:

[0028] ,

[0029] Among them, y t is a time series model, represents a constant term, describing the intercept or baseline level of the time series model, represents the autoregressive coefficient, i.e., the influence coefficient of the past values ​​of aluminum smelting product quality, h represents the number of past values ​​of aluminum smelting product quality, y t-g represents the hysteresis value of aluminum smelting product quality at time t−g, It represents the coefficient of key parameters in the smelting process of aluminum smelting products, that is, the coefficient of influence of key parameters in the smelting process of aluminum smelting products on product quality, x t-l represents the lag value of the key parameters in the smelting process of aluminum smelting products at time t−l, represents the key parameters in the smelting process of aluminum smelting products at the past time point, represents the error term.

[0030] Specifically, the analysis of the reasons for the substandard quality of aluminum smelting products and tracing back to specific process links include:

[0031] According to the time series model, the abnormal time point and key parameters of the process link in the smelting process are traced back to when the aluminum smelting products are unqualified. The abnormal time point of the process link in the smelting process of aluminum smelting products is set as J, and the corresponding key parameter set is S J ;

[0032] Extract the characteristics that have the greatest impact on the quality of aluminum smelting products, that is, the categories of key parameters. The specific formula is:

[0033] ,

[0034] Among them, tz represents the feature that has the greatest impact on the quality of aluminum smelting products, N represents the set of features, that is, the key parameters of aluminum smelting products, N(\d) represents the feature set that does not contain feature d, S represents the subset of the set N(\d), |S| represents the number of features in the subset S, |N| represents the number of features in the set N, ! represents factorial, min represents the minimum value function, f(S) represents the value function output using the subset S, Represents the value function output when using subset S and feature d.

[0035] Specifically, the preprocessing includes: data cleaning, missing value processing and removal of redundant values.

[0036] The aluminum smelting product quality monitoring and traceability system based on big data modeling is used to implement the aluminum smelting product quality monitoring and traceability method based on big data modeling, including: a data acquisition module, a preprocessing module, a model building module, a traceability module and an optimization module;

[0037] The data acquisition module is used to collect key parameter data in the aluminum smelting process in real time through a sensor network, including: temperature, pressure, component concentration and cooling rate;

[0038] The preprocessing module is used to preprocess the key parameter data collected during the aluminum smelting process;

[0039] The model building module is used to build a big data model of aluminum smelting products and perform real-time detection and analysis on the quality of aluminum smelting products;

[0040] The traceability module is used to set a quality threshold. When the detection and analysis results exceed the quality threshold, the quality of the aluminum smelting product is judged to be unqualified. The traceability analysis is performed based on the historical data in the aluminum smelting product big data model to analyze the reasons for the unqualified quality of the aluminum smelting product and trace it back to the key parameters in the specific process links;

[0041] The optimization module is used to optimize key parameters in the traced process based on the traceability results.

[0042] Specifically, the traceability module includes: a product traceability unit and a key parameter traceability unit;

[0043] The product traceability unit is used to trace the stage where the aluminum smelting products are unqualified, that is, to trace them back to the process link;

[0044] The key parameter traceability unit is used to extract the features that have the greatest impact on the traced process links.

[0045] An electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of a method for quality monitoring and tracing of aluminum smelting products based on big data modeling when executing the computer program.

[0046] A computer-readable storage medium stores computer instructions, which, when executed, execute the steps of a method for quality monitoring and tracing of aluminum smelting products based on big data modeling.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The present invention proposes an aluminum smelting product quality monitoring and traceability method based on big data modeling. Through big data technology, various parameters in the aluminum smelting process, such as temperature, pressure, chemical composition, etc., can be monitored and analyzed in real time, deviations can be discovered and corrected in time, and the stability and consistency of product quality can be ensured.

[0049] 2. The present invention proposes an aluminum smelting product quality monitoring and traceability method based on big data modeling. By using the data analysis model, the key factors affecting product quality can be traced back, and the production process can be optimized and adjusted to improve product quality.

[0050] 3. The present invention proposes an aluminum smelting product quality monitoring and traceability method based on big data modeling. Through precise quality control and process optimization, it can significantly reduce the scrap rate, reduce raw material and energy consumption, optimize production processes and resource allocation, reduce unnecessary expenses, and improve overall production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A flow chart of the aluminum smelting product quality monitoring and traceability method based on big data modeling provided by the present invention;

[0052] Figure 2 This is an architecture diagram of the aluminum smelting product quality monitoring and traceability system based on big data modeling provided by the present invention;

[0053] Figure 3 A schematic diagram of an electronic device provided by the present invention;

[0054] Figure 4 A schematic diagram of the computer-readable storage medium structure provided by the present invention. DETAILED DESCRIPTION

[0055] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, in the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside" and the like indicate the orientation or position relationship based on the orientation or position relationship shown in the accompanying drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "No. 1", "No. 2" and "No. 3" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. The present invention is further explained below in conjunction with specific embodiments.

[0056] Example 1

[0057] See also Figure 1 The present invention provides an embodiment: a method for monitoring and tracing the quality of aluminum smelting products based on big data modeling, comprising the following specific steps:

[0058] Step S1: collecting data of key parameters in the aluminum smelting process in real time through a sensor network, including but not limited to temperature, pressure, component concentration, current, voltage, cooling rate, etc.;

[0059] Through the sensors and automated control systems deployed at the production site, data from the aluminum smelting production process is collected in real time, and the data is transmitted to the data center through wired or wireless communication technology;

[0060] Step S2: preprocessing the collected data, including data cleaning, missing value processing, data standardization, etc., to ensure the accuracy and consistency of the data;

[0061] Step S3: Establishing a big data model for aluminum smelting products to conduct real-time detection and analysis of the quality of aluminum smelting products;

[0062] The specific steps of step S3 are:

[0063] Step S301: set the collected aluminum smelting furnace temperature set as T, the aluminum smelting furnace pressure set as P, the aluminum smelting product chemical composition set as C, and the aluminum smelting product cooling rate as v;

[0064] The above data include data during the smelting process and at the completion of smelting. When building the model below, the data at the completion of smelting is used. The data during the smelting process is used for: tracing the source, in order to trace which parameters of the unqualified aluminum smelting products deviate during the smelting process, resulting in unqualified aluminum smelting products when they are completed;

[0065] Step S302: Establish a big data model for aluminum smelting products to evaluate the quality of aluminum smelting products. The specific formula of the big data model for aluminum smelting products is:

[0066] ,

[0067] Among them, Q represents the big data model of aluminum smelting products, that is, the quality of aluminum smelting products smelted by the s-th aluminum smelting furnace, represents the intercept term, which is a constant term, and n represents the total number of the sth aluminum smelting furnace temperature power terms. represents the ith power of the sth aluminum smelting furnace temperature, represents the coefficient of the sth aluminum smelting furnace temperature i-th power, m represents the total number of pressure power items of the sth aluminum smelting furnace, represents the jth power of the pressure of the sth aluminum smelting furnace, represents the coefficient of the jth power of the pressure of the sth aluminum smelting furnace, q represents the total number of chemical components of the aluminum smelting product smelted by the sth aluminum smelting furnace, It represents the content of the kth item of chemical composition of the aluminum smelting product smelted by the sth aluminum smelting furnace. Indicates chemical composition The coefficient of The coefficient representing the cooling rate of the aluminum smelting product smelted by the s-th aluminum smelting furnace, The coefficient that represents the interaction between temperature, pressure and chemical composition in the aluminum smelting process. represents the error term.

[0068] It represents the base value of quality when there is no influence of other variables. It represents the influence of temperature at time s on the quality of aluminum smelting products, taking into account the different powers of temperature (i ranges from 1 to n), each power term has a corresponding coefficient, It reflects the influence of different temperature powers on quality. It represents the influence of pressure at time s on the quality of aluminum smelting products, taking into account the different powers of pressure (j ranges from 1 to m), each power term has a corresponding coefficient, It reflects the influence of different pressure powers on quality. Reflects the influence of chemical composition on quality. Reflects the effect of cooling rate on quality. It represents the partial error fluctuation of the model, reflecting the impact of random errors or unconsidered factors on the quality threshold;

[0069] The interaction coefficients of temperature, pressure and chemical composition in aluminum smelting process The specific formula is:

[0070] ,

[0071] in, It represents the interaction coefficient of temperature, pressure and chemical composition in the aluminum smelting process, reflecting the complex interactive effects between these variables.

[0072] In the aluminum smelting process, chemical composition refers to the various elements contained in the aluminum alloy. The content and proportion of these elements will directly affect the quality and performance of the final product. Common chemical compositions include but are not limited to the following: Aluminum (Al): base metal, the main component of aluminum alloy; Silicon (Si): usually added to improve casting performance and hardness, but too much will reduce ductility; Copper (Cu): increase strength and hardness, but excessive amount will affect corrosion resistance; Magnesium (Mg): significantly improves the strength and hardness of the alloy while maintaining good weldability and corrosion resistance; Zinc (Zn): used to improve strength and hardness, but the content needs to be controlled to avoid stress corrosion cracking; Manganese (Mn): used to improve strength and corrosion resistance, commonly found in aluminum-magnesium-silicon alloys; Iron (Fe): usually an impurity element, and its content needs to be controlled to avoid affecting the performance of the alloy; Titanium (Ti): used to refine the grain structure and improve mechanical properties; Chromium (Cr): improves corrosion resistance and oxidation resistance; Lithium (Li): reduces density and increases elastic modulus, often used in high-strength and lightweight applications;

[0073] For example: if C1 represents the silicon (Si) content, γ1 represents the influence coefficient of silicon content on the quality of aluminum alloy (such as purity and hardness);

[0074] If C2 represents the magnesium (Mg) content, γ2 represents the influence coefficient of magnesium content on the quality of aluminum alloy;

[0075] The ratio and content of these chemical components have an important influence on the quality of aluminum alloys, so the content of each component needs to be accurately controlled and monitored during the smelting process;

[0076] Step S4: setting a quality threshold. When the detection and analysis results exceed the quality threshold, the quality of the aluminum smelting product is judged to be unqualified. The traceability analysis is performed based on the historical data in the big data model of the aluminum smelting product to analyze the reasons for the unqualified quality of the aluminum smelting product and trace it back to the specific process link.

[0077] The specific steps of step S4 are:

[0078] Step S401: Set the quality threshold to Q yz , when the quality of aluminum smelting product a after smelting is less than the quality threshold Q yz When the aluminum smelting product a is judged to be unqualified in quality;

[0079] Step S402: Set the aluminum smelting product set as A, and the key parameter set when the aluminum smelting product is completed as S A , calculate the set of key parameters S when the aluminum smelting product set A is completed A The correlation between each parameter and product quality is calculated as follows:

[0080] ,

[0081] Among them, r xy The set S represents the key parameters of the aluminum smelting product set A when smelting is completed. A The correlation between each parameter and product quality, x ef Indicates S A The fth parameter value of the eth aluminum smelting product in, Indicates S A The average value of the fth parameter in Q e represents the quality of the e-th aluminum smelting product, It represents the mean value of the quality of aluminum smelting products;

[0082] Step S403: trace the source of unqualified aluminum smelting products and establish a time series model. The specific formula is:

[0083] ,

[0084] Among them, y t is a time series model, representing the quality of aluminum smelting products at time t (e.g. qualified or unqualified), Represents a constant term that describes the intercept or baseline level of the time series model. It is a fixed value used to adjust the benchmark value of the time series model. represents the autoregressive coefficient, i.e., the coefficient of influence of the past value of aluminum smelting product quality, The larger the value, the greater the impact of the past value of aluminum smelting product quality on the current value. h represents the number of past values ​​of aluminum smelting product quality, y t-g represents the hysteresis value of aluminum smelting product quality at time t−g, It indicates the coefficient of key parameters in the smelting process of aluminum smelting products, that is, the coefficient of influence of key parameters in the smelting process of aluminum smelting products on product quality. The larger the value is, the greater the impact of key parameters in the smelting process of aluminum smelting products on the quality of aluminum smelting products. t-l represents the lag value of the key parameters in the smelting process of aluminum smelting products at time t−l, represents the key parameters (such as temperature, pressure, etc.) in the smelting process of aluminum smelting products at the past time point, represents the error term;

[0085] Step S404: According to the time series model, trace back to the time point and key parameters of the abnormal process link in the smelting process when the aluminum smelting product is unqualified, set the time point of the abnormal process link in the smelting process of the aluminum smelting product as J, and the corresponding key parameter set as S J , extract the characteristics that have the greatest impact on the quality of aluminum smelting products, that is, the category of key parameters. The specific formula is:

[0086] ,

[0087] Among them, tz represents the feature that has the greatest impact on the quality of aluminum smelting products, N represents the set of features, that is, the key parameters of aluminum smelting products, N(\d) represents the feature set that does not contain feature d, S represents the subset of the set N(\d), |S| represents the number of features in the subset S, |N| represents the number of features in the set N, ! represents factorial, min represents the minimum value function, f(S) represents the value function output using the subset S, Represents the value function output when using subset S and feature d.

[0088] Step S5: Based on the traceability results, optimize key parameters to reduce the generation of unqualified products.

[0089] The traceability result is that there is a deviation in the key parameter tz at time point J, which includes all the time and key parameters when the aluminum smelting product is unqualified during the smelting process.

[0090] Example 2

[0091] See also Figure 2 Another embodiment provided by the present invention is an aluminum smelting product quality monitoring and traceability system based on big data modeling, comprising:

[0092] Data acquisition module, preprocessing module, model building module, traceability module and optimization module;

[0093] The data acquisition module is used to collect key parameter data in the aluminum smelting process in real time through a sensor network, including: temperature, pressure, component concentration and cooling rate;

[0094] The preprocessing module is used to preprocess the key parameter data collected during the aluminum smelting process;

[0095] The model building module is used to build a big data model of aluminum smelting products and perform real-time detection and analysis on the quality of aluminum smelting products;

[0096] The traceability module is used to set a quality threshold. When the detection and analysis results exceed the quality threshold, the quality of the aluminum smelting product is judged to be unqualified. The traceability analysis is performed based on the historical data in the aluminum smelting product big data model to analyze the reasons for the unqualified quality of the aluminum smelting product and trace it back to the key parameters in the specific process links;

[0097] The optimization module is used to optimize key parameters in the traced process based on the traceability results.

[0098] The traceability module includes: product traceability unit and key parameter traceability unit;

[0099] The product traceability unit is used to trace the stage where the aluminum smelting products are unqualified, that is, to trace them back to the process link;

[0100] The key parameter traceability unit is used to extract the features that have the greatest impact on the traced process links.

[0101] Example 3

[0102] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3 As shown, according to another aspect of the present application, an electronic device 500 is also provided. The electronic device 500 may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are executed by one or more processors, the aluminum smelting product quality monitoring and traceability method based on big data modeling can be executed.

[0103] The method or system according to the embodiment of the present application can also be used by Figure 3 The electronic device architecture shown in FIG. Figure 3As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, ROM 503, RAM 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as ROM 503 or hard disk 507, may store the aluminum smelting product quality monitoring and traceability method based on big data modeling provided in the present application. The aluminum smelting product quality monitoring and traceability method based on big data modeling may, for example, include: collecting key parameter data in the aluminum smelting process in real time through a sensor network, including: temperature, pressure, component concentration and cooling rate, preprocessing the collected key parameter data in the aluminum smelting process, establishing a big data model for aluminum smelting products, performing real-time detection and analysis on the quality of aluminum smelting products, setting a quality threshold, and when the detection and analysis results exceed the quality threshold, determining that the quality of the aluminum smelting product is unqualified, and performing traceability analysis based on historical data in the big data model for aluminum smelting products, analyzing the reasons for the unqualified quality of aluminum smelting products, and tracing back to specific process links, and optimizing the key parameters in the traced process links based on the traceability results. Furthermore, the electronic device 500 may also include a user interface 508. Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0104] Example 4

[0105] Figure 4 Schematic diagram of a computer-readable storage medium structure provided by an embodiment of the present application. Figure 4 As shown, it is a computer-readable storage medium 600 according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, the aluminum smelting product quality monitoring and traceability method based on big data modeling according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache). Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0106] It should be understood that the methods, apparatuses, and devices of the present application can be implemented in many ways. For example, the methods, apparatuses, and devices of the present application can be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is only for illustration, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application can also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers a recording medium storing a program for executing the method according to the present application.

[0107] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0108] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. Aluminum smelting product quality monitoring and traceability method based on big data modeling, characterized in that: include: The sensor network collects real-time data on key parameters in the aluminum smelting process, including temperature, pressure, component concentration and cooling rate; Pre-process the collected data of key parameters in the aluminum smelting process; Establish a big data model for aluminum smelting products to conduct real-time detection and analysis of the quality of aluminum smelting products; Set a quality threshold. When the test and analysis results exceed the quality threshold, the aluminum smelting product is judged to be unqualified. According to the historical data in the big data model of aluminum smelting products, traceability analysis is carried out to analyze the reasons for the unqualified quality of aluminum smelting products and trace them back to the key parameters in the specific process links; Based on the traceability results, optimize the key parameters in the traceable process; The said establishment of a big data model for aluminum smelting products to conduct real-time detection and analysis of the quality of aluminum smelting products includes: Set the collected aluminum smelting furnace temperature set as T, the aluminum smelting furnace pressure set as P, the aluminum smelting product chemical composition set as C, and the aluminum smelting product cooling rate as v; A big data model for aluminum smelting products is established to evaluate the quality of aluminum smelting products. The specific formula of the big data model for aluminum smelting products is: ， Among them, Q represents the big data model of aluminum smelting products, that is, the quality of aluminum smelting products smelted by the s-th aluminum smelting furnace, represents the intercept term, which is a constant term, and n represents the total number of the sth aluminum smelting furnace temperature power terms. represents the ith power of the sth aluminum smelting furnace temperature, represents the coefficient of the sth aluminum smelting furnace temperature i-th power, m represents the total number of pressure power items of the sth aluminum smelting furnace, represents the jth power of the pressure of the sth aluminum smelting furnace, represents the coefficient of the jth power of the pressure of the sth aluminum smelting furnace, q represents the total number of chemical components of the aluminum smelting product smelted by the sth aluminum smelting furnace, It indicates the content of the kth item of chemical composition of the aluminum smelting product smelted by the sth aluminum smelting furnace. Indicates chemical composition The coefficient of The coefficient representing the cooling rate of the aluminum smelting product smelted by the s-th aluminum smelting furnace, The coefficient that represents the interaction between temperature, pressure and chemical composition in the aluminum smelting process. represents the error term; The traceability analysis based on the historical data in the big data model of aluminum smelting products includes: Set the quality threshold to Q yz , when the quality of aluminum smelting product a after smelting is less than the quality threshold Q yz When the aluminum smelting product a is judged to be unqualified in quality; Assume that the aluminum smelting product set is A, and the key parameter set when the aluminum smelting product is completed is S. A , calculate the set of key parameters S when the aluminum smelting product set A is completed A The correlation between each parameter and product quality is calculated as follows: ， Among them, r xy The set S represents the key parameters of the aluminum smelting product set A when smelting is completed. A The correlation between each parameter and product quality, x ef Indicates S A The fth parameter value of the eth aluminum smelting product in, Indicates S A The average value of the fth parameter in Q e represents the quality of the e-th aluminum smelting product, It represents the mean value of the quality of aluminum smelting products; Trace the unqualified aluminum smelting products and establish a time series model. The specific formula is: ， Among them, y t is a time series model, represents a constant term, describing the intercept or baseline level of the time series model, represents the autoregressive coefficient, i.e., the influence coefficient of the past values ​​of aluminum smelting product quality, h represents the number of past values ​​of aluminum smelting product quality, y t-g represents the hysteresis value of aluminum smelting product quality at time t−g, It represents the coefficient of key parameters in the smelting process of aluminum smelting products, that is, the coefficient of influence of key parameters in the smelting process of aluminum smelting products on product quality, x t-l represents the lag value of the key parameters in the smelting process of aluminum smelting products at time t−l, represents the key parameters in the smelting process of aluminum smelting products at the past time point, represents the error term; The analysis of the reasons for the unqualified quality of aluminum smelting products and tracing back to the key parameters in the specific process links include: According to the time series model, the time point and key parameters of the abnormal process in the smelting process are traced back to when the aluminum smelting products are unqualified. The time point of the abnormal process in the smelting process of aluminum smelting products is set as J, and the corresponding key parameter set is S J ; Extract the characteristics that have the greatest impact on the quality of aluminum smelting products, that is, the categories of key parameters. The specific formula is: ， Among them, tz represents the feature that has the greatest impact on the quality of aluminum smelting products, N represents the set of features, that is, the key parameters of aluminum smelting products, N(\d) represents the feature set that does not contain feature d, S represents the subset of the set N(\d), |S| represents the number of features in the subset S, |N| represents the number of features in the set N, ! represents factorial, min represents the minimum value function, f(S) represents the value function output using the subset S, Represents the value function output when using subset S and feature d.

2. The aluminum smelting product quality monitoring and traceability method based on big data modeling according to claim 1 is characterized in that: The influence coefficients of the interaction between temperature, pressure and chemical composition in the aluminum smelting process The specific formula is: ， in, It represents the interaction coefficient of temperature, pressure and chemical composition in the aluminum smelting process.

3. The aluminum smelting product quality monitoring and traceability method based on big data modeling according to claim 1 is characterized in that: The preprocessing includes: data cleaning, missing value processing and removal of redundant values.

4. A system for monitoring and tracing the quality of aluminum smelting products based on big data modeling, used to implement the method for monitoring and tracing the quality of aluminum smelting products based on big data modeling as described in any one of claims 1 to 3, characterized in that: include: Data acquisition module, preprocessing module, model building module, traceability module and optimization module; The data acquisition module is used to collect key parameter data in the aluminum smelting process in real time through a sensor network, including: temperature, pressure, component concentration and cooling rate; The preprocessing module is used to preprocess the key parameter data collected during the aluminum smelting process; The model building module is used to build a big data model of aluminum smelting products and perform real-time detection and analysis on the quality of aluminum smelting products; The traceability module is used to set a quality threshold. When the detection and analysis results exceed the quality threshold, the quality of the aluminum smelting product is judged to be unqualified. The traceability analysis is performed based on the historical data in the aluminum smelting product big data model to analyze the reasons for the unqualified quality of the aluminum smelting product and trace it back to the key parameters in the specific process links; The optimization module is used to optimize key parameters in the traced process based on the traceability results; The traceability module includes: a product traceability unit and a key parameter traceability unit; The product traceability unit is used to trace the stage where the aluminum smelting products are unqualified, that is, to trace them back to the process link; The key parameter tracing unit is used to extract the features that have the greatest impact on the process links traced back.

5. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the aluminum smelting product quality monitoring and traceability method based on big data modeling described in any one of claims 1-3 are implemented.

6. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed, the steps of the aluminum smelting product quality monitoring and traceability method based on big data modeling described in any one of claims 1-3 are executed.

Images