Integrated management system and method for molten aluminum processing technology

Abstract

The invention relates to the technical field of integrated management, and discloses a molten aluminum processing technology integrated management system and method. The system comprises a coding module, a configuration module, a quality inspection module, an embedding module, a decoupling module and a regulation and control module, all the modules are connected in series to form a data processing chain, the coding module is further connected with the quality inspection module to provide depth identification information, and the regulation and control module is connected with the coding module to provide feature chain data. According to the system, through multi-level coding, dynamic configuration, cross quality inspection, information embedding, parameter decoupling and linkage regulation and control, full-process management of molten aluminum processing is achieved. According to the method, the problems of data splitting and unsmooth information intercommunication in each link in the existing molten aluminum processing technology management are solved, and the whole-process data integrated management from raw materials to finished products is realized.

Description

Technical Field

[0001] The present application relates to the field of integrated management, and in particular to an integrated management system and method for a molten aluminum processing process. Background Art

[0002] Molten aluminum processing is an important process in aluminum production. Traditional molten aluminum processing technology mainly relies on manual experience for control. A variety of molten aluminum processing process management methods have been developed in the prior art, including temperature control systems, quality inspection systems, and transportation monitoring systems. These systems can monitor and control the temperature, composition, fluidity and other parameters of molten aluminum in real time, and record and analyze data through computer systems. At the same time, with the development of information technology, some intelligent process management methods have gradually been applied to the field of molten aluminum processing, such as using sensor networks for temperature field monitoring and using digital equipment for quality inspection.

[0003] However, the existing molten aluminum processing technology management method has the phenomenon of data islands. The control systems of various process links are relatively independent and lack effective data interaction and information sharing mechanisms. Especially between different processes such as smelting, transportation and casting, the transmission of data often relies on manual recording and transcription, which can easily cause information distortion and delay. At the same time, the existing system lacks in-depth analysis of the correlation between raw material characteristics, process parameters and quality indicators, making it difficult to achieve precise regulation of process parameters and stable control of quality. In addition, in the transportation link, the dynamic changes of the temperature field and the spatial position information are difficult to effectively combine, which affects the maintenance of melt quality. Summary of the invention

[0004] The present application provides an integrated management system and method for molten aluminum processing technology, which is used to overcome the problems of data fragmentation and poor information exchange in various links in the existing molten aluminum processing technology management, and realize the integrated management of data in the whole process from raw materials to finished products.

[0005] In the first aspect, the present application provides an integrated management system for molten aluminum processing technology, and the integrated management system for molten aluminum processing technology includes: a coding module, a configuration module, a quality inspection module, an embedding module, a decoupling module and a control module; the output end of the coding module is connected to the input end of the configuration module, the output end of the configuration module is connected to the input end of the quality inspection module, the output end of the quality inspection module is connected to the input end of the embedding module, the output end of the embedding module is connected to the input end of the decoupling module, and the output end of the decoupling module is connected to the input end of the control module, wherein the coding module is also connected to the quality inspection module for providing depth identification information to the quality inspection module, and the output end of the control module is also connected to the coding module for providing process feature chain data; the coding module is used to obtain a batch feature code by performing multi-level cross-coding processing on aluminum raw materials, perform multi-dimensional mapping analysis on the batch feature code and the inherent characteristic data of the material to obtain a process feature matrix, and hierarchically deconstruct the material properties according to the process feature matrix to obtain depth identification information; the configuration module is used to deconstruct the molten aluminum raw materials according to the depth identification information. The nonlinear dynamic configuration of melting parameters is carried out, and the melting state is subjected to multi-dimensional quantitative processing through coupling analysis of the temperature field, flow field and pressure field data in the melting process to obtain the melting characteristic spectrum; the quality inspection module is used to perform multi-variable cross-quality inspection on the molten aluminum according to the melting characteristic spectrum, and the detection data is analyzed in layers and progressively, and the depth identification information, the melting characteristic spectrum and the quality inspection data are multi-dimensionally cross-mapped to obtain the quality characterization spectrum; the embedding module is used to embed the hierarchical information of the ladle recording unit according to the quality characterization spectrum, and the spatial position data is four-dimensionally associated with the quality characterization spectrum by dynamically tracking the temperature field to generate a transportation control matrix; the decoupling module is used to perform multi-parameter decoupling of the temperature change according to the transportation control matrix, and the position state and the temperature field data are adaptively integrated by layered quantitative adjustment of the insulation state to construct the casting characteristic field; the control module is used to perform multi-dimensional parameter linkage control on the insulation furnace through the casting characteristic field, adaptively compensate the casting process, and progressively integrate the process parameters at multiple levels to form a process characteristic chain.

[0006] In the second aspect, the present application provides an integrated management method for molten aluminum processing technology, the integrated management method for molten aluminum processing technology includes: performing multi-level cross-coding processing on aluminum raw materials to obtain batch characteristic codes, performing multi-dimensional mapping analysis on the batch characteristic codes and material inherent characteristic data to obtain a process characteristic matrix, hierarchically deconstructing material properties according to the process characteristic matrix to obtain depth identification information; performing nonlinear dynamic configuration of melting parameters according to the depth identification information, performing multi-dimensional quantitative processing on the melting state through coupling analysis of the temperature field, flow field, and pressure field data during the melting process to obtain a melting characteristic spectrum; performing multi-variable cross-quality inspection on the molten aluminum according to the melting characteristic spectrum, and performing multi-variable cross-quality inspection on the detection data. The data is analyzed hierarchically and progressively, and the depth identification information, melting characteristic spectrum and quality inspection data are cross-mapped in multiple dimensions to obtain a quality characterization spectrum; according to the quality characterization spectrum, the ladle recording unit is embedded with hierarchical information, and the temperature field is dynamically tracked, and the spatial position data and the quality characterization spectrum are four-dimensionally associated to generate a transportation control matrix; based on the transportation control matrix, the temperature change is decoupled with multiple parameters, and the position state and temperature field data are adaptively fused by hierarchical quantitative adjustment of the insulation state to construct a casting characteristic field; through the casting characteristic field, the insulation furnace is controlled by multi-dimensional parameter linkage, the casting process is adaptively compensated, and the process parameters are progressively integrated at multiple levels to form a process characteristic chain.

[0007] In the technical solution provided by the present application, multi-level cross-coding processing and multi-dimensional mapping analysis are performed through the coding module to establish the corresponding relationship between the raw material characteristics and the process parameters, which effectively improves the utilization efficiency of the material characteristic data. The configuration module uses a nonlinear dynamic configuration method to regulate the melting parameters, and realizes the accurate grasp of the melting state through the coupled analysis of the temperature field, flow field, and pressure field, thereby improving the control accuracy of the melting process. The quality inspection module realizes the all-round collection and analysis of quality data through multi-variable cross-quality inspection and hierarchical progressive analysis, and the application of multi-dimensional cross-mapping technology ensures the accuracy of quality assessment. The embedding module adopts hierarchical information embedding and four-dimensional correlation analysis technology to realize real-time monitoring and data tracking during transportation, and ensures the stability of melt quality. The decoupling module makes temperature control more accurate through multi-parameter decoupling and hierarchical quantitative adjustment, and the adaptive fusion of position state and temperature field data improves the flexibility of temperature control. The control module adopts multi-dimensional parameter linkage control and adaptive compensation technology to ensure the stable progress of the casting process, and the multi-level progressive integration of process parameters realizes the continuity of process control. The close cooperation between the modules forms a complete data processing chain, which significantly improves the automation level and quality control capability of the molten aluminum processing technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0009] Figure 1 This is a schematic diagram of an embodiment of the integrated management system for molten aluminum processing technology in the embodiment of the present application; Figure 2 This is a schematic diagram of an embodiment of the integrated management method of molten aluminum processing technology in an embodiment of the present application. DETAILED DESCRIPTION

[0010] The embodiments of the present application provide an integrated management system and method for molten aluminum processing technology. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0011] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 , an embodiment of the molten aluminum processing technology integrated management system in the embodiment of the present application includes: Coding module 101, configuration module 102, quality inspection module 103, embedding module 104, decoupling module 105 and control module 106; the output end of the coding module 101 is connected to the input end of the configuration module 102, the output end of the configuration module 102 is connected to the input end of the quality inspection module 103, the output end of the quality inspection module 103 is connected to the input end of the embedding module 104, the output end of the embedding module 104 is connected to the input end of the decoupling module 105, and the output end of the decoupling module 105 is connected to the input end of the control module 106, wherein the coding module 101 is also connected to the quality inspection module 103 to provide depth identification information to the quality inspection module 103, and the output end of the control module 106 is also connected to the coding module 101 to provide process feature chain data; The encoding module 101 is used to obtain a batch feature code by performing multi-level cross-coding processing on the aluminum raw materials, perform multi-dimensional mapping analysis on the batch feature code and the inherent characteristic data of the material to obtain a process feature matrix, and perform hierarchical deconstruction of the material attributes according to the process feature matrix to obtain deep identification information; Configuration module 102, for performing nonlinear dynamic configuration of melting parameters according to the depth identification information, and performing multi-dimensional quantitative processing of the melting state by coupling analysis of the temperature field, flow field, and pressure field data during the melting process to obtain a melting characteristic spectrum; The quality inspection module 103 is used to perform multivariate cross-quality inspection on the molten aluminum according to the melting characteristic spectrum, perform hierarchical progressive analysis on the inspection data, and perform multi-dimensional cross-mapping of the depth identification information, the melting characteristic spectrum and the quality inspection data to obtain a quality characterization spectrum; The embedding module 104 is used to embed the graded information of the ladle recording unit according to the quality characterization spectrum, and to generate a transportation control matrix by dynamically tracking the temperature field and four-dimensionally correlating the spatial position data with the quality characterization spectrum; The decoupling module 105 is used to decouple the temperature change in multiple parameters according to the transport control matrix, and to adaptively fuse the position state and the temperature field data by performing layered quantitative adjustment on the insulation state to construct a casting characteristic field; The control module 106 is used to perform multi-dimensional parameter linkage control on the holding furnace through the casting characteristic field, perform adaptive compensation on the casting process, and perform multi-level progressive integration of the process parameters to form a process characteristic chain.

[0012] Specifically, the integrated management system for molten aluminum processing technology completes the management of the entire processing technology through the close cooperation of the encoding module 101, the configuration module 102, the quality inspection module 103, the embedding module 104, the decoupling module 105 and the control module 106. A strict data transmission chain is formed between the modules, wherein the output end of the encoding module 101 is connected to the input end of the configuration module 102, the output end of the configuration module 102 is connected to the input end of the quality inspection module 103, the output end of the quality inspection module 103 is connected to the input end of the embedding module 104, the output end of the embedding module 104 is connected to the input end of the decoupling module 105, and the output end of the decoupling module 105 is connected to the input end of the control module 106. In particular, the encoding module 101 also establishes a direct connection with the quality inspection module 103 for transmitting depth identification information, and the output end of the control module 106 is connected to the encoding module 101 through feedback to provide process feature chain data.

[0013] The coding module 101 processes the aluminum raw materials. The module uses multi-level cross-coding technology to extract material information. For a batch of aluminum raw materials, the basic information is first digitized, such as the Al-99.7% purity value, the melting point temperature of 700°C, the density value of 2.7g / cm³ and other parameters are standardized. These values ​​are used to generate a unique batch characteristic code, such as "AL97-D27-T700" through a batch coding algorithm. Subsequently, the batch characteristic code is multi-dimensionally mapped and analyzed with other inherent characteristic data of the material (thermal conductivity, heat capacity, etc.) to construct a process characteristic matrix. The matrix contains a complete data structure of the physical, chemical and process characteristics of the material. Through the hierarchical deconstruction algorithm, the data in the matrix is ​​layered according to importance and relevance, and finally forms deep identification information.

[0014] After receiving the depth identification information, the configuration module 102 starts the nonlinear dynamic configuration process. Taking the melting temperature control as an example, according to the melting point parameters in the depth identification information, a temperature change curve is established, and the flow field data (such as flow rate, viscosity) and the pressure field data (such as static pressure, dynamic pressure) are combined for coupling analysis. By real-time monitoring of the changes in these three fields, such as maintaining the temperature field in the range of 680-720°C, maintaining the flow rate at 0.5-1.0m / s, and controlling the pressure within the range of ±5% of the standard atmospheric pressure, these data are subjected to multi-dimensional quantitative processing, and finally a characteristic spectrum reflecting the melting state is generated. After obtaining the melting characteristic spectrum, the quality inspection module 103 carries out multivariate cross-quality inspection. The molten aluminum is subjected to a full range of quality inspection, including element content analysis, impurity detection, temperature uniformity inspection, etc. The detection data is analyzed in a hierarchical and progressive manner, and each indicator is graded according to its importance. Subsequently, these data are multi-dimensionally cross-mapped with the previous depth identification information and melting characteristic spectrum to generate a complete quality characterization spectrum.

[0015] The embedding module 104 is responsible for writing the information of the quality characterization spectrum into the ladle recording unit. By classifying the data, key information such as temperature, composition, and physical properties are allocated to different storage areas according to priority levels. At the same time, a dynamic tracking mechanism for the temperature field is established, and temperature change data is collected in real time through sensors arranged at key positions of the ladle. These spatial position data (including the three-dimensional coordinates and time information of the temperature collection point) are subjected to four-dimensional correlation analysis with the quality characterization spectrum, and finally a transportation control matrix containing complete transportation process monitoring information is generated. After receiving the transportation control matrix, the decoupling module 105 first performs parameter decoupling on the temperature change data. By separating the data of the time dimension and the space dimension, the key influencing factors of the temperature change are identified. The insulation state is layered and quantitatively adjusted, and the optimal insulation parameters are calculated according to the temperature difference at different positions. The position state information is fused with the temperature field data to construct a casting characteristic field that reflects the temperature distribution characteristics of the entire casting process.

[0016] The control module 106 realizes precise control of the holding furnace based on the data of the casting characteristic field. Through the multi-dimensional parameter linkage mechanism, the coordinated adjustment of various process parameters is ensured. During the casting process, parameter compensation is performed in real time, and dynamic adjustments are made to temperature deviations, fluidity changes, etc. Finally, the parameter changes, control records and other information of the entire process are progressively integrated at multiple levels to form a complete process characteristic chain.

[0017] For example, when processing a batch of aluminum raw materials, the encoding module 101 first extracts its basic characteristics: purity 99.7%, density 2.7g / cm³, melting point 660℃. These data are cross-coded at multiple levels to generate the batch characteristic code "AL97D27T660". Based on this information, the configuration module 102 sets the initial melting temperature to 700℃. When the actual temperature is detected to reach 680℃, the coupling analysis finds that the flow rate drops to 0.3m / s, which is 0.5m / s lower than the expected value. The system immediately adjusts the heating power. The quality inspection module 103 continuously monitors during the melting process. When it detects that the local temperature fluctuation exceeds ±10℃, it triggers the embedded module 104 to record the abnormality and write the information into the ladle recording unit. The decoupling module 105 analyzes and finds that this temperature fluctuation is correlated with the transportation speed. It is calculated that the optimal transportation speed should be controlled between 15-20km / h. The control module 106 adjusts the power output of the holding furnace in real time based on these data to ensure the temperature uniformity of the molten aluminum. The parameter changes of the entire process are recorded in the process feature chain.

[0018] In a specific embodiment, the encoding module 101 is specifically used to: (1) Extracting component composition, material specifications, and production batch number data from aluminum raw materials, grouping the data according to a preset arrangement order, and obtaining a raw material basic data group; (2) Perform numerical processing on each data set in the raw material basic data set, convert the component composition into the percentage of element content, convert the specification data into the standard size value, and convert the batch number data into the time series value to obtain a numerical data sequence; (3) The numerical data sequence is weighted according to the importance of the elements, and the weighted data is cross-combined to generate a batch feature code; (4) By extracting data on the purity value, density value, thermal conductivity, and melting point temperature of aluminum raw materials, a material inherent characteristic data set is constructed, and the batch characteristic code is matched with the material inherent characteristic data set to establish a data mapping relationship and obtain a process characteristic matrix; (5) Based on the process characteristic matrix, the material attribute data is layered according to the three dimensions of physical properties, chemical properties, and process characteristics, and the correlation degree of each layer of data is calculated to obtain attribute correlation data; (6) Extract the key parameters from the attribute-related data, quantify the degree of mutual influence between the parameters, fuse the quantified results with the process feature matrix, and obtain deep identification information.

[0019] Specifically, the encoding module 101 can convert the physical information of aluminum raw materials into calculable and processable digital information. In the information extraction stage, the raw materials are comprehensively parameterized, including the basic information of aluminum materials (composition, material specifications, and production batch numbers). Composition specifically refers to the type and content of aluminum and its alloy elements. Material specifications include size specifications (length, width, thickness) and shape specifications (plates, bars, profiles, etc.), and the production batch number includes information such as production date and production line number. For the collected raw data, a standardized data format is formed through standardization. Specifically, the composition data is uniformly converted into a percentage form, such as the content of the main element Al, the percentage of the content of the added elements Si, Cu, Mg, etc.; the specification data is standardized into a numerical value of metric units, such as the length unit is unified into millimeters (mm); the production batch number is converted into a time series value, using the format of "year, month, day, hour, and minute" to facilitate subsequent data processing and traceability. On the basis of the numerical data sequence, weight values ​​are assigned according to the degree of influence of different elements on the melting process. The main element Al has the highest weight, followed by alloy elements that have a greater impact on melting properties (such as the impact of Si on fluidity), and then other trace elements. Through this hierarchical weighting method, the importance of key elements is highlighted, and through a cross-combination algorithm, these weighted data are integrated into a unique batch feature code.

[0020] In the process of extracting the inherent characteristic data of materials, the focus is on the key physical parameters that affect the melting process: purity value (reflecting the purity of the material), density value (determining the mass-volume relationship of the material), thermal conductivity (affecting the heating efficiency), and melting point temperature (determining the process temperature setting). After these parameters are obtained through professional testing equipment, they are constructed into a multidimensional data set, mapped with the batch feature codes generated previously, and a process feature matrix is ​​formed. The hierarchical processing of the process feature matrix is ​​a key step, and the material attribute data is classified according to three dimensions: physical properties (such as thermal conductivity, density, etc.), chemical properties (such as component purity, chemical activity, etc.), and process characteristics (such as plasticity, fluidity, etc.). By calculating the correlation coefficient between different characteristics, the mutual influence relationship between the parameters is evaluated, and attribute correlation data is generated.

[0021] In the deep identification information generation stage, the key parameters that have the most significant impact on the melting process, such as the melting characteristics and flow properties of the material, are extracted from the attribute association data. By establishing a parameter impact evaluation model, the interaction between these parameters is quantitatively analyzed, and finally these quantitative results are integrated with the process feature matrix to form complete deep identification information.

[0022] For example, the complete workflow of encoding module 101: a batch of aluminum alloy materials to be processed undergoes initial testing to obtain basic information such as its composition (Al-96.8%, Si-2.5%, Cu-0.5%, others-0.2%), specification parameters (plate 1200mm×600mm×10mm), and production batch number (20231225-A01). These data are first converted into a standardized form: the composition data is retained as a percentage to two decimal places, the size data is unified into millimeter units, and the batch number is converted into a time series value (2023122508, where 08 represents the production period). In the hierarchical weighting stage, the weight of the main element Al is set to 1.0, Si with significant process influence is set to 0.8, Cu is set to 0.6, and other elements are set to 0.4. These weight values ​​are weighted with the content of each element, combined with the specification parameters and time series values ​​to generate a unique batch feature code. At the same time, the purity value (99.3%), density value (2.71g / cm³), thermal conductivity (235W / (m·K)), and melting point temperature (660℃) of this batch of materials were measured by professional testing equipment. These data constitute the material's inherent property data set.

[0023] In the three-dimensional layered processing of physical properties, chemical properties, and process properties, each dimension contains multiple parameter indicators. By calculating the degree of correlation between these indicators, such as the relationship between thermal conductivity and melting rate, the relationship between purity and fluidity, etc., a complete correlation matrix is ​​obtained. All processing results are integrated to form in-depth identification information that reflects the complete characteristics of the batch of materials.

[0024] In a specific embodiment, the configuration module 102 is specifically configured to: (1) Extract the physical characteristic parameters, chemical characteristic parameters, and process characteristic parameters from the depth identification information respectively, divide the parameters into numerical intervals, and obtain the melting control parameters; (2) Calculating the data correlation of the melting control parameters, combining the parameters with correlation coefficients higher than the set threshold, and obtaining a parameter correlation group; (3) Prioritize the parameter association groups according to the process importance, cross-validate each parameter association group, and obtain the nonlinear dynamic configuration parameters; (4) By collecting the temperature value, flow velocity, and pressure change data in the melting furnace, the collected data are analyzed in time series to obtain the field data sequence; (5) Correlation calculation is performed on the temperature field, flow field, and pressure field data in the field data sequence, and the coupling characteristic value is obtained by quantifying the interaction intensity of the physical quantities; (6) Perform multidimensional spatial transformation on the coupled eigenvalues, cross-map the transformed data with the nonlinear dynamic configuration parameters, and quantitatively evaluate the mapping results to obtain the melting characteristic spectrum.

[0025] Specifically, after receiving the depth identification information transmitted by the encoding module 101, the configuration module 102 performs parameter classification and extraction. The depth identification information contains three major categories of parameters: physical property parameters (such as thermal conductivity, melting point temperature, specific heat capacity, etc.), chemical property parameters (such as element content, purity value, activity level, etc.) and process characteristic parameters (such as fluidity, formability, etc.). Each type of parameter needs to be divided into numerical intervals to determine the control range in the melting process. For example, the melting point temperature in the physical property parameters is divided into preheating interval, melting interval and overheating interval, the element content in the chemical property parameters is divided into standard interval and allowable fluctuation interval, and the fluidity in the process characteristic parameters is divided into three levels of high, medium and low. The initial melting control parameters are formed through this interval division. For the extracted melting control parameters, data correlation calculation is required to determine the mutual influence relationship between the parameters. First, the correlation coefficient between the parameters is calculated, and the Pearson correlation coefficient is calculated using the standardized data. When the correlation coefficient exceeds the preset threshold (usually set to 0.7 or higher), these highly correlated parameters are combined together to form a parameter association group. These association groups reflect the intrinsic relationship between parameters and provide a basis for subsequent process control.

[0026] The priority of parameter association groups is determined based on their importance in the process. In the molten aluminum processing process, the parameter group related to temperature control has the highest priority because temperature directly affects the melting quality; followed by the parameter group related to fluidity, which affects the filling effect of the material; and then the parameter group related to pressure, which affects the stability of the melt. By cross-validating each parameter association group, their adaptability under different working conditions is tested, and finally nonlinear dynamic configuration parameters are formed. Field data acquisition is a key link in the control of the melting process. Multiple sensors are arranged in the melting furnace to collect temperature values ​​(including temperature distribution at different locations), flow velocity (including surface velocity and internal velocity) and pressure change data (including static pressure and dynamic pressure) in real time. These raw data are processed by time series analysis to examine the change law of various parameters over time, and through denoising, smoothing and other processing, an effective field data sequence is obtained.

[0027] There is a complex interaction between the temperature field, flow field, and pressure field data in the field data sequence. Changes in the temperature field will affect the fluidity of the material, and then affect the distribution of the flow field; changes in the flow field will affect the distribution of the pressure field, and changes in the pressure field will in turn affect the temperature conduction effect. By establishing a model of the interaction relationship between physical quantities, the intensity of these interactions is quantitatively described, and the coupling eigenvalues ​​reflecting the degree of coupling between fields are obtained. Multidimensional spatial transformation of the coupling eigenvalues ​​is essentially processing the data of the three fields in a unified mathematical space. The data of each field is mapped to the same reference system through coordinate transformation, and cross-mapped with nonlinear dynamic configuration parameters. This process needs to consider the time-varying characteristics and spatial distribution characteristics of the parameters, and quantitatively evaluate the mapping results through appropriate evaluation indicators to finally form a complete melting characteristic spectrum.

[0028] For example, after receiving the deep identification information of a batch of aluminum alloy materials, the configuration module 102 first extracts key parameters from them: the melting point temperature (660°C) and thermal conductivity (237 W / m·K) in physical properties, the main element content (Al-96.8%) and impurity content (0.2%) in chemical properties, and the fluidity index in process characteristics. These parameters are divided into different control intervals: the temperature control interval is 660°C ± 40°C, the thermal conductivity is allowed to fluctuate within ±5%, and the upper limit of the impurity content is 0.3%. Through data correlation analysis, it is found that the correlation coefficient between temperature and fluidity reaches 0.85, indicating that they have a strong correlation, so they are combined into the same parameter association group. At the same time, it is found that the correlation coefficient between pressure change and fluidity is 0.65, which is lower than the threshold, so it is treated as an independent parameter. After the parameter association groups are sorted according to process importance, the temperature-fluidity association group is given the highest priority.

[0029] In the actual melting process, the temperature data collected by multi-point temperature sensors showed that the temperature difference at different positions fluctuated between 5-15°C, and the flow rate detection showed that there was a 2-3 times difference between the surface flow rate and the internal flow rate. These data were analyzed in time series to eliminate abnormal fluctuations and form a field data sequence that reflects the change in the melt state. The temperature field data and the flow field data were correlated and analyzed, and it was found that when the temperature increased by 10°C, the flow rate increased by about 0.1m / s. This correlation was quantified as a coupling eigenvalue. Finally, through spatial transformation and cross-mapping, a melting characteristic spectrum containing complete information such as temperature distribution, flow characteristics, and pressure changes was generated.

[0030] In a specific embodiment, the quality inspection module 103 is specifically used to: (1) Segment the melting characteristic spectrum according to element content, impurity content, and temperature distribution, and normalize the segmented data to obtain quality inspection benchmark data; (2) Conduct density, hardness, thermal conductivity and fluidity tests on the molten aluminum, compare and analyze the test results with the quality inspection benchmark data, and obtain a quality inspection parameter group; (3) Combine and classify the relevant parameters in the quality inspection parameter group, perform progressive analysis on the classified data, and obtain the quality inspection characteristic value; (4) Extract material attribute data from the depth identification information, calculate the correlation between the material attribute data and the quality inspection characteristic value, and obtain the quality correlation matrix; (5) Fusing the quality correlation matrix with the melting characteristic spectrum, and obtaining the quality feature group by cross-validating the fused data; (6) The quality feature groups are graded according to the importance of the parameters, the graded data are combined in multiple dimensions, and numerical mapping is performed according to the quality evaluation standards to obtain the quality characterization spectrum.

[0031] Specifically, after receiving the melting characteristic spectrum from the configuration module 102, the data needs to be segmented. The data contained in the melting characteristic spectrum, such as element content (content data of main elements, alloy elements, and impurity elements), impurity content (non-metallic inclusions, gas content, etc.), temperature distribution (temperature values ​​at each point in space), etc., need to be segmented according to different standards. The element content is segmented according to the chemical composition standard, the impurity content is segmented according to the purity level, and the temperature distribution is segmented according to the spatial position. These segmented data are normalized, and the data of different dimensions are converted into a unified standard range to form comparable quality inspection benchmark data. Performing multiple physical property tests on aluminum materials in a molten state is a key link in quality control. Density detection uses a drainage method or a ray method to obtain the density value of the melt; hardness detection uses a dedicated melt hardness tester to measure the resistance value of the melt; thermal conductivity detection uses a thermal diffusion coefficient measuring device to obtain the thermal conductivity; fluidity detection uses a dedicated fluidity tester to record the flow distance and time of the melt. These test data are compared and analyzed with the quality inspection benchmark data obtained previously to examine the degree of deviation between the actual measured values ​​and the standard values, and form a quality inspection parameter group.

[0032] The quality inspection parameter group contains a large amount of test data, which needs to be reasonably organized and classified. First, combine them according to the correlation of physical properties, for example, combine parameters related to flow characteristics such as density and fluidity, and combine parameters related to material intrinsic characteristics such as hardness and thermal conductivity. A progressive analysis method is used for the classified data, from basic physical quantities to composite physical quantities, and the correlation between parameters is gradually analyzed in depth, and finally the quality inspection characteristic value reflecting the overall performance of the material is obtained.

[0033] The deep identification information contains the original attribute data of the material, which are the characteristic parameters of the material at room temperature. By extracting these material attribute data and conducting correlation analysis with the quality inspection characteristic values ​​obtained in the molten state, the corresponding relationship between the performance parameters of the material at room temperature and in the molten state is established. By calculating the correlation coefficient, establishing regression equations and other methods, a quality correlation matrix that reflects the law of material performance change is formed. The quality correlation matrix contains the performance change data of the material from solid to liquid, which needs to be fused with the process parameters in the melting characteristic spectrum. The fusion process adopts multi-source data fusion technology to comprehensively process data from different sources, and verify the consistency and reliability of the data through cross-validation methods, and finally obtain a quality feature group that fully reflects the material performance.

[0034] The quality characteristic group is a collection of multidimensional data, which needs to be graded according to the degree of influence of each parameter on product quality. For example, parameters that directly affect product performance (such as component uniformity) are classified as primary indicators, and parameters that indirectly affect product performance (such as temperature uniformity) are classified as secondary indicators. The graded data is combined and mapped in multiple dimensions according to the quality evaluation criteria, and finally a complete quality characterization spectrum is formed.

[0035] For example, when a batch of aluminum alloy materials enters the smelting stage, the quality inspection module 103 first receives the melting characteristic spectrum of the batch. The element content data in the characteristic spectrum shows the distribution of the main element Al content, the alloy element Si content and other trace elements. These data are first divided into different composition intervals. At the same time, the temperature distribution data shows the temperature value of the melt at different positions, and these data are segmented according to the spatial coordinates. All segmented data are normalized and converted into values ​​within the standard 0-1 interval to form the initial quality inspection benchmark. Subsequently, the melt is monitored in real time by various testing equipment: the density detector measures the actual density of the melt and compares it with the theoretical density; the hardness tester measures the apparent hardness value of the melt; the thermal conductivity tester records the thermal conductivity; and the fluidity tester determines the flow characteristics of the melt. These test data are compared with the quality inspection benchmark data, and it is found that there is an obvious correlation between density and fluidity, so these two groups of parameters are classified into one category.

[0036] Through progressive analysis, it is found that when the density changes by 0.1g / cm³, the fluidity will change accordingly, and this relationship is recorded as the quality inspection characteristic value. At the same time, the performance parameters of the material at room temperature are extracted from the depth identification information, and compared with the characteristic values ​​in the molten state to establish a corresponding relationship between temperature and performance, which is recorded in the quality correlation matrix. The quality correlation matrix is ​​fused with the original melting characteristic spectrum to obtain a complete data set reflecting the performance changes of the material throughout the melting process. These data are graded according to the degree of their impact on the quality of the final product, forming a multi-dimensional quality characterization spectrum.

[0037] In a specific embodiment, the embedding module 104 is specifically configured to: (1) The temperature data, composition data, and physical property data in the quality characterization spectrum are classified according to their importance, and the classified data are coded and converted to obtain a classified data group; (2) dividing the storage capacity of the ladle recording unit into blocks, and writing the graded data groups into corresponding blocks in order of data priority to obtain a recording data sequence; (3) Collecting temperature data at temperature sensing points arranged inside the ladle, performing time series analysis on the collected data, and obtaining a temperature change curve; (4) Combine the longitude, latitude, altitude, and time data of the ladle during transportation to obtain a spatial position sequence; (5) Data association is performed between the temperature change curve and the spatial position sequence, and the association result is cross-validated with the recorded data sequence to obtain multi-dimensional association data; (6) By performing numerical conversion on multi-dimensional correlated data, the conversion results are reorganized and integrated according to the time-space correspondence to generate a transportation control matrix.

[0038] Specifically, the embedding module 104 effectively records and tracks the transportation process with the quality characterization spectrum data generated by the quality inspection module 103. First, three types of key data are extracted from the quality characterization spectrum: temperature data (including melt temperature, ambient temperature and their distribution), composition data (including main element content, alloy element distribution, impurity level) and physical property data (including physical properties such as fluidity, thermal conductivity, density, etc.). These data are graded according to their importance according to the degree of influence on the quality of molten aluminum. Temperature data is classified as primary important data because it directly affects the state of the melt; composition data is classified as secondary important data because it affects the performance of the final product; physical property data is classified as tertiary important data as a state monitoring parameter. The graded data is converted into a standardized digital sequence through specific coding rules to form a standardized graded data group. The ladle recording unit is a data storage device installed on the transport ladle, and it needs to be divided into blocks according to the importance and storage characteristics of the data. The storage space is divided into multiple functional blocks: real-time data area (used to store data that needs to be updated frequently, such as temperature), static data area (used to store relatively stable data such as composition) and state data area (used to store data that is regularly updated, such as physical properties). The data in the hierarchical data group is written into the corresponding storage block according to the priority. The high-priority temperature data is written into the real-time data area to ensure fast access and update; the composition data is written into the static data area to ensure data integrity; the physical property data is written into the status data area for easy monitoring and analysis. This partition storage method forms an orderly sequence of recorded data.

[0039] Temperature monitoring is one of the most critical links in the transportation process. Multiple temperature sensing points are set up inside the ladle. The arrangement of these sensing points follows the principle of "three-dimensional uniform distribution": temperature sensors are arranged at the top, middle and bottom, and are also evenly distributed in the radial direction. Each sensing point collects temperature data at a preset sampling frequency (such as once per minute), arranges these data points in chronological order, and removes abnormal fluctuations through data smoothing, and finally forms a temperature change curve that reflects the temperature change over time. The geographical location information of the ladle, including longitude, latitude and altitude, is recorded in real time through the GPS positioning system. These location data are recorded together with the time information (accurate to seconds) to form a spatial position sequence that describes the transportation trajectory. The introduction of the time dimension gives the location information a time series characteristic, which is convenient for subsequent correlation analysis with temperature data.

[0040] The correlation analysis between the temperature change curve and the spatial position sequence is an important means to discover the law of temperature change. By pairing the temperature data at each time point with the corresponding position data, a three-dimensional correlation relationship of temperature-position-time is established. These correlation data also need to be cross-validated with other parameters (such as composition, physical properties, etc.) stored in the recorded data sequence to ensure the consistency and reliability of the data, and finally form multi-dimensional correlation data containing multi-dimensional information. Convert the multi-dimensional correlation data into a standardized transportation control matrix. This process includes normalizing the data so that different types of data can be compared within the same numerical range; reorganizing the data structure according to the correspondence between time and space, and integrating discrete data points into a continuous control sequence. The transportation control matrix finally generated contains complete transportation process monitoring data, providing a basis for subsequent process control.

[0041] For example, when a batch of molten aluminum is transported from the smelting workshop to the casting workshop, the embedded module 104 first receives the quality characterization spectrum of the batch. The temperature data shows that the current melt temperature is 720°C, the composition data shows that the main element Al content is 99.7%, and the physical property data shows that the thermal conductivity is 237W / (m·K). After these data are graded, the temperature data is marked as the highest priority and updated in real time; the composition data is fixedly stored as a basic parameter; and the physical property data is updated and stored regularly. The temperature sensing points arranged in the ladle continuously collect data during transportation. For example, at a certain time point, the top sensor records a temperature distribution of 718°C, 721°C in the middle, and 719°C at the bottom. These data points form a temperature curve over time, and the GPS system records the location information of the transport vehicle. When the transport vehicle turns or climbs a slope, the temperature sensor may detect local temperature fluctuations. These changes correspond to the position data to help analyze the impact of the external environment on the temperature distribution. Finally, all these data are integrated into the transport control matrix to provide a basis for real-time adjustment of insulation measures.

[0042] In a specific embodiment, the decoupling module 105 is specifically used to: (1) Group the temperature data, location data, and time data in the transportation control matrix, perform correlation analysis on the grouped data, and obtain a parameter combination sequence; (2) Decompose the temperature change data in the parameter combination sequence in the time dimension, classify the decomposed data according to the change trend, and obtain the temperature change characteristic value; (3) Analyze the temperature change characteristic values ​​and position change data accordingly, sort the analysis results, and obtain the insulation control parameters; (4) By performing layered processing on the insulation control parameters, the processing results are quantified according to the insulation requirements to obtain the insulation adjustment data; (5) Numerically match the thermal insulation adjustment data with the position state data, combine the matching results according to the time-space correspondence, and obtain the temperature fusion sequence; (6) Extract the key parameters in the temperature fusion sequence, perform spatial distribution analysis on the extracted data, reconstruct the data according to the process requirements, and construct the casting feature field.

[0043] Specifically, the decoupling module 105 is responsible for processing the transport control matrix transmitted from the embedding module 104, and first classifies the data in the matrix. The temperature data includes the real-time temperature value of each point of the melt and its change trend, the position data includes the spatial coordinates and the moving speed during the transportation process, and the time data records the time nodes of the entire transportation process. When grouping these data, the time window division method is adopted to segment the continuous data stream according to a fixed time interval (such as 5 minutes), and the data in each time window is used as an analysis unit. By calculating the correlation coefficient between each parameter, the parameter combination with significant correlation is identified, such as the relationship between temperature change and transportation speed, the relationship between temperature distribution and terrain change, etc., to form a parameter combination sequence reflecting the correlation between parameters. The time dimension decomposition of temperature change data is to deeply understand the law of temperature change. First, the temperature data is expanded according to the time series, and the temperature change is decomposed into three parts: trend term, periodic term and random term through Fourier transform. The trend term reflects the overall change direction of temperature, the periodic term reflects the regular fluctuation of temperature, and the random term represents unpredictable fluctuation. According to these characteristics, the temperature change is divided into a stable period, a fluctuating period and a transition period, and the characteristic parameters of each period, such as the temperature change rate, fluctuation amplitude, etc., are calculated, and finally the temperature change characteristic value describing the temperature change characteristics is obtained.

[0044] When analyzing the temperature change characteristic value and the position change data, the time-space correspondence is first established. Each temperature characteristic value corresponds to a specific position point and time point. By analyzing the mapping relationship between temperature change and position change, the key position points that affect temperature change, such as turning points and slope change points, are identified. The data of these key points are prioritized, and the insulation control requirements of different position points are determined according to the sensitivity of temperature change to form insulation control parameters to guide insulation control. The hierarchical processing of insulation control parameters is to achieve precise temperature control. The insulation control parameters are divided into emergency control layer, conventional control layer and preventive control layer according to the control level. The emergency control layer handles the situation of rapid temperature change, the conventional control layer maintains the normal temperature fluctuation range, and the preventive control layer targets the potential temperature change risks. The control parameters of each level are quantified and calculated to determine specific control indicators, such as heating power, insulation time, etc., and finally form executable insulation adjustment data.

[0045] When matching the insulation adjustment data with the position status data, the actual situation during transportation is taken into account. For example, the insulation intensity needs to be increased in the uphill section, the temperature needs to be maintained constant in the waiting area, and the temperature needs to be prevented from dropping too quickly in the downhill section. By establishing a correspondence between insulation adjustment and position status, it is ensured that appropriate insulation measures can be taken at different locations. These matching results are sorted according to the correspondence between time and space to form a temperature fusion sequence that reflects the temperature control strategy throughout the process. Constructing the casting feature field is a key step in preparing for the subsequent casting process. Extract key control parameters from the temperature fusion sequence, such as temperature uniformity index, temperature gradient distribution, etc. Perform spatial distribution analysis on these parameters to understand the overall distribution characteristics of the temperature field. According to the specific requirements of the casting process, these data are reorganized to construct a feature field reflecting the casting conditions, providing a basis for the precise control of the casting process.

[0046] For example, during the transportation of molten aluminum, the transport control matrix received by the decoupling module 105 shows that at the beginning of transportation, the temperature distribution in the ladle is relatively uniform, and the temperature difference between the top, middle and bottom is within 5°C. When the transport vehicle starts to move, the temperature data shows a correlation with the speed change. The temperature fluctuation increases when accelerating, and the temperature tends to be stable at a constant speed. Through the decomposition of the time dimension, it is found that the temperature change has a periodic fluctuation of about 30 minutes, which coincides with the terrain change cycle of the transportation route. Corresponding analysis found that the temperature drop rate increases at specific locations (such as long uphill sections), and the insulation intensity needs to be increased in advance. These key locations are given a higher control priority, and the corresponding insulation control parameters are also adjusted. For example, the insulation power is increased before the uphill section, and the basic insulation level is maintained in the flat section to ensure that the temperature fluctuation is controlled within the allowable range throughout the process. The constructed casting feature field contains complete temperature distribution information, showing the spatial distribution characteristics of the temperature inside the ladle, and the evolution law of the temperature field over time. This information directly guides the subsequent casting process parameter setting to ensure the smooth progress of the casting process.

[0047] In a specific embodiment, the control module 106 includes: (1) A correlation unit is used to classify and combine the temperature distribution data, spatial position data, and time series change data in the casting characteristic field, and to perform correlation analysis on the combined data to obtain the furnace temperature control parameters; (2) A division unit is used to subdivide the furnace temperature control parameters and divide the subdivision results into intervals according to the temperature fluctuation trend to obtain a heat preservation control sequence; (3) An extraction unit, used to extract data from key control points in the insulation control sequence, cross-validate the extracted data, and obtain compensation control parameters; (4) A comparison unit, which is used to compare the compensation control parameters with the casting process requirements, and to classify the comparison results according to the degree of deviation to obtain a compensation data group; (5) an arrangement unit, used to arrange the process parameters in the compensation data group according to the process sequence, and to perform progressive analysis on the arranged data to obtain a process parameter sequence; (6) Combination unit, which is used to perform multi-level combination of related parameters in the process parameter sequence, reconstruct the data of the combination results according to the process flow, and form a process feature chain.

[0048] Specifically, the control module 106 converts the casting characteristic field transmitted by the decoupling module 105 into specific process control parameters. First, the association unit receives the casting characteristic field data, which contains three types of key information: temperature distribution data (reflecting the temperature value and distribution law of the melt at each point in space), spatial position data (describing the spatial coordinates of the temperature measurement point and its relative relationship), and time series change data (recording the temperature change trend over time). These three types of data are classified and combined to form a data group, and then the internal connection between the data is identified by the association analysis method, such as the correlation between the temperatures at different positions, the corresponding relationship between the temperature change and time, etc., and finally the control parameters for controlling the furnace temperature are obtained. After receiving the furnace temperature control parameters, the division unit first performs parameter segmentation. The temperature change range is divided into multiple control intervals, such as preheating interval, insulation interval, temperature adjustment interval, etc. In each interval, the specific control requirements are determined according to the characteristics of the temperature fluctuation (such as fluctuation amplitude, fluctuation frequency, change rate, etc.). These subdivided control requirements are integrated into a complete insulation control sequence to guide the operation of the insulation furnace.

[0049] The main task of the extraction unit is to identify and extract key control points from the insulation control sequence. These control points include temperature mutation points, steady-state transition points, critical control points, etc. The data of each control point needs to be cross-validated, that is, compared and verified with the data of adjacent time points and adjacent spatial points to ensure the accuracy and representativeness of the data. The verified control point data is organized into compensation control parameters for subsequent temperature compensation control. The comparison unit compares the compensation control parameters with the preset casting process requirements in detail. The process requirements include temperature control accuracy, uniformity requirements, insulation time requirements and other aspects. By calculating the deviation value between the parameters and the requirements, and grading them according to the size of the deviation, such as dividing the deviation into severe deviation, moderate deviation, slight deviation and other levels, corresponding compensation strategies are formulated for different levels of deviation, and finally a compensation data group is formed.

[0050] The arrangement unit is responsible for rearranging the process parameters in the compensation data group according to the order of the actual casting process. The casting process includes multiple stages such as preheating, heating, constant temperature maintenance, temperature adjustment, pouring, etc., and each stage has its specific process requirements. By progressively analyzing the arranged data, the connectivity and continuity of the parameters between the various processes are ensured, and finally a complete process parameter sequence is generated. The combination unit is the last processing link, which is responsible for multi-level combination of related parameters in the process parameter sequence. This combination takes into account the mutual influence and constraint relationship between the parameters to ensure that the various parameters can be coordinated during the execution process. The final combination result is reconstructed according to the process flow to form a complete process feature chain, which includes the process parameters and control requirements of the whole process from raw materials to finished products.

[0051] For example, when a batch of molten aluminum enters the casting stage, the control module 106 first processes the casting characteristic field data through the association unit. The temperature distribution data shows the temperature values ​​at different positions in the furnace, the spatial position data records the specific positions of these temperature measurement points, and the time series change data reflects the temperature change trend. After the correlation analysis of these data, the influence relationship between each temperature control point is determined. The division unit divides the temperature control range into different intervals, such as 720-740℃ as the working interval and 710-720℃ as the warning interval. Each interval has a corresponding control strategy, for example, a conventional heating mode is used in the working interval, and a rapid heating mode needs to be started in the warning interval. These control strategies are integrated into a heat preservation control sequence. The extraction unit identifies key points from the control sequence, such as the inflection point where the temperature begins to drop, the mutation point where the temperature fluctuation increases, etc. The data of these points are cross-validated with the surrounding data to confirm their reliability, and then form compensation control parameters. The comparison unit compares these parameters with the process standards, and when it is found that there is a deviation in temperature uniformity, the corresponding compensation plan is immediately generated. The arrangement unit sorts the compensation schemes according to the casting process to ensure that the temperature parameters of each process can meet the process requirements. Finally, the combination unit integrates these sorted parameters into a complete process feature chain to guide the temperature control of the entire casting process.

[0052] In a specific embodiment, the division unit is specifically used for: (1) The furnace temperature control parameters are grouped according to the temperature range, change rate, and fluctuation amplitude, and the grouped data are converted into numerical values ​​to obtain temperature characteristic data; (2) Segment the temperature characteristic data in the time dimension, sort the segmentation results according to the numerical value, and obtain a time series data group; (3) Combine the associated parameters in the time series data group, calculate the correlation of the combined data, and obtain the fluctuation trend value; (4) Delimit the interval of the fluctuation trend value according to the law of change, normalize the definition result, and obtain the interval parameter; (5) Match the interval parameters with the temperature control requirements, perform graded processing on the matching results, and obtain a control data group; (6) Reconstruct the parameters of the control data group according to the insulation requirements, integrate the reconstruction results, and obtain the insulation control sequence.

[0053] Specifically, the division unit first groups the received furnace temperature control parameters in multiple dimensions, including temperature range (temperature range of the melt in different areas), rate of change (how fast the temperature changes over time), and amplitude of fluctuation (how much the temperature deviates from the average value). These grouped data are standardized and converted into numerical forms of unified dimensions to form temperature characteristic data. Time dimension segmentation is an important step in time series analysis of temperature characteristic data. Continuous temperature data are segmented at fixed time intervals, and each time segment is used as an independent analysis unit. These segmented data are sorted according to the size of the temperature value to form an ordered time series data group, which is convenient for discovering the regular characteristics of temperature changes.

[0054] The time series data set contains multiple related parameters, such as the average temperature, temperature change rate, temperature fluctuation range, etc. within a certain period of time. These intrinsically related parameters are combined, and the correlation coefficient between the parameters is calculated to evaluate the degree of correlation between the parameters. This correlation analysis helps to identify the main trend of temperature change and obtain the fluctuation trend value that reflects the characteristics of temperature change. The interval definition of the fluctuation trend value is to divide the continuous data into discrete control intervals. According to the law of temperature change, stable intervals, fluctuation intervals, transition intervals, etc. can be divided. The definition results of these intervals are normalized to unify the data of different scales into the standard range to obtain standardized interval parameters.

[0055] The interval parameters need to be matched with the specific temperature control requirements. The temperature control requirements include the allowable temperature fluctuation range, temperature uniformity requirements, heating and cooling rate limits, etc. By comparing the degree of compliance between the interval parameters and the control requirements, the matching results are graded to form a hierarchical control data group.

[0056] Parameter reconstruction reorganizes the control data group according to the requirements of the actual insulation process. This process takes into account the requirements of insulation time, insulation temperature, temperature uniformity, etc., and integrates discrete control parameters into a complete insulation control sequence.

[0057] For example, when a batch of molten aluminum needs to be kept warm, the furnace temperature control parameters are first received. These parameters show that the temperature distribution range at different locations is between 710-730°C, the temperature change rate is about 2°C / minute, and the temperature fluctuation range is within ±5°C. These data are standardized and converted into relative values. The time dimension segmentation divides the temperature data into a time window of 10 minutes. The temperature data in each window is sorted to show the periodic characteristics of temperature changes. Correlation analysis found that there is a positive correlation between the temperature change rate and the fluctuation amplitude, that is, the faster the temperature changes, the greater the fluctuation amplitude.

[0058] According to these analysis results, the temperature control interval is divided into: stable interval (temperature change rate <1℃ / minute), adjustment interval (temperature change rate 1-3℃ / minute) and transition interval (temperature change rate >3℃ / minute). Each interval has a corresponding control strategy, such as maintaining the existing heating power in the stable interval, dynamically adjusting the heating power in the adjustment interval, and implementing special control measures in the transition interval.

[0059] In a specific embodiment, the comparison unit is specifically used for: (1) Extract the temperature value, time value, and fluidity value in the compensation control parameters, standardize the extracted data, and obtain the compensation reference value; (2) Numerically process the parameter indicators in the casting process requirements, sort the processing results according to priority, and obtain the process standard value; (3) Calculate the difference between the compensation reference value and the process standard value, screen the calculation results, and obtain the deviation data; (4) The deviation data is graded according to the numerical value, and the classification results are thresholded to obtain a deviation grade table; (5) Reorganize the parameters in the deviation level table according to the compensation requirements, optimize the reorganization results, and obtain the compensation parameter group; (6) Integrate the compensation parameter group data, calibrate the integration results according to the process requirements, and obtain the compensation data group.

[0060] Specifically, key data in the compensation control parameters are extracted, including temperature values ​​(reflecting the current temperature state of the melt), time values ​​(indicating the duration of the process), fluidity values ​​(characterizing the flow characteristics of the melt), etc. These extracted raw data are standardized, and data of different dimensions are converted into a unified numerical range to form comparable compensation reference values. Casting process requirements usually include process indicators at multiple levels, and these qualitative and quantitative requirements need to be converted into specific numerical parameters. For example, temperature uniformity requirements are converted into the allowable temperature fluctuation range, fluidity requirements are converted into flow rate range values, and time requirements are converted into the duration of each process. These converted values ​​are prioritized according to the degree of impact on product quality, and ultimately form standardized process standard values.

[0061] The difference calculation between the compensation reference value and the process standard value reflects the degree of deviation between the actual process parameters and the standard requirements. The difference calculation adopts the relative error method, which takes into account both the size of the absolute error and the deviation ratio relative to the standard value. The calculated difference is screened to eliminate insignificant deviations and retain the deviation data that needs to be compensated. The grading of deviation data is to formulate compensation strategies of different levels. According to the numerical size of the deviation, multiple threshold intervals are set to divide the deviation into different levels. For example, it can be divided into levels such as slight deviation (needs fine-tuning), moderate deviation (needs regular adjustment), and severe deviation (needs urgent treatment) to form a complete deviation grade table.

[0062] The parameters in the deviation level table need to be reorganized according to the compensation requirements. Different compensation strategies are used for different levels of deviations, such as progressive compensation for minor deviations, step compensation for moderate deviations, and mandatory compensation measures for severe deviations. These compensation strategies are optimized to form executable compensation parameter groups. The compensation parameter groups are integrated and calibrated. The integration process needs to consider the mutual influence between parameters to ensure that there is no conflict between the various compensation measures. The calibration process is to adjust the compensation parameters to the range that best suits the actual process conditions, and finally form a complete compensation data group.

[0063] For example, when a set of compensation control parameters is received, the current temperature value of 725°C, the process duration of 45 minutes, the fluidity index and other data are first extracted. These data are standardized and uniformly converted to a numerical range of 0-1 to form a compensation reference value. At the same time, the process requirements stipulate that the standard temperature is 720±5°C, the process time is required to be 40-50 minutes, and the fluidity is required to be in a specific range. These requirements are converted into specific numerical standards, among which temperature control is given the highest priority because it directly affects product quality.

[0064] By calculating the difference between the compensation reference value and the process standard value, it was found that the temperature exceeded the standard by 5°C, the time was within the allowable range, and the fluidity had a slight deviation. These deviations are divided into different levels. The temperature deviation is a moderate deviation and needs to be adjusted in time; the fluidity deviation is a slight deviation and can be solved by fine-tuning. Compensation strategies are formulated according to the deviation level. For temperature deviation, a step-by-step cooling method is adopted, with a cooling of 1°C each time and an interval of 2 minutes to observe the effect; for fluidity deviation, indirect adjustment is made by fine-tuning the temperature. These compensation measures are integrated and calibrated to form a complete compensation plan to guide subsequent process adjustments.

[0065] The above describes the integrated management system for the molten aluminum processing technology in the embodiment of the present application. The following describes the integrated management method for the molten aluminum processing technology in the embodiment of the present application. Figure 2In the embodiment of the present application, an embodiment of the integrated management method of molten aluminum processing technology includes: S201, performing multi-level cross-coding processing on aluminum raw materials to obtain batch feature codes, performing multi-dimensional mapping analysis on the batch feature codes and material inherent characteristic data to obtain a process feature matrix, hierarchically deconstructing material properties according to the process feature matrix to obtain deep identification information; S202, performing nonlinear dynamic configuration of melting parameters according to the depth identification information, performing multi-dimensional quantitative processing on the melting state by coupling analysis of the temperature field, flow field, and pressure field data during the melting process, and obtaining a melting characteristic spectrum; S203, performing multivariate cross-quality inspection on the molten aluminum according to the melting characteristic spectrum, performing hierarchical progressive analysis on the inspection data, performing multi-dimensional cross-mapping on the depth identification information, the melting characteristic spectrum and the quality inspection data, and obtaining a quality characterization spectrum; S204, embedding hierarchical information into the ladle recording unit according to the quality characterization spectrum, dynamically tracking the temperature field, four-dimensionally associating the spatial position data with the quality characterization spectrum, and generating a transportation control matrix; S205, decoupling multiple parameters of temperature changes according to the transport control matrix, adaptively fusing the position state and the temperature field data by performing layered quantitative adjustment on the insulation state, and constructing a casting characteristic field; S206. Through the casting characteristic field, the holding furnace is controlled by multi-dimensional parameter linkage, the casting process is adaptively compensated, and the process parameters are progressively integrated at multiple levels to form a process characteristic chain.

[0066] In the embodiment of the present application, a deep deconstruction of raw material characteristics is achieved by combining multi-level cross coding with multi-dimensional mapping analysis, providing an accurate data basis for subsequent process control. The nonlinear dynamic configuration technology is used to regulate the melting parameters, and the coupled analysis of temperature field, flow field and pressure field is combined to make the control of the melting process more accurate. Through multi-variable cross quality inspection and hierarchical progressive analysis, all-round monitoring of quality data is achieved, and a complete quality characterization system is established through multi-dimensional cross mapping. In the transportation link, hierarchical information embedding technology and four-dimensional correlation analysis are used to achieve accurate tracking and control of the transportation process. The application of multi-parameter decoupling technology makes the control of temperature changes more flexible, and the stability of melt temperature is ensured through hierarchical quantitative adjustment and adaptive fusion. Finally, multi-dimensional parameter linkage regulation and adaptive compensation technology are used to achieve accurate control of the casting process, and multi-level progressive integration ensures the continuity and stability of process parameters. This integrated management method for the entire process significantly improves the automation level and process control accuracy of molten aluminum processing, effectively reduces product quality fluctuations, and provides reliable data support for process optimization through full data tracing.

[0067] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application 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 application.

Claims

1. A molten aluminum processing technology integrated management system, characterized in that: The molten aluminum processing technology integrated management system includes: an encoding module, a configuration module, a quality inspection module, an embedding module, a decoupling module and a control module; the output end of the encoding module is connected to the input end of the configuration module, the output end of the configuration module is connected to the input end of the quality inspection module, the output end of the quality inspection module is connected to the input end of the embedding module, the output end of the embedding module is connected to the input end of the decoupling module, and the output end of the decoupling module is connected to the input end of the control module, wherein the encoding module is also connected to the quality inspection module to provide depth identification information to the quality inspection module, and the output end of the control module is also connected to the encoding module to provide process feature chain data; The coding module is used to obtain a batch feature code by performing multi-level cross-coding processing on the aluminum raw materials, and to perform multi-dimensional mapping analysis on the batch feature code and the inherent characteristic data of the material to obtain a process feature matrix, and to perform hierarchical deconstruction of the material attributes according to the process feature matrix to obtain deep identification information; A configuration module is used to perform nonlinear dynamic configuration of melting parameters according to the depth identification information, and to obtain a melting characteristic spectrum by performing multi-dimensional quantitative processing on the melting state through coupling analysis of the temperature field, flow field, and pressure field data during the melting process; A quality inspection module is used to perform multivariate cross-quality inspection on the molten aluminum according to the melting characteristic spectrum, perform hierarchical and progressive analysis on the inspection data, and perform multi-dimensional cross-mapping of the depth identification information, the melting characteristic spectrum and the quality inspection data to obtain a quality characterization spectrum; An embedding module is used to embed hierarchical information into the ladle recording unit according to the quality characterization spectrum, and to generate a transportation control matrix by dynamically tracking the temperature field and four-dimensionally correlating the spatial position data with the quality characterization spectrum; A decoupling module is used to perform multi-parameter decoupling of temperature changes according to the transport control matrix, and to adaptively fuse the position state and the temperature field data by performing hierarchical quantitative adjustment on the insulation state to construct a casting characteristic field; The control module is used to perform multi-dimensional parameter linkage control on the holding furnace through the casting characteristic field, perform adaptive compensation on the casting process, and perform multi-level progressive integration of process parameters to form a process characteristic chain.

2. The molten aluminum processing technology integrated management system according to claim 1, characterized in that: The encoding module is specifically used for: Extracting component composition, material specifications, and production batch number data from the aluminum raw materials, and grouping the data according to a preset arrangement order to obtain a raw material basic data group; Numerical processing is performed on each group of data in the raw material basic data group, the component composition is converted into the element content percentage, the specification data is converted into the standard size value, and the batch number data is converted into the time series value, so as to obtain a numerical data sequence; The numerical data sequence is weighted according to the importance of the elements, and the weighted data is cross-combined to generate a batch feature code; By extracting data on the purity value, density value, thermal conductivity, and melting point temperature of the aluminum raw material, a material inherent characteristic data set is constructed, the batch characteristic code is matched with the material inherent characteristic data set, a data mapping relationship is established, and a process characteristic matrix is ​​obtained; According to the process characteristic matrix, the material attribute data is layered according to the three dimensions of physical properties, chemical properties, and process characteristics, and the correlation degree of each layer of data is calculated to obtain attribute correlation data; The key parameters in the attribute association data are extracted, the mutual influence between the parameters is quantified, and the quantification result is fused with the process feature matrix to obtain deep identification information.

3. The molten aluminum processing technology integrated management system according to claim 1, characterized in that: The configuration module is specifically used for: The physical characteristic parameters, chemical characteristic parameters, and process characteristic parameters in the depth identification information are extracted respectively, and the parameters are divided into numerical intervals to obtain melting control parameters; Calculating the data correlation of the melting control parameters, combining the parameters with correlation coefficients higher than a set threshold value, and obtaining a parameter correlation group; Prioritizing the parameter association groups according to process importance, cross-validating each parameter association group, and obtaining nonlinear dynamic configuration parameters; By collecting the temperature value, flow velocity and pressure change data in the melting furnace, the collected data are analyzed in time series to obtain the field data sequence; The temperature field, flow field and pressure field data in the field data sequence are correlated and calculated, and the coupling characteristic value is obtained by quantifying the interaction intensity of the physical quantities; The coupling characteristic values ​​are transformed in a multi-dimensional space, the transformed data are cross-mapped with the nonlinear dynamic configuration parameters, the mapping results are quantitatively evaluated, and the melting characteristic spectrum is obtained.

4. The molten aluminum processing technology integrated management system according to claim 1, characterized in that: The quality inspection module is specifically used for: Segmenting the melting characteristic spectrum according to element content, impurity content, and temperature distribution, and normalizing the segmented data to obtain quality inspection benchmark data; Conducting density, hardness, thermal conductivity and fluidity tests on the molten aluminum, comparing and analyzing the test results with quality inspection benchmark data to obtain a quality inspection parameter group; Combining and classifying the relevant parameters in the quality inspection parameter group, and performing progressive analysis on the classified data to obtain quality inspection characteristic values; Extract material attribute data from the depth identification information, and calculate the correlation between the material attribute data and the quality inspection characteristic value to obtain a quality correlation matrix; Performing data fusion on the mass correlation matrix and the melting characteristic spectrum, and obtaining a quality characteristic group by cross-validating the fused data; The quality feature groups are graded according to parameter importance, the graded data are combined in multiple dimensions, and numerical mapping is performed according to quality evaluation standards to obtain a quality characterization spectrum.

5. The molten aluminum processing technology integrated management system according to claim 1, characterized in that: The embedded module is specifically used for: The temperature data, the composition data, and the physical property data in the quality characterization spectrum are graded according to their importance, and the graded data are coded and converted to obtain a graded data group; Dividing the storage capacity of the ladle recording unit into blocks, and writing the hierarchical data groups into corresponding blocks according to the data priority order to obtain a recording data sequence; The temperature data are collected by temperature sensing points arranged inside the ladle, and a time series analysis is performed on the collected data to obtain a temperature change curve; Combining the longitude, latitude, altitude, and time data of the ladle during transportation to obtain a spatial position sequence; Performing data association between the temperature change curve and the spatial position sequence, cross-validating the association result with the recorded data sequence, and obtaining multi-dimensional association data; By performing numerical conversion on the multi-dimensional correlation data, reorganizing the conversion results, and integrating the data according to the time-space correspondence, a transportation control matrix is ​​generated.

6. The molten aluminum processing technology integrated management system according to claim 1, characterized in that: The decoupling module is specifically used for: The temperature data, the position data, and the time data in the transportation control matrix are grouped, and a correlation analysis is performed on the grouped data to obtain a parameter combination sequence; Decomposing the temperature change data in the parameter combination sequence in a time dimension, classifying the decomposed data according to the change trend, and obtaining a temperature change characteristic value; Analyze the temperature change characteristic value and the position change data accordingly, sort the analysis results, and obtain the insulation control parameters; By performing layered processing on the insulation control parameters, the processing results are quantitatively calculated according to the insulation requirements to obtain insulation adjustment data; Numerical matching is performed on the thermal insulation adjustment data and the position state data, and the matching results are combined according to the time-space correspondence to obtain a temperature fusion sequence; The key parameters in the temperature fusion sequence are extracted, the spatial distribution analysis is performed on the extracted data, the data is reconstructed according to the process requirements, and the casting characteristic field is constructed.

7. The molten aluminum processing technology integrated management system according to claim 1, characterized in that: The control module comprises: A correlation unit is used to classify and combine the temperature distribution data, spatial position data, and time series change data in the casting characteristic field, and to perform correlation analysis on the combined data to obtain furnace temperature control parameters; A division unit, used for performing subdivision processing on the furnace temperature control parameters, dividing the subdivision results into intervals according to the temperature fluctuation trend, and obtaining a heat preservation control sequence; An extraction unit, used for extracting data from key control points in the insulation control sequence, cross-validating the extracted data, and obtaining compensation control parameters; A comparison unit, used for comparing the compensation control parameters with the casting process requirements, and performing graded processing on the comparison results according to the degree of deviation to obtain a compensation data group; An arrangement unit, used for arranging the process parameters in the compensation data group according to the process sequence, and performing progressive analysis on the arranged data to obtain a process parameter sequence; The combination unit is used to perform multi-level combination on the related parameters in the process parameter sequence, reconstruct the data of the combination result according to the process flow, and form a process feature chain.

8. The molten aluminum processing technology integrated management system according to claim 7, characterized in that: The division unit is specifically used for: The furnace temperature control parameters are grouped according to the temperature range, change rate, and fluctuation amplitude, and the grouped data are converted into numerical values ​​to obtain temperature characteristic data; The temperature characteristic data is segmented by time dimension, and the segmentation results are sorted according to the numerical values ​​to obtain a time series data group; Combining the associated parameters in the time series data group, performing correlation calculation on the combined data, and obtaining a fluctuation trend value; Delimiting the fluctuation trend value according to the variation law, and performing numerical normalization processing on the definition result to obtain the interval parameter; Performing data matching between the interval parameters and the temperature control requirements, and performing graded processing on the matching results to obtain a control data group; The control data group is parameter reconstructed according to the insulation requirements, and the reconstruction results are integrated to obtain the insulation control sequence.

9. The molten aluminum processing technology integrated management system according to claim 8, characterized in that: The comparison unit is specifically used for: Extracting the temperature value, time value and fluidity value in the compensation control parameters, and standardizing the extracted data to obtain a compensation reference value; Numerically processing the parameter indicators in the casting process requirements, sorting the processing results according to priority, and obtaining process standard values; Calculate the difference between the compensation reference value and the process standard value, and perform data screening on the calculation result to obtain deviation data; The deviation data is graded according to the numerical value, and the grading results are thresholded to obtain a deviation grade table; Reorganize the parameters in the deviation level table according to the compensation requirements, optimize the reorganization results, and obtain a compensation parameter group; The compensation parameter group is integrated, and the integration result is calibrated according to the process requirements to obtain a compensation data group.

10. A method for integrated management of molten aluminum processing technology, characterized in that: The integrated management method for molten aluminum processing technology comprises: The batch characteristic code is obtained by performing multi-level cross-coding processing on the aluminum raw materials, and the batch characteristic code is analyzed with the inherent characteristic data of the material in a multi-dimensional manner to obtain a process characteristic matrix. The material properties are hierarchically deconstructed according to the process characteristic matrix to obtain deep identification information; According to the depth identification information, nonlinear dynamic configuration of melting parameters is performed, and the melting state is quantitatively processed in multiple dimensions by coupling analysis of temperature field, flow field, and pressure field data during the melting process to obtain a melting characteristic spectrum; According to the melting characteristic spectrum, a multivariate cross-quality inspection is performed on the molten aluminum, the detection data is analyzed in layers and progressively, and the depth identification information, the melting characteristic spectrum and the quality inspection data are multi-dimensionally cross-mapped to obtain a quality characterization spectrum; According to the quality characterization spectrum, hierarchical information is embedded in the ladle recording unit, and the spatial position data is four-dimensionally associated with the quality characterization spectrum by dynamically tracking the temperature field to generate a transportation control matrix; According to the transport control matrix, multiple parameters of temperature change are decoupled, and the position state and temperature field data are adaptively fused by layered quantitative adjustment of the insulation state to construct a casting characteristic field; Through the casting characteristic field, the holding furnace is controlled by multi-dimensional parameter linkage, the casting process is adaptively compensated, and the process parameters are progressively integrated at multiple levels to form a process characteristic chain.

Images