Intelligent Monitoring and Scheduling System for the Entire Phosphoric Acid Production Process Based on Industrial Internet

Abstract

This invention discloses an intelligent monitoring and scheduling system for the entire phosphoric acid production process based on the Industrial Internet, relating to the field of phosphoric acid production management technology. It includes: a data acquisition module for acquiring key process parameters and product parameters for each production stage in the phosphoric acid production process; a data processing module for processing the acquired key process parameters for each production stage to obtain dynamic simulation nodes for each production stage; a data analysis module for performing production process balance analysis on each dynamic simulation node and determining imbalance nodes based on the analysis results; and a production scheduling module for optimizing the key process parameters of the determined imbalance nodes. By obtaining the balance coefficient of the corresponding production stage within the sampling window and based on the causal relationship between key process items and product parameter items, the system identifies items to be optimized, avoiding blind global adjustments and significantly improving scheduling efficiency and production stability.

Description

Technical Field

[0001] This invention relates to the field of phosphoric acid production management technology, specifically to an intelligent monitoring and scheduling system for the entire phosphoric acid production process based on the Industrial Internet. Background Technology

[0002] Phosphoric acid production is a complex physicochemical process involving multiple stages and variables. Existing phosphoric acid production monitoring systems mostly remain at the level of basic data acquisition and single-threshold alarms, exhibiting significant shortcomings: First, the phosphoric acid production process has a significant time lag, making it difficult to accurately correlate changes in front-end process parameters with changes in back-end product parameters, thus failing to establish an accurate dynamic process mapping relationship; second, when product quality anomalies occur, there is a lack of systematic quantification and analysis methods, making it difficult to quickly and accurately trace the specific process steps causing the anomalies among numerous interdependent process parameters. Therefore, we present an intelligent monitoring and scheduling system for the entire phosphoric acid production process based on the Industrial Internet. Summary of the Invention

[0003] The purpose of this invention is to provide an intelligent monitoring and scheduling system for the entire phosphoric acid production process based on the Industrial Internet.

[0004] The objective of this invention can be achieved through the following technical solution: an intelligent monitoring and scheduling system for the entire phosphoric acid production process based on the Industrial Internet, comprising: The data acquisition module is used to acquire key process parameters and product parameters at each stage of phosphoric acid production. The data processing module is used to process the key parameters of the production process at each production stage to obtain the dynamic simulation nodes of each production stage. The data analysis module is used to analyze the balance of the production process at each dynamic simulation node and identify the imbalance nodes based on the analysis results. The production scheduling module is used to optimize the key process parameters of the production process at the identified imbalance nodes.

[0005] Furthermore, the phosphoric acid production process includes several production stages, each with corresponding key process parameters and product parameters. The key process parameters include several key process items, each with its own corresponding process parameters. The product parameters include several product parameter items, each with its own corresponding product parameters, and each product parameter item has a corresponding standard parameter error range. Each key process item also has a corresponding standard process parameter range.

[0006] Furthermore, the data processing module processes the key parameters of the production process at each stage, including: Generate corresponding process parameter change curves based on the process parameters corresponding to each key process item, and generate corresponding product parameter change curves based on the product parameters corresponding to each product parameter item. Set the time sampling window; The process parameter variation curves and product parameter variation curves within the time sampling window are sampled at equal intervals to obtain several process parameter sampling points and product parameter sampling points respectively. The process parameters corresponding to each key process item and the product parameters corresponding to each product parameter item at each process parameter sampling point are summarized to obtain the corresponding multi-dimensional process parameter set and multi-dimensional product parameter set.

[0007] Furthermore, the process of obtaining dynamic simulation nodes for each production stage includes: Based on the obtained multidimensional process parameter set, the corresponding theoretical product parameter set is obtained; Set the lag time for the corresponding production stage; Based on the lag time of this production stage, obtain the corresponding lag node, and obtain the multi-dimensional product parameter set corresponding to the product parameter sampling point closest to the lag node. The product parameters corresponding to each product parameter item in the multidimensional product parameter set are compared with the product parameters of the corresponding product parameter items in the theoretical product parameter set to obtain the parameter difference of each product parameter item. Set the deviation threshold; The absolute value of the obtained parameter difference is compared with the corresponding deviation threshold to determine whether the product parameter is qualified. If all product parameters are qualified, it means that the sampling point of the process parameter corresponds to the sampling point of the product parameter. If not all product parameter items are qualified, then search the multidimensional product parameter set corresponding to each time point near the product parameter sampling point. If there is a multidimensional product parameter set in the search where all product parameter items are qualified, then select the time closest to the product parameter sampling point and perform oversampling to obtain a new product parameter sampling point, indicating that the new product parameter sampling point corresponds to the process parameter sampling point; if there is no such point, then the process parameter sampling point is an empty node. Process parameter sampling points that have corresponding product parameter sampling points are marked as dynamic simulation nodes.

[0008] Furthermore, the data analysis module performs production process balance analysis on each dynamic simulation node, and the process of determining the imbalance nodes based on the analysis results includes: Compare the process parameters corresponding to key process items with the corresponding standard process parameter ranges to obtain the corresponding process parameter comparison differences; Obtain the product parameters affected by each key process item, and compare the product parameters corresponding to the obtained product parameters with the corresponding standard parameter error range to obtain the corresponding product parameter comparison difference; The imbalance coefficient of the dynamic simulation node is obtained by comparing the process parameters corresponding to the key process items and the product parameters. The average imbalance coefficient of all dynamic simulation nodes within the time sampling window is obtained as the production balance coefficient of the production stage within the time sampling window. Set a balance threshold and compare the obtained production balance coefficient with the set balance threshold; If the production balance coefficient is less than the balance threshold, it means that the process in this production stage is in a balanced state; otherwise, it is in an unbalanced state. If the production stage is in an unbalanced state, then obtain the maximum value of the absolute value of the process parameter comparison difference corresponding to the key process item and the product parameter comparison difference corresponding to the product parameter item. The corresponding key process items and product parameter items are then marked as imbalance nodes.

[0009] Furthermore, if the process parameter is within the standard process parameter range, the corresponding process parameter comparison difference is 0. If the process parameter is less than the lower limit of the standard process parameter range, the corresponding process parameter comparison difference is the value obtained by subtracting the lower limit of the standard process parameter range from the process parameter. If the process parameter is greater than the upper limit of the standard process parameter range, the corresponding process parameter comparison difference is the value obtained by subtracting the upper limit of the standard process parameter range from the process parameter. If the product parameter is within the standard parameter error range, the corresponding product parameter comparison difference is 0. If the product parameter is less than the lower limit of the standard parameter error range, the corresponding product parameter comparison difference is the product parameter minus the lower limit of the standard parameter error range. If the product parameter is greater than the upper limit of the standard parameter error range, the corresponding product parameter comparison difference is the product parameter minus the upper limit of the standard parameter error range.

[0010] Furthermore, the process by which the production scheduling module optimizes the key parameters of the production process at the identified imbalance nodes includes: Mark the product parameter items and key process items corresponding to the imbalance node. If the key process item affects the product parameter item, then directly mark the key process item as an item to be optimized. If the critical process item does not affect the product parameter item, then obtain all critical process items that will affect the product parameter item, and mark the maximum absolute value of the difference between the process parameters among the obtained critical process items; The critical process items in the imbalanced nodes, as well as the aforementioned critical process items, are marked as items to be optimized. Adjust the process parameters corresponding to the item to be optimized to the corresponding standard process parameter range.

[0011] Compared with the prior art, the beneficial effects of the present invention are: 1. By obtaining the balance coefficient of the corresponding production stage within the sampling window, and based on the causal relationship between key process items and product parameter items, the items to be optimized are obtained, avoiding blind global adjustments and significantly improving scheduling efficiency and production stability. 2. By introducing a sampling matching mechanism that combines lag time and deviation threshold, the time delay problem between process parameters and product parameters in phosphoric acid production is effectively solved. Invalid empty nodes are automatically eliminated and valid sampling points are added to construct a highly accurate dynamic simulation node, providing a real and reliable data foundation for production analysis. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0013] Figure 1 This is a system principle block diagram of the present invention. Detailed Implementation

[0014] like Figure 1 As shown, the intelligent monitoring and scheduling system for the entire phosphoric acid production process based on the Industrial Internet includes: The data acquisition module is used to acquire key process parameters and product parameters at each stage of phosphoric acid production. The data processing module is used to process the key parameters of the production process at each production stage to obtain the dynamic simulation nodes of each production stage. The data analysis module is used to analyze the balance of the production process at each dynamic simulation node and identify the imbalance nodes based on the analysis results. The production scheduling module is used to optimize the key process parameters of the production process at the identified imbalance nodes.

[0015] It should be further explained that, in the specific implementation process, the phosphoric acid production process usually involves several production stages, namely the phosphate rock preparation stage, the acid hydrolysis reaction stage, the filtration stage, the concentration stage, and the purification stage. Each production stage has corresponding key process parameters and product parameters. The key process parameters include several key process items, and each key process item corresponds to a corresponding process parameter. The product parameters include several product parameter items, and each product parameter item corresponds to a corresponding product parameter. It should be noted that the key process items and product parameter items are different in different production stages, and each product parameter item has a corresponding standard parameter error range, and each key process item has a corresponding standard process parameter range. Example: In the phosphate rock preparation stage, the key process items are ore particle size, ore moisture content, ore grade and impurity content, and the corresponding product parameters are feed flow rate and slurry temperature. During the acidolysis reaction stage, the key process parameters are reaction temperature, free sulfuric acid concentration, liquid-to-solid ratio, stirring intensity, and reaction time; the corresponding product parameters are phosphoric acid concentration in the slurry and crystal parameters. In the filtration stage, the key process items are vacuum degree, washing water temperature, washing water volume, filtration intensity, filter cake thickness and moisture content, and the corresponding product parameters are phosphoric acid concentration, solid content, impurity content and phosphogypsum content. During the concentration stage, the key process items are evaporation temperature, vacuum degree, heating steam pressure and temperature, and circulating slurry concentration, while the product parameters are phosphoric acid concentration, viscosity, and fluorine content. During the purification stage, the key process items are the extractant ratio, extraction temperature, and washing liquid parameters, while the corresponding product parameters are color, heavy metal limits, fluoride limits, chloride limits, and sulfate limits.

[0016] It should be further explained that, in the specific implementation process, the data processing module processes the key process parameters of each production stage to obtain the dynamic simulation nodes of each production stage. This process includes: For each production stage, a time axis is constructed for each key process item. Based on the process parameters corresponding to each key process item, a corresponding process parameter change curve is generated, and the generated process parameter change curve is mapped to the corresponding time axis. Similarly, for each production stage, a time axis is constructed for each product parameter item, and a corresponding product parameter change curve is generated based on the product parameters corresponding to each product parameter item. The generated product parameter change curve is then mapped to the corresponding time axis. Set a time sampling window, with the start time and end time of the time sampling window being t1 and t2, respectively, where t2 corresponds to the current time and t1 is the previous time; The process parameter variation curves within the time sampling window are sampled at equal intervals to obtain several process parameter sampling points. It should be noted that equal interval sampling means that the time interval between each process parameter sampling point is the same. On the other hand, time t1 and time t2 of the time sampling window are also process parameter sampling points. The sampling points for each process parameter are sorted in chronological order. Based on the sorting results, the process parameters corresponding to each key process item at each process parameter sampling point are summarized to obtain the corresponding multidimensional process parameter set. By sampling the product parameter change curve at equal intervals within the time sampling window, several product parameter sampling points are obtained. It should be noted that the sampling time interval corresponding to the product parameter sampling point is less than the sampling time interval of the process parameter sampling point, and the time t1 and t2 of the time sampling window are also product parameter sampling points. The sampling points for each product parameter are sorted in chronological order. Based on the sorting results, the product parameters corresponding to each product parameter item at each product parameter sampling point are summarized to obtain the corresponding multidimensional product parameter set. The theoretical product parameter set is obtained based on the obtained multidimensional process parameter set. It should be noted that the theoretical product parameter set is obtained by a machine learning regression model trained on historical DCS operation data. Its input is multidimensional process parameters and its output is theoretical product parameters. The process is a conventional technical means in the field of industrial digital twins, which will not be elaborated here. Set the lag time for the corresponding production stage; Based on the lag time of this production stage, obtain the corresponding lag node, and obtain the multi-dimensional product parameter set corresponding to the product parameter sampling point closest to the lag node. It should be noted that in industrial control, since the macroscopic physical lag time is relatively constant within a long time window (such as the design dwell time), the microscopic fluctuations are random errors and do not affect the corresponding matching of macroscopic nodes. Therefore, during the design process, technicians themselves need to set this value in combination with the design parameters of the specific production line. This is a routine operation for those skilled in the art. The product parameters corresponding to each product parameter item in the multidimensional product parameter set are compared with the product parameters of the corresponding product parameter items in the theoretical product parameter set to obtain the parameter difference of each product parameter item. Set the deviation threshold; The absolute value of the obtained parameter difference is compared with the corresponding deviation threshold. If the parameter difference is less than the deviation threshold, it means that the corresponding product parameter is qualified; otherwise, it is unqualified. If all product parameters are qualified, it means that the sampling point of the process parameter corresponds to the sampling point of the product parameter. If not all product parameter items are qualified, then search the multidimensional product parameter set corresponding to each time point near the product parameter sampling point. If there is a multidimensional product parameter set where all product parameter items are qualified, then select the time point closest to the product parameter sampling point for oversampling to obtain a new product parameter sampling point, indicating that the new product parameter sampling point corresponds to the process parameter sampling point; if there is no such point, then the process parameter sampling point is an empty node. It should be noted that "near the product parameter sampling point" refers to the range between the product parameter sampling point and adjacent product parameter sampling points (excluding adjacent product parameter sampling points). By analogy, the product parameter sampling points corresponding to all process parameter sampling points within the time sampling window are determined. Mark the corresponding process parameter sampling points as dynamic simulation nodes; Taking advantage of the extremely high sampling frequency (seconds or minutes) of industrial DCS systems, although some nodes may be marked as empty under harsh conditions, the large number of sampling points means that the remaining effective dynamic simulation nodes are sufficient to support continuous time-series curve fitting and monitoring without "losing continuity". In addition, discarding some abnormal nodes can reduce the interference of dirty data on monitoring.

[0017] It should be further explained that, in the specific implementation process, the data analysis module performs production process balance analysis on each dynamic simulation node, and the process of determining the unbalanced nodes based on the analysis results includes: Each key process item contained in the dynamic simulation node is labeled and denoted as i, where i = 1, 2, ..., n; The process parameters corresponding to the key process item labeled i are compared with the corresponding standard process parameter range to obtain the corresponding process parameter comparison difference. It should be noted that if the process parameter is within the standard process parameter range, the corresponding process parameter comparison difference is 0. If the process parameter is less than the lower limit of the standard process parameter range, the corresponding process parameter comparison difference is the process parameter minus the lower limit of the standard process parameter range. If the process parameter is greater than the upper limit of the standard process parameter range, the corresponding process parameter comparison difference is the process parameter minus the upper limit of the standard process parameter range. Obtain the product parameter affected by each key process item, denoted as j, where j = 1, 2, ..., m. Compare the product parameter corresponding to the product parameter item with the corresponding standard parameter error range to obtain the corresponding product parameter comparison difference. It should be noted that if the product parameter is within the standard parameter error range, the corresponding product parameter comparison difference is 0. If the product parameter is less than the lower limit of the standard parameter error range, the corresponding product parameter comparison difference is the product parameter minus the lower limit of the standard parameter error range. If the product parameter is greater than the upper limit of the standard parameter error range, the corresponding product parameter comparison difference is the product parameter minus the upper limit of the standard parameter error range. The imbalance coefficient of this dynamic simulation node is obtained based on the comparison difference of process parameters corresponding to the key process items and the comparison difference of product parameters, denoted as Sh, where: ; Among them, k1 and k2 are weighting coefficients, which are determined by technical personnel based on experience. This represents the difference in process parameters corresponding to the key process item labeled i. This represents the difference in product parameters corresponding to product parameter item j, which is affected by the key process item labeled i. It should be noted that all parameters in the above process are calculated by removing dimensions and taking their numerical values; The average imbalance coefficient of all dynamic simulation nodes within the time sampling window is obtained as the production balance coefficient of the production stage within the time sampling window. Set a balance threshold and compare the obtained production balance coefficient with the set balance threshold; If the production balance coefficient is less than the balance threshold, it means that the process in this production stage is in a balanced state; otherwise, it is in an unbalanced state. If the production stage is in an unbalanced state, then obtain the maximum value of the absolute value of the process parameter comparison difference corresponding to the key process item and the product parameter comparison difference corresponding to the product parameter item. The corresponding key process items and product parameter items are then marked as imbalance nodes.

[0018] It should be further explained that, in the specific implementation process, the production scheduling module optimizes the key process parameters of the production process at the identified imbalance nodes, including: Mark the product parameter items and key process items corresponding to the imbalance node. If the key process item affects the product parameter item, then directly mark the key process item as an item to be optimized. If the critical process item does not affect the product parameter item, then obtain all critical process items that will affect the product parameter item, and mark the maximum absolute value of the difference between the process parameters among the obtained critical process items; The critical process items in the imbalanced nodes, as well as the aforementioned critical process items, are marked as items to be optimized. Adjust the process parameters corresponding to the item to be optimized to the corresponding standard process parameter range; Repeat all the above operations within the new time sampling window.

[0019] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any modifications or equivalent substitutions made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. An intelligent monitoring and scheduling system for the entire phosphoric acid production process based on the Industrial Internet, characterized in that: include: The data acquisition module is used to acquire key process parameters and product parameters at each stage of phosphoric acid production. The data processing module is used to process the key parameters of the production process at each production stage to obtain the dynamic simulation nodes of each production stage. The data analysis module is used to analyze the balance of the production process at each dynamic simulation node and identify the imbalance nodes based on the analysis results. The production scheduling module is used to optimize the key process parameters of the production process at the identified imbalance nodes; The data processing module processes the key process parameters of each production stage obtained from the data processing module, including: For each production stage, a time axis is constructed for each key process item, and a corresponding process parameter variation curve is generated based on the process parameters corresponding to each key process item. Similarly, for each production stage, a time axis is constructed for each product parameter item, and a corresponding product parameter variation curve is generated based on the product parameters corresponding to each product parameter item. A time sampling window is set, and the process parameter variation curves within the time sampling window are sampled at equal intervals to obtain several process parameter sampling points. The process parameter sampling points are sorted in chronological order. Based on the sorting results, the process parameters corresponding to each key process item for each process parameter sampling point are summarized to obtain a corresponding multidimensional process parameter set. Similarly, by sampling the product parameter variation curves within the time sampling window at equal intervals, several product parameter sampling points are obtained. The product parameter sampling points are sorted in chronological order. Based on the sorting results, the product parameters corresponding to each product parameter item for each product parameter sampling point are summarized to obtain a corresponding multidimensional product parameter set. Based on the obtained multidimensional process parameter set, a corresponding theoretical product parameter set is obtained. The theoretical product parameter set is based on historical DCS. The machine learning regression model trained on the running data is obtained, with multidimensional process parameters as input and theoretical product parameters as output; the lag time of the corresponding production stage is set; the corresponding lag node is obtained according to the lag time of the production stage, and the multidimensional product parameter set corresponding to the product parameter sampling point closest to the lag node is obtained. The process of obtaining dynamic simulation nodes for each production stage includes: Based on the obtained multidimensional process parameter set, the corresponding theoretical product parameter set is obtained; Set the lag time for the corresponding production stage; Based on the lag time of this production stage, the corresponding lag node is obtained, and the multi-dimensional product parameter set corresponding to the product parameter sampling point closest to the lag node is obtained. The product parameters corresponding to each product parameter item in the multidimensional product parameter set are compared with the product parameters of the corresponding product parameter items in the theoretical product parameter set to obtain the parameter difference of each product parameter item. Set the deviation threshold; The absolute value of the obtained parameter difference is compared with the corresponding deviation threshold to determine whether the product parameter is qualified. If all product parameters are qualified, it means that the sampling point of the process parameter corresponds to the sampling point of the product parameter. If not all product parameter items are qualified, then search the multidimensional product parameter set corresponding to each time point near the product parameter sampling point. If there is a multidimensional product parameter set in the search where all product parameter items are qualified, then select the time closest to the product parameter sampling point and perform oversampling to obtain a new product parameter sampling point, indicating that the new product parameter sampling point corresponds to the process parameter sampling point; if there is no such point, then the process parameter sampling point is an empty node. Mark the process parameter sampling points that have corresponding product parameter sampling points as dynamic simulation nodes; The data analysis module performs production process balance analysis on each dynamic simulation node, and the process of determining the unbalanced nodes based on the analysis results includes: Each key process item contained in the dynamic simulation node is labeled and denoted as i, where i = 1, 2, ..., n; Compare the process parameters corresponding to key process items with the corresponding standard process parameter ranges to obtain the corresponding process parameter comparison differences; Obtain the product parameter items affected by each key process item, denoted as j, where j = 1, 2, ..., m, and compare the product parameters corresponding to the obtained product parameter items with the corresponding standard parameter error range to obtain the corresponding product parameter comparison difference. The imbalance coefficient of this dynamic simulation node is obtained based on the comparison difference of process parameters corresponding to the key process items and the comparison difference of product parameters, denoted as Sh, where: ； Among them, k1 and k2 are weighting coefficients, which are determined by technical personnel based on experience. This represents the difference in process parameters corresponding to the key process item labeled i. This represents the difference in product parameters corresponding to product parameter item j, which is affected by the key process item labeled i. All parameters in the above process are calculated by removing dimensions and taking their numerical values. The average imbalance coefficient of all dynamic simulation nodes within the time sampling window is obtained as the production balance coefficient of the production stage within the time sampling window. Set a balance threshold and compare the obtained production balance coefficient with the set balance threshold; If the production balance coefficient is less than the balance threshold, it means that the process in this production stage is in a balanced state; otherwise, it is in an unbalanced state. If the production stage is in an unbalanced state, then obtain the maximum value of the absolute value of the process parameter comparison difference corresponding to the key process item and the product parameter comparison difference corresponding to the product parameter item. The corresponding key process items and product parameter items are then marked as imbalance nodes.

2. The intelligent monitoring and scheduling system for the entire phosphoric acid production process based on the Industrial Internet as described in claim 1, characterized in that, The phosphoric acid production process includes several production stages, each with corresponding key process parameters and product parameters. The key process parameters include several key process items, each with its own corresponding process parameters. The product parameters include several product parameter items, each with its own corresponding product parameters, and each product parameter item has a set standard parameter error range. Each key process item also has a set standard process parameter range.

3. The intelligent monitoring and scheduling system for the entire phosphoric acid production process based on the Industrial Internet as described in claim 2, characterized in that, If the process parameter is within the standard process parameter range, the corresponding process parameter comparison difference is 0. If the process parameter is less than the lower limit of the standard process parameter range, the corresponding process parameter comparison difference is the value obtained by subtracting the lower limit of the standard process parameter range from the process parameter. If the process parameter is greater than the upper limit of the standard process parameter range, the corresponding process parameter comparison difference is the value obtained by subtracting the upper limit of the standard process parameter range from the process parameter. If the product parameter is within the standard parameter error range, the corresponding product parameter comparison difference is 0. If the product parameter is less than the lower limit of the standard parameter error range, the corresponding product parameter comparison difference is the product parameter minus the lower limit of the standard parameter error range. If the product parameter is greater than the upper limit of the standard parameter error range, the corresponding product parameter comparison difference is the product parameter minus the upper limit of the standard parameter error range.

4. The intelligent monitoring and scheduling system for the entire phosphoric acid production process based on the Industrial Internet as described in claim 3, characterized in that, The process by which the production scheduling module optimizes the key process parameters of the production process at the identified imbalance nodes includes: Mark the product parameter items and key process items corresponding to the imbalance node. If the key process item affects the product parameter item, then directly mark the key process item as an item to be optimized. If the critical process item does not affect the product parameter item, then obtain all critical process items that will affect the product parameter item, and mark the maximum absolute value of the difference between the process parameters among the obtained critical process items; The critical process items in the imbalanced nodes, as well as the aforementioned critical process items, are marked as items to be optimized. Adjust the process parameters corresponding to the item to be optimized to the corresponding standard process parameter range.

Images