A multi-parameter coordination-based carbon graphite product pressing control system and method

Abstract

The application discloses a carbon graphite product pressing control system and method based on multi-parameter cooperation, relates to the graphite pressing control technical field, and sets initial process parameters for each processing link by using a process parameter setting unit, adopts a real-time monitoring unit and a feedback compensation unit, establishes a feedback mechanism for adjusting the initial process parameters by using real-time data, realizes first-stage adjustment of the process parameters, adjusts other parameters by using the correlation between different process parameters in a single processing link through a process parameter adjustment unit, realizes second-stage adjustment of the process parameters, and finally adjusts the process parameters of subsequent processing links by using real-time process parameters of previous processing links through a process parameter coupling unit, and completes third-stage adjustment of the process parameters. The application realizes optimization of the graphite product pressing process by establishing a three-stage adjustment mechanism for the process parameters, so that the quality of the graphite product is improved.

Description

Technical Field

[0001] This invention relates to the field of graphite molding control technology, and in particular to a carbon graphite product molding control system and method based on multi-parameter coordination. Background Technology

[0002] The molding process for carbon graphite products is a crucial step in the carbon graphite production process, shaping raw materials into preforms with specific shapes, sizes, and densities. Its core principle is to use external force to densify and shape the plastic raw material within a mold, providing a qualified preform for subsequent processes such as calcination and graphitization. This process directly affects the key properties of the final product, including density, strength, and structural uniformity, and is widely used in the production of graphite products.

[0003] The main process of molding can be divided into several stages, including raw material preparation, mixing, and molding. However, the current molding process suffers from the following problems: First, there are numerous process parameters in each stage, and the lack of a unified coupling mechanism between these parameters leads to uncontrolled process stability. Second, there is a lack of a collaborative compensation mechanism between parameters in each stage. Third, real-time monitoring data in each stage cannot be fed back in a timely manner. These problems make it impossible to guarantee the quality of the paste, the molding process, and batch consistency, ultimately resulting in defects such as cracks, dimensional deviations, out-of-roundness, and quality fluctuations, severely affecting the quality of graphite products. Summary of the Invention

[0004] In view of this, this application provides a carbon graphite product molding control system and method based on multi-parameter coordination to overcome the shortcomings of the prior art.

[0005] The first aspect of this application provides a carbon graphite product molding control system based on multi-parameter coordination, comprising:

[0006] Process parameter setting unit: Sets corresponding initial process parameters for each processing step in the carbon graphite product molding process;

[0007] Real-time monitoring unit: Each processing stage is equipped with corresponding monitoring equipment, which simultaneously acquires real-time monitoring data;

[0008] Feedback compensation unit: Based on the real-time monitoring data, adjusts the corresponding initial process parameters in each processing stage to obtain real-time process parameters;

[0009] Process parameter adjustment unit: Based on the real-time process parameters and corresponding initial process parameters in each processing stage, determine whether there is a change ratio between the real-time process parameter and the corresponding initial process parameter in a single processing stage that exceeds the set value. If so, record the corresponding process parameter as the main process parameter and the remaining process parameters as the secondary process parameters, and use each main process parameter to adjust all secondary process parameters in sequence. If not, do not take any action.

[0010] Process parameter coupling unit: Based on the processing sequence of the processing steps, it obtains the adjusted real-time process parameters in the initial processing step and integrates them to obtain the initial processing result. Based on the initial processing result, different influence coefficients are set for all subsequent processing steps.

[0011] In all subsequent processing stages except the final processing stage, any processing stage is selected and denoted as an intermediate processing stage. The adjusted real-time process parameters of the intermediate processing stage are obtained and integrated with the influence coefficients transmitted by all upstream processing stages located in the intermediate processing stage to obtain the intermediate processing result. Based on the intermediate processing result, different influence coefficients are set for all downstream processing stages located in the intermediate processing stage.

[0012] The real-time process parameters, adjusted in all processing stages, are dynamically adjusted in conjunction with all received influence coefficients.

[0013] In one possible implementation of the first aspect, based on the real-time monitoring data, the corresponding initial process parameters in each processing stage are adjusted to obtain the real-time process parameters, including:

[0014] Acquire all real-time monitoring data within the first time interval and construct a curve showing the change of real-time monitoring data over time;

[0015] The curve is fitted to obtain the curvature value of the corresponding real-time monitoring data for each first time interval;

[0016] Based on the changed curvature value, the process parameters corresponding to the real-time monitoring data are adjusted to obtain the real-time process parameters.

[0017] In one possible implementation of the first aspect, determining whether there is a change ratio between real-time process parameters and corresponding initial process parameters exceeding a set value in a single processing step includes:

[0018] The following formula is used to calculate the ratio of change between real-time process parameters and corresponding initial process parameters:

[0019]

[0020] The change ratio value, For real-time process parameters, These are the corresponding initial process parameters.

[0021] In one possible implementation of the first aspect, the corresponding process parameters are denoted as master process parameters, the remaining process parameters are denoted as slave process parameters, and all slave process parameters are adjusted sequentially using each master process parameter, including:

[0022] Acquire any processing step, denoted as the first processing step, and simultaneously acquire historical data of all process parameters in the first processing step;

[0023] Based on the historical data and the prior data of the first processing stage, a correlation model between a single process parameter and other process parameters is constructed.

[0024] Obtain the association model corresponding to the main process parameters in the first processing step, and record the corresponding main process parameters as the first main process parameters;

[0025] After inputting the first master process parameter and the remaining slave process parameters into the corresponding association model, the adjusted slave process parameters are output, thus completing the adjustment of the remaining slave process parameters.

[0026] In one possible implementation of the first aspect, the process of obtaining the initial processing result includes:

[0027] Obtain all adjusted real-time process parameters of the initial processing stage, and record them as the first real-time process parameters;

[0028] All first real-time process parameters are normalized under the same data protocol and placed into a preset dataset, corresponding to a multi-parameter feature set;

[0029] Obtain all multi-parameter feature sets and corresponding processing quality index data of the initial processing stage within the second time interval, and extract distribution features from the multi-parameter feature sets;

[0030] Establish a mapping table between the distribution characteristics of the multi-parameter feature set and the corresponding processing quality index data;

[0031] Using the adjusted real-time process parameters from the initial processing stage and the mapping table, the processing quality index data corresponding to the initial processing stage is output as the initial processing result.

[0032] In one possible implementation of the first aspect, different influence coefficients are set for all subsequent processing stages, including:

[0033] Based on the initial processing results, the corresponding processing quality index data is obtained and recorded as the first processing quality index data;

[0034] Based on all the first processing quality index data and the corresponding processing quality index data of the remaining processing steps within the third time interval, a quantitative model for adjusting the corresponding process parameters of the remaining processing steps is constructed and trained.

[0035] The first processing quality index data in the initial processing stage and the real-time process parameters of the remaining processing stages are obtained and input into the trained quantization model, and the influence coefficients on the remaining processing stages are output.

[0036] In one possible implementation of the first aspect, the intermediate processing results include:

[0037] The adjusted real-time process parameters in the intermediate processing stage are obtained and multiplied with the influence coefficients transmitted from all corresponding upstream processing stages to obtain the corrected real-time process parameters.

[0038] Using the corrected real-time process parameters and corresponding mapping table of the intermediate processing steps, the processing quality index data corresponding to the intermediate processing steps are output as the intermediate processing result.

[0039] In one possible implementation of the first aspect, based on the intermediate processing result, setting different influence coefficients for all downstream processing stages located in the intermediate processing stage includes:

[0040] Obtain the quantization model corresponding to the intermediate processing step, denoted as the first quantization model, and train it.

[0041] The processing quality index data corresponding to the intermediate processing stage and the real-time process parameters of the remaining processing stages are input into the first quantification model after training, and the influence coefficients on all downstream processing stages located in the intermediate processing stage are output.

[0042] In one possible implementation of the first aspect, the dynamic adjustment of the adjusted real-time process parameters in all processing stages, combined with all received influence coefficients, includes:

[0043] Calculate the product of the adjusted real-time process parameters in any processing stage and the corresponding received influence coefficients to obtain the product result;

[0044] Based on the product result, the real-time process parameters of the corresponding processing steps are dynamically adjusted.

[0045] The second aspect of this application provides a method for controlling the molding of carbon graphite products based on multi-parameter synergy, including:

[0046] For each processing step in the carbon graphite product molding process, corresponding initial process parameters are set;

[0047] Each processing stage is equipped with corresponding monitoring equipment, and real-time monitoring data is acquired simultaneously.

[0048] Based on the real-time monitoring data, the corresponding initial process parameters in each processing stage are adjusted to obtain the real-time process parameters;

[0049] Based on the real-time process parameters and corresponding initial process parameters in each processing stage, determine whether there is a change ratio between the real-time process parameter and the corresponding initial process parameter in a single processing stage that exceeds the set value. If so, record the corresponding process parameter as the main process parameter and the remaining process parameters as the secondary process parameters, and use each main process parameter to adjust all secondary process parameters in sequence. If not, do not take any action.

[0050] Based on the processing sequence of the processing steps, the adjusted real-time process parameters in the initial processing step are obtained and integrated to obtain the initial processing result. Based on the initial processing result, different influence coefficients are set for all subsequent processing steps.

[0051] In all subsequent processing stages except the final processing stage, any processing stage is selected and denoted as an intermediate processing stage. The adjusted real-time process parameters of the intermediate processing stage are obtained and integrated with the influence coefficients transmitted by all upstream processing stages located in the intermediate processing stage to obtain the intermediate processing result. Based on the intermediate processing result, different influence coefficients are set for all downstream processing stages located in the intermediate processing stage.

[0052] The real-time process parameters, adjusted in all processing stages, are dynamically adjusted in conjunction with all received influence coefficients.

[0053] The beneficial effects are as follows: This invention discloses a carbon graphite product molding control system and method based on multi-parameter coordination. It utilizes a process parameter setting unit to set initial process parameters for each processing stage, and employs a real-time monitoring unit and a feedback compensation unit to establish a feedback mechanism that adjusts the initial process parameters using real-time data, achieving primary adjustment of the process parameters. Then, through a process parameter adjustment unit, it utilizes the correlation between different process parameters in a single processing stage, and combines this with process parameters that have a larger adjustment range to adaptively adjust other parameters, achieving secondary adjustment of the process parameters. Finally, using a process parameter coupling unit, it analyzes the coupling of multiple process parameters between different stages, and uses the real-time process parameters of the preceding processing stages to adaptively adjust the process parameters of subsequent processing stages, completing tertiary adjustment of the process parameters. This invention optimizes the graphite product molding process by establishing a three-level adjustment mechanism for process parameters, thereby improving the quality of graphite products. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0055] Figure 1 This is a schematic diagram of a carbon graphite product molding control system based on multi-parameter coordination, provided in an embodiment of this application.

[0056] Figure 2 This is a schematic diagram of a carbon graphite product molding control method based on multi-parameter coordination provided in an embodiment of this application. Detailed Implementation

[0057] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0058] In this application, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0059] Example 1

[0060] In existing technologies, the main process of molding can be divided into several steps such as raw material preparation, mixing, and molding. However, the current molding process has the following problems: First, there are many process parameters in each step, and there is no unified coupling mechanism between the parameters in each step, which leads to the loss of process stability control. Second, there is no collaborative compensation mechanism between parameters in each step. Third, real-time monitoring data in each step cannot be fed back in a timely manner.

[0061] Therefore, this application provides a carbon graphite product molding control system based on multi-parameter coordination, such as... Figure 1As shown, it includes:

[0062] Process parameter setting unit: Sets corresponding initial process parameters for each processing step in the carbon graphite product molding process;

[0063] Real-time monitoring unit: Each processing stage is equipped with corresponding monitoring equipment, which simultaneously acquires real-time monitoring data;

[0064] Feedback compensation unit: Based on the real-time monitoring data, adjusts the corresponding initial process parameters in each processing stage to obtain real-time process parameters;

[0065] Process parameter adjustment unit: Based on the real-time process parameters and corresponding initial process parameters in each processing stage, determine whether there is a change ratio between the real-time process parameter and the corresponding initial process parameter in a single processing stage that exceeds the set value. If so, record the corresponding process parameter as the main process parameter and the remaining process parameters as the secondary process parameters, and use each main process parameter to adjust all secondary process parameters in sequence. If not, do not take any action.

[0066] Process parameter coupling unit: Based on the processing sequence of the processing steps, it obtains the adjusted real-time process parameters in the initial processing step and integrates them to obtain the initial processing result. Based on the initial processing result, different influence coefficients are set for all subsequent processing steps.

[0067] In all subsequent processing stages except the final processing stage, any processing stage is selected and denoted as an intermediate processing stage. The adjusted real-time process parameters of the intermediate processing stage are obtained and integrated with the influence coefficients transmitted by all upstream processing stages located in the intermediate processing stage to obtain the intermediate processing result. Based on the intermediate processing result, different influence coefficients are set for all downstream processing stages located in the intermediate processing stage.

[0068] The real-time process parameters, adjusted in all processing stages, are dynamically adjusted in conjunction with all received influence coefficients.

[0069] In particular, corresponding initial process parameters are set for each processing step in the carbon graphite product molding process. The processing steps include raw material preparation, raw material mixing, molding, and blank processing. Initial process parameters are set for each processing step, such as conveyor belt speed, mixing machine processing power, mold cavity temperature, mold cavity pressure, and mold preheating power. The setting logic is set using prior data.

[0070] Each processing stage is equipped with corresponding monitoring equipment to simultaneously acquire real-time monitoring data. This data is used to adjust the initial process parameters at each stage, establishing a feedback mechanism for adjusting initial process parameters based on real-time monitoring data. For example, a laser particle size analyzer monitors the particle size distribution of raw materials in real time, adjusting the conveyor belt speed and the sampling frequency of the weighing sensor; an ambient humidity sensor monitors humidity data in real time, adjusting the amount of binder (coal tar pitch) added; multiple infrared temperature sensors are deployed on the inner wall of the mixer to monitor internal temperature data in real time, adjusting the power of the heating zones; and online... A viscosity counter monitors viscosity data in real time and adjusts the kneading time to prevent insufficient plasticization. Thermocouples and temperature sensors are embedded at key points in the mold, and the initial temperature is automatically set, stabilizing the mold cavity temperature within a controllable range. Pressure sensors monitor the pressure in different areas of the mold cavity in real time, adjusting the pressure of the hydraulic cylinder zones. A laser displacement sensor detects the blank height and adjusts the corrected holding time. Micro-strain gauges are embedded in key contact surfaces of the mold head to compensate for the compression displacement. An outdoor temperature sensor monitors environmental data and adjusts the mold preheating time.

[0071] In this embodiment, the initial processing parameters in each processing stage are adjusted based on real-time monitoring data. The specific adjustment logic is as follows: all real-time monitoring data within a certain time interval are obtained, and a curve of the real-time monitoring data changing with time is constructed and fitted to obtain the curvature value of the corresponding real-time monitoring data. The process parameters are then adjusted. In other words, a feedback adjustment model is established and trained using the curvature of the real-time monitoring data and the corresponding process parameters to adjust the process parameters.

[0072] In this embodiment, a unified feedback adjustment logic is set for the initial process parameters based on real-time monitoring data, and specific feedback adjustment logic can also be set according to different real-time monitoring data.

[0073] For example, a material density-particle size feedback model can be constructed. Real-time monitoring of raw material particle size distribution data using a laser particle size analyzer is input into the model, automatically adjusting the conveyor belt speed and the weighing sensor sampling frequency. Since the particle size distribution of the raw material directly affects its bulk density—for example, smaller particles result in a larger bulk density, and vice versa—smaller particles with a larger bulk density may cause the weight of material passing through the weighing area per unit time to exceed the limit at the same conveying speed. This could lead to weighing sensor overload or data fluctuations. Therefore, it is necessary to reduce the conveyor belt speed and increase the weighing sensor sampling frequency. Similarly, for raw materials with larger particle sizes, it is necessary to increase the conveyor belt speed and decrease the weighing sensor sampling frequency.

[0074] For example, based on environmental humidity sensor data, the amount of adhesive added can be dynamically adjusted. The adjustment algorithm uses: , Add based on the baseline amount, This is humidity deviation data. Humidity coefficient To adjust the amount added.

[0075] If a laser displacement sensor is used to monitor the billet height, the billet's corrective holding time can be adjusted. The adjustment algorithm is as follows: , For high correction factor, For height deviation, As the baseline holding time, To adjust the holding time.

[0076] If micro-strain gauges are embedded in the critical contact surfaces of the mold, the compression molding displacement can be automatically compensated. The adjustment logic is as follows: calculate the wear coefficient, calculate the amount of compression molding displacement to be compensated. , The wear coefficient is... This is the amount of compensation.

[0077] Specifically, based on the real-time process parameters and corresponding initial process parameters in each processing stage, it is determined whether there is a ratio between the real-time process parameters and the corresponding initial process parameters in a single processing stage that exceeds a set value.

[0078]

[0079] The change ratio value, For real-time process parameters, For the corresponding initial process parameters;

[0080] If the change rate of a real-time process parameter exceeds the set value, it indicates that the adjustment range of the corresponding real-time process parameter is large. For a single processing stage, a large adjustment range of a single process parameter will affect other process parameters. For example, in the raw material pretreatment stage, if the adjustment range of the conveyor belt speed and the weighing sensor sampling frequency is large, it means that the particle size of the raw material is either too large or too small. In this case, the amount of binder added per unit volume and the processing temperature of the paste need to be adjusted accordingly. In this case, the conveyor belt speed and the weighing sensor sampling frequency are the primary process parameters, while the amount of binder added per unit volume and the processing temperature of the paste are the secondary process parameters. It should be noted that the primary and secondary process parameters in a single processing stage are only distinguished by the magnitude of the adjustment, not by fixed parameters.

[0081] Specifically, the main process parameters in a single processing step are used to adjust all secondary process parameters. This involves: using historical and prior data to construct a correlation model between a single process parameter and other process parameters. Since both the main and secondary process parameters change in a single processing step, there are multiple correlation models for a single processing step; and obtaining any one main process parameter and its corresponding correlation model to adjust the remaining secondary process parameters.

[0082] Based on the processing sequence of the processing stages, the processing stages are processed sequentially. For example, processing stages B, C, D, and E are set. Each processing stage acquires adjusted real-time process parameters. It should be noted that the adjusted real-time process parameters refer to the process parameters after primary adjustment based on real-time monitoring data and secondary adjustment based on the main process parameters.

[0083] Processing step B serves as the initial processing step. All adjusted real-time process parameters for processing step B are acquired. These parameters are then normalized under the same data protocol to obtain a multi-parameter feature set. This eliminates dimensional and magnitude differences between parameters, providing a unified analytical benchmark for extracting the distribution characteristics of parameters in a single processing step. Next, all multi-parameter feature sets for processing step B within a second time interval (e.g., three months) and the corresponding processing quality index data for that processing step are acquired, and the parameter distribution characteristics are extracted simultaneously. A mapping table between the parameter distribution characteristics and the corresponding processing quality index data is established. Using this mapping table and the adjusted real-time process parameters, the corresponding processing quality index data is output. The above processing logic involves normalizing the real-time process parameters of the processing step, extracting parameter distribution characteristics, and establishing a mapping table with prior processing quality index data. This allows for the direct output of the corresponding processing quality index data as the distribution characteristics of the real-time process parameters after the adjusted real-time process parameters are subsequently acquired.

[0084] Obtain the processing quality index data of processing stage B and the remaining processing stages within the third time interval. Construct and train a quantitative model for adjusting the corresponding process parameters of the remaining processing stages. Using the trained quantitative model, output the influence coefficients on the remaining processing stages, such as setting an influence coefficient for processing stage C. Influence coefficients are set for processing steps. Influence coefficients are set for processing steps. .

[0085] Similarly, the remaining processing steps C, D, and E are processed sequentially. Steps C and D are considered intermediate processing steps, and their processing logic is consistent with that of the intermediate processing steps. The adjusted real-time process parameters of the intermediate processing steps are obtained and multiplied by the influence coefficients transmitted from the upstream processing steps to obtain the corrected real-time process parameters. Then, combined with the corresponding mapping table, the processing quality index data of the intermediate processing steps are output. Finally, the influence coefficients of downstream processing steps are set using the quantitative model of the intermediate processing steps. For example, based on the intermediate processing results of processing step C, an influence coefficient is set for processing step D. An influence coefficient is set for processing step E. Based on the intermediate processing results of processing step D, an influence coefficient is set for processing step E. .

[0086] Finally, the adjusted real-time process parameters in all processing stages are dynamically adjusted based on all received influence coefficients. Specifically: processing stage B receives the adjusted real-time process parameters but takes no action; processing stage C receives the adjusted real-time process parameters... Therefore, the real-time process parameters after dynamic adjustment should be: Processing step D obtains the adjusted real-time process parameters as follows: Therefore, the real-time process parameters after dynamic adjustment should be: The processing stage E obtains the adjusted real-time process parameters as follows: Therefore, the adjusted real-time process parameters should be: In this embodiment, the coupling logic for multi-parameter coupling of each processing stage is to convert the distribution characteristics of processing parameters in the preceding processing stage into corresponding processing quality index data, and then use the processing quality index data to set an influence coefficient on the degree of influence of the subsequent processing stage. The influence coefficients transmitted by the subsequent processing stage to all upstream processing stages are superimposed, thereby adjusting the real-time process parameters and realizing the coupling and unification of multiple parameters among each processing stage.

[0087] In this embodiment, an environment-initial process parameter database is also established. By utilizing the different outdoor ambient temperatures, the process parameter mode is switched, and different initial process parameters are set accordingly.

[0088] In some embodiments, based on the real-time monitoring data, the corresponding initial process parameters in each processing stage are adjusted to obtain the real-time process parameters, including:

[0089] Acquire all real-time monitoring data within the first time interval and construct a curve showing the change of real-time monitoring data over time;

[0090] The curve is fitted to obtain the curvature value of the corresponding real-time monitoring data for each first time interval;

[0091] Based on the changed curvature value, the process parameters corresponding to the real-time monitoring data are adjusted to obtain the real-time process parameters.

[0092] In some embodiments, determining whether there is a change ratio between real-time process parameters and corresponding initial process parameters in a single processing step that exceeds a set value includes:

[0093] The following formula is used to calculate the ratio of change between real-time process parameters and corresponding initial process parameters:

[0094]

[0095] The change ratio value, For real-time process parameters, These are the corresponding initial process parameters.

[0096] In some embodiments, the corresponding process parameters are denoted as master process parameters, the remaining process parameters are denoted as slave process parameters, and the adjustment of all slave process parameters sequentially using each master process parameter includes:

[0097] Acquire any processing step, denoted as the first processing step, and simultaneously acquire historical data of all process parameters in the first processing step;

[0098] Based on the historical data and the prior data of the first processing stage, a correlation model between a single process parameter and other process parameters is constructed.

[0099] Obtain the association model corresponding to the main process parameters in the first processing step, and record the corresponding main process parameters as the first main process parameters;

[0100] After inputting the first master process parameter and the remaining slave process parameters into the corresponding association model, the adjusted slave process parameters are output, thus completing the adjustment of the remaining slave process parameters.

[0101] In some embodiments, obtaining an initial processing result includes:

[0102] Obtain all adjusted real-time process parameters of the initial processing stage, and record them as the first real-time process parameters;

[0103] All first real-time process parameters are normalized under the same data protocol and placed into a preset dataset, corresponding to a multi-parameter feature set;

[0104] Obtain all multi-parameter feature sets and corresponding processing quality index data of the initial processing stage within the second time interval, and extract distribution features from the multi-parameter feature sets;

[0105] Establish a mapping table between the distribution characteristics of the multi-parameter feature set and the corresponding processing quality index data;

[0106] Using the adjusted real-time process parameters from the initial processing stage and the mapping table, the processing quality index data corresponding to the initial processing stage is output as the initial processing result.

[0107] In some embodiments, based on the initial processing result, different influence coefficients are set for all subsequent processing steps, including:

[0108] Based on the initial processing results, the corresponding processing quality index data is obtained and recorded as the first processing quality index data;

[0109] Based on all the first processing quality index data and the corresponding processing quality index data of the remaining processing steps within the third time interval, a quantitative model for adjusting the corresponding process parameters of the remaining processing steps is constructed and trained.

[0110] The first processing quality index data in the initial processing stage and the real-time process parameters of the remaining processing stages are obtained and input into the trained quantization model, and the influence coefficients on the remaining processing stages are output.

[0111] In some embodiments, obtaining intermediate processing results includes:

[0112] The adjusted real-time process parameters in the intermediate processing stage are obtained and multiplied with the influence coefficients transmitted from all corresponding upstream processing stages to obtain the corrected real-time process parameters.

[0113] Using the corrected real-time process parameters and corresponding mapping table of the intermediate processing steps, the processing quality index data corresponding to the intermediate processing steps are output as the intermediate processing result.

[0114] In some embodiments, based on the intermediate processing results, different influence coefficients are set for all downstream processing stages located in the intermediate processing stage, including:

[0115] Obtain the quantization model corresponding to the intermediate processing step, denoted as the first quantization model, and train it.

[0116] The processing quality index data corresponding to the intermediate processing stage and the real-time process parameters of the remaining processing stages are input into the first quantification model after training, and the influence coefficients on all downstream processing stages located in the intermediate processing stage are output.

[0117] In some embodiments, the dynamic adjustment of the adjusted real-time process parameters in all processing stages, combined with all received influence coefficients, includes:

[0118] Calculate the product of the adjusted real-time process parameters in any processing stage and the corresponding received influence coefficients to obtain the product result;

[0119] Based on the product result, the real-time process parameters of the corresponding processing steps are dynamically adjusted.

[0120] Example 2

[0121] Based on the multi-parameter collaborative carbon graphite product molding control system provided in Embodiment 1 of this application, correspondingly, Embodiment 2 of this application also provides a multi-parameter collaborative carbon graphite product molding control method, such as... Figure 2 As shown, it includes:

[0122] For each processing step in the carbon graphite product molding process, corresponding initial process parameters are set;

[0123] Each processing stage is equipped with corresponding monitoring equipment, and real-time monitoring data is acquired simultaneously.

[0124] Based on the real-time monitoring data, the corresponding initial process parameters in each processing stage are adjusted to obtain the real-time process parameters;

[0125] Based on the real-time process parameters and corresponding initial process parameters in each processing stage, determine whether there is a change ratio between the real-time process parameter and the corresponding initial process parameter in a single processing stage that exceeds the set value. If so, record the corresponding process parameter as the main process parameter and the remaining process parameters as the secondary process parameters, and use each main process parameter to adjust all secondary process parameters in sequence. If not, do not take any action.

[0126] Based on the processing sequence of the processing steps, the adjusted real-time process parameters in the initial processing step are obtained and integrated to obtain the initial processing result. Based on the initial processing result, different influence coefficients are set for all subsequent processing steps.

[0127] In all subsequent processing stages except the final processing stage, any processing stage is selected and denoted as an intermediate processing stage. The adjusted real-time process parameters of the intermediate processing stage are obtained and integrated with the influence coefficients transmitted by all upstream processing stages located in the intermediate processing stage to obtain the intermediate processing result. Based on the intermediate processing result, different influence coefficients are set for all downstream processing stages located in the intermediate processing stage.

[0128] The real-time process parameters, adjusted in all processing stages, are dynamically adjusted in conjunction with all received influence coefficients.

[0129] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computing software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0130] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the invention.

[0131] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A carbon graphite product molding control system based on multi-parameter coordination, characterized in that, include: Process parameter setting unit: Sets corresponding initial process parameters for each processing step in the carbon graphite product molding process; Real-time monitoring unit: Each processing stage is equipped with corresponding monitoring equipment, which simultaneously acquires real-time monitoring data; Feedback compensation unit: Based on the real-time monitoring data, adjusts the corresponding initial process parameters in each processing stage to obtain real-time process parameters; Process parameter adjustment unit: Based on the real-time process parameters and corresponding initial process parameters in each processing stage, determine whether there is a change ratio between the real-time process parameter and the corresponding initial process parameter in a single processing stage that exceeds the set value. If so, record the corresponding process parameter as the main process parameter and the remaining process parameters as the secondary process parameters, and use each main process parameter to adjust all secondary process parameters in sequence. If not, do not take any action. Process parameter coupling unit: Based on the processing sequence of the processing steps, it obtains the adjusted real-time process parameters in the initial processing step and integrates them to obtain the initial processing result. Based on the initial processing result, different influence coefficients are set for all subsequent processing steps. In all subsequent processing stages except the final processing stage, any processing stage is selected and denoted as an intermediate processing stage. The adjusted real-time process parameters of the intermediate processing stage are obtained and integrated with the influence coefficients transmitted by all upstream processing stages located in the intermediate processing stage to obtain the intermediate processing result. Based on the intermediate processing result, different influence coefficients are set for all downstream processing stages located in the intermediate processing stage. The real-time process parameters, adjusted in all processing stages, are dynamically adjusted in conjunction with all received influence coefficients.

2. The carbon graphite product molding control system based on multi-parameter coordination according to claim 1, characterized in that, Based on the real-time monitoring data, the corresponding initial process parameters in each processing stage are adjusted to obtain the real-time process parameters, including: Acquire all real-time monitoring data within the first time interval and construct a curve showing the change of real-time monitoring data over time; The curve is fitted to obtain the curvature value of the corresponding real-time monitoring data for each first time interval; Based on the changed curvature value, the process parameters corresponding to the real-time monitoring data are adjusted to obtain the real-time process parameters.

3. The carbon graphite product molding control system based on multi-parameter coordination according to claim 1, characterized in that, Determining whether there is a change ratio between real-time process parameters and corresponding initial process parameters exceeding a set value in a single processing step includes: The following formula is used to calculate the ratio of change between real-time process parameters and corresponding initial process parameters: The change ratio value, For real-time process parameters, These are the corresponding initial process parameters.

4. The carbon graphite product molding control system based on multi-parameter coordination according to claim 1, characterized in that, The corresponding process parameters are designated as master process parameters, and the remaining process parameters are designated as slave process parameters. All slave process parameters are then adjusted sequentially using each master process parameter, including: Acquire any processing step, denoted as the first processing step, and simultaneously acquire historical data of all process parameters in the first processing step; Based on the historical data and the prior data of the first processing stage, a correlation model between a single process parameter and other process parameters is constructed. Obtain the association model corresponding to the main process parameters in the first processing step, and record the corresponding main process parameters as the first main process parameters; After inputting the first master process parameter and the remaining slave process parameters into the corresponding association model, the adjusted slave process parameters are output, thus completing the adjustment of the remaining slave process parameters.

5. The carbon graphite product molding control system based on multi-parameter coordination according to claim 1, characterized in that, The initial processing results include: Obtain all adjusted real-time process parameters of the initial processing stage, and record them as the first real-time process parameters; All first real-time process parameters are normalized under the same data protocol and placed into a preset dataset, corresponding to a multi-parameter feature set; Obtain all multi-parameter feature sets and corresponding processing quality index data of the initial processing stage within the second time interval, and extract distribution features from the multi-parameter feature sets; Establish a mapping table between the distribution characteristics of the multi-parameter feature set and the corresponding processing quality index data; Using the adjusted real-time process parameters from the initial processing stage and the mapping table, the processing quality index data corresponding to the initial processing stage is output as the initial processing result.

6. The carbon graphite product molding control system based on multi-parameter coordination according to claim 5, characterized in that, Based on the initial processing results, different influence coefficients are set for all subsequent processing steps, including: Based on the initial processing results, the corresponding processing quality index data is obtained and recorded as the first processing quality index data; Based on all the first processing quality index data and the corresponding processing quality index data of the remaining processing steps within the third time interval, a quantitative model for adjusting the corresponding process parameters of the remaining processing steps is constructed and trained. The first processing quality index data in the initial processing stage and the real-time process parameters of the remaining processing stages are obtained and input into the trained quantization model, and the influence coefficients on the remaining processing stages are output.

7. A carbon graphite product molding control system based on multi-parameter coordination according to claim 6, characterized in that, The intermediate processing results obtained include: The adjusted real-time process parameters in the intermediate processing stage are obtained and multiplied with the influence coefficients transmitted from all corresponding upstream processing stages to obtain the corrected real-time process parameters. Using the corrected real-time process parameters and corresponding mapping table of the intermediate processing steps, the processing quality index data corresponding to the intermediate processing steps are output as the intermediate processing result.

8. The carbon graphite product molding control system based on multi-parameter coordination according to claim 7, characterized in that, Based on the intermediate processing results, different influence coefficients are set for all downstream processing stages located in the intermediate processing stage, including: Obtain the quantization model corresponding to the intermediate processing step, denoted as the first quantization model, and train it. The processing quality index data corresponding to the intermediate processing stage and the real-time process parameters of the remaining processing stages are input into the first quantification model after training, and the influence coefficients on all downstream processing stages located in the intermediate processing stage are output.

9. The carbon graphite product molding control system based on multi-parameter coordination according to claim 1, characterized in that, The real-time process parameters, adjusted after modification in all processing stages, are dynamically adjusted based on all received influence coefficients, including: Calculate the product of the adjusted real-time process parameters in any processing stage and the corresponding received influence coefficients to obtain the product result; Based on the product result, the real-time process parameters of the corresponding processing steps are dynamically adjusted.

10. A method for controlling the molding of carbon graphite products based on multi-parameter synergy, characterized in that, include: For each processing step in the carbon graphite product molding process, corresponding initial process parameters are set; Each processing stage is equipped with corresponding monitoring equipment, and real-time monitoring data is acquired simultaneously. Based on the real-time monitoring data, the corresponding initial process parameters in each processing stage are adjusted to obtain the real-time process parameters; Based on the real-time process parameters and corresponding initial process parameters in each processing stage, determine whether there is a change ratio between the real-time process parameter and the corresponding initial process parameter in a single processing stage that exceeds the set value. If so, record the corresponding process parameter as the main process parameter and the remaining process parameters as the secondary process parameters, and use each main process parameter to adjust all secondary process parameters in sequence. If not, do not take any action. Based on the processing sequence of the processing steps, the adjusted real-time process parameters in the initial processing step are obtained and integrated to obtain the initial processing result. Based on the initial processing result, different influence coefficients are set for all subsequent processing steps. In all subsequent processing stages except the final processing stage, any processing stage is selected and denoted as an intermediate processing stage. The adjusted real-time process parameters of the intermediate processing stage are obtained and integrated with the influence coefficients transmitted by all upstream processing stages located in the intermediate processing stage to obtain the intermediate processing result. Based on the intermediate processing result, different influence coefficients are set for all downstream processing stages located in the intermediate processing stage. The real-time process parameters, adjusted in all processing stages, are dynamically adjusted in conjunction with all received influence coefficients.

Images