An intelligent automation control system and method for petrochemical production

Abstract

The present invention proposes an intelligent automatic control system and method for petrochemical production, wherein the system includes a data acquisition module, a data analysis module, a control module and a monitoring and early warning module, and the method includes collecting petrochemical production related data through the data acquisition module; classifying the data, and performing correlation analysis on the production data, product quality data and waste content in the petrochemical production process to obtain analysis results and comprehensive parameters; adjusting and controlling the production parameters through the control module; monitoring the production process in real time through the monitoring and early warning module, and early warning and diagnosis of possible faults, and taking timely measures; through this method and system, the dual goals of waste control and product quality control are achieved by controlling parameters, the amount of waste generated in the production process is reduced, the environmental protection pressure and cost burden of the enterprise are reduced, and the production efficiency and product quality are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of petrochemical product production, and in particular to an intelligent automatic control system and method for petrochemical production. Background Art

[0002] In the petrochemical production process, the generation of waste is inevitable. Changes in waste content directly affect the quality and output of petrochemical products. In traditional automated control systems, these changes cannot be accurately sensed, and effective measures cannot be taken to adjust them. Therefore, how to achieve real-time monitoring and refined control of waste content has become an urgent problem to be solved in the current petrochemical production process. Summary of the invention

[0003] The present invention provides an intelligent automatic control system and method for petrochemical production, which are used to achieve controllability of the production process and product quality, reduce the amount of waste generated, and achieve environmental protection and emission reduction.

[0004] The present invention proposes an intelligent automatic control system for petrochemical production, the system comprising:

[0005] Data acquisition module: collects parameters in the petrochemical production process in real time and records them in the database;

[0006] Data analysis module: analyzes and processes the collected data to derive corresponding control strategies; the analysis includes correlation analysis between waste content and production data and product quality data; and adjusts the production data according to the correlation analysis;

[0007] Control module: converts control strategies into control instructions, controls production equipment through controllers, and realizes automated control;

[0008] Monitoring and early warning module: monitor the production process in real time, warn and diagnose possible faults, and take timely measures.

[0009] Furthermore, in a petrochemical production intelligent automation control system, the data acquisition module comprises:

[0010] Production data acquisition module: collects production data through sensors, and the production data includes equipment status, temperature, pressure and flow;

[0011] Product quality data collection module: collects and stores product quality data; the quality data includes product composition, purity and physical state.

[0012] Waste data collection module: collects the content of waste through a collector, and the waste includes wastewater, waste gas and solid waste.

[0013] Furthermore, in a petrochemical production intelligent automation control system, the data analysis module includes:

[0014] Data preprocessing module: cleans, de-duplicates, removes outliers and missing data for each parameter data;

[0015] Classification module: classify data according to product type, raw materials and production stage to obtain classification results;

[0016] Production data analysis module: According to the classification results, various data in the petrochemical production process are analyzed to obtain dynamic changes and abnormal conditions in the production process;

[0017] Product quality analysis module: collects, monitors and analyzes product quality parameters according to the classification results to obtain real-time data and trend changes of product quality;

[0018] Waste content analysis module: performs real-time analysis and monitoring of waste content according to classification results, including trend analysis and statistical analysis;

[0019] Correlation analysis module: performs correlation analysis on waste content, production data and product quality data to obtain correlation results.

[0020] Furthermore, in a petrochemical production intelligent automation control system, the correlation analysis module includes:

[0021] Data selection module: selects historical data and real-time data of corresponding types in the database for analysis according to the classification results;

[0022] First analysis module: Under the same classification result, the waste content is correlated with the corresponding production parameters to obtain the correlation coefficient R between the production parameters and the waste content. ij ;

[0023] The first judgment module: If the correlation coefficient |R ij |≥ the first threshold, the production parameter is determined to be an associated parameter;

[0024] The second analysis module: performs correlation analysis between the associated parameters to obtain a second correlation coefficient r between the associated parameters;

[0025] The second judgment module: if the second correlation coefficient |r|≥ the second threshold value; orthogonalizing the corresponding two correlation parameters to obtain the processed correlation parameters;

[0026] Modeling module: Model the processed correlation parameters through analysis software; obtain comprehensive parameters and the third correlation coefficient Rz between comprehensive parameters and waste;

[0027] Comprehensive parameter monitoring module: Add comprehensive parameters as new parameters to the monitoring system; and predict and control the waste content based on the values ​​of comprehensive parameters and production parameters;

[0028] The third correlation module: performs correlation analysis on the waste content and product quality data; adjusts the waste content threshold according to the product quality data;

[0029] Threshold adjustment module: adjusts comprehensive parameters and corresponding production parameters according to the waste content threshold;

[0030] The third determination module: if the correlation parameters obtained for different waste contents are the same; then calculate the impact factor Yi of the waste content related to this correlation parameter,

[0031] Among them, |R ij | represents the absolute value of the correlation coefficient between waste i and production parameter j; w k is the weight of waste; α and β are coefficients, and their value ranges are (0, 1) respectively;

[0032] This associated parameter is adjusted using the waste threshold corresponding to the highest Yi value as a reference standard.

[0033] Furthermore, in a petrochemical production intelligent automation control system, the third association module includes:

[0034] Establish a multiple regression model for the relationship between indicators related to waste content and product quality;

[0035] L=c+d1Z1+d2Z2+...+dnZn;

[0036] Wherein, L represents the waste content, Z1, Z2, ..., Zn represent indicators related to product quality, c, d1, d2, ..., dn represent constants and coefficients;

[0037] According to the model, the waste content data and product quality related indicators are fitted using the fitting formula to obtain constants and coefficients;

[0038] Different data sets under the same category are modeled to obtain different models, and the number of modeling times f ≥ 3;

[0039] Substituting product quality indicators into different models to calculate the waste content L yv ;

[0040] Calculate the mean value L of waste content corresponding to the same product quality index under different models y ;

[0041] Let the preset waste threshold be Lyy ; The standard deviation of all waste contents is σ;

[0042] If L y >L yy ; and L y -L yy ≥σ / 2; then the waste content threshold is adjusted to L yy +σ / 2;

[0043] If L y <L yy ; and L yy -L y ≥σ / 2; then the waste content threshold is adjusted to L y +σ / 2;

[0044] If |L y -L yy |<σ / 2; the preset waste threshold remains unchanged.

[0045] Furthermore, a petrochemical production intelligent automation control system, the control module includes:

[0046] Actuator drive module: responsible for converting control instructions into control signals and controlling production equipment through actuators;

[0047] Control instruction management module: responsible for managing all control instructions and ensuring the accuracy and stability of the generation, management, storage, sending and execution of control instructions.

[0048] Furthermore, in a petrochemical production intelligent automation control system, the monitoring and early warning module includes:

[0049] Real-time monitoring module: real-time monitoring of petrochemical production process parameters through a visual interface;

[0050] Early warning and prediction module: The historical data and real-time data collected by the data collection module are passed through the data analysis module to provide early warning and prediction of possible abnormal situations;

[0051] Fault diagnosis and maintenance module: Through real-time monitoring and diagnosis of abnormal situations in the production process, faults in production can be discovered and resolved in a timely manner;

[0052] Alarm management module: alarm for abnormal situations that may occur during the production process.

[0053] The present invention provides a petrochemical production intelligent automation control method, the method comprising:

[0054] S1. Collect production data, product quality data and waste content in the petrochemical production process through the data acquisition module;

[0055] S2. Classify the data collected by the data collection module according to product type, raw material and production stage to obtain classification results;

[0056] S3. Select the classified data and perform correlation analysis on the production data, product quality data and waste content in the petrochemical production process through the data analysis module to obtain analysis results and comprehensive parameters;

[0057] S4. Using the analysis results to adjust and control production parameters through a control module; including: adjusting waste threshold settings according to product quality data, adjusting production parameters and comprehensive parameters according to the waste thresholds; predicting and controlling waste content according to production parameters and comprehensive parameters;

[0058] S5. Use the monitoring and early warning module to monitor the production process in real time, warn and diagnose possible faults, and take timely measures.

[0059] Further, a petrochemical production intelligent automation control method, said S3 comprises:

[0060] 6. A petrochemical production intelligent automation control method, characterized in that S3 comprises:

[0061] S301, selecting historical data and real-time data of corresponding types in the database for analysis according to the classification results;

[0062] S302. Under the same classification result, the waste content is correlated with the corresponding production parameters to obtain the correlation coefficient R between the production parameters and the waste content. ij ;

[0063] S303, if the correlation coefficient | R ij |≥ the first threshold, the production parameter is determined to be an associated parameter;

[0064] S304, performing correlation analysis between the associated parameters to obtain a second correlation coefficient r between the associated parameters;

[0065] S305, if the second correlation coefficient |r|≥ the second threshold value, orthogonalizing the corresponding two correlation parameters to obtain processed correlation parameters;

[0066] S306, modeling the processed correlation parameters through analysis software; obtaining comprehensive parameters and the third correlation coefficient Rz between the comprehensive parameters and the waste;

[0067] Among them, |Rz|>|Rij |; The comprehensive parameter is Y=a1+a2b1+a3b2+…+a n b n-1 , where a1, a2…a n are coefficients; b1, b2…b n-1 is the processed correlation parameter; the correlation coefficient is obtained by the analysis software;

[0068] S307, adding the comprehensive parameter as a new parameter to the monitoring system; and predicting and controlling the waste content according to the values ​​of the comprehensive parameter and the production parameter;

[0069] S308, performing correlation analysis on the waste content and product quality data; adjusting different waste content thresholds according to different product quality data;

[0070] S309. Adjust the comprehensive parameters and corresponding production parameters according to the waste content threshold;

[0071] S310, if the correlation parameters obtained for different waste contents are the same; then calculate the impact factor Yi of the waste content related to the correlation parameter,

[0072] Among them, |R ij | represents the absolute value of the correlation coefficient between waste i and production parameter j; w k is the weight of waste; α and β are coefficients, and their value ranges are (0, 1) respectively;

[0073] This associated parameter is adjusted using the waste threshold corresponding to the highest Yi value as a reference standard.

[0074] Furthermore, a petrochemical production intelligent automation control method, wherein the waste content and product quality data are subjected to correlation analysis; different waste content thresholds are adjusted according to different product quality data; including:

[0075] Establish a multiple regression model for the relationship between indicators related to waste content and product quality;

[0076] L=c+d1Z1+d2Z2+...+dnZn;

[0077] Wherein, L represents the waste content, Z1, Z2, ..., Zn represent indicators related to product quality, c, d1, d2, ..., dn represent constants and coefficients;

[0078] According to the model, the waste content data and product quality related indicators are fitted using the fitting formula to obtain constants and coefficients;

[0079] Different data sets under the same category are modeled to obtain different models, and the number of modeling times f ≥ 3;

[0080] Substituting product quality indicators into different models to calculate the waste content L yv ;

[0081] Calculate the mean value L of waste content corresponding to the same product quality index under different models y ;

[0082] Let the preset waste threshold be L yy ; The standard deviation of all waste contents is σ;

[0083] If L y >L yy ; and L y -L yy ≥σ / 2; then the waste content threshold is adjusted to L yy +σ / 2;

[0084] If L y <L yy ; and L yy -L y ≥σ / 2; then the waste content threshold is adjusted to L y +σ / 2;

[0085] If |L y -L yy |<σ / 2; the preset waste threshold remains unchanged.

[0086] The beneficial effects of the present invention are as follows: through the intelligent automatic control system and method for petrochemical production of the present invention, the dual goals of waste control and product quality control are achieved, and the efficiency and quality of the production process are improved; through data collection and analysis, the data in the production process are monitored and analyzed in real time, and the controllability of the production process is improved; through real-time monitoring and control of the waste content, the amount of waste generated is reduced, and the goals of resource conservation and environmental protection are achieved while achieving the target output; through real-time monitoring and early warning, the faults that may occur in the production process can be quickly diagnosed and processed, and the reliability and safety of the production process are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] Figure 1 This is a schematic diagram of an intelligent and automated control system for petrochemical production according to the present invention;

[0088] Figure 2 This is a schematic diagram of the associated modules of an intelligent and automated control system for petrochemical production according to the present invention;

[0089] Figure 3This is a schematic diagram of an intelligent and automated control method for petrochemical production according to the present invention. DETAILED DESCRIPTION

[0090] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0091] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. The embodiments described are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0092] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0093] This embodiment provides an intelligent automatic control system for petrochemical production, characterized in that the system includes:

[0094] Data acquisition module: collects various data in real time to gain detailed understanding of the production process; in addition to conventional parameters such as raw materials, products, temperature and pressure, many other parameters can be collected to achieve more refined production process control and more accurate fault diagnosis.

[0095] Specifically, the data acquisition module includes:

[0096] Production data acquisition module: collects production data through sensors, and the production data includes:

[0097] Liquid level: used to monitor the height or depth of liquids in order to control the flow and mixing of liquids;

[0098] Flow: Monitor the flow rate of liquid or gas in order to control and regulate the flow rate and velocity;

[0099] Motion: Detect the operating status and speed of motion equipment (such as pumps, valves, rotating machinery, etc.) in order to diagnose motion equipment failures and optimize motion efficiency;

[0100] Product quality data collection module: collects and stores product quality data; the quality data includes but is not limited to product composition, purity and physical state;

[0101] Waste data collection module: collects the content of waste through a collector, the waste includes wastewater, waste gas and solid waste; the collector includes a pH meter, a turbidity meter, a redox potentiometer, an ion selective electrode, a COD detector, etc.;

[0102] The frequency of data collection is:

[0103] Where ΔT is the network delay, T e is the network delay threshold; d is the bandwidth utilization; G i-1 is the i-1th sampling data set; G i-2 The i-2th sampling data group; where G i-1 , G i-2 For multiple data sampled simultaneously, such as temperature, humidity, and flow rate, select the value with the largest rate of change;

[0104] Maintenance data collection module: collects data on equipment care, maintenance and repair to help production managers plan regular and preventive maintenance.

[0105] Data analysis module: analyzes and processes the collected data to derive corresponding control strategies; the analysis includes correlation analysis between waste content and production data and product quality data; and adjusts the production data according to the correlation analysis;

[0106] Control module: converts control strategies into control instructions, controls production equipment through controllers, and realizes automated control;

[0107] Monitoring and early warning module: monitor the production process in real time, warn and diagnose possible faults, and take timely measures.

[0108] The working principle of the above technical solution is: by collecting, analyzing and processing various real-time data and waste content in the petrochemical production process, the corresponding analysis results are obtained, and then the control module is used to adjust the waste threshold setting according to the product quality data, and the production parameters are adjusted according to the waste threshold setting, so as to control the entire production process and realize automation and intelligent control. In addition, the production process is monitored in real time through the monitoring and early warning module, possible faults are warned and diagnosed, and timely measures are taken to improve production efficiency and product quality, reduce production costs and environmental pollution, etc.

[0109] The effects of the above technical solutions are: through the collection, analysis and processing of real-time data, the production process can be optimized and adjusted to improve production efficiency and output; by analyzing correlation data, adjusting waste thresholds and production parameters, etc., the production quality of products can be controlled to ensure the stability and consistency of product quality. Through automated control and real-time monitoring, labor costs, equipment downtime, production waste losses, etc. can be reduced, thereby reducing production costs; by adjusting waste thresholds, waste emissions in the production process can be controlled, thereby reducing the negative impact of environmental pollution.

[0110] This embodiment provides an intelligent automation control system for petrochemical production, wherein the data analysis module includes:

[0111] Data preprocessing module: cleans, de-duplicates, removes outliers and missing data for each parameter data;

[0112] Classification module: Classify data according to product type, raw material and production stage to obtain classification results; usually classified according to factors such as material code, product grade, production batch and time in the production process. The specific classification method can be determined according to production needs and management requirements; for example, in the production process, data can be classified according to variety, raw material, production stage, etc. according to the classification of raw materials, different stages of the production process, and different processing procedures; raw material classification methods include the following:

[0113] Chemical property classification: Raw materials are classified into different categories according to their chemical properties (such as pH, redox properties, etc.) so that they can be processed and treated.

[0114] Physical property classification: Raw materials are classified into different categories based on their physical characteristics (such as density, melting point, boiling point, etc.) so that they can be processed and handled.

[0115] Content classification: Raw materials are classified into different categories according to their content in order to rationally utilize and control their quality.

[0116] Origin classification: Raw materials are classified into different categories according to their sources for the purpose of management and quality control.

[0117] Raw material classification is very important in petrochemical production, because different raw materials may produce different wastes and pollutants during the production process. Therefore, classifying each raw material can better grasp and manage the wastes and pollutants in the production process, and improve the economic benefits and environmental sustainability of production.

[0118] The production stages include pre-processing stage, separation stage, transformation stage, processing stage and post-processing stage;

[0119] Production data analysis module: According to the classification results, various data in the petrochemical production process are analyzed to obtain dynamic changes and abnormal conditions in the production process; the various data include temperature, pressure, and flow; for example, by conducting multi-dimensional statistical analysis of key indicators in the production process, anomalies and changes can be identified, and decision support based on fault warning and maintenance can be provided; specific analysis methods may include data mining, model building, intelligent diagnosis and other methods to achieve real-time monitoring, prediction and control of the petrochemical production process;

[0120] Product quality analysis module: collects, monitors and analyzes product quality parameters according to the classification results to obtain real-time data and trend changes of product quality;

[0121] Waste content analysis module: Real-time analysis and monitoring of waste content according to classification results, including trend analysis and statistical analysis; statistically analyze the mean, standard deviation and coefficient of variation for different wastes under each classification result of historical data;

[0122] By analyzing the trend of waste content, we can understand the law of waste generation and whether it is within the controllable range. If the trend of waste content is unstable, it is necessary to adjust the production process in time to maintain stable output; for different types of waste, waste content data can be collected in real time and analyzed using statistical methods, such as mean value, standard deviation, coefficient of variation, etc.

[0123] Correlation analysis module: performs correlation analysis on waste content, production data and product quality to obtain correlation results.

[0124] The working principle and effect of the above technical solution are as follows: the data analysis module of the petrochemical production intelligent automation control system, based on big data analysis technology, can pre-process and analyze various data in the petrochemical production process, obtain data from various aspects of the production process, and classify the data according to the classification results, so as to better understand and grasp the situation of the production process; the data pre-processing module can clean, de-duplicate, remove outliers and missing data for various parameter data, and transmit the cleaned data to the classification module; the classification module classifies the data according to factors such as material code, product grade, production batch and time in the production process for subsequent analysis and management. The classified data can be transmitted to the production data analysis module, product quality analysis module and waste content analysis module;

[0125] The production data analysis module can monitor and analyze the production process in real time based on the classified data, so as to find problems and make improvements in time. For example, during the production process, the operating status of the production equipment and the maintenance information of the equipment can be analyzed to ensure the stability and reliability of the equipment operation. By monitoring and analyzing parameters such as temperature, pressure, flow, content, and usage during the production process, the real-time changes in production parameters can be obtained, and trend analysis and anomaly detection can be performed to find and solve problems in time.

[0126] The product quality analysis module can collect, monitor and analyze product quality parameters to understand product quality and grasp its trend changes. For example, it can monitor and analyze product content, purity, density, color and other parameters in real time, and perform trend analysis, anomaly detection and fault diagnosis to improve product quality.

[0127] The waste content analysis module can analyze and monitor the waste content in real time, so as to find and solve pollution problems in time. It can also analyze the trend and statistics of waste content, so as to understand the pollution source and take corresponding treatment measures.

[0128] The correlation analysis module can perform correlation analysis on waste content, production data and product quality to obtain correlation results in order to understand the pollution sources and their impact on production.

[0129] In short, the data analysis module of the intelligent automation control system for petrochemical production can effectively monitor, analyze and control various data and parameters in the production process, thereby improving product quality, reducing pollution, and achieving efficient, high-quality and stable production of the enterprise.

[0130] This embodiment is a petrochemical production intelligent automation control system, the correlation analysis module includes:

[0131] Data selection module: select the corresponding types of historical data in the database for analysis according to the classification results; select the analysis category. Under the selected category, the historical data can be the latest week or month. The purpose is to obtain sufficient data under this category that can reflect the current production;

[0132] First analysis module: Under the same classification result, the waste content is correlated with the corresponding production parameters to obtain the correlation coefficient R between the production parameters and the waste content. ij; Among them, the continuous parameter uses the Pearson correlation coefficient, and the discrete data uses the Spearman correlation coefficient; the content of each waste corresponds to each production parameter; the correlation between different wastes and different parameters is obtained respectively; for example, if there are two types of waste and two production parameters, two correlation coefficients are obtained for each type of waste; the following obtains different comprehensive parameters for each type of waste content;

[0133] The first judgment module: If the correlation coefficient |R ij |≥ the first threshold, the production parameter is determined to be an associated parameter;

[0134] The second analysis module: performs correlation analysis between the associated parameters to obtain a second correlation coefficient r between the associated parameters;

[0135] The second judgment module: if the second correlation coefficient |r|≥ the second threshold value; orthogonalizing the corresponding two correlation parameters to obtain the processed correlation parameters;

[0136] Modeling module: Model the processed correlation parameters through analysis software; obtain comprehensive parameters and the third correlation coefficient Rz between comprehensive parameters and waste;

[0137] Among them, |Rz|>|R ij |; The comprehensive parameter is Y=a1+a2b1+a3b2+…+a n b n-1 , where a1, a2…a n are coefficients; b1, b2…b n-1 is the processed correlation parameter; the correlation coefficient is obtained by the analysis software;

[0138] Comprehensive parameter monitoring module: Add comprehensive parameters as new parameters to the monitoring system; and predict and control the waste content based on the values ​​of comprehensive parameters and production parameters;

[0139] The third correlation module: performs correlation analysis on the waste content and product quality data; adjusts different waste content thresholds according to different product quality data;

[0140] Threshold adjustment module: adjusts comprehensive parameters and corresponding production parameters according to the waste content threshold;

[0141] The third determination module: if the correlation parameters obtained for different waste contents are the same; then calculate the impact factor Yi of the waste content related to this correlation parameter,

[0142] Among them, |R ij | represents the absolute value of the correlation coefficient between waste i and production parameter j; w kis the weight of the waste; α and β are coefficients, and their value ranges are (0, 1) respectively; the weight of the waste is rated according to the type of waste and the difficulty of treatment, and the weight is allocated according to the level; the number of levels is m, w1>w2>…>w m ; Preferably α=0.4, β=0.6;

[0143] This associated parameter is adjusted using the waste threshold corresponding to the highest Yi value as a reference standard.

[0144] The working principle of the above technical solution is as follows: the intelligent automatic control system for petrochemical production adopts a correlation analysis module, which analyzes the correlation between production parameters and waste content, builds a correlation model between comprehensive parameters and waste content, and realizes the prediction and control of waste content;

[0145] The specific implementation steps are as follows:

[0146] (1) Data selection module: selects historical data of corresponding types from the database for analysis according to the classification results;

[0147] (2) First analysis module: Under the same classification result, the waste content is respectively correlated with the corresponding production parameters to obtain the correlation coefficient between the production parameters and the waste content. Among them, the Pearson correlation coefficient is used for continuous parameters, and the Spearman correlation coefficient is used for discrete data. For each waste content, different comprehensive parameters can be obtained to obtain the correlation between different wastes and different parameters. If the absolute value of the correlation coefficient is greater than or equal to the first threshold, the production parameter is judged to be a correlation parameter;

[0148] (3) Second analysis module: performing correlation analysis between the associated parameters to obtain a second correlation coefficient r between the associated parameters. If the absolute value of the second correlation coefficient is greater than or equal to the second threshold, orthogonalizing the corresponding two associated parameters to obtain the processed associated parameters;

[0149] (4) Modeling module: The processed correlation parameters are modeled through analysis software to obtain comprehensive parameters and the correlation Rz between comprehensive parameters and waste;

[0150] (5) Comprehensive parameter monitoring module: the comprehensive parameters are added as new parameters to the monitoring system, and the waste content is predicted based on the values ​​of the associated parameters;

[0151] (6) The third correlation module: performs correlation analysis between the waste content and product quality data, and adjusts different waste content thresholds according to different product quality data;

[0152] (7) Threshold adjustment module: adjusts comprehensive parameters and corresponding production parameters according to the waste content threshold;

[0153] (8) The third determination module: If the correlation parameters obtained for different waste contents are the same, the waste influence factor Yi is calculated.

[0154] Among them, |R ij | represents the absolute value of the correlation coefficient between waste i and production parameter j; w k is the weight of the waste; α and β are coefficients, and their value ranges are (0, 1) respectively; the weight of the waste is rated according to the type of waste and the difficulty of treatment, and the weight is allocated according to the level; the number of levels is m, w1>w2>…>w m ; Preferably α=0.4, β=0.6;

[0155] This associated parameter is adjusted using the waste threshold corresponding to the highest Yi value as a reference standard.

[0156] The effect of the above technical solution is: by realizing the real-time prediction and control of waste content, the production efficiency is improved, the risk of environmental pollution is reduced, and the threshold of waste content can be automatically adjusted according to different product quality requirements, further optimizing the production process. At the same time, the system adopts a variety of correlation analysis methods, which can process different types of data, and select reasonable parameter factors for different types of correlation analysis results and eliminate the mutual influence between various parameter factors to perform multivariate regression modeling, thereby improving the accuracy of the model. After modeling, a comprehensive parameter is obtained, and the comprehensive parameter is added to the control system to improve the precision and accuracy of monitoring; at the same time, according to the comprehensive parameter and the model of waste and the threshold of waste, the comprehensive parameter and each production factor are adjusted, and the threshold of waste is adjusted according to the quality of the product. Under the premise of ensuring product quality, the content of waste is reduced to achieve the purpose of energy conservation and emission reduction. If the correlation parameters obtained for different waste contents are the same, the impact factor of waste is calculated; wherein, the calculation of the impact factor Yi includes two parts: waste weight and the absolute value of the correlation coefficient between waste and production parameters. The waste weight evaluates the difficulty of various wastes in treatment, thereby determining the degree of influence of various wastes on the production process; the absolute value of the correlation coefficient between wastes and production parameters characterizes the degree of association between various wastes and production parameters. The larger the correlation coefficient, the closer the relationship between the two, and the greater the impact on the production process. Finally, the adjustment direction and intensity of each production parameter are determined by targeting the influencing factors Yi of different wastes. This reduces the amount of waste generated in the production process, reduces the environmental pressure and cost burden of the enterprise, and at the same time improves production efficiency and product quality.

[0157] This embodiment is a petrochemical production intelligent automation control system, the third association module includes:

[0158] Establish a multiple regression model for the relationship between indicators related to waste content and product quality;

[0159] L=c+d1Z1+d2Z2+...+dnZn;

[0160] Wherein, L represents the waste content, Z1, Z2, ..., Zn represent indicators related to product quality, c, d1, d2, ..., dn represent constants and coefficients;

[0161] According to the model, the waste content data and product quality related indicators are fitted using the fitting formula to obtain constants and coefficients;

[0162] Different data sets under the same category are modeled to obtain different models, and the number of modeling times is 5≥f≥3; where different data sets are under the same category, such as the data of the most recent month, and the weekly data are modeled to obtain four models;

[0163] Substituting product quality indicators into different models to calculate the waste content L yv ;

[0164] Calculate the mean value L of waste content corresponding to the same product quality index under different models y ;

[0165] Let the preset waste threshold be L yy ; The standard deviation of all waste contents is σ;

[0166] If L y >L yy ; and L y -L yy ≥σ / 2; then the waste content threshold is adjusted to L yy +σ / 2; this means that the current waste content threshold is too low and needs to be increased to better control the waste content;

[0167] If L y <L yy ; and L yy -L y ≥σ / 2; then the waste content threshold is adjusted to L y +σ / 2; then the waste content threshold is adjusted to L y +σ / 2; this means that the current waste content threshold is high and can be moderately reduced to improve product quality.

[0168] If |L y -Lyy |<σ / 2; the preset waste threshold remains unchanged.

[0169] The working principle and effect of the above technical solution are as follows: by establishing a multiple regression model between waste content and product quality, the waste content is predicted and controlled according to the fitting formula, so as to achieve the purpose of reducing waste generation, improving product quality and optimizing the production process. By establishing a multiple regression model L=c+d1Z1+d2Z2+...+dnZn, the waste content is used as the dependent variable, and the product quality-related indicators are used as the independent variables, and the constants and coefficients of the model are obtained by fitting historical data. This model can reflect the degree of influence of different product quality indicators on the amount of waste generation, and then can predict and control the waste in actual production; according to the fitting formula, the corresponding waste content under a specific product quality indicator can be calculated; by establishing multiple models according to the data set, calculating the mean and considering the standard deviation, the appropriate adjustment of the waste content threshold can be more accurately judged. This can improve the control effect of waste and ensure that the product quality meets the expected standards. And according to different situations, corresponding adjustments can be made to better control waste gas emissions and reduce environmental pollution; by adjusting the product quality indicator threshold, the emission of various wastes can be further adjusted to achieve the purpose of environmental protection emission reduction and improving product quality.

[0170] This embodiment provides an intelligent automation control system for petrochemical production, wherein the control module comprises:

[0171] Actuator drive module: responsible for converting control instructions into control signals and controlling production equipment through actuators;

[0172] Control instruction management module: responsible for managing all control instructions and ensuring the accuracy and stability of the generation, management, storage, sending and execution of control instructions.

[0173] The monitoring and early warning module includes:

[0174] Real-time monitoring module: real-time monitoring of petrochemical production process parameters through a visual interface;

[0175] Early warning and prediction module: The historical data and real-time data collected by the data collection module are passed through the data analysis module to provide early warning and prediction of possible abnormal situations;

[0176] Fault diagnosis and maintenance module: Through real-time monitoring and diagnosis of abnormal situations in the production process, faults in production can be discovered and resolved in a timely manner;

[0177] Alarm management module: alarm for abnormal situations that may occur during the production process.

[0178] The working principle and effect of the above technical solution are as follows: the control module is mainly responsible for generating, managing, storing, sending and executing control instructions according to the real-time changing production situation, and controlling the equipment to perform production operations; the monitoring and early warning module ensures the efficiency, safety and stability of the production process through sub-modules such as real-time monitoring, early warning and prediction, fault diagnosis and maintenance.

[0179] Specifically, the actuator drive module controls the equipment by converting control instructions into control signals, thereby realizing the automation of production operations; the control instruction management module ensures the accuracy and stability of the entire control instruction generation, management, storage, sending and execution process, thereby ensuring the smooth progress of the production process.

[0180] The real-time monitoring module provides a visual interface to monitor the parameters of the petrochemical production process in real time, including important physical parameters such as temperature, pressure, and flow, so as to obtain key data in the production process in real time and monitor abnormal conditions in the production process. The early warning and prediction module predicts and warns of possible abnormal conditions through the collection, statistical analysis, and modeling of historical data and real-time data, so as to adjust the production plan in time during the production process and prevent and avoid possible production accidents.

[0181] The fault diagnosis and maintenance module monitors and diagnoses abnormal situations in the production process in real time, discovers and solves faults in production in a timely manner, and avoids accidents. The alarm management module alarms abnormal situations that may occur in the production process, notifies management personnel in a timely manner to handle them, and ensures safety in the production process.

[0182] The effect of this petrochemical production intelligent automation control system is that, through integrated design, it realizes automation, intelligence and visualization of the production process, improves production efficiency and product quality, while also improving production safety and stability, reducing production costs and environmental pollution, thereby achieving the goals of lean production and sustainable development.

[0183] This embodiment provides a petrochemical production intelligent automation control method, the method comprising:

[0184] S1. Collect production data, product quality data and waste content in the petrochemical production process through the data acquisition module;

[0185] The data collection frequency is:

[0186] Where ΔT is the network delay, T e is the network delay threshold; d is the bandwidth utilization; G i-1 is the i-1th sampling data set; G i-2 The i-2th sampling data group; where G i-1, G i-2 For multiple data sampled simultaneously, such as temperature, humidity, and flow rate, select the value with the largest rate of change;

[0187] S2. Classify the data collected by the data collection module according to product type, raw material and production stage to obtain classification results; usually, the classification is based on factors such as material code, product grade, production batch and time in the production process. The specific classification method can be determined according to production needs and management requirements; for example, in the production process, the data can be classified according to variety, raw material, production stage, etc. according to the classification of raw materials, different stages of the production process, and different processing procedures;

[0188] S3. Select the classified data and perform correlation analysis on the production data, product quality data and waste content in the petrochemical production process through the data analysis module to obtain analysis results and comprehensive parameters;

[0189] S4. Using the analysis results to adjust and control production parameters through a control module; including: adjusting waste threshold settings according to product quality data, adjusting production parameters and comprehensive parameters according to the waste thresholds; predicting and controlling waste content according to production parameters and comprehensive parameters;

[0190] S5. Use the monitoring and early warning module to monitor the production process in real time, warn and diagnose possible faults, and take timely measures.

[0191] The working principle of the above technical solution is: various data in the petrochemical production process are collected in real time through the data acquisition module, including real-time data, product quality data and waste content, and the data analysis module is used to perform correlation analysis to obtain analysis results; according to the analysis results, the control module is used to adjust the waste threshold setting, and according to the adjusted waste threshold setting, the production parameters are adjusted to achieve the goals of product quality and waste control; at the same time, the method performs real-time monitoring through the monitoring and early warning module, warns and diagnoses possible faults, and takes timely measures to adjust and control.

[0192] The effects of the above technical solution are: achieving the dual goals of waste control and product quality control, and improving the efficiency and quality of the production process; through data collection and analysis, real-time monitoring and analysis of data in the production process, improving the controllability of the production process; through real-time monitoring and control of waste content, reducing the amount of waste generated, achieving resource conservation and environmental protection goals while achieving target output; through real-time monitoring and early warning, it is possible to quickly diagnose and handle possible faults in the production process, improving the reliability and safety of the production process.

[0193] This embodiment provides a petrochemical production intelligent automation control method, wherein S3 includes:

[0194] S301, selecting historical data and real-time data of corresponding types in the database for analysis according to the classification results;

[0195] S302. Under the same classification result, the waste content is correlated with the corresponding production parameters to obtain the correlation coefficient R between the production parameters and the waste content. ij ;

[0196] S303, if the correlation coefficient | R ij |≥ the first threshold, the production parameter is determined to be an associated parameter;

[0197] S304, performing correlation analysis between the associated parameters to obtain a second correlation coefficient r between the associated parameters;

[0198] S305, if the second correlation coefficient |r|≥ the second threshold value, orthogonalizing the corresponding two correlation parameters to obtain processed correlation parameters;

[0199] S306, modeling the processed correlation parameters through analysis software; obtaining comprehensive parameters and the third correlation coefficient Rz between the comprehensive parameters and the waste;

[0200] Among them, |Rz|>|R ij |; The comprehensive parameter is Y=a1+a2b1+a3b2+…+a n b n-1 , where a1, a2…a n are coefficients; b1, b2…b n-1 is the processed correlation parameter; the correlation coefficient is obtained by the analysis software;

[0201] S307, adding the comprehensive parameter as a new parameter to the monitoring system; and predicting and controlling the waste content according to the values ​​of the comprehensive parameter and the production parameter;

[0202] S308, performing correlation analysis on the waste content and product quality data; adjusting different waste content thresholds according to different product quality data;

[0203] S309. Adjust the comprehensive parameters and corresponding production parameters according to the waste content threshold;

[0204] S310, if the correlation parameters obtained for different waste contents are the same; then calculate the impact factor Yi of the waste content related to the correlation parameter,

[0205] Among them, |R ij| represents the absolute value of the correlation coefficient between waste i and production parameter j; w k is the weight of waste; α and β are coefficients, and their value ranges are (0, 1) respectively;

[0206] This associated parameter is adjusted using the waste threshold corresponding to the highest Yi value as a reference standard.

[0207] The working principle of the above technical solution is: by analyzing historical data and real-time data to establish the correlation between production parameters and waste content, and then using correlation coefficients, orthogonal processing and modeling techniques to extract comprehensive parameters and add them to the monitoring system to predict and control waste content. At the same time, the method also considers the correlation analysis of waste content and product quality data, adjusts the waste content threshold according to different product quality data, and further optimizes the control effect.

[0208] The effect of the above technical solution is: by comprehensively analyzing the correlation between different production parameters, a comprehensive parameter that can predict and control the waste content is established, and the waste content threshold is adjusted according to the product quality data, so that the control system can more accurately predict and adjust the waste content. In addition, by calculating the waste impact factor, the associated parameters can be adjusted to further optimize the effect of waste treatment. Through this method, the level of intelligence of petrochemical production can be improved, the emission of waste can be reduced, the product quality can be improved, and the consumption of resources and energy can be saved.

[0209] This embodiment provides an intelligent and automated control method for petrochemical production, wherein the waste content and product quality data are subjected to correlation analysis; different waste content thresholds are adjusted according to different product quality data; and the method includes:

[0210] Establish a multiple regression model for the relationship between indicators related to waste content and product quality;

[0211] L=c+d1Z1+d2Z2+...+dnZn;

[0212] Wherein, L represents the waste content, Z1, Z2, ..., Zn represent indicators related to product quality, c, d1, d2, ..., dn represent constants and coefficients;

[0213] According to the model, the waste content data and product quality related indicators are fitted using the fitting formula to obtain constants and coefficients;

[0214] Different data sets under the same category are modeled to obtain different models, and the number of modeling times is 5 ≥ f ≥ 3;

[0215] Substituting product quality indicators into different models to calculate the waste content L yv ;

[0216] Calculate the mean value L of waste content corresponding to the same product quality index under different models y ;

[0217] Let the preset waste threshold be L yy ; The standard deviation of all waste contents is σ;

[0218] If L y >L yy ; and L y -L yy ≥σ / 2; then the waste content threshold is adjusted to L yy +σ / 2;

[0219] If L y <L yy ; and L yy -L y ≥σ / 2; then the waste content threshold is adjusted to L y +σ / 2;

[0220] If |L y -L yy |<σ / 2; the preset waste threshold remains unchanged.

[0221] The working principle of the above technical solution is: by establishing a relationship model between waste content and product quality, a multivariate regression model is used to describe the correlation between the two. First, a certain amount of waste content and product quality data is collected and correlation analysis is performed. Then, the threshold of waste content is adjusted according to different product quality data to achieve control and adjustment of waste content.

[0222] The effect of the above technical solution is: the effect of this method is to realize the intelligent and automated control of the petrochemical production process, and can timely adjust the threshold of the waste content according to the product quality data to ensure that the quality of the product meets the requirements and control the discharge of waste; the specific effects include: by establishing a relationship model between the waste content and the product quality, the intelligent control and adjustment of the waste content is realized, and the intelligence level of the production process is improved; by adjusting the threshold of the waste content according to different product quality data, the production process can be adjusted in time to ensure the stability and consistency of product quality and reduce the generation of defective products; by adjusting the threshold of the waste content according to the product quality data, the discharge of waste can be effectively controlled, the pollution to the environment can be reduced, and green production can be achieved; through the intelligent and automated control method, the precise control of the production process is achieved, the production efficiency and resource utilization can be improved, and the production cost can be reduced; by establishing multiple models and calculating the mean of the waste content under different models, the waste content corresponding to the predicted product quality can be provided, so as to optimize and adjust in the production process to achieve better quality control and waste management.

[0223] In general, the intelligent and automated control method for petrochemical production establishes a relationship model between waste content and product quality, and adjusts the waste content threshold according to actual product quality data to achieve control and adjustment of waste content, thereby improving product quality stability, reducing waste emissions, improving production efficiency and resource utilization, and achieving the goals of green and sustainable development.

[0224] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent automatic control system for petrochemical production, characterized in that: The system comprises: Data acquisition module: collects parameters in the petrochemical production process in real time and records them in the database; Data analysis module: analyzes and processes the collected data to derive corresponding control strategies; the analysis includes correlation analysis between waste content and production data and product quality data; and adjusts the production data according to the correlation analysis; Control module: converts control strategies into control instructions, controls production equipment through controllers, and realizes automated control; Monitoring and early warning module: monitor the production process in real time, warn and diagnose possible faults, and take timely measures; Wherein, the data analysis module includes: Data preprocessing module: cleans, de-duplicates, removes outliers and missing data for each parameter data; Classification module: classify data according to product type, raw materials and production stage to obtain classification results; Production data analysis module: According to the classification results, various data in the petrochemical production process are analyzed to obtain dynamic changes and abnormal conditions in the production process; Product quality analysis module: collects, monitors and analyzes product quality parameters according to the classification results to obtain real-time data and trend changes of product quality; Waste content analysis module: performs real-time analysis and monitoring of waste content according to classification results, including trend analysis and statistical analysis; Correlation analysis module: performs correlation analysis on waste content, production data and product quality data to obtain correlation results; Wherein, the association analysis module includes: Data selection module: selects historical data and real-time data of corresponding types in the database for analysis according to the classification results; First analysis module: Under the same classification result, the waste content is correlated with the corresponding production parameters to obtain the correlation coefficient R between the production parameters and the waste content. ij ; The first judgment module: If the correlation coefficient |R ij |≥ the first threshold, the production parameter is determined to be an associated parameter; The second analysis module: performs correlation analysis between the associated parameters to obtain a second correlation coefficient r between the associated parameters; The second judgment module: if the second correlation coefficient |r|≥ the second threshold value; orthogonalizing the corresponding two correlation parameters to obtain the processed correlation parameters; Modeling module: Model the processed correlation parameters through analysis software; obtain comprehensive parameters and the third correlation coefficient Rz between comprehensive parameters and waste; Comprehensive parameter monitoring module: Add comprehensive parameters as new parameters to the monitoring system; and predict and control the waste content based on the values ​​of comprehensive parameters and production parameters; The third correlation module: performs correlation analysis on the waste content and product quality data; adjusts the waste content threshold according to the product quality data; Threshold adjustment module: adjusts comprehensive parameters and corresponding production parameters according to the waste content threshold; The third determination module: if the correlation parameters obtained for different waste contents are the same; then calculate the impact factor Yi of the waste content related to this correlation parameter, Among them, |R ij | represents the absolute value of the correlation coefficient between waste i and production parameter j; w k is the weight of the waste; α and β are coefficients, with a range of values ​​of (0, 1), respectively; n is the number of selected waste parameters; This correlation parameter is adjusted using the waste threshold corresponding to the highest value of Yi as a reference standard; Wherein, the third association module includes: Establish a multiple regression model for the relationship between indicators related to waste content and product quality; L=c+d1Z1+d2Z2+...+dnZn; Wherein, L represents the waste content, Z1, Z2, ..., Zn represent indicators related to product quality, c, d1, d2, ..., dn represent constants and coefficients; According to the model, the waste content data and product quality related indicators are fitted using the fitting formula to obtain constants and coefficients; Different data sets under the same category are modeled to obtain different models, and the number of modeling times f ≥ 3; Substitute the product quality index into the different models to calculate the waste content L yv ; Calculate the mean value L of waste content corresponding to the same product quality index under different models y ; Let the preset waste threshold be L yy ; The standard deviation of all waste contents is σ; If L y >L yy ; and L y -L yy ≥σ / 2; then the waste content threshold is adjusted to L yy +σ / 2; If L y <L yy ; and L yy -L y ≥σ / 2; then the waste content threshold is adjusted to L y +σ / 2; If |L y -L yy |<σ / 2; the preset waste threshold remains unchanged.

2. The intelligent automatic control system for petrochemical production according to claim 1 is characterized in that: The data acquisition module comprises: Production data acquisition module: collects production data through sensors, and the production data includes equipment status, temperature, pressure and flow; Product quality data collection module: collects and stores product quality data; the quality data includes product composition, purity and physical state; Waste data collection module: collects the content of waste through a collector, and the waste includes wastewater, waste gas and solid waste.

3. The intelligent automatic control system for petrochemical production according to claim 1 is characterized in that: The control module comprises: Actuator drive module: responsible for converting control instructions into control signals and controlling production equipment through actuators; Control instruction management module: responsible for managing all control instructions and ensuring the accuracy and stability of the generation, management, storage, sending and execution of control instructions.

4. The intelligent automatic control system for petrochemical production according to claim 1 is characterized in that: The monitoring and early warning module includes: Real-time monitoring module: real-time monitoring of petrochemical production process parameters through a visual interface; Early warning and prediction module: The historical data and real-time data collected by the data collection module are passed through the data analysis module to provide early warning and prediction of possible abnormal situations; Fault diagnosis and maintenance module: Through real-time monitoring and diagnosis of abnormal situations in the production process, faults in production can be discovered and resolved in a timely manner.

5. A petrochemical production intelligent automation control method, characterized in that: The method comprises: S1. Collect production data, product quality data and waste content in the petrochemical production process through the data acquisition module; S2. Classify the data collected by the data collection module according to product type, raw material and production stage to obtain classification results; S3. Select the classified data and perform correlation analysis on the production data, product quality data and waste content in the petrochemical production process through the data analysis module to obtain analysis results and comprehensive parameters; S4. Using the analysis results to adjust and control production parameters through a control module; including: adjusting waste threshold settings according to product quality data, adjusting production parameters and comprehensive parameters according to the waste thresholds; predicting and controlling waste content according to production parameters and comprehensive parameters; S5. Monitor the production process in real time through the monitoring and early warning module, and provide early warning and diagnosis of possible faults, and take timely measures; Wherein, the S3 includes: S301, selecting historical data and real-time data of corresponding types in the database for analysis according to the classification results; S302. Under the same classification result, the waste content is correlated with the corresponding production parameters to obtain the correlation coefficient R between the production parameters and the waste content. ij ; S303, if the correlation coefficient | R ij |≥ the first threshold, the production parameter is determined to be an associated parameter; S304, performing correlation analysis between the associated parameters to obtain a second correlation coefficient r between the associated parameters; S305, if the second correlation coefficient |r|≥ the second threshold value, orthogonalizing the corresponding two correlation parameters to obtain processed correlation parameters; S306, modeling the processed correlation parameters through analysis software; obtaining comprehensive parameters and the third correlation coefficient Rz between the comprehensive parameters and the waste; S307, adding the comprehensive parameter as a new parameter to the monitoring system; and predicting and controlling the waste content according to the values ​​of the comprehensive parameter and the production parameter; S308, performing correlation analysis on the waste content and product quality data; adjusting different waste content thresholds according to different product quality data; S309. Adjust the comprehensive parameters and corresponding production parameters according to the waste content threshold; S310, if the correlation parameters obtained for different waste contents are the same; then calculate the impact factor Yi of the waste content related to the correlation parameter, Among them, |R ij | represents the absolute value of the correlation coefficient between waste i and production parameter j; w k is the weight of the waste; α and β are coefficients, with a range of values ​​of (0, 1), respectively; n is the number of selected waste parameters; This correlation parameter is adjusted using the waste threshold corresponding to the highest value of Yi as a reference standard; Wherein, the S308 includes: Establish a multiple regression model for the relationship between indicators related to waste content and product quality; L=c+d1Z1+d2Z2+...+dnZn; Wherein, L represents the waste content, Z1, Z2, ..., Zn represent indicators related to product quality, c, d1, d2, ..., dn represent constants and coefficients; According to the model, the waste content data and product quality related indicators are fitted using the fitting formula to obtain constants and coefficients; Different data sets under the same category are modeled to obtain different models, and the number of modeling times f ≥ 3; Substitute the product quality index into the different models to calculate the waste content L yv ; Calculate the mean value L of waste content corresponding to the same product quality index under different models y ; Let the preset waste threshold be L yy ; The standard deviation of all waste contents is σ; If L y >L yy ; and L y -L yy ≥σ / 2; then the waste content threshold is adjusted to L yy +σ / 2; If L y <L yy ; and L yy -L y ≥σ / 2; then the waste content threshold is adjusted to L y +σ / 2; If |L y -L yy |<σ / 2; the preset waste threshold remains unchanged.

Images