Production bottleneck link determination method

Abstract

The invention is a divisional application, and the application number of the original application is 2024110006582. The invention relates to the technical field of production control, in particular to a production bottleneck link determination method. The method comprises the steps of obtaining a real-time production data set of the organic chemical product, performing time smoothing processing on each piece of real-time production data in the real-time production data set according to a preset total analysis duration and a preset separation duration, and determining corresponding low-fluctuation smoothing data of each piece of real-time production data under the preset analysis duration; based on the low-fluctuation smooth data, determining a fluctuation index of each piece of real-time production data under the preset total analysis duration according to the real-time production data set; determining a relation fluctuation index between each piece of real-time production data and other real-time production data according to the fluctuation index of each piece of real-time production data; and analyzing the relation fluctuation index of each piece of real-time production data, and determining a production bottleneck link. And the accuracy of production bottleneck links can be improved.

Description

[0001] This application is a divisional application. The application date of the original application is July 24, 2024, the application number is 2024110006582, and the name of the invention is: A MES intelligent production control system based on cloud computing. Technical Field

[0002] The present application relates to the field of production control technology, and in particular to a method for determining a production bottleneck link. Background Art

[0003] 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, and help enterprises achieve the goals of lean production and information-based intelligent manufacturing.

[0004] When the existing MES system manages and monitors the production process of organic chemical products, due to the complexity of the production process of organic chemical products and the frequent dynamic changes of products during the production process, the existing MES system is unable to flexibly respond to the many variables in the production process of organic chemical products, resulting in uneven quality of organic chemical products and even safety accidents. Summary of the Invention

[0005] In order to overcome the above-mentioned deficiencies of the prior art, the present application provides a method for determining a production bottleneck link to improve the accuracy of the production bottleneck link.

[0006] The present application provides a method for determining a production bottleneck link, the method comprising:

[0007] Obtain a real-time production data set of an organic chemical product, perform time smoothing processing on each real-time production data in the real-time production data set according to a preset total analysis time and a preset separation time, and determine a low-volatility smoothed data corresponding to each real-time production data under the preset analysis time;

[0008] Based on the low-volatility smoothed data and the real-time production data set, determining a volatility index for each real-time production data within the preset total analysis time;

[0009] According to the fluctuation index of each real-time production data, determining the relationship fluctuation index between each real-time production data and other real-time production data;

[0010] The relationship fluctuation index of each real-time production data is analyzed to determine the production bottleneck link.

[0011] Through the above technical solution, each real-time production data is time-smoothed according to the preset total analysis time and the preset analysis time to obtain low-volatility smoothed data that is easier to parse and process. On the basis of the low-volatility smoothed data, a relationship 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 relationship fluctuation index, the production bottleneck link is determined. While improving the efficiency of the mathematical analysis process, the relationship fluctuation index can more comprehensively reflect the fluctuation of the real-time production data and improve the accuracy of the production bottleneck link. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0013] Figure 1 A schematic diagram of an application scenario provided in one embodiment of the present application;

[0014] Figure 2 A flowchart of a cloud computing-based MES intelligent production control system provided in one embodiment of the present application. DETAILED DESCRIPTION

[0015] To make the purpose, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0016] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0017] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0018] When the existing MES system manages and monitors the production process of organic chemical products, due to the complexity of the production process of organic chemical products and the frequent dynamic changes of products during the production process, the existing MES system is unable to flexibly respond to the many variables in the production process of organic chemical products, resulting in uneven quality of organic chemical products and even safety accidents.

[0019] Based on this, the present application provides a cloud computing-based MES intelligent production control system, which analyzes the real-time production data set in the production process of organic chemical products, determines the production bottleneck link that causes uneven quality of organic chemical products, and determines several optimizable factors in the production bottleneck link by analyzing the real-time production data set. On the basis of several optimizable factors, the adjustment results are determined by simulating the production process of organic chemical products, and the real-time production data set is adjusted according to the adjustment results to obtain a bottleneck optimization data set. According to the bottleneck optimization data set, the production equipment is controlled to make corresponding adjustments, so as to flexibly respond to the many variables in the organic chemical production process, make timely and accurate adjustments to the production equipment, ensure the quality of organic chemical products, and reduce the probability of safety accidents.

[0020] Figure 1 This 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 production equipment to make corresponding adjustments.

[0021] Specifically, the system provided in the present application is installed on any server, which communicates with the production equipment, obtains the real-time production data set provided by the production equipment through the equipment, analyzes the real-time production data set, determines the production bottleneck link that causes the uneven quality of organic chemical products, and determines several optimizable factors in the production bottleneck link by analyzing the real-time production data set. Based on the several optimizable factors, the adjustment results are determined by simulating the production process of organic chemical products, and the real-time production data set is adjusted according to the adjustment results to obtain a bottleneck optimization data set. According to the bottleneck optimization data set, the production equipment is controlled to make corresponding adjustments, so as to flexibly respond to the many variables in the organic chemical production process, make timely and accurate adjustments to the production equipment, ensure the quality of organic chemical products, and reduce the probability of safety accidents.

[0022] For specific implementation methods, please refer to the following embodiments.

[0023] Figure 2 This 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. Figure 2 As shown, the system includes:

[0024] S201. Obtain a real-time production data set of an organic chemical product, analyze the real-time production data set, and determine a production bottleneck.

[0025] Organic chemical products can be chemical products based on organic compounds and produced through chemical reactions and processing.

[0026] Real-time production data can be a series of real-time parameters of the chemical reaction stage of the current organic chemical product production process, such as temperature, reaction pressure and pH value. Real-time production data can be obtained through various sensors arranged in the organic chemical product production line.

[0027] The production bottleneck link can be the link in the current production process of organic chemical products that has a negative impact on the final quality of organic chemical products.

[0028] Specifically, since 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, when the reaction conditions are abnormal, the quality of organic chemical products often fails in batches. Moreover, since organic chemical products are continuously in multi-stage chemical reactions in the production time series, when batches of products fail to meet the standards, it is difficult to locate and adjust the problematic links in a timely manner, resulting in uneven quality of organic chemical products and inability to ensure a high yield rate.

[0029] Real-time production data from the production process of organic chemical products is analyzed through mathematical analysis to quantify the changing status of each production data in the same production time series, thereby locating abnormal bottleneck links and providing basic data for subsequent adjustments to the production process.

[0030] S202. Based on the production bottleneck, analyze the real-time production data set and determine several factors that can be optimized.

[0031] The optimizable factors may be the corresponding production data that needs to be adjusted in the bottleneck link.

[0032] Specifically, since each production link involves a series of production data, and a production link is often identified as a production bottleneck link due to anomalies caused by the mutual influence of multiple production data, after determining the production bottleneck link, based on the production bottleneck link, mathematical analysis methods are used to quantify the impact of production data in the real-time production data set on the production bottleneck link, so as to determine several corresponding optimizable factors in the production bottleneck link, providing a basis for subsequent adjustments to organic chemical products.

[0033] S203. Based on several optimizable factors, simulate the production process of organic chemical products and determine the adjustment results.

[0034] The adjustment result may be the adjustment values corresponding to the several optimizable factors obtained by optimizing the several optimizable factors and simulating the production process of the organic chemical product.

[0035] Specifically, since organic chemical products are very sensitive to reaction conditions during the production process, it is difficult to ensure real-time production results if the factors that can be optimized are directly adjusted after the factors can be determined. Therefore, based on the factors that can be optimized, the production process of organic chemical products is simulated using process flow simulation software, such as Aspen Plus (Advanced System for Process Engineering), to determine the values that need to be adjusted for the factors that can be optimized, so as to provide accurate data for subsequent adjustments to the actual production process of organic chemical products.

[0036] S204: Adjust the real-time production data set according to the adjustment result and determine the bottleneck optimization data set.

[0037] The bottleneck optimization dataset may be a set containing all adjusted and unadjusted production data after the real-time production dataset is adjusted according to the adjustment result.

[0038] Specifically, according to the adjustment values corresponding to several optimizable factors in the adjustment results, the production data in the real-time production data set is adjusted to obtain a bottleneck optimization data set containing all adjusted and unadjusted production data, providing a data basis for subsequent accurate adjustment of the control entity production equipment.

[0039] S205. Optimize the data set according to the bottleneck and control the production equipment to make corresponding adjustments.

[0040] Production equipment can be a series of physical equipment on a production line for producing organic chemical products.

[0041] Specifically, after determining the bottleneck optimization data set, the cloud computing platform communicates with the physical equipment, and remotely controls the production equipment based on the bottleneck optimization data set, so that the production equipment can make corresponding adjustments in real time to ensure the product qualification rate.

[0042] Through the method provided in this embodiment, a real-time production dataset from the organic chemical product production process is analyzed to identify production bottlenecks that contribute to uneven quality of organic chemical products. Furthermore, through analysis of the real-time production dataset, several optimizable factors in the production bottlenecks are identified. Based on these optimizable factors, an adjustment result is determined through simulation of the organic chemical product production process. Based on the adjustment result, the real-time production dataset is adjusted to obtain a bottleneck-optimized dataset. Based on the bottleneck-optimized dataset, production equipment is controlled to make corresponding adjustments. This allows for flexible response to the numerous variables in the organic chemical production process, timely and precise adjustments to production equipment, guaranteed quality of organic chemical products, and reduced probability of safety accidents.

[0043] In some embodiments, time smoothing is performed on each real-time production data in the real-time production data set according to a preset total analysis time and a preset separation time, and low-volatility smoothed data corresponding to each real-time production data under the preset analysis time is determined; based on the low-volatility smoothed data, the volatility index of each real-time production data under the preset total analysis time is determined according to the real-time production data set; based on the volatility index of each real-time production data, the relationship volatility index between each real-time production data and other real-time production data is determined; and the relationship volatility index of each real-time production data is analyzed to determine the production bottleneck link.

[0044] The preset total analysis time may be a preset analysis time for real-time production data, and the preset total analysis time may be set according to actual production conditions.

[0045] The preset separation time may be obtained by dividing the preset total analysis time to determine the time information of different time nodes.

[0046] Low-volatility smoothed data can be data that can clearly reflect the changing trend of real-time production data.

[0047] The volatility index may be data reflecting the severity of fluctuations in real-time production data.

[0048] The relationship 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.

[0049] Specifically, since the directly acquired production data set contains a large number of different types of production data, these production data are affected differently, and the measurement standards of the fluctuation amplitude are also very different, making it difficult to perform a unified mathematical analysis. The preset analysis time is divided into several time nodes through a preset separation time, and the production data corresponding to each time node in the real-time production data set is time-smoothed to obtain low-volatility smoothed data. While retaining the fluctuation characteristics of the production data, the noise in the production data is eliminated, and the sensitivity of subsequent mathematical analysis to noise is reduced. While reflecting the changing trend of the real-time production data, the low-volatility smoothed data is easier to parse and process, which helps to improve the efficiency of subsequent mathematical analysis.

[0050] After obtaining the low-volatility smoothed data, mathematical analysis is used to use the quantitatively derived volatility index to reflect the volatility of the current real-time volatility data on the time axis corresponding to the preset analysis time. At the same time, since different production data are not independent of each other, different production data will affect each other in the production process of organic chemical products. The fluctuation of a real-time production data needs to consider the impact of other real-time production data on it on the basis of the volatility index. Through mathematical analysis, on the basis of the volatility index, the quantitatively derived relationship volatility index is used to reflect the actual fluctuation of the current real-time production data under the influence of different real-time production data, and by analyzing the abnormal fluctuations in the relationship volatility index, the corresponding production bottleneck link is determined.

[0051] Through the method of this embodiment, time smoothing is performed on each real-time production data according to the preset total analysis time and the preset analysis time to obtain low-volatility smoothed data that is easier to parse and process. On the basis of the low-volatility smoothed data, a relationship 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 relationship fluctuation index, the production bottleneck link is determined. While improving the efficiency of the mathematical analysis process, the relationship fluctuation index can more comprehensively reflect the fluctuation of the real-time production data, thereby improving the accuracy of the production bottleneck link.

[0052] In some embodiments, time smoothing is performed on each real-time production data set according to a preset total analysis time and a preset separation time, and low-fluctuation smoothed data corresponding to each real-time production data set under the preset analysis time is determined, referring to formula (1):

[0053]

[0054] Among them, t is the preset total analysis time, LD i,t is the low-volatility smoothed data of the i-th real-time production data in the real-time production data set under the preset analysis time t, N is the preset separation time, X i,kis the specific data corresponding to the i-th real-time production data at time node k.

[0055] Specifically, the real-time production data values at nearly N time nodes are uniformly smoothed using formula (1) to obtain a low-fluctuation smoothed value for each real-time production data under a preset total analysis time, thereby reducing the instability of the real-time production data.

[0056] Through the method provided in this embodiment, mathematical analysis methods are used. On the basis of a preset total analysis time and a preset separation time, a mathematical formula is designed to perform uniform time smoothing processing on each piece of real-time production data, and the low-volatility smoothed data corresponding to each real-time production data under the preset analysis time is obtained, thereby reducing the instability of the real-time production data, reducing the sensitivity of the corresponding mathematical formula to noise when performing subsequent mathematical analysis on the low-volatility smoothed data, and improving the accuracy of the volatility index obtained subsequently.

[0057] In some embodiments, based on the low-volatility smoothed data and the real-time production data set, a volatility index of each real-time production data in the preset total analysis time is determined, referring to formula (2):

[0058]

[0059] Among them, t is the preset total analysis time, σ i,t is the fluctuation index of the ith real-time production data under the preset total analysis time t, N is the preset separation time, X i,j is the specific value corresponding to the i-th real-time production data at time node j, LD i,t It is the low-fluctuation smoothed data of the i-th real-time production data in the preset analysis time t.

[0060] Specifically, by using X in formula (2) i,j -LD i,t The difference between the specific data of each real-time production data and the corresponding low-volatility smoothed data is quantified, and the degree of volatility of each real-time production data is reflected through the standard deviation between the specific data of each real-time production data and the corresponding low-volatility smoothed data, and a volatility index is obtained, so that the volatility index can comprehensively and intuitively reflect the changes of the real-time production data on the time axis corresponding to the entire preset analysis time.

[0061] Through the method provided in this embodiment, mathematical analysis methods are used to design a mathematical formula to quantify the degree of fluctuation of each real-time production data on the basis of low-volatility smoothed data, and a fluctuation index is obtained. The fluctuation index can comprehensively and intuitively reflect the changes in the real-time production data on the time axis corresponding to the entire preset analysis time, so as to improve the accuracy and comprehensiveness of the fluctuation index.

[0062] In some embodiments, the relationship fluctuation index of each real-time production data is determined based on the fluctuation index of each real-time production data, referring to formula (3):

[0063]

[0064] Among them, σ′ i,t is the relationship fluctuation index of the i-th real-time production data under the preset total analysis time t, σ i,t is the volatility index of the ith real-time production data under the preset total analysis time t, C ij is 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, σ j,t is the fluctuation index of the jth real-time production data under the preset total analysis time t, and M is the number of real-time production data in the real-time production data.

[0065] The preset relationship data matrix may be a preset symmetric matrix for storing 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 may be obtained by analyzing historical data.

[0066] 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 through formula (3). The weighted sum of the volatility of the current real-time production data is calculated, and the relationship volatility index is obtained by adding the weighted sum of the volatility and the volatility index, and comprehensively considering the impact of other real-time production data on the current real-time production data.

[0067] Through the method provided in this embodiment, on the basis of each real-time production data fluctuation index, a mathematical formula is designed through mathematical analysis means, and the influence of other real-time production data on the current real-time production data is integrated to quantify the relationship fluctuation index, so that the relationship fluctuation index can more comprehensively reflect the fluctuation of the real-time production data, thereby making the subsequent production bottleneck link derived based on the relationship fluctuation index more accurate.

[0068] In some embodiments, according to a preset relationship fluctuation threshold, referring to formula (4), a set of positions of several abnormal relationship fluctuation indices in the real-time production data set is determined:

[0069]

[0070] Among them, S is the location set, I′ i,t is the indicator variable, σ′ i,tis the relationship fluctuation index of the i-th real-time production data under the preset total analysis time t, and T is the preset relationship fluctuation threshold; based on the location set, the real-time production data set is analyzed to determine several abnormal production data; based on these several abnormal production data, the production bottleneck link is determined.

[0071] The preset relationship fluctuation threshold may be preset threshold data for determining whether the relationship fluctuation index is abnormal. The preset relationship fluctuation threshold may be obtained by analyzing historical data.

[0072] The abnormal relationship fluctuation index may be abnormal data that is greater than a preset relationship fluctuation threshold among several current relationship fluctuation indexes.

[0073] The position set may be a set of position subscripts of real-time production data corresponding to a number of abnormal relationship fluctuation indices in the real-time production data set.

[0074] Specifically, through formula (4) Judge whether the relationship fluctuation index is abnormal, assign values to the indicator variables, and then use i|I′ i,t =1 to screen the indicator variables, extract the position subscripts of the real-time production data corresponding to the abnormal relationship fluctuation index, and integrate several position subscripts to obtain a position set. The corresponding real-time production data in the real-time production data set are located through the position set to obtain several abnormal production data. Based on the several abnormal production data and the production process of organic chemical products, several production links corresponding to the several abnormal production data are determined, and the production links with the highest priority in the execution order in several production environments are determined as production bottleneck links.

[0075] Through the method provided in this embodiment, mathematical analysis methods are used, and on the basis of a preset abnormal relationship fluctuation index, a mathematical formula is designed to determine whether the relationship fluctuation index has an abnormality. By assigning and screening indicator variables, 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 production bottleneck link is located through several abnormal production data corresponding to the position set, making the production bottleneck link location process faster and more accurate.

[0076] In some embodiments, based on the production bottleneck link, the real-time production data set is analyzed to determine several bottleneck production data related to the production bottleneck link; 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.

[0077] The bottleneck production data may be a number of real-time production data that are highly relevant to the production bottleneck.

[0078] Sensitivity may be data used to indicate the extent to which current bottleneck production data is affected by a number of abnormal production data.

[0079] The preset sensitivity threshold may be threshold data used to determine whether adjusting the current bottleneck production data will produce a significant effect on a number of abnormal production data. The preset sensitivity threshold may be obtained by analyzing historical data.

[0080] Specifically, in the production process of organic chemical products, there is a series of real-time production data that are highly correlated with it in a link. These real-time production data have an impact on each other, but it is not possible to directly adjust all of these real-time production data. 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, according to the production bottleneck link, based on the production process of organic chemical products, the real-time production data set is analyzed, and several bottleneck production data corresponding to the production bottleneck link are determined. Through mathematical analysis, the several 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 the preset sensitivity threshold, it means that the adjustment of these bottleneck production data can effectively affect the several abnormal production data, and these bottleneck production data are determined as several optimizable factors.

[0081] Through the method provided in this embodiment, based on the production bottleneck link, a number of bottleneck production data are analyzed, a number of bottleneck production data are determined, and by analyzing the number of bottleneck production data, the sensitivity of each bottleneck production data to a number of abnormal production data is determined. According to the sensitivity and the preset sensitivity threshold, a number of optimizable factors are determined. By introducing sensitivity, a number of bottleneck production data are screened, and a number of bottleneck production data with the highest necessity for optimization are determined, and used as a number of optimizable factors, thereby improving the subsequent adjustment efficiency of the production process and helping to accurately control the adjustment results of the subsequent production process.

[0082] In some embodiments, a plurality of bottleneck production data are analyzed to determine the sensitivity of each bottleneck production data to a plurality of abnormal production data, referring to formula (5):

[0083]

[0084] Among them, Y is the sensitivity, β0 is the preset intercept term, ∈ is the preset disturbance term, β a Producing data for the current bottleneck, X j is the jth abnormal production data, F j is the preset relationship index between the jth abnormal production data and the current bottleneck production data, and n is the total number of abnormal production data.

[0085] The preset intercept term may be a constant term used to represent a sensitivity reference value, and the preset intercept term may be obtained by analyzing historical data.

[0086] The preset disturbance term may be a constant term used to represent an average calculation error of the sensitivity, and the preset disturbance term may be obtained by analyzing historical data.

[0087] The preset relationship index may be data used to express the degree to which bottleneck production data is affected by corresponding abnormal production data. The preset relationship index may be obtained by analyzing historical data.

[0088] Specifically, based on several bottleneck production data, the sensitivity is regressed and analyzed by 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 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 the disturbance term, and finally the sensitivity of each bottleneck production data to several abnormal production data is obtained.

[0089] Through the method provided in this embodiment, mathematical analysis methods are used. On the basis of a number of bottleneck production data, a mathematical formula is designed to perform regression analysis on the sensitivity of each bottleneck production data to the said several abnormal production data. The preset relationship index is used to reflect the closeness of the relationship between the current bottleneck production data and the current abnormal production data, and the sensitivity error is reduced by the disturbance term. Finally, the sensitivity of each bottleneck production data to the several abnormal production data is obtained, thereby improving the accuracy and comprehensiveness of the sensitivity.

[0090] In some embodiments, a real-time production process is simulated based on preset production process information and a real-time production data set; the real-time production process is adjusted based on a number of optimizable factors, and the adjusted production process is simulated; the adjusted production process is analyzed, and a number of production data in the adjusted production process are determined as adjustment results.

[0091] The preset production process flow information may be the production process flow of current organic chemical products, and the preset production process flow information may be provided by professional staff.

[0092] The real-time production process may be a virtual real-time production process simulated based on the real-time production data set.

[0093] The adjusted production process may be a virtual production process obtained by adjusting the real-time production process according to a number of optimizable factors.

[0094] Specifically, through process simulation software, such as Aspen Plus, the real-time production process is simulated according to the preset production process information and the real-time production data set to obtain a virtual process of the real-time production process. Based on a number of optimizable factors, the virtual process of the real-time production process is adjusted through the process simulation software to simulate the adjusted production process, and a series of production data in the adjusted production process is extracted. The above series of production data are determined as the adjustment results, providing accurate data basis for the subsequent adjustment of the actual production process.

[0095] Through the method provided by this implementation, the real-time production process is simulated according to the preset production process information and the real-time production data set, and the real-time production process is adjusted according to a number of optimizable factors. The adjusted production process is analyzed, and a number of production data corresponding to the adjusted production process are determined as the adjustment results, thereby improving the accuracy of the adjustment results, avoiding irreversible consequences caused by direct adjustments to the actual production process, and providing an intuitive data basis for subsequent adjustments to the actual production process.

[0096] In some embodiments, based on the real-time production data set and the adjustment results, the data of each production data in the real-time production data and the adjustment results at each time node in the analysis time after being separated by a preset separation time are recorded to form a dynamic data set; based on the dynamic data set, the visual dynamic production data is determined and output for professional personnel to view.

[0097] 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.

[0098] The visualized dynamic production data can be data obtained after visual processing of the dynamic production data, which can be used by relevant personnel for direct interactive analysis.

[0099] Professionals may be persons responsible for adjusting organic chemical production processes.

[0100] Specifically, dynamic data sets are dynamically visualized through data visualization processing libraries, such as D3.js (Data-Driven Documents), to obtain visualized dynamic production data. The visualized dynamic production data is then output through human-computer interaction devices, such as high-definition touch screens, for interactive analysis by professionals.

[0101] Through the method provided in this embodiment, real-time production data sets and adjustment results are analyzed to determine a dynamic data set. The dynamic data set is then visualized through data visualization technology to determine visualized dynamic production data. The visualized dynamic production data is then provided for analysis by professionals, enabling them to understand changes in production process data and providing intuitive and comprehensive data for professionals to improve organic chemical production processes.

Claims

1. A method for determining a production bottleneck, characterized in that: include: Obtain a real-time production data set of an organic chemical product, perform time smoothing processing on each real-time production data in the real-time production data set according to a preset total analysis time and a preset separation time, and determine a low-volatility smoothed data corresponding to each real-time production data under the preset analysis time; Based on the low-volatility smoothed data and the real-time production data set, determining a volatility index for each real-time production data within the preset total analysis time; According to the fluctuation index of each real-time production data, determining the relationship fluctuation index between each real-time production data and other real-time production data; The relationship fluctuation index of each real-time production data is analyzed to determine the production bottleneck link.

2. The method according to claim 1, characterized in that According to the preset total analysis time and the preset separation time, time smoothing processing is performed on each real-time production data in the real-time production data set to determine the low-fluctuation smoothed data corresponding to each real-time production data under the preset analysis time, referring to the following formula: Among them, t is the preset total analysis time, LD i,t is the low-volatility smoothed data of the ith real-time production data in the real-time production data set under the preset analysis time t, N is the preset separation time, X i,k is the specific data corresponding to the i-th real-time production data at time node k.

3. The method according to claim 2, characterized in that Based on the low-volatility smoothed data and the real-time production data set, a volatility index of each real-time production data within the preset total analysis time is determined, referring to the following formula: Among them, t is the preset total analysis time, σ i,t is the fluctuation index of the ith real-time production data under the preset total analysis time t, N is the preset separation time, X i,j is the specific value corresponding to the i-th real-time production data at time node j, LD i,t It is the low-fluctuation smoothed data of the i-th real-time production data in the preset analysis time t.

4. The method according to claim 3, characterized in that The relationship fluctuation index of each real-time production data is determined based on the fluctuation index of each real-time production data, referring to the following formula: Among them, σ′ i,t is the relationship fluctuation index of the i-th real-time production data under the preset total analysis time t, σ i,t is the fluctuation index of the ith real-time production data under the preset total analysis time t, C ij is the preset data relationship matrix, σ j,t It is the fluctuation index of the j-th real-time production data in the preset total analysis time t.

5. The method according to claim 4, characterized in that The analyzing the relationship fluctuation index of each real-time production number to determine the production bottleneck includes: According to the preset relationship fluctuation threshold, refer to the following formula to determine the location set of several abnormal relationship fluctuation indexes in the real-time production data set: Where S is the position set, I′ i,t is the indicator variable, σ′ i,t is the relationship fluctuation index of the i-th real-time production data under the preset total analysis time t, and T is the preset relationship fluctuation threshold; Analyzing the real-time production data set according to the location set to determine a number of abnormal production data; The production bottleneck link is determined based on the plurality of abnormal production data.

Images