Intelligent production control method for MES based on cloud computing

Abstract

To provide an intelligent production control method of an MES based on cloud computing.SOLUTION: Acquiring a real-time production data set of an organic chemical product, analyzing the real-time production data set, and identifying a production bottleneck stage, analyzing the real-time production data set based on the production bottleneck stage, and identifying a plurality of optimizable factors, simulating a production process of the organic chemical product based on the plurality of optimizable factors, and determining an adjustment result, adjusting the real-time production data set based on the adjustment result, and determining a bottleneck optimization data set, and controlling a production device based on the bottleneck optimization data set to perform corresponding adjustment.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present application relates to the technical field of production control, and in particular to a smart production control method for MES based on cloud computing. [Background technology]

[0002] With the advancement of information technology in industry, the use of MES (Manufacturing Execution System) to manage and monitor industrial production processes can improve production efficiency and product quality, helping enterprises achieve the goals of lean production and information-based smart manufacturing.

[0003] When using traditional MES systems to manage and monitor the production process of organic chemical products, the manufacturing process of organic chemical products is complex and the products change frequently and dynamically during the production process. Therefore, traditional MES systems have difficulty responding flexibly to the many variables that exist in the production process of organic chemical products, which can lead to variations in the quality of organic chemical products and even safety accidents. Summary of the Invention [Problem to be solved by the invention]

[0004] To solve the above technical problems, this application provides a smart production control method for MES based on cloud computing. [Means for solving the problem]

[0005] In a first aspect, the present application provides a smart production control method for MES based on cloud computing, acquiring a real-time production dataset of an organic chemical industry product, analyzing the real-time production dataset, and identifying a bottleneck stage in the manufacturing; analyzing the real-time production data set based on the manufacturing bottleneck stage to identify a plurality of optimizable factors; simulating the organic chemical industry production process based on the plurality of optimizable factors to determine an adjustment result; adjusting the real-time production dataset based on the adjustment result to determine a bottleneck optimization dataset; controlling production equipment and making corresponding adjustments based on the bottleneck optimization data set; The above method, comprising:

[0006] The present application analyzes real-time production datasets during the production process of organic chemical products to identify the manufacturing bottleneck stage that causes quality variations in the organic chemical products; analyzes the real-time production datasets to identify multiple optimizable factors during the manufacturing bottleneck stage; simulates the organic chemical product production process based on the multiple optimizable factors to determine an adjustment result; adjusts the real-time production datasets based on the adjustment result to obtain a bottleneck optimization dataset; and controls the production equipment to make corresponding adjustments based on the bottleneck optimization dataset, thereby flexibly responding to the many variables existing in the production process of organic chemical products, making timely and accurate adjustments to the production equipment, ensuring the quality of the organic chemical products, and reducing the probability of safety accidents.

[0007] Alternatively, the step of analyzing the real-time production dataset and identifying a manufacturing bottleneck stage comprises: applying a time smoothing process to each piece of real-time production data in the real-time production data set based on a cutoff time, and determining low-variation smoothed data corresponding to each piece of real-time production data at a predetermined analysis time; determining a fluctuation index of each real-time production data set during the predetermined total analysis time based on the low-fluctuation smoothed data; determining a relationship fluctuation index between each real-time production data and other real-time production data according to the fluctuation index of each real-time production data; and analyzing the related variability index of each real-time production data to identify a bottleneck stage in manufacturing.

[0008] By using the above technical means, a time smoothing process is performed on each piece of real-time production data based on a predetermined total analysis time and a predetermined analysis time, to obtain low-fluctuation smoothed data that is easier to analyze and process. Based on the low-fluctuation smoothed data, a relational fluctuation index is determined that can reflect the actual fluctuation situation of the current real-time production data under the influence of different real-time production data. The bottleneck stage in manufacturing is identified based on the relational fluctuation index, which improves the efficiency of the mathematical analysis process while allowing the relational fluctuation index to more comprehensively reflect the fluctuation situation of the real-time production data, and improves the accuracy of identifying the bottleneck stage in manufacturing.

[0009] Alternatively, the step of applying a time smoothing process to each real-time production data in the real-time production dataset based on a predetermined total analysis time and a predetermined division time, and determining low-variation smoothed data corresponding to each real-time production data at a predetermined analysis time, refers to the following equation:

[0010] Number 1 JPEG2026020159000002.jpg46170

[0011] The above technical means uses a mathematical analysis method to design a formula for performing a unified time smoothing process on each piece of real-time production data based on a predetermined total analysis time and a predetermined division time, derives low-fluctuation smoothed data corresponding to each piece of real-time production data within the predetermined analysis time, reduces the instability of the real-time production data, and then reduces the sensitivity of the formula to noise in the mathematical analysis of the low-fluctuation smoothed data, thereby improving the accuracy of the resulting fluctuation index.

[0012] Alternatively, the step of determining a fluctuation index for each real-time production data set during the predetermined total analysis time based on the low-fluctuation smoothed data in accordance with the real-time production data set refers to the following formula:

[0013] Number 2 JPEG2026020159000003.jpg60170

[0014] By using the above technical means, a mathematical analysis method is used to design a formula for quantifying the degree of fluctuation in each piece of real-time production data based on low-fluctuation smoothed data, and a fluctuation index is derived, so that the fluctuation index can comprehensively and intuitively reflect the changes in the real-time production data on a time axis corresponding to the entire specified analysis time, thereby improving the accuracy and comprehensiveness of the fluctuation index.

[0015] Alternatively, the step of determining the relationship fluctuation index between each piece of real-time production data and other real-time production data based on the fluctuation index of each piece of real-time production data refers to the following formula:

[0016] Number 3 JPEG2026020159000004.jpg54170

[0017] By using the above technical means, a mathematical analysis method is used to design a formula based on the fluctuation index of each piece of real-time production data, and the influence of other real-time production data on the current real-time production data is comprehensively considered to quantify the relational fluctuation index, so that the relational fluctuation index can more comprehensively reflect the fluctuation situation of the real-time production data, and then the accuracy of identifying the manufacturing bottleneck stage derived based on the relational fluctuation index is further improved.

[0018] Alternatively, the step of analyzing the relational fluctuation index of each real-time production data to identify a bottleneck stage in manufacturing comprises the steps of: identifying a set of locations of a plurality of abnormal relationship variability indices within the real-time production dataset based on a predetermined relationship variability threshold, by referencing the following formula:

[0019] Number 4 JPEG2026020159000005.jpg41170

[0020] analyzing the real-time production data set based on the location set to identify a plurality of anomalous production data; Identifying the manufacturing bottleneck stage based on the plurality of abnormal production data.

[0021] By using the above technical means, based on a manufacturing bottleneck stage, a real-time production dataset is analyzed, a plurality of bottleneck production data related to the manufacturing bottleneck stage is identified, the plurality of bottleneck production data is analyzed, the sensitivity of each bottleneck production data to a plurality of abnormal production data is determined, and based on the sensitivity of each bottleneck production data to the plurality of abnormal production data and a predetermined sensitivity threshold, the plurality of optimizable factors are identified.

[0022] Alternatively, the step of analyzing the real-time production data set based on the manufacturing bottleneck stage and identifying a plurality of optimizable factors comprises: analyzing a real-time production dataset based on the manufacturing bottleneck stage to identify a plurality of bottleneck production data associated with the manufacturing bottleneck stage; analyzing the plurality of bottleneck production data to determine sensitivity of each bottleneck production data to the plurality of abnormal production data; and identifying the plurality of optimizable factors based on the sensitivity of each bottleneck production data to the plurality of abnormal production data and a predetermined sensitivity threshold.

[0023] The above technical means analyzes multiple bottleneck production data based on the bottleneck stage of manufacturing, identifies multiple bottleneck production data, and analyzes the multiple bottleneck production data to determine the sensitivity of each bottleneck production data to multiple abnormal production data, and identifies multiple optimizable factors based on the sensitivity and a predetermined sensitivity threshold.By introducing the concept of sensitivity, multiple bottleneck production data can be sorted out, and the multiple bottleneck production data that are most in need of optimization can be identified from among them and used as multiple optimizable factors, which can subsequently improve the adjustment efficiency of the production process and help accurately understand the adjustment results of the production process.

[0024] Alternatively, the step of analyzing the plurality of bottleneck production data and determining the sensitivity of each bottleneck production data to the plurality of abnormal production data refers to the following equation:

[0025] Number 5 JPEG2026020159000006.jpg48170

[0026] By using the above technical means, a mathematical analysis method is used to design a formula based on multiple bottleneck production data, a regression analysis is performed on the sensitivity of each bottleneck production data to the multiple abnormal production data, a predetermined relationship index is used to reflect the degree of relationship between the current bottleneck production data and the current abnormal production data, and a disturbance term is used to reduce the error in sensitivity, and finally the sensitivity of each bottleneck production data to multiple abnormal production data is derived, thereby improving the accuracy and comprehensiveness of the method.

[0027] Alternatively, the step of simulating the organic chemical industry production process based on the plurality of optimizable factors and determining an adjustment result may include: simulating a real-time production process based on predetermined manufacturing process information and the real-time production data set; adjusting the real-time production process based on the plurality of optimizable factors and simulating the adjusted production process; and analyzing the adjusted production process and determining a plurality of production data in the adjusted production process as an adjusted result.

[0028] By using the above technical means, a real-time production process is simulated based on predetermined manufacturing process information and the real-time production data set, the real-time production process is adjusted based on multiple optimizable factors, the adjusted production process is analyzed, and multiple corresponding production data in the adjusted production process are determined as the adjustment result, thereby improving the accuracy of the adjustment result, avoiding irreversible consequences caused by direct adjustment to the actual production process, and providing an intuitive data basis for subsequent adjustment of the actual production process.

[0029] Alternatively, the method comprises: Based on the real-time production data set and the adjustment result, for each production data in the real-time production data and the adjustment result, recording data at each time node within the analysis time separated by the predetermined separation time, and constructing a dynamic data set; The method further includes identifying and outputting visualized dynamic production data based on the dynamic data set for viewing by a technical expert.

[0030] By using the above technical means, the real-time production dataset and the adjustment results are analyzed, the dynamic dataset is identified, and the dynamic dataset is visualized using data visualization technology to identify visualized dynamic production data, which is provided for analysis by professional engineers, allowing the professional engineers to understand the changes in the production process data, and providing intuitive and comprehensive data for the professional engineers to improve the manufacturing process of organic chemical industrial products.

[0031] In order to clearly describe the embodiments of the present application or the technical means in the prior art, the accompanying drawings that need to be used to depict the embodiments or the prior art will be briefly described below. The accompanying drawings depicted below are only some embodiments of the present application, and those skilled in the art can obtain other drawings based on these accompanying drawings without any creative effort. [Brief explanation of the drawings]

[0032] [Figure 1] FIG. 1 is a schematic diagram illustrating an application scenario provided in an embodiment of the present application. [Figure 2] 1 is a flowchart of a smart production control method for MES based on cloud computing provided in an embodiment of the present application; DETAILED DESCRIPTION OF THE INVENTION

[0033] In order to clarify the purpose, technical means and advantages of the present application, the technical means in the embodiments of the present application will be described in detail below with reference to the drawings in the embodiments of the present application, but it goes without saying that the described embodiments are only some of the embodiments of the present application and do not include all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments in the present application without any creative activity fall within the scope of protection of the present application.

[0034] As used herein, the term "and / or" includes any and all combinations of one or more associated listed elements, for example, A and / or B means that A exists alone, A and B exist simultaneously, or B exists alone. Also, as used herein, the symbol " / " generally means that the associated elements before and after it are in an "or" relationship, unless otherwise specified.

[0035] Hereinafter, embodiments of the present application will be specifically described with reference to the drawings of the specification.

[0036] When using traditional MES methods to manage and monitor the production process of organic chemical products, the manufacturing process of organic chemical products is complex and the products frequently change dynamically during the production process. Therefore, traditional MES methods have difficulty responding flexibly to the many variables that exist in the production process of organic chemical products, which may result in variations in the quality of organic chemical products and even safety accidents.

[0037] Based on this, the cloud computing-based MES smart production control method provided in this application analyzes real-time production data sets during the production process of organic chemical products, identifies the manufacturing bottleneck stage that causes quality variations of the organic chemical products, identifies a number of optimizable factors in the manufacturing bottleneck stage by analyzing the real-time production data sets, determines an adjustment result by simulating the organic chemical product production process based on the multiple optimizable factors, adjusts the real-time production data sets based on the adjustment result to obtain a bottleneck optimization data set, and controls the production equipment to make corresponding adjustments based on the bottleneck optimization data set, thereby flexibly responding to the many variables existing in the production process of organic chemical products, making timely and accurate adjustments to the production equipment, ensuring the quality of the organic chemical products, and reducing the probability of safety accidents.

[0038] 1 is a schematic diagram illustrating an application scenario provided in one embodiment of the present application: In the production process of organic chemical industry products, the method provided in the present application is used to analyze real-time production data and control production equipment to make corresponding adjustments.

[0039] Specifically, the method provided in the present application is installed in an arbitrary server, which communicates with production equipment to obtain real-time production data sets provided by the production equipment, analyzes the real-time production data sets, and identifies the production bottleneck stage that causes quality variations in organic chemical products. By analyzing the real-time production data sets, it identifies multiple optimizable factors in the production bottleneck stage, and based on the multiple optimizable factors, it simulates the production process of the organic chemical products to determine an adjustment result. Based on the adjustment result, it adjusts the real-time production data sets to obtain a bottleneck optimization data set, and controls the production equipment to make corresponding adjustments based on the bottleneck optimization data set, thereby flexibly responding to the many variables existing in the production process of organic chemical products, and timely and accurately adjusting the production equipment, thereby ensuring the quality of the organic chemical products and reducing the probability of safety accidents.

[0040] For specific implementation methods, please refer to the following embodiments.

[0041] 2 is a flowchart of a cloud computing-based MES smart production control method provided in an embodiment of the present application. The method of this embodiment can be used in the server in the above scenario. As shown in FIG. 2, the method includes the following steps:

[0042] S201: A step of acquiring a real-time production dataset of an organic chemical industrial product, analyzing the real-time production dataset, and identifying a manufacturing bottleneck stage.

[0043] Organic chemical products can be chemical products based on organic compounds and produced through chemical reactions and processing.

[0044] The real-time production data can be a series of real-time parameters (such as temperature, reaction pressure, pH value, etc.) of the current chemical reaction stage of the organic chemical industry product in the production process. The real-time production data can be obtained through various sensors arranged in the organic chemical industry product production line.

[0045] A manufacturing bottleneck step can be a step in the current production process of an organic chemical product that adversely affects the final quality of the organic chemical product.

[0046] Specifically, the production process of organic chemical products involves complex chemical reactions, and the various raw materials of the products are extremely sensitive to the reaction conditions during the reaction process. Therefore, if an abnormality occurs in the reaction conditions, the quality of the organic chemical products will often be unacceptable. Furthermore, because organic chemical products continuously undergo multiple chemical reactions in the production timeline, even if a batch of products is unacceptable, it is difficult to timely identify and adjust the stage at which the problem occurred, resulting in variations in the quality of organic chemical products and making it impossible to maintain a high yield rate.

[0047] By using a passing mathematical analysis method to analyze real-time production data during the production process of organic chemical industrial products and quantifying the change state of each production data in the same production time series, it is possible to identify abnormal bottleneck processes and provide basic data for subsequent adjustments to the production process.

[0048] S202: A step of analyzing a real-time production dataset based on a manufacturing bottleneck stage and identifying multiple optimizable factors.

[0049] The optimizable factors may be corresponding production data that need to be adjusted at the bottleneck process.

[0050] Specifically, each manufacturing stage is accompanied by a set of production data, and the cause of the identified manufacturing bottleneck stage is an abnormality resulting from the interaction between multiple production data. After the manufacturing bottleneck stage is identified, a mathematical analysis method is used based on the manufacturing bottleneck stage to quantify the impact of the production data in the real-time production dataset on the manufacturing bottleneck stage, and multiple corresponding optimizable factors during the manufacturing bottleneck stage are identified, which then provides a basis for adjusting organic chemical industrial products.

[0051] S203: A step of simulating a production process of an organic chemical industry product based on a plurality of optimizable factors and determining an adjustment result.

[0052] The adjustment result may be an adjustment value corresponding to a plurality of optimizable factors obtained by optimizing a plurality of optimizable factors and simulating a production process of an organic chemical industry product.

[0053] Specifically, organic chemical products are very sensitive to reaction conditions during the production process, so if multiple optimizable factors are identified and then directly adjusted, it is difficult to ensure real-time production effects. Therefore, based on multiple optimizable factors, the production process of organic chemical products is simulated through process simulation software, such as Aspen Plus (Advanced System for Process Engineering), to determine the values ​​that need to be adjusted for multiple optimizable factors, and provide accurate data for subsequent adjustments to the actual organic chemical product production process.

[0054] S204: Adjusting the real-time production dataset based on the adjustment result to determine a bottleneck optimization dataset.

[0055] The bottleneck optimization data set may be a set that includes all of the production data before and after adjusting the real-time production data set based on the adjustment results.

[0056] Specifically, the production data in the real-time production dataset is adjusted based on the adjustment values ​​corresponding to multiple optimizable factors in the adjustment result, and a bottleneck optimization dataset including all the adjusted and unadjusted production data is obtained, thereby providing a data foundation for making accurate adjustments in the subsequent control of physical production equipment.

[0057] S205: Controlling the production equipment and making corresponding adjustments based on the bottleneck optimization data set.

[0058] A production facility can be a series of physical facilities on a production line for producing an organic chemical industrial product.

[0059] Specifically, after determining the bottleneck optimization data set, communication is made with the physical equipment through the cloud computing platform, and the production equipment is remotely controlled based on the bottleneck optimization data set, so that the production equipment makes corresponding adjustments in real time to ensure the pass rate of the products.

[0060] The method provided in this embodiment analyzes real-time production datasets during the production process of organic chemical products, identifies the manufacturing bottleneck stage that causes quality variations in the organic chemical products, identifies multiple optimizable factors in the manufacturing bottleneck stage by analyzing the real-time production datasets, determines an adjustment result by simulating the organic chemical product production process based on the multiple optimizable factors, adjusts the real-time production datasets based on the adjustment result to obtain a bottleneck optimization dataset, and controls the production equipment to make corresponding adjustments based on the bottleneck optimization datasets, thereby flexibly responding to the many variables existing in the production process of organic chemical products, and timely and accurately adjusting the production equipment, ensuring the quality of the organic chemical products, and reducing the probability of safety accidents.

[0061] In some embodiments, a time smoothing process is performed on each real-time production data in the real-time production dataset based on a predetermined total analysis time and a predetermined division time, low-variation smoothed data corresponding to each real-time production data at the predetermined analysis time is determined, a fluctuation index of each real-time production data at the predetermined total analysis time according to the real-time production dataset is determined based on the low-variation smoothed data, a relationship fluctuation index between each real-time production data and other real-time production data is determined based on the fluctuation index of each real-time production data, and the relationship fluctuation index of each real-time production data is analyzed to identify a manufacturing bottleneck stage.

[0062] The predetermined total analysis time may be a preset analysis time for real-time production data, and may be set according to actual production conditions.

[0063] The predetermined division time may be used to identify time information of different time nodes by dividing a preset total analysis time.

[0064] The low-fluctuation smoothed data can be data that can clearly reflect the trend of changes in real-time production data.

[0065] The fluctuation index may be data that reflects the intensity of fluctuations in real-time production data.

[0066] The relational fluctuation index may be data indicating the degree to which fluctuations in current real-time production data are affected by fluctuations in other real-time production data.

[0067] Specifically, the directly acquired production dataset contains many different types of production data, which are affected by different factors and have significantly different measurement standards for fluctuation ranges, making it difficult to perform a unified mathematical analysis. Therefore, by dividing a given analysis period into multiple time nodes at predetermined intervals and applying time smoothing processing to the production data corresponding to each time node in the real-time production dataset, smoothed data with low fluctuations can be obtained, and noise in the production data can be removed while maintaining the fluctuation characteristics of the production data, reducing the sensitivity to noise in the subsequent mathematical analysis process. The low-fluctuation smoothed data not only reflects the change trends of the real-time production data, but is also easy to analyze and process, and is also useful for improving the efficiency of subsequent mathematical analysis.

[0068] After obtaining the low-fluctuation smoothed data, the fluctuation index quantitatively obtained by mathematical analysis methods is used to reflect the fluctuation situation of the current real-time fluctuation data on the time axis corresponding to the specified analysis time, and since different production data are not independent of each other, different production data affect each other in the production process of organic chemical industrial products. The fluctuation situation of the real-time production data needs to be considered based on the fluctuation index, and the influence of other real-time production data is also taken into account. The relational fluctuation index quantitatively obtained based on the fluctuation index by mathematical analysis methods is used to reflect the actual fluctuation situation of the current real-time production data under the influence of different real-time production data, and the abnormal fluctuation situation in the relational fluctuation index is analyzed to identify the corresponding manufacturing bottleneck stage.

[0069] The method provided in this embodiment performs time smoothing processing on each piece of real-time production data based on a predetermined total analysis time and a predetermined analysis time to obtain low-fluctuation smoothed data that is easier to analyze and process. Based on the low-fluctuation smoothed data, a relational fluctuation index is determined that can reflect the actual fluctuation situation of the current real-time production data under the influence of different real-time production data. The manufacturing bottleneck stage is identified based on the relational fluctuation index, which improves the efficiency of the mathematical analysis process while allowing the relational fluctuation index to more comprehensively reflect the fluctuation situation of the real-time production data, and improves the accuracy of identifying the manufacturing bottleneck stage.

[0070] In some embodiments, applying a time smoothing process to each real-time production data in the real-time production dataset based on a predetermined total analysis time and a predetermined division time, and determining low-variation smoothed data corresponding to each real-time production data at the predetermined analysis time, refers to the following equation (1):

[0071] Number 6 JPEG2026020159000007.jpg46170

[0072] Specifically, a unified smoothing process is applied to the real-time production data values ​​on the most recent N time nodes in equation (1) to obtain smoothed values ​​with low fluctuations for each real-time production data in a predetermined total analysis time, thereby reducing the instability of the real-time production data.

[0073] The method provided in this embodiment uses mathematical analysis techniques to design a formula for performing a unified time smoothing process on each piece of real-time production data based on a predetermined total analysis time and a predetermined division time, derives low-fluctuation smoothed data corresponding to each piece of real-time production data within the predetermined analysis time, reduces the instability of the real-time production data, and then reduces the sensitivity of the formula to noise in the mathematical analysis of the low-fluctuation smoothed data, thereby improving the accuracy of the resulting fluctuation index.

[0074] In some embodiments, determining a fluctuation index for each real-time production data set during the predetermined total analysis time based on the low-fluctuation smoothed data according to the real-time production data set refers to the following equation (2):

[0075] Number 7 JPEG2026020159000008.jpg60170

[0076] Specifically, the difference between the specific data of each real-time production data and the corresponding low-fluctuation smoothed data is quantified by Xi,j-LDi,t in formula (2), and the standard difference between the specific data of each real-time production data and the corresponding low-fluctuation smoothed data is used to reflect the degree of fluctuation of each real-time production data, and the fluctuation index is calculated, so that the fluctuation index can comprehensively and intuitively reflect the change situation of the real-time production data on the time axis corresponding to the entire specified analysis time.

[0077] The method provided in this embodiment uses mathematical analysis techniques to design a formula for quantifying the degree of fluctuation in each piece of real-time production data based on low-fluctuation smoothed data, and derive a fluctuation index, which enables the fluctuation index to comprehensively and intuitively reflect the changes in the real-time production data on a time axis corresponding to the entire specified analysis time, thereby improving the accuracy and comprehensiveness of the fluctuation index.

[0078] In some embodiments, determining the relationship fluctuation index between each real-time production data and other real-time production data based on the fluctuation index of each real-time production data refers to the following equation (3):

[0079] Number 8 JPEG2026020159000009.jpg68170

[0080] The predetermined relationship data matrix may be a preset symmetric matrix for storing correlation coefficients between any two pieces of real-time production data. The diagonal elements of the predetermined relationship data matrix are 0. The predetermined relationship data matrix may be obtained by analyzing historical data.

[0081] JPEG2026020159000010.jpg45170

[0082] The method provided in this embodiment uses mathematical analysis methods to design a formula based on the fluctuation index of each real-time production data, comprehensively considers the impact of other real-time production data on the current real-time production data, and quantifies the relationship fluctuation index, so that the relationship fluctuation index can more comprehensively reflect the fluctuation situation of the real-time production data, and then the accuracy of identifying the manufacturing bottleneck stage derived based on the relationship fluctuation index is further improved.

[0083] In some embodiments, based on a predetermined relationship variability threshold, a set of locations of multiple abnormal relationship variability indices within the real-time production dataset is identified with reference to the following equation (4):

[0084] Number 9 JPEG2026020159000011.jpg40170

[0085] The predetermined relationship variation threshold may be preset threshold data for determining whether or not there is an abnormality in the relationship variation index, and may be obtained by analyzing historical data.

[0086] The abnormal relationship fluctuation index may be abnormal data that is greater than a predetermined relationship fluctuation threshold among the current plurality of relationship fluctuation indexes.

[0087] The location set may be a collection of location indices of real-time production data corresponding to multiple abnormal relational variation indices within the real-time production data set.

[0088] JPEG2026020159000012.jpg72170

[0089] The method provided in this embodiment uses a mathematical analysis method to design a formula for determining whether there is an abnormality in the relationship variation index based on a predetermined abnormal relationship variation index, and extracts position indexes of real-time production data corresponding to the abnormal relationship variation index by assigning values ​​to index variables and selecting them. A plurality of position indexes are combined to obtain a position set, and the manufacturing bottleneck stage is identified through a plurality of abnormal production data corresponding to the position set, making the process of identifying the manufacturing bottleneck stage faster and more accurate.

[0090] In some embodiments, based on a manufacturing bottleneck stage, a real-time production dataset is analyzed to identify a plurality of bottleneck production data associated with the manufacturing bottleneck stage, the plurality of bottleneck production data is analyzed to determine the sensitivity of each bottleneck production data to a plurality of anomalous production data, and the plurality of optimizable factors are identified based on the sensitivity of each bottleneck production data to the plurality of anomalous production data and a predetermined sensitivity threshold.

[0091] The bottleneck production data may be a plurality of real-time production data that are highly correlated with the production bottleneck.

[0092] Sensitivity can be data used to indicate how much the current bottleneck production data is affected by multiple abnormal production data.

[0093] The predetermined sensitivity threshold may be threshold data used to determine whether adjusting the current bottleneck production data will produce a significant effect on multiple abnormal production data, and may be obtained by analyzing historical data.

[0094] Specifically, in the manufacturing process of organic chemical products, a series of highly correlated real-time production data exist at each stage, and these real-time production data influence each other, but these real-time production data cannot be directly adjusted, which on the one hand results in low adjustment efficiency, and on the other hand, directly adjusting the real-time production data in batches makes it difficult to stably control the adjustment results. Therefore, based on the manufacturing process of organic chemical products according to the bottleneck stages in the manufacturing, the real-time production data set is analyzed to identify multiple bottleneck production data corresponding to the bottleneck stages in the manufacturing, and mathematical analysis methods are used to analyze the multiple bottleneck production data to determine the sensitivity of each bottleneck production data to the multiple abnormal production data. If the sensitivity of the multiple bottleneck production data is greater than a predetermined sensitivity threshold, it is shown that adjusting these bottleneck production data can effectively affect the multiple abnormal production data, and these bottleneck production data are determined as multiple optimizable factors.

[0095] The method provided in this embodiment analyzes multiple bottleneck production data based on the bottleneck stage of manufacturing, identifies the multiple bottleneck production data, and analyzes the multiple bottleneck production data to determine the sensitivity of each bottleneck production data to multiple abnormal production data, and identifies multiple optimizable factors based on the sensitivity and a predetermined sensitivity threshold. By introducing the concept of sensitivity, multiple bottleneck production data can be sorted out, and the multiple bottleneck production data that are most in need of optimization can be identified from among them and used as multiple optimizable factors, which can subsequently improve the adjustment efficiency of the production process and help accurately understand the adjustment results of the production process.

[0096] In some embodiments, analyzing the plurality of bottleneck production data and identifying the sensitivity of each bottleneck production data to the plurality of abnormal production data refers to the following equation (5):

[0097] Number 10 JPEG2026020159000013.jpg47170

[0098] The predetermined intercept term may be a constant term representing a sensitivity measure, and may be obtained by analyzing historical data.

[0099] The predetermined disturbance term may be a constant term representing the average calculation error of the sensitivity. The predetermined disturbance term is obtained by analyzing historical data.

[0100] The predetermined relationship index may be data representing the degree to which the bottleneck production data is affected by the corresponding abnormal production data, and may be obtained by analyzing historical data.

[0101] Specifically, based on multiple bottleneck production data, a regression analysis of sensitivity is performed using equation (5), and a predetermined intercept term is used to limit the reference value of the result of equation (5) to prevent the sensitivity from deviating from the normal range. A predetermined relationship index is used to reflect the degree of relationship between the current bottleneck production data and the current abnormal production data, and a disturbance term is used to reduce the sensitivity error, so that the sensitivity of each bottleneck production data to multiple abnormal production data is finally obtained.

[0102] The method provided in this embodiment uses a mathematical analysis method to design a formula based on multiple bottleneck production data, performs regression analysis on the sensitivity of each bottleneck production data to the multiple abnormal production data, reflects the degree of relationship between the current bottleneck production data and the current abnormal production data using a predetermined relationship index, reduces the error in sensitivity using a disturbance term, and finally derives the sensitivity of each bottleneck production data to multiple abnormal production data, thereby improving the accuracy and comprehensiveness of the method.

[0103] In some embodiments, a real-time production process is simulated based on predetermined manufacturing process information and a real-time production dataset, the real-time production process is adjusted based on a plurality of optimizable factors, the adjusted production process is simulated, the adjusted production process is analyzed, and a plurality of production data in the adjusted production process is determined as the adjustment result.

[0104] The predetermined manufacturing process information may be the current manufacturing process of an organic chemical industry product, and may be provided by a professional staff member.

[0105] The real-time production process may be a virtual real-time production process that is simulated based on a real-time production dataset.

[0106] The adjusted production process may be a virtual production process obtained after adjusting the real-time production process based on multiple optimizable factors.

[0107] Specifically, using process simulation software, such as Aspen Plus, a real-time production process is simulated based on predetermined manufacturing process information and real-time production data sets to obtain a virtual process of the real-time production process. Based on multiple optimizable factors, the virtual process of the real-time production process is adjusted using the process simulation software to simulate the adjusted production process. A series of production data for the adjusted production process is extracted, and the above series of production data is determined as the adjustment result, providing an accurate data basis for subsequent adjustment of the actual production process.

[0108] The method provided in this embodiment simulates a real-time production process based on predetermined manufacturing process information and the real-time production data set, adjusts the real-time production process based on multiple optimizable factors, analyzes the adjusted production process, and determines multiple corresponding production data in the adjusted production process as the adjustment result, thereby improving the accuracy of the adjustment result, avoiding irreversible consequences caused by direct adjustment to the actual production process, and providing an intuitive data basis for subsequent adjustment of the actual production process.

[0109] In some embodiments, based on the real-time production dataset and the adjustment results, for each production data in the real-time production data and the adjustment results, data at each time node within an analysis time period separated by a predetermined time interval is recorded to construct a dynamic dataset, and visualized dynamic production data is identified based on the dynamic dataset, output, and made available for viewing by a specialist engineer.

[0110] The dynamic data set may be a data set in which the real-time production data and the production data in the adjustment results change along with the production time series.

[0111] The visualized dynamic production data may be data obtained after performing visualization processing on the dynamic production data, and which can be directly and interactively analyzed by interested parties.

[0112] A technical specialist may be responsible for coordinating the manufacturing process of an organic chemical product.

[0113] Specifically, a data visualization library, such as D3.js (Data-Driven Documents), is used to perform dynamic visualization processing on the dynamic dataset to obtain visualized dynamic production data, and the visualized dynamic production data is output through a human-computer interaction device, such as a high-resolution touch screen, allowing professional engineers to perform interactive analysis.

[0114] The method provided in this embodiment analyzes the real-time production dataset and the adjustment results, identifies the dynamic dataset, visualizes the dynamic dataset using data visualization technology, identifies visualized dynamic production data, and provides the visualized dynamic production data for analysis by professional engineers, allowing the professional engineers to understand the changes in the production process data and providing intuitive and comprehensive data for the professional engineers to improve the manufacturing process of organic chemical industrial products.

Claims

1. A smart production control method for MES based on cloud computing, comprising: acquiring a real-time production dataset of an organic chemical industry product, analyzing the real-time production dataset, and identifying a bottleneck stage in the manufacturing; analyzing the real-time production data set based on the manufacturing bottleneck stage to identify a plurality of optimizable factors; simulating the organic chemical industry production process based on the plurality of optimizable factors to determine an adjustment result; adjusting the real-time production dataset based on the adjustment result to determine a bottleneck optimization dataset; and controlling the production equipment and making corresponding adjustments based on the bottleneck optimization data set; analyzing the real-time production data set and identifying a manufacturing bottleneck stage, applying a time smoothing process to each piece of real-time production data in the real-time production data set based on a predetermined total analysis time and a predetermined division time, and determining low-variation smoothed data corresponding to each piece of real-time production data at the predetermined analysis time; determining a fluctuation index of each real-time production data set during the predetermined total analysis time based on the low-fluctuation smoothed data; determining a relationship fluctuation index between each of the real-time production data and other real-time production data according to the fluctuation index of each of the real-time production data; analyzing the related fluctuation index of each of the real-time production data to identify the manufacturing bottleneck stage; The step of performing a time smoothing process on each piece of real-time production data in the real-time production data set based on a predetermined total analysis time and a predetermined division time, and determining low-variation smoothed data corresponding to each piece of real-time production data at a predetermined analysis time, refers to the following formula: Number 1 The step of determining a fluctuation index of each piece of real-time production data during the predetermined total analysis time according to the real-time production data set based on the low-fluctuation smoothed data, refers to the following formula: Number 2 12. The step of determining the relationship fluctuation index between each real-time production data and other real-time production data based on the fluctuation index of each real-time production data, refers to the following formula: Number 3 The step of analyzing the related fluctuation index of each real-time production data to identify a bottleneck stage in manufacturing includes: identifying a set of locations of a plurality of abnormal relationship variability indexes within the real-time production dataset based on a predetermined relationship variability threshold, with reference to the following formula: Number 4 analyzing the real-time production data set based on the set of locations to identify a plurality of anomalous production data; and identifying the manufacturing bottleneck stage based on the plurality of abnormal production data; analyzing the real-time production data set based on the manufacturing bottleneck stage and identifying a plurality of optimizable factors, analyzing a real-time production dataset based on the manufacturing bottleneck stage to identify a plurality of bottleneck production data associated with the manufacturing bottleneck stage; analyzing the plurality of bottleneck production data to determine sensitivity of each bottleneck production data to the plurality of abnormal production data; identifying the plurality of optimizable factors based on the sensitivity of each bottleneck production data to the plurality of abnormal production data and a predetermined sensitivity threshold; The step of analyzing the plurality of bottleneck production data and determining the sensitivity of each bottleneck production data to the plurality of abnormal production data refers to the following equation: Number 5 A method characterized by:

2. The step of simulating the production process of the organic chemical industry product based on the plurality of optimizable factors and determining an adjustment result includes: simulating a real-time production process based on predetermined manufacturing process information and the real-time production data set; adjusting the real-time production process based on the plurality of optimizable factors and simulating the adjusted production process; analyzing the adjusted production process and determining a plurality of production data in the adjusted production process as an adjusted result; 2. The method of claim 1, comprising:

3. Based on the real-time production data set and the adjustment result, for each production data in the real-time production data and the adjustment result, recording data at each time node within the analysis time separated by the predetermined separation time, and constructing a dynamic data set; Identifying and outputting visualized dynamic production data based on the dynamic data set for viewing by a technical expert; 3. The method of claim 2, further comprising:

Images