Cloud computing- and MES-based intelligent production control system

Abstract

The present application relates to the technical field of production control, and in particular to a cloud computing- and MES-based intelligent production control system. The system comprises: acquiring a real-time production data set of an organic chemical product, analyzing the real-time production data set, and determining a production bottleneck stage; on the basis of the production bottleneck stage, analyzing the real-time production data set, and determining a plurality of optimizable factors; on the basis of the plurality of optimizable factors, simulating a production process of the organic chemical product, and determining an adjustment result; on the basis of the adjustment result, adjusting the real-time production data set, and determining a bottleneck optimization data set; and on the basis of the bottleneck optimization data set, controlling a production device to perform corresponding adjustment. In the present application, by analyzing the real-time production data set and controlling the production device to perform corresponding adjustment, flexible responses to many variables present in an organic chemical production process can be achieved, and the production device can be accurately adjusted in a timely manner, thereby ensuring the quality of organic chemical products and reducing the occurrence probability of safety accidents.

Description

A cloud-based MES intelligent production control system Technical Field

[0001] This application relates to the field of production control technology, and in particular to a cloud computing-based MES intelligent production control system. Background Technology

[0002] With the development of industrial informatization, 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 intelligent manufacturing.

[0003] When managing and monitoring the production process of organic chemical products, existing MES systems are unable to flexibly cope with the many variables in the production process due to the complexity of the organic chemical production process and the frequent dynamic changes of the products during the production process. This results in inconsistent quality of organic chemical products and even the occurrence of safety accidents. Summary of the Invention

[0004] This application provides a cloud-based MES intelligent production control system to solve the above-mentioned technical problems.

[0005] Firstly, this application provides a cloud-based MES intelligent production control system, the system comprising:

[0006] Obtain real-time production datasets of organic chemical products, analyze the real-time production datasets, and identify production bottlenecks.

[0007] Based on the aforementioned production bottleneck, the real-time production dataset is analyzed to identify several optimizable factors.

[0008] Based on the aforementioned optimizable factors, the production process of the organic chemical product is simulated to determine the adjustment results;

[0009] Based on the adjustment results, adjust the real-time production dataset and determine the bottleneck optimization dataset;

[0010] Based on the bottleneck optimization dataset, the production equipment is controlled to make corresponding adjustments.

[0011] This application analyzes real-time production datasets during the production process of organic chemical products to identify bottlenecks that cause inconsistent product quality. By analyzing these datasets, several optimizable factors within these bottlenecks are determined. Based on these optimizable factors, the production process is simulated to determine adjustment results. These results are then used to adjust the real-time production dataset, resulting in an optimized bottleneck dataset. Based on this optimized dataset, production equipment is adjusted accordingly to flexibly address the numerous variables present in the organic chemical production process, enabling timely and precise adjustments to the equipment, ensuring product quality, and reducing the probability of safety accidents.

[0012] Optionally, analyzing the real-time production dataset to identify production bottlenecks includes:

[0013] Based on the preset total analysis time and preset segmentation time, time smoothing is performed on each real-time production data in the real-time production dataset to determine the low-fluctuation smoothed data corresponding to each real-time production data under the preset analysis time.

[0014] Based on the low-fluctuation smoothed data, and according to the real-time production dataset, the fluctuation index of each real-time production data under the preset total analysis time is determined.

[0015] Based on the fluctuation index of each real-time production data, determine the relationship fluctuation index between each real-time production data and other real-time production data.

[0016] Analyze the relationship fluctuation index of each real-time production data to identify production bottlenecks.

[0017] Through the above technical solution, based on the preset total analysis time and preset analysis duration, time smoothing is performed on each real-time production data to obtain low-fluctuation smoothed data that is easier to analyze and process. On the basis of low-fluctuation smoothed data, a relational fluctuation index is determined that can reflect the actual fluctuation of the current real-time production data under the influence of different real-time production data. Based on the relational fluctuation index, the production bottleneck is identified. While improving the efficiency of the mathematical analysis process, the relational fluctuation index more comprehensively reflects the fluctuation of real-time production data and improves the accuracy of the production bottleneck.

[0018] Optionally, based on a preset total analysis time and a preset segmentation time, time smoothing is performed on each real-time production data in the real-time production dataset to determine the low-fluctuation smoothed data corresponding to each real-time production data under the preset analysis time, referring to the following formula:

[0019] Where t is the preset total analysis time, LD i,tThe low-fluctuation smoothed data of the i-th real-time production data in the real-time production dataset under the preset analysis duration t, where N is the preset separation duration, and X... i,k This refers to the specific data corresponding to the i-th real-time production data at time node k.

[0020] By employing the above technical solution and utilizing mathematical analysis methods, based on the preset total analysis time and preset segmentation time, a mathematical formula is designed to perform uniform time smoothing on each real-time production data. This yields low-fluctuation smoothed data corresponding to each real-time production data under the preset analysis time, reducing the instability of real-time production data and decreasing the sensitivity of the corresponding mathematical formula to noise when performing subsequent mathematical analysis on the low-fluctuation smoothed data, thereby improving the accuracy of the subsequently derived fluctuation index.

[0021] Optionally, based on the low-fluctuation smoothed data and according to the real-time production dataset, the fluctuation index of each real-time production data point under the preset total analysis duration is determined, referring to the following formula:

[0022] Where t is the preset total analysis time, σ i,t X is the fluctuation index of the i-th real-time production data under the preset total analysis time t, where N is the preset interval time and X is the fluctuation index of the i-th real-time production data under the preset total analysis time t. i,j Let LD be the specific value corresponding to the i-th real-time production data at time node j. i,t The low-fluctuation smoothed data for the i-th real-time production data under the preset analysis duration t.

[0023] By employing the above technical solutions and mathematical analysis methods, a mathematical formula is designed to quantify the degree of fluctuation of each real-time production data based on low-fluctuation smoothed data, thereby deriving a fluctuation index. This fluctuation index can comprehensively and intuitively reflect the changes of real-time production data on the time axis corresponding to the entire preset analysis period, thus improving the accuracy and comprehensiveness of the fluctuation index.

[0024] Optionally, the relationship fluctuation index of each real-time production data point is determined based on the fluctuation index of each real-time production data point, referring to the following formula:

[0025] Where, σ′ i,t σ is the relationship fluctuation index of the i-th real-time production data under the preset total analysis time t. i,t C is the fluctuation index of the i-th real-time production data under the preset total analysis time t. ij For the preset data relationship matrix, σ j,t The fluctuation index of the j-th real-time production data under the preset total analysis time t.

[0026] Through the above technical solution, based on the fluctuation index of each real-time production data, mathematical formulas are designed using mathematical analysis methods to comprehensively consider the impact of other real-time production data on the current real-time production data, thereby quantifying the relationship fluctuation index. This allows the relationship fluctuation index to more comprehensively reflect the fluctuation of real-time production data, and consequently makes the production bottleneck links identified based on the relationship fluctuation index more accurate.

[0027] Optionally, the analysis of the relationship fluctuation index of each real-time production number to determine the production bottleneck includes:

[0028] Based on a preset relationship fluctuation threshold, and referring to the following formula, determine the set of locations of several abnormal relationship fluctuation indices in the real-time production dataset:

[0029] Where S is the set of locations, I′ i,t As an indicator variable, σ′ i,t The relationship fluctuation index of the i-th real-time production data under the preset total analysis time t, where T is the preset relationship fluctuation threshold;

[0030] Based on the set of locations, analyze the real-time production dataset to identify several abnormal production data.

[0031] Based on the aforementioned abnormal production data, the bottleneck in production is identified.

[0032] Through the above technical solution, based on the production bottleneck, the real-time production dataset is analyzed to determine several bottleneck production data related to the production bottleneck; the several bottleneck production data are analyzed to determine the sensitivity of each bottleneck production data to several abnormal production data; based on the sensitivity of each bottleneck production data to the several abnormal production data and the preset sensitivity threshold, the several optimizable factors are determined.

[0033] Optionally, based on the production bottleneck, the analysis of the real-time production dataset determines several optimizable factors, including:

[0034] Based on the production bottleneck, analyze the real-time production dataset to determine several bottleneck production data related to the production bottleneck.

[0035] Analyze the bottleneck production data to determine the sensitivity of each bottleneck production data point to the abnormal production data points.

[0036] Based on the sensitivity of each bottleneck production data to the aforementioned abnormal production data and a preset sensitivity threshold, the aforementioned optimizable factors are determined.

[0037] The above technical solution analyzes several bottleneck production data points based on the production bottleneck process, identifies these bottleneck production data points, and determines the sensitivity of each bottleneck production data point to several abnormal production data points. Based on the sensitivity and a preset sensitivity threshold, several optimizable factors are identified. By introducing sensitivity, the bottleneck production data points are screened to determine the bottleneck production data points with the highest optimization necessity, and these are used as optimizable factors. This improves the efficiency of subsequent adjustments to the production process and helps to accurately control the results of subsequent production process adjustments.

[0038] Optionally, the analysis of the bottleneck production data to determine the sensitivity of each bottleneck production data point to the abnormal production data is performed using the following formula:

[0039] Among them, Y j Let β0 be the sensitivity, ∈ be the preset intercept term, and β be the preset perturbation term. a For current bottleneck production data, X j For the j-th abnormal production data, F j The index is a preset relationship index between the j-th abnormal production data and the current bottleneck production data, and n is the total number of the abnormal production data.

[0040] By employing the above technical solution and mathematical analysis methods, a mathematical formula is designed based on several bottleneck production data to perform regression analysis on the sensitivity of each bottleneck production data to several abnormal production data. A preset relationship index is used to reflect the closeness of the relationship between the current bottleneck production data and the current abnormal production data. The error of the sensitivity is reduced by a perturbation term, and finally the sensitivity of each bottleneck production data to several abnormal production data is obtained, thereby improving the accuracy and comprehensiveness of the sensitivity.

[0041] Optionally, the step of simulating the production process of the organic chemical product based on the aforementioned optimizable factors and determining the adjustment results includes:

[0042] Based on the preset production process information and the real-time production dataset, simulate the real-time production process;

[0043] Based on the aforementioned optimizable factors, the real-time production process is adjusted, and the adjusted production process is simulated.

[0044] Analyze the adjusted production process and determine several production data points from the adjusted production process as the adjustment results.

[0045] The above technical solution simulates the real-time production process based on the preset production process flow information and real-time production dataset. It then adjusts the real-time production process according to several optimizable factors, analyzes the adjusted production process, and determines several production data corresponding to the adjusted production process as the adjustment result. This improves the accuracy of the adjustment result, avoids irreversible consequences from directly adjusting the actual production process, and provides intuitive data basis for subsequent adjustments to the actual production process.

[0046] Optionally, the system further includes:

[0047] Based on the real-time production dataset and the adjustment results, record the data of each production data point within the real-time production data and the adjustment results at each time point under the analysis duration after being separated by the preset separation duration, thus forming a dynamic dataset.

[0048] Based on the dynamic dataset, visualized dynamic production data is determined and output for professionals to view.

[0049] By analyzing the real-time production dataset and adjustment results using the above technical solutions, a dynamic dataset is determined. Through data visualization technology, the dynamic dataset is visualized to identify and visualize dynamic production data. This visualized dynamic production data is then provided to professionals for analysis, enabling them to understand the changes in production process data and providing them with intuitive and comprehensive data for improving organic chemical production processes. Attached Figure Description

[0050] 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 some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 is a schematic diagram of an application scenario provided by an embodiment of this application;

[0052] Figure 2 is a flowchart of a cloud computing-based MES intelligent production control system provided in an embodiment of this application. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0054] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0055] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0056] When managing and monitoring the production process of organic chemical products, existing MES systems are unable to flexibly cope with the many variables in the production process due to the complexity of the organic chemical production process and the frequent dynamic changes of the products during the production process. This results in inconsistent quality of organic chemical products and even the occurrence of safety accidents.

[0057] Based on this, this application provides a cloud-based MES intelligent production control system. It analyzes real-time production datasets during the organic chemical product production process to identify bottlenecks causing inconsistent product quality. By analyzing these datasets, it identifies several optimizable factors within these bottlenecks. Based on these optimizable factors, it simulates the organic chemical product production process to determine adjustment results. The system then adjusts the real-time production dataset according to these results, obtaining a bottleneck optimization dataset. Based on this optimized dataset, it controls the production equipment to make corresponding adjustments, flexibly responding to the numerous variables present in the organic chemical production process, enabling timely and precise adjustments to the equipment, ensuring the quality of organic chemical products, and reducing the probability of safety accidents.

[0058] Figure 1 is a schematic diagram of an application scenario provided by this application. In the production process of organic chemical products, the system provided by this application is used to analyze real-time production data and control the production equipment to make corresponding adjustments.

[0059] Specifically, the system provided by this application is installed on any server, which communicates with production equipment, obtains the real-time production data set provided by the production equipment through this equipment, analyzes the real-time production data set, determines the production bottleneck links that cause uneven quality of organic chemical products, and determines several optimizable factors in the production bottleneck links through analyzing the real-time production data set. Based on the several optimizable factors, through the simulation of the production process of organic chemical products, the adjustment result is determined, and the real-time production data set is adjusted according to the adjustment result to obtain the bottleneck optimization data set. According to the bottleneck optimization data set, the production equipment is controlled to make corresponding adjustments to flexibly respond to the many variables existing in the organic chemical production process, timely and accurately adjust the production equipment, ensure the quality of organic chemical products, and reduce the occurrence probability of safety accidents.

[0060] Specific implementation methods can refer to the following embodiments.

[0061] FIG. 2 is a flowchart of a cloud computing-based MES intelligent production control system provided by an embodiment of this application. The system of this embodiment can be applied to the server in the above scenario. As shown in FIG. 2, the system includes:

[0062] S201. Obtain the real-time production data set of organic chemical products, analyze the real-time production data set, and determine the production bottleneck links.

[0063] Organic chemical products can be chemical products produced based on organic compounds through chemical reactions and processing processes.

[0064] The real-time production data can be a series of real-time parameters in the chemical reaction stage during the production process of current organic chemical products, such as temperature, reaction pressure, and pH value, etc. The real-time production data can be obtained through various sensors arranged in the organic chemical product production line.

[0065] The production bottleneck links can be the links that have a negative impact on the final quality of organic chemical products during the current production process of organic chemical products.

[0066] Specifically, due to the complex chemical reactions involved in the production process of organic chemical products, and various raw materials of the products are extremely sensitive to reaction conditions during the reaction process, when the reaction conditions are abnormal, the quality of organic chemical products often shows a situation of batch unqualified. And because organic chemical products are continuously in multi-stage chemical reactions in the production time series, when there is a situation of batch unqualified products, it is difficult to locate and adjust the problematic links in a timely manner, resulting in uneven quality of organic chemical products and unable to ensure a high良品率 (the text seems to be missing the Chinese character for "qualified product rate", assuming it should be "qualified product rate" here).

[0067] By using mathematical analysis methods to analyze real-time production data in the production process of organic chemical products, the changes in production data under the same production time series are quantified, and bottleneck links with abnormalities are located, providing basic data for subsequent adjustments to the production process.

[0068] S202. Based on the bottleneck links in production, analyze the real-time production dataset and identify several optimizable factors.

[0069] Optimizable factors can be the production data that needs to be adjusted in the bottleneck process.

[0070] Specifically, since each production stage involves a series of production data, and a production stage is often identified as a bottleneck stage due to anomalies caused by the interaction between multiple production data, after identifying the bottleneck stage, mathematical analysis is used to quantify the impact of centralized production data in real-time production datasets on the bottleneck stage. This helps to determine several optimizable factors in the bottleneck stage, providing a basis for subsequent adjustments to organic chemical products.

[0071] S203. Based on several optimizable factors, simulate the production process of organic chemical products and determine the adjustment results.

[0072] The adjustment result can be the adjustment value of several optimizable factors obtained by optimizing several optimizable factors and simulating the production process of organic chemical products.

[0073] Specifically, because organic chemical products are highly sensitive to reaction conditions during production, directly adjusting these factors after identifying several optimizable factors can hardly guarantee real-time production results. Therefore, based on these optimizable factors, process simulation software, such as Aspen Plus (Advanced System for Process Engineering), is used to simulate the production process of organic chemical products to determine the values ​​that need to be adjusted for these optimizable factors. This provides accurate data for subsequent adjustments to the actual production process of organic chemical products.

[0074] S204. Based on the adjustment results, adjust the real-time production dataset and determine the bottleneck optimization dataset.

[0075] The bottleneck optimization dataset can be a collection of all adjusted and unadjusted production data after the real-time production dataset has been adjusted based on the adjustment results.

[0076] Specifically, based on the adjustment values ​​corresponding to several optimizable factors in the adjustment results, the production data in the real-time production dataset is adjusted to obtain a bottleneck optimization dataset containing all adjusted and unadjusted production data, providing a data foundation for subsequent accurate adjustment of the control entity's production equipment.

[0077] S205. Based on the bottleneck optimization dataset, control the production equipment to make corresponding adjustments.

[0078] Production equipment can be a series of physical devices on a production line that produces organic chemical products.

[0079] Specifically, after determining the bottleneck optimization dataset, the system communicates with the physical equipment through a cloud computing platform. Based on the bottleneck optimization dataset, the system remotely controls the production equipment to enable it to make corresponding adjustments in real time and ensure the product qualification rate.

[0080] This embodiment analyzes real-time production datasets during the production of organic chemical products to identify bottlenecks that cause inconsistent product quality. By analyzing these datasets, several optimizable factors within these bottlenecks are determined. Based on these optimizable factors, the production process is simulated to determine adjustment results. These results are then used to adjust the real-time production dataset, resulting in a bottleneck optimization dataset. Based on this optimized dataset, production equipment is adjusted accordingly to flexibly address the numerous variables present in the organic chemical production process. Timely and precise adjustments to the equipment ensure product quality and reduce the probability of safety accidents.

[0081] In some embodiments, time smoothing is performed on each real-time production data in the real-time production dataset according to a preset total analysis time and a preset segmentation time to determine the low-fluctuation smoothed data corresponding to each real-time production data under the preset analysis time; based on the low-fluctuation smoothed data, the fluctuation index of each real-time production data under the preset total analysis time is determined according to the real-time production dataset; based on the fluctuation index of each real-time production data, the relationship fluctuation index between each real-time production data and other real-time production data is determined; the relationship fluctuation index of each real-time production data is analyzed to identify the production bottleneck.

[0082] The preset total analysis time can be the preset analysis time for real-time production data, and the preset total analysis time can be set according to the actual production situation.

[0083] The preset segmentation duration can be a preset total analysis duration that is divided to determine the duration information of different time nodes.

[0084] Low-fluctuation smoothed data can be data that clearly reflects the changing trends of real-time production data.

[0085] A volatility index can be a measure of the degree of volatility in real-time production data.

[0086] The relational volatility index can be a measure of the degree to which fluctuations in current real-time production data are affected by fluctuations in other real-time production data.

[0087] Specifically, since the directly acquired production dataset contains a large number of different types of production data, these production data are affected differently, and the standards for measuring fluctuation amplitude also vary greatly, making it difficult to conduct unified mathematical analysis. By pre-setting the separation time, the preset analysis time is divided into several time nodes, and the production data corresponding to each time node in the real-time production dataset is time-smoothed to obtain low-fluctuation smoothed data. While preserving the fluctuation characteristics of the production data, noise in the production data is eliminated, reducing the sensitivity of subsequent mathematical analysis to noise. Low-fluctuation smoothed data not only reflects the changing trend of real-time production data, but is also easier to analyze and process, which helps to improve the efficiency of subsequent mathematical analysis.

[0088] After obtaining low-fluctuation smoothed data, mathematical analysis is used to quantify the fluctuation index to reflect the fluctuation of the current real-time data within the time axis corresponding to the preset analysis duration. Meanwhile, since different production data are not independent of each other, they will affect each other in the production process of organic chemical products. The fluctuation of a real-time production data needs to consider the influence of other real-time production data on it in addition to the fluctuation index. Through mathematical analysis, a relational fluctuation index is quantified to reflect the actual fluctuation of the current real-time production data under the influence of different real-time production data. By analyzing the abnormal fluctuations in the relational fluctuation index, the corresponding production bottleneck is identified.

[0089] In this embodiment, based on a preset total analysis time and a preset analysis duration, time smoothing is performed on each real-time production data 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 reflects the actual fluctuation of the current real-time production data under the influence of different real-time production data. Based on the relational fluctuation index, the production bottleneck is identified. This improves the efficiency of the mathematical analysis process and makes the relational fluctuation index more comprehensively reflect the fluctuation of real-time production data, thereby improving the accuracy of the production bottleneck.

[0090] In some embodiments, based on a preset total analysis time and a preset separation time, time smoothing is performed on each real-time production data in the real-time production dataset to determine the low-fluctuation smoothed data corresponding to each real-time production data under the preset analysis time, referring to formula (1):

[0091] Where t is the preset total analysis time, LD i,t This represents the low-fluctuation smoothed data of the i-th real-time production data in the real-time production dataset under a preset analysis duration t, where N is the preset separation duration and X... i,k This refers to the specific data corresponding to the i-th real-time production data at time node k.

[0092] Specifically, the real-time production data values ​​at nearly N time points are uniformly smoothed using formula (1) to obtain a low-fluctuation smoothed value for each real-time production data under the preset total analysis time, thereby reducing the instability of real-time production data.

[0093] The method provided in this embodiment utilizes mathematical analysis techniques to design mathematical formulas to perform uniform time smoothing on each real-time production data based on a preset total analysis time and a preset segmentation time. This yields low-fluctuation smoothed data corresponding to each real-time production data under the preset analysis time, reducing the instability of real-time production data and decreasing the sensitivity of the corresponding mathematical formula to noise when performing subsequent mathematical analysis on the low-fluctuation smoothed data, thereby improving the accuracy of the subsequently derived fluctuation index.

[0094] In some embodiments, based on the low-fluctuation smoothed data, the fluctuation index of each real-time production data point under the preset total analysis duration is determined according to the real-time production dataset, referring to formula (2):

[0095] Where t is the preset total analysis time, σ i,t X is the fluctuation index of the i-th real-time production data under the preset total analysis time t, where N is the preset interval time and X is the fluctuation index of the i-th real-time production data under the preset total analysis time t. i,j Let LD be the specific value corresponding to the i-th real-time production data at time node j. i,t The low-fluctuation smoothed data for the i-th real-time production data under the preset analysis duration t.

[0096] Specifically, through X in formula (2) i,j -LD i,t The difference between the specific data of each real-time production data point and the corresponding low-fluctuation smoothed data point is quantified. Then, the standard deviation between the specific data of each real-time production data point and the corresponding low-fluctuation smoothed data point is used to reflect the degree of fluctuation of each real-time production data point, and a fluctuation index is obtained. The fluctuation index can comprehensively and intuitively reflect the changes of real-time production data on the time axis corresponding to the entire preset analysis period.

[0097] The method provided in this embodiment utilizes mathematical analysis to design mathematical formulas to quantify the degree of fluctuation of each real-time production data based on low-fluctuation smoothed data, thereby deriving a fluctuation index. This fluctuation index can comprehensively and intuitively reflect the changes of real-time production data on the time axis corresponding to the entire preset analysis period, thus improving the accuracy and comprehensiveness of the fluctuation index.

[0098] In some embodiments, the relational volatility index of each real-time production data is determined based on the volatility index of each real-time production data, referring to formula (3):

[0099] Where, σ′ i,t Let σ be the relationship fluctuation index of the i-th real-time production data under the preset total analysis time t. i,t Let C be the fluctuation index of the i-th real-time production data under the preset total analysis time t. ij Let σ be the relationship coefficient between the i-th real-time production data and the j-th real-time production data in the preset data relationship matrix. j,t Let M be the fluctuation index of the j-th real-time production data under the preset total analysis time t, and M be the number of real-time production data within the real-time production data.

[0100] The preset relationship data matrix can be a preset symmetric matrix used to store the relationship coefficients between any two real-time production data. The diagonal elements in the preset relationship data matrix are 0. The preset relationship data matrix can be obtained by analyzing historical data.

[0101] Specifically, based on the fluctuation index of each real-time production data, the influence of other real-time production data on the current real-time production data is taken into consideration using formula (3). Calculate the volatility weighted sum of the current real-time production data. By summing the volatility weighted sum with the volatility index, and taking into account the impact of other real-time production data on the current real-time production data, the relational volatility index is obtained.

[0102] The method provided in this embodiment, based on each real-time production data fluctuation index, uses mathematical analysis to design a mathematical formula, integrates the impact of other real-time production data on the current real-time production data, and quantifies the relationship fluctuation index. This makes the relationship fluctuation index more comprehensively reflect the fluctuation of real-time production data, thereby making the production bottleneck links derived from the relationship fluctuation index more accurate.

[0103] In some embodiments, based on a preset relationship fluctuation threshold and referring to formula (4), a set of locations of several abnormal relationship fluctuation indices in the real-time production dataset is determined:

[0104] Where S is the set of locations, I′i,t As an indicator variable, σ′ i,t Let be the relationship fluctuation index of the i-th real-time production data under the preset total analysis time t, where T is the preset relationship fluctuation threshold; analyze the real-time production dataset based on the location set to identify several abnormal production data; and identify the production bottleneck based on the several abnormal production data.

[0105] The preset relationship fluctuation threshold can be a preset threshold data used to determine whether the relationship fluctuation index is abnormal. The preset relationship fluctuation threshold can be obtained by analyzing historical data.

[0106] The abnormal relationship fluctuation index can be any abnormal data that exceeds a preset relationship fluctuation threshold from among several current relationship fluctuation indices.

[0107] The location set can be a set of location indices of real-time production data corresponding to several abnormal relationship fluctuation indices in the real-time production dataset.

[0108] Specifically, through formula (4) The system determines whether the relationship fluctuation index is abnormal, assigns values ​​to the indicator variables, and then uses i|I′ to determine the relationship fluctuation index. i,t =1. The indicator variables are filtered, the position subscripts of the real-time production data corresponding to the abnormal relationship fluctuation index are extracted, and several position subscripts are integrated to obtain a position set. The corresponding real-time production data in the real-time production dataset is located through the position set to obtain several abnormal production data. Based on the production process of organic chemical products, several production links corresponding to several abnormal production data are determined, and the production links with the highest priority in the execution order of several production environments are identified as production bottleneck links.

[0109] The method provided in this embodiment utilizes mathematical analysis to design a mathematical formula based on a preset abnormal relationship fluctuation index to determine whether the relationship fluctuation index is abnormal. By assigning values ​​to the indicator variables and filtering them, the location index of the real-time production data corresponding to the abnormal relationship fluctuation index is extracted. Several location indices are integrated to obtain a location set. Then, by using several abnormal production data corresponding to the location set, the production bottleneck link is located, making the process of locating the production bottleneck link faster and more accurate.

[0110] In some embodiments, based on the production bottleneck, a real-time production dataset is analyzed to determine several bottleneck production data related to the production bottleneck; the several bottleneck production data are analyzed to determine the sensitivity of each bottleneck production data to several abnormal production data; and the several optimizable factors are determined based on the sensitivity of each bottleneck production data to the several abnormal production data and a preset sensitivity threshold.

[0111] Bottleneck production data can be several real-time production data that are highly correlated with the production bottleneck.

[0112] Sensitivity can be a measure of how much current bottleneck production data is affected by several abnormal production data.

[0113] The preset sensitivity threshold can be a threshold value used to determine whether adjusting the current bottleneck production data will have a significant effect on several abnormal production data. The preset sensitivity threshold can be obtained by analyzing historical data.

[0114] Specifically, in the production process of organic chemical products, a series of highly correlated real-time production data exist within a certain stage. These real-time production data influence each other, but it is not possible to directly adjust all of them. On the one hand, the adjustment efficiency is low, and on the other hand, it is difficult to stably control the adjustment results by directly adjusting the above-mentioned real-time production data in batches. Therefore, based on the production bottleneck stage and the production process of organic chemical products, the real-time production dataset is analyzed to determine several bottleneck production data corresponding to the bottleneck stage. Through mathematical analysis, these bottleneck production data are analyzed to determine the sensitivity of each bottleneck production data to the several abnormal production data. When the sensitivity of several bottleneck production data is greater than a preset sensitivity threshold, it indicates that adjusting these bottleneck production data can effectively affect the several abnormal production data. Therefore, these bottleneck production data are identified as several optimizable factors.

[0115] The method provided in this embodiment analyzes several bottleneck production data based on the production bottleneck, identifies several bottleneck production data, and determines the sensitivity of each bottleneck production data to several abnormal production data by analyzing the bottleneck production data. Based on the sensitivity and a preset sensitivity threshold, several optimizable factors are identified. By introducing sensitivity, several bottleneck production data are screened to identify the bottleneck production data with the highest necessity for optimization, and these are used as several optimizable factors. This improves the efficiency of subsequent adjustments to the production process and helps to accurately control the results of subsequent production process adjustments.

[0116] In some embodiments, several bottleneck production data are analyzed to determine the sensitivity of each bottleneck production data to several abnormal production data, referring to formula (5):

[0117] Where Y is the sensitivity, β0 is the preset intercept term, ε is the preset perturbation term, and β a For current bottleneck production data, X j For the j-th abnormal production data, F j Let n be the preset relationship index between the j-th abnormal production data and the current bottleneck production data, and n be the total number of abnormal production data.

[0118] The preset intercept term can be a constant term used to represent the sensitivity benchmark value, and the preset intercept term can be obtained by analyzing historical data.

[0119] The preset perturbation term can be a constant term used to represent the average calculation error of sensitivity, and the preset perturbation term can be obtained by analyzing historical data.

[0120] The preset relationship index can be used to express the degree to which bottleneck production data is affected by corresponding abnormal production data. The preset relationship index can be obtained by analyzing historical data.

[0121] Specifically, based on several bottleneck production data, the sensitivity is regressed using formula (5). The baseline value of the result of formula (5) is limited by a preset intercept term to prevent the sensitivity from deviating from the normal range. The relationship between the current bottleneck production data and the current abnormal production data is reflected by a preset relationship index. The error of the sensitivity is reduced by a perturbation term. Finally, the sensitivity of each bottleneck production data to several abnormal production data is obtained.

[0122] The method provided in this embodiment utilizes mathematical analysis techniques to design mathematical formulas based on several bottleneck production data to perform regression analysis on the sensitivity of each bottleneck production data to several abnormal production data. A preset relationship index reflects the closeness of the relationship between the current bottleneck production data and the current abnormal production data, and a perturbation term reduces the error of the sensitivity. Finally, the sensitivity of each bottleneck production data to several abnormal production data is obtained, improving the accuracy and comprehensiveness of the sensitivity.

[0123] In some embodiments, a real-time production process is simulated based on preset production process flow information and real-time production dataset; the real-time production process is adjusted based on several optimizable factors, and the adjusted production process is simulated; the adjusted production process is analyzed, and several production data in the adjusted production process are determined as the adjustment result.

[0124] The preset production process information can be the current production process of organic chemical products, and the preset production process information can be provided by professional staff.

[0125] A real-time production process can be a virtual real-time production process simulated based on a real-time production dataset.

[0126] The adjusted production process can be a virtual production process obtained by adjusting the real-time production process based on several optimizable factors.

[0127] Specifically, using process simulation software such as Aspen Plus, the real-time production process is simulated based on preset production process information and real-time production datasets to obtain a virtual process. Then, based on several optimizable factors, the virtual process is adjusted using the process simulation software to simulate the adjusted production process. A series of production data in the adjusted production process are extracted and identified as the adjustment results, providing accurate data basis for subsequent adjustments to the actual production process.

[0128] The method provided in this implementation simulates the real-time production process based on preset production process information and real-time production datasets. It then adjusts the real-time production process according to several optimizable factors, analyzes the adjusted production process, and determines several production data points corresponding to the adjusted production process as the adjustment results. This improves the accuracy of the adjustment results, avoids irreversible consequences from directly adjusting the actual production process, and provides intuitive data basis for subsequent adjustments to the actual production process.

[0129] In some embodiments, based on the real-time production dataset and adjustment results, the data of each production data point within the real-time production data and adjustment results is recorded at each time point within the analysis duration after being separated by a preset separation duration, forming a dynamic dataset; based on the dynamic dataset, visualized dynamic production data is determined and output for professionals to view.

[0130] A dynamic dataset can be a collection of real-time production data and production data within the adjustment results that change over a production time series.

[0131] Visualized dynamic production data can be obtained by visualizing dynamic production data, which can be directly analyzed interactively by relevant personnel.

[0132] Professionals can be those responsible for adjusting organic chemical production processes.

[0133] Specifically, dynamic datasets are dynamically visualized using data visualization libraries such as D3.js (Data-Driven Documents) to produce visualized dynamic production data. This visualized dynamic production data is then output through human-computer interaction devices, such as high-definition touch screens, for professionals to perform interactive analysis.

[0134] The method provided in this embodiment analyzes real-time production datasets and adjustment results to determine dynamic datasets. Through data visualization technology, the dynamic datasets are visualized to determine visualized dynamic production data. This visualized dynamic production data is then provided to professionals for analysis, enabling them to understand changes in production process data and providing them with intuitive and comprehensive data for improving organic chemical production processes.

Claims

1. A cloud computing-based MES intelligent production control system, characterized in that, The method comprises: acquiring a real-time production data set of an organic chemical product, analyzing the real-time production data set, and determining a production bottleneck link; based on the production bottleneck link, analyzing the real-time production data set, and determining a plurality of optimization factors; according to the plurality of optimization factors, simulating the production process of the organic chemical product to determine an adjustment result; according to the adjustment result, adjusting the real-time production data set to determine a bottleneck optimization data set; according to the bottleneck optimization data set, controlling the production equipment to make corresponding adjustments.

2. The system of claim 1, wherein, The analysis of the real-time production data set and the determination of the production bottleneck link comprises: according to a preset total analysis time length and a preset separation time length, performing time smoothing processing on each real-time production data in the real-time production data set to determine low fluctuation smoothing data corresponding to each real-time production data under a preset analysis time length; based on the low fluctuation smoothing data, determining a fluctuation index of each real-time production data under the preset total analysis time length according to the real-time production data set; according to the fluctuation index of each real-time production data, determining a relationship fluctuation index between each real-time production data and other real-time production data; analyzing the relationship fluctuation index of each real-time production data to determine the production bottleneck link.

3. The system of claim 2, wherein, The time smoothing processing is performed on each real-time production data in the real-time production data set according to the preset total analysis time length and the preset separation time length, and low fluctuation smoothing data corresponding to each real-time production data under the preset analysis time length is determined, and the following formula is referred to: wherein t is a preset total analysis time length, LD i,t is the low fluctuation smoothing data of the i-th real-time production data in the real-time production data set under the preset analysis time length t, N is a preset separation time length, X i,k is the specific data corresponding to the i-th real-time production data at the time node k.

4. The system of claim 3, wherein, The fluctuation index of each real-time production data under the preset total analysis time length is determined according to the real-time production data set based on the low-fluctuation smooth data, referring to the following formula: Wherein, t is a preset total analysis time length, σ i,t is the fluctuation index of the i th real-time production data under the preset total analysis time length t, N is a preset separation time length, X i,j is the specific value corresponding to the i th real-time production data at the time node j, LD i,t is the low fluctuation smoothing data of the i th real-time production data under the preset analysis time length t.

5. The system of claim 4, wherein, The relationship fluctuation index of each real-time production data is determined according to the fluctuation index of each real-time production data, and the following formula is referred to: wherein σ′ i,t is the relationship fluctuation index of the i-th real-time production data under the preset total analysis duration t, σ i,t is the fluctuation index of the i-th real-time production data under the preset total analysis duration t, C ij is a preset data relationship matrix, σ j,t is the fluctuation index of the j-th real-time production data under the preset total analysis duration t.

6. The system of claim 5, wherein, The analysis of the relationship fluctuation index of each real-time production data and the determination of the production bottleneck link comprise: According to the preset relationship fluctuation threshold, a position set of a plurality of abnormal relationship fluctuation indexes in the real-time production data set is determined according to the following formula: Wherein, S is the position set, I' i,t is an index variable, σ' i,t is the relationship fluctuation index of the ith real-time production data under the preset total analysis time t, and T is the preset relationship fluctuation threshold. according to the position set, analyzing the real-time production data set to determine a plurality of abnormal production data; determining the production bottleneck link according to the plurality of abnormal production data.

7. The system of claim 6, wherein, The analysis of the real-time production data set based on the production bottleneck link and the determination of the plurality of optimization factors comprise: according to the production bottleneck link, analyzing the real-time production data set to determine a plurality of bottleneck production data related to the production bottleneck link; analyzing the plurality of bottleneck production data to determine the sensitivity of each bottleneck production data to the plurality of abnormal production data; according to the sensitivity of each bottleneck production data to the plurality of abnormal production data and a preset sensitivity threshold, determining the plurality of optimization factors.

8. The system of claim 7, wherein, The analysis of the several bottleneck production data determines the sensitivity of each bottleneck production data to the several abnormal production data, referring to the following formula: wherein Y j is the sensitivity, β0is a preset intercept term, ∈ is a preset disturbance term, β a is the current bottleneck production data, X j is the jth abnormal production data, F j is a preset relationship index between the jth abnormal production data and the current bottleneck production data, and n is the total number of the abnormal production data.

9. The system of claim 2, wherein, The simulation of the production process of the organic chemical product according to the plurality of optimization factors and the determination of the adjustment result comprise: according to the preset production process information and the real-time production data set, simulating a real-time production process; according to the plurality of optimization factors, adjusting the real-time production process to simulate an adjusted production process; analyzing the adjusted production process to determine a plurality of production data in the adjusted production process as the adjustment result.

10. The system of claim 9, wherein, The system further comprises: according to the real-time production data set and the adjustment result, recording the data of each production data at each time node under the analysis time length after being separated by the preset separation time length, to form a dynamic data set; according to the dynamic data set, determining and outputting visual dynamic production data for professionals to view.

Images