Chemical production control model generation method and system and medium

Abstract

The invention relates to the technical field of automatic control, in particular to a chemical production control model generation method and system and a medium. The method comprises the following steps: obtaining a chemical production process product; carrying out production process original data acquisition on a chemical production process product to obtain chemical production original data; performing data preprocessing on the chemical production original data to obtain standard chemical production data; and carrying out production stage division on the standard chemical production data to obtain chemical production stage data. According to the invention, through a data analysis technology, a mode identification technology and an automatic control technology, production index offset detection is carried out on each stage of chemical product production, and abnormity identification is carried out on the operation condition of chemical production equipment according to the production index offset. Therefore, the precision of chemical production control and the production efficiency of chemical products are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automation control, and particularly to a method, a system and a medium for generating a chemical production control model. Background Art

[0002] In the early stage of the development of chemical production control models, traditional control theories such as PID control were mainly adopted. Specifically, process parameters were measured, compared with set values, and then control variables were adjusted. For example, in some simple chemical production processes, the flow rate of fluids was controlled by adjusting the opening degree of valves to achieve the expected production effect. With the high requirements for the control fineness of chemical production processes, it is necessary to simulate various phenomena in the production process based on physical and chemical principles such as material balance and energy balance to achieve the effect of chemical production control. However, the existing chemical production control technologies fail to measure the production index offset amounts in multiple stages such as synthesis, purification, and drying of chemical product production, and it is difficult to detect abnormal operation conditions of chemical production equipment based on the production index offset amounts, resulting in insufficient accuracy of chemical production control and low production efficiency of chemical products. Summary of the Invention

[0003] Based on this, it is necessary to provide a method, a system and a medium for generating a chemical production control model to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for generating a chemical production control model includes the following steps:

[0005] Step S1: Obtain products in the chemical production process; collect original production data of the chemical production process products to obtain original chemical production data; perform data preprocessing on the original chemical production data to obtain standard chemical production data;

[0006] Step S2: Divide the standard chemical production data into production stage data; determine chemical reaction condition indicators for the chemical production stage data to generate chemical reaction condition indicators; perform production index offset detection on the chemical reaction condition indicators to obtain production index offset data;

[0007] Step S3: Extract production equipment operation parameters from the standard chemical production data to obtain production equipment operation data; map the production equipment operation data according to the production index offset data to generate equipment operation state data; perform equipment abnormal operation detection on the equipment operation state data to obtain equipment abnormal operation data;

[0008] Step S4: Perform production offset optimization control on the products in the chemical production process according to the production index offset data to obtain production offset optimization measures; perform production equipment operation response control on the equipment abnormal operation data to obtain equipment abnormal operation response measures; generate a chemical production control model based on the production offset optimization measures and the equipment abnormal operation response measures.

[0009] The present invention collects the original production data in the chemical production process and performs data preprocessing to obtain standard chemical production data, which can ensure that the data for subsequent analysis and processing has a unified format and quality, providing a reliable data basis for the precise control of chemical production and avoiding production control errors caused by non-standard and inaccurate data. Divide the standard chemical production data into production stages to obtain chemical production stage data, then determine the chemical reaction condition indicators and perform production index offset detection to obtain production index offset data. This process realizes the refined management and monitoring of each stage of chemical production, can timely detect the subtle changes in chemical reaction conditions during the production process, provides a basis for subsequent targeted optimization control, and improves the quality and production efficiency of chemical products. Extract the production equipment operation parameters from the standard chemical production data to obtain production equipment operation data, map and generate equipment operation status data based on the production index offset data, and perform equipment abnormal operation detection to obtain equipment abnormal operation data. This makes the operation status of the production equipment closely related to the production index, can accurately locate the impact of equipment abnormalities on the production index offset, facilitates taking measures in advance to prevent equipment failures, ensures the stable operation of the production equipment, and reduces production interruptions and defective products caused by equipment problems. Perform production offset optimization control on the products in the chemical production process according to the production index offset data to obtain production offset optimization measures. At the same time, perform production equipment operation response control on the equipment abnormal operation data to obtain equipment abnormal operation response measures, and generate a chemical production control model based on the two. This model comprehensively considers the production index and the equipment operation status, realizes the closed-loop control of chemical production, can adjust the process parameters and equipment operation strategies in real time during the production process, makes the chemical production process always in the optimal state, and effectively improves the overall efficiency and safety of chemical production. Therefore, the present invention realizes the detection of the production index offset amount in each stage of chemical product production through data analysis technology, pattern recognition technology and automatic control technology, and identifies the abnormal operation of the chemical production equipment by the production index offset amount, thereby improving the accuracy of chemical production control and the production efficiency of chemical products.

[0010] Preferably, step S2 includes the following steps:

[0011] Step S21: Extract the production stage timestamp from the standardized chemical production data to obtain the production stage timestamp; mark the standardized chemical production data according to the production stage timestamp to generate production stage identification data;

[0012] Step S22: Classify the production stage identification data to obtain the production stage identification category; divide the production stage through the production stage identification category to obtain the chemical production stage data;

[0013] Step S23: Identify the chemical production stage status of the chemical production stage data to obtain the chemical production stage status data; detect the chemical reaction conditions of the chemical products for the chemical production stage status data to generate stage chemical reaction data;

[0014] Step S24: Judge the production stage reaction condition indicators for the stage chemical reaction data to generate chemical reaction condition indicators; determine the production stage chemical reaction index benchmark according to the chemical reaction condition indicators to obtain the stage chemical reaction index benchmark;

[0015] Step S25: Detect the anomalies of the stage chemical reaction indicators for the stage chemical reaction data to obtain the reaction indicator anomaly data; measure the production index offset for the reaction indicator anomaly data according to the stage chemical reaction index benchmark to obtain the production index offset data.

[0016] The present invention extracts the production-phase timestamps from the standardized chemical production data, enabling accurate acquisition of the time nodes of each production phase and providing an accurate time reference for subsequent data processing. Based on the production-phase timestamps, the standardized chemical production data is marked with production phases, and the generated production-phase identification data can clearly distinguish different production phases, enabling the production data to be classified in an orderly manner by phase. The production-phase identification data is classified by phase identification, and the production phases are systematically classified, making the division of production phases more scientific and reasonable. Through the production-phase identification categories, the production process is decomposed into multiple clear phases. The operating states of each production phase are accurately reflected by identifying the states of the chemical production phases of the chemical production-phase data, providing key information for subsequent analysis. The key parameters of the chemical reactions in each phase are covered by detecting the chemical reaction conditions of the chemical products for the chemical production-phase state data. By judging the reaction-condition indicators of the production phases for the phase chemical-reaction data, it is possible to quantitatively evaluate whether the chemical reaction conditions of each production phase meet the expected standards. Based on the chemical reaction-condition indicators, the chemical-reaction-index benchmarks for the production phases are determined, and the obtained chemical-reaction-index benchmarks for the phases are helpful for accurately controlling the quality of chemical reactions in the production process. By detecting anomalies in the chemical-reaction indicators of the phase chemical-reaction data, it is possible to promptly discover anomalies in the chemical-reaction indicators during the production process. By measuring the production-index offset of the reaction-index anomaly data based on the chemical-reaction-index benchmarks for the phases, it is possible to quantitatively analyze the deviation degree between the anomaly indicators and the normal benchmarks, effectively ensuring the stability of chemical production and the quality of products.

[0017] Preferably, step S3 includes the following steps:

[0018] Step S31: Identify the characteristics of the production equipment from the standardized chemical production data to obtain the chemical production equipment; extract the equipment operating parameters of the chemical production equipment to obtain the production equipment operating data;

[0019] Step S32: Determine the production phase in which the production-index offset data is located to obtain the data of the phase where the offset is located; match the phase equipment operating characteristics with the production equipment operating data according to the data of the phase where the offset is located to generate the phase equipment operating data;

[0020] Step S33: Identify the operating mode of the operation from the phase equipment operating data to obtain the operating mode data; map the operating mode data to the equipment operating state to generate the equipment operating state data;

[0021] Step S34: Detect abnormal operation of the equipment from the equipment operating state data to obtain the equipment abnormal operation data.

[0022] The present invention identifies the characteristics of production equipment for standard chemical production data, and can accurately determine various types of equipment participating in production. It extracts the operating parameters of chemical production equipment, covering the key operating indicators of the equipment during the production process, providing detailed data support for subsequent evaluation of the equipment operating status and analysis of the deviation correlation with production indicators. It determines the production stage where the production indicator deviation data is located, clarifying the specific production stage where the production indicator anomaly occurs. According to the data in the deviation stage, it matches the operating characteristics of the equipment in the stage for the production equipment operating data, and the generated stage equipment operating data can accurately focus on the equipment operating conditions corresponding to the abnormal indicators, facilitating in-depth exploration of the internal connection between equipment operation and production indicator deviation. It identifies the operating mode of the equipment for the stage equipment operating data, and can accurately determine the operating mode of the equipment in a specific production stage, such as normal operation, low-load operation, etc. It maps the operating mode data to the equipment operating status, further refining the detailed status information of the equipment operation. It detects the abnormal operation of the equipment for the equipment operating status data, and can timely discover the abnormal operation of the equipment during the production process. These data can be directly associated with the production indicator deviation, providing key evidence for quickly locating the equipment failures or operating problems that cause production indicator anomalies, facilitating timely adoption of targeted maintenance or adjustment measures to ensure the continuity and stability of chemical production.

[0023] Preferably, step S34 includes the following steps:

[0024] Step S341: Classify the equipment in the operating stage for the equipment operating status data to obtain equipment type data; Correspond the equipment type data to the equipment in the chemical production stage to generate stage-corresponding equipment data;

[0025] Step S342: Determine the chemical production process operations for the stage-corresponding equipment data to obtain equipment process operation data; Identify the temperature of the chemical equipment for the equipment process operation data to obtain chemical equipment temperature data;

[0026] Step S343: Locate the abnormal temperature area of the equipment for the chemical equipment temperature data to obtain the abnormal temperature area of the equipment; Detect the parameters of the chemical rotating centrifugal equipment for the equipment operating status data according to the abnormal temperature area of the equipment to generate rotating centrifugal equipment parameters;

[0027] Step S344: Detect the abnormal centrifugal speed of the equipment for the rotating centrifugal equipment parameters to obtain the abnormal speed equipment parts; Identify the abnormal jitter state of the equipment for the abnormal speed equipment parts to generate equipment abnormal jitter data;

[0028] Step S345: Integrate the abnormal temperature area of the equipment and the equipment abnormal jitter data to obtain equipment abnormal operation data.

[0029] The present invention classifies and corresponds to the device operation status data, realizes the accurate identification of the device and the precise matching of the production stage, provides an accurate basis for determining the subsequent targeted device process operations, ensures the adaptation of the device operation to the production stage, and improves the production efficiency and product quality. The device process operation data is determined based on the stage-corresponding device data, and the temperature data of chemical equipment is identified, so that the device operation is closely associated with the temperature parameters, and the device process operation can be adjusted in a timely manner according to the temperature change, ensuring the stability and safety of the chemical production process and avoiding equipment damage and product quality problems caused by abnormal temperature. The abnormal area of the temperature data of chemical equipment is located, and the parameters of the rotating centrifugal equipment are detected accordingly, realizing the precise monitoring of the key parameters of the device, being able to timely detect the abnormal temperature area of the device and the deviation of the parameters of the rotating centrifugal equipment, providing strong support for the preventive maintenance and fault diagnosis of the device, extending the service life of the device, and reducing the production cost. The abnormal centrifugal speed of the rotating centrifugal equipment parameters is detected, and the abnormal jitter state of the device is identified, further refining the dimension of the device abnormal detection. Through the dual monitoring of the speed and the jitter state, the operation status of the device can be grasped more comprehensively and accurately, the equipment failure risk can be warned in advance, and the continuity of the production process can be guaranteed. The abnormal temperature area of the device and the device abnormal jitter data are integrated, realizing the centralized management and comprehensive analysis of the device abnormal information, facilitating the production management personnel to quickly and comprehensively understand the device abnormal situation, taking effective countermeasures in a timely manner, improving the efficiency of handling device abnormalities, and ensuring the stable operation of the chemical production process.

[0030] Preferably, step S4 includes the following steps:

[0031] Step S41: Determine the offset index type of the production index offset data to obtain the offset index type data; perform production offset optimization control on the products in the chemical production process according to the offset index type data to obtain production offset optimization measures;

[0032] Step S42: Perform device temperature abnormal response control on the abnormal temperature area of the device to obtain device temperature abnormal response measures;

[0033] Step S43: Perform device abnormal jitter response control on the device abnormal jitter data to obtain device abnormal jitter response measures;

[0034] Step S44: Perform chemical production control on the chemical production equipment according to the production offset optimization measures and the device abnormal operation response measures to obtain chemical production control data; construct a chemical production control model based on the chemical production control data to obtain a chemical production control pre-model;

[0035] Step S45: Use the production offset optimization measures and the device abnormal operation response measures to train the chemical production control pre-model to obtain a chemical production control training model;

[0036] Step S46: Perform model cross-validation evaluation on the chemical production control training model to obtain chemical production control model evaluation data; adjust the model parameters of the chemical production control training model through the chemical production control model evaluation data to obtain the chemical production control model.

[0037] The present invention determines the deviation index type for the production index deviation data, clarifying the specific types of production index deviations. According to the deviation index type data, optimize the production deviation control for the products in the chemical production process, which can effectively control different types of production index deviations in a targeted manner, thereby reducing the quality fluctuations in the production process and improving the consistency and stability of the products. Perform equipment temperature anomaly response control on the equipment abnormal temperature area, which can timely and accurately handle the temperature anomaly of the equipment, prevent production interruption or product quality decline caused by equipment temperature anomaly, ensure the stable operation of the equipment within an appropriate temperature range, extend the service life of the equipment, and at the same time ensure the continuity of chemical production and the reliability of product quality. Perform equipment abnormal jitter response control on the equipment abnormal jitter data, which can effectively respond to the abnormal jitter situation that occurs during the operation of the equipment. By timely controlling the equipment jitter, reduce the equipment damage and production efficiency reduction caused by jitter, ensure the smooth operation of the equipment, and thus ensure the smooth progress of chemical production, improve production efficiency and product quality. Control the chemical production equipment according to the production deviation optimization measures and equipment abnormal operation response measures, covering the effective control results of the production process and equipment operation. Construct a chemical production control model based on the chemical production control data, and the obtained chemical production control pre-model provides a preliminary framework and basis for the subsequent optimization and application of the model, enabling the model to initially reflect the control logic and laws of the production process and equipment operation. Use the production deviation optimization measures and equipment abnormal operation response measures to train the chemical production control pre-model, and the obtained chemical production control training model enables the model to better adapt to various situations in actual production, improve the accuracy and reliability of the model for the production process and equipment operation control, and enhance the practicality and effectiveness of the model. Perform model cross-validation evaluation on the chemical production control training model, and the obtained chemical production control model evaluation data can comprehensively and objectively evaluate the performance and accuracy of the model. Adjust the model parameters of the chemical production control training model through the chemical production control model evaluation data, and the obtained chemical production control model further optimizes the parameter settings of the model, enabling the model to more accurately reflect the actual control requirements of chemical production, improving the control effect and stability of the model in actual application, and providing a strong guarantee for the efficient and stable operation of chemical production.

[0038] Preferably, step S41 includes the following steps:

[0039] Step S411: Determine the deviation index type for the production index deviation data to obtain deviation index type data, where the deviation index type data includes reaction conversion rate deviation data and product quality deviation data;

[0040] Step S412: Determine the reaction catalyst for the reaction conversion rate deviation data to obtain reaction catalyst data; Detect the dosage of the reaction catalyst data to produce the reaction catalyst dosage;

[0041] Step S413: Measure the conversion rate deviation amount for the reaction conversion rate deviation data to produce the conversion rate deviation amount; Determine the addition amount of the chemical production catalyst for the reaction catalyst dosage according to the conversion rate deviation amount to obtain the production catalyst addition amount;

[0042] Step S414: Control the chemical catalyst dosage for the products in the chemical production process according to the production catalyst addition amount to obtain the chemical catalyst dosage addition data;

[0043] Step S415: Determine the product impurity type for the product quality deviation data to obtain product impurity type data; Measure the content of the impurity type for the product impurity type data to generate the impurity type content; Put the impurity neutralizer for the products in the chemical production process according to the impurity type content to obtain the impurity neutralizer addition data;

[0044] Step S416: Perform chemical production deviation optimization control on the products in the chemical production process with the chemical catalyst dosage addition data and the impurity neutralizer addition data to obtain the production deviation optimization measures.

[0045] The present invention determines the types of offset indicators for production indicator offset data, clarifying the specific classifications of production indicator offsets. This provides a clear direction for subsequent in-depth analysis and optimized control of different types of offset indicators, making the optimization measures more targeted and effective. For the reaction conversion rate offset data, the reaction catalyst is determined, clarifying the key catalyst factors affecting the reaction conversion rate. Detecting the dosage of the reaction catalyst data helps to accurately control the use of the catalyst, thereby optimizing the reaction conversion rate, improving production efficiency and product quality. Measuring the conversion rate offset amount for the reaction conversion rate offset data quantifies the offset degree of the reaction conversion rate. Determining the addition amount of the chemical production catalyst based on the conversion rate offset amount can accurately adjust the addition amount of the catalyst according to the actual offset situation, bringing the reaction conversion rate back to the normal range and reducing the problems of unstable product quality and increased production costs caused by the conversion rate fluctuation. Controlling the chemical catalyst dosage for the products in the chemical production process based on the addition amount of the production catalyst records the actual added catalyst dosage, which helps to continuously improve the catalytic control link in the production process and ensure the stability of the reaction conversion rate and the high efficiency of production. Determining the types of product impurities for the product quality offset data clarifies the specific types of impurities in the product quality offset. Measuring the content level of the impurity types for the product impurity type data quantifies the impurity content level. Adding impurity neutralizers to the products in the chemical production process based on the impurity type content can targetedly add an appropriate amount of impurity neutralizers, effectively reducing the impurity content and improving the product quality. Optimizing and controlling the chemical production offset for the products in the chemical production process with the chemical catalyst dosage addition data and the impurity neutralizer addition data integrates the optimization strategies for the two key links of catalyst addition and impurity neutralization. This enables the production process to be optimized and controlled simultaneously from multiple perspectives, comprehensively solving the problem of production indicator offsets, improving the overall quality and stability of chemical production, and enhancing the controllability and reliability of the production process.

[0046] Preferably, step S42 includes the following steps:

[0047] Step S421: Perform thermal imaging processing on the abnormal temperature area of the equipment to obtain an equipment thermal imaging map; identify the abnormal temperature distribution of the equipment thermal imaging map to generate temperature abnormal distribution data;

[0048] Step S422: Detect the equipment affected by temperature for the chemical production equipment according to the temperature abnormal distribution data to obtain temperature abnormal influence data;

[0049] Step S423: Identify the structural position of the equipment affected by temperature for the temperature abnormal influence data to generate the structural position data of the equipment affected by temperature; judge the degree of influence by temperature for the structural position data of the equipment affected by temperature to obtain the degree of influence by temperature;

[0050] Step S424: Start the equipment location cooling system for the chemical production equipment based on the affected equipment structure location data to obtain the cooling system start data; control the gear of the equipment cooling system for the chemical production equipment based on the degree of temperature influence to generate the equipment cooling control data;

[0051] Step S425: Perform equipment temperature anomaly response control according to the cooling system start data and the equipment cooling control data to obtain the equipment temperature anomaly response measures.

[0052] The present invention performs equipment area thermal imaging processing on the equipment abnormal temperature area, visually presenting the temperature distribution of each area of the equipment. Identify the abnormal temperature distribution of the equipment thermal imaging map, accurately locate the specific area with abnormal temperature on the equipment, providing a clear basis for subsequent targeted detection and treatment of equipment temperature abnormal problems, helping to quickly focus on the fault location and improve the problem troubleshooting efficiency. Detect the temperature-affected equipment of the chemical production equipment according to the abnormal temperature distribution data, clarifying which equipment is affected by the abnormal temperature. This helps to further narrow the troubleshooting scope, concentrate on detailed analysis and treatment of the affected equipment, avoid unnecessary inspections of the normally operating equipment, save time and resources, and improve the pertinence and efficiency of equipment maintenance. Identify the structure location of the affected equipment for the temperature anomaly influence data, determining the specific structure location of the affected equipment. Judge the degree of temperature influence for the affected equipment structure location data, quantifying the severity of the equipment affected by the temperature anomaly. This provides an accurate reference for subsequent reasonable cooling measures, and corresponding cooling strategies can be formulated according to different degrees of influence, effectively reducing the risk of equipment damage due to excessive temperature and ensuring the stable operation of the equipment. Start the equipment location cooling system for the chemical production equipment based on the affected equipment structure location data, recording the start situation of the cooling system. Control the gear of the equipment cooling system for the chemical production equipment based on the degree of temperature influence, achieving precise control of the cooling system gear. This enables the cooling system to automatically adjust the cooling intensity according to the actual heat absorption situation of the equipment, ensuring the effective cooling of the equipment. Perform equipment temperature anomaly response control according to the cooling system start data and the equipment cooling control data, and the obtained equipment temperature anomaly response measures integrate the optimized strategies of the cooling system start and gear control. This can timely and effectively respond to the equipment temperature abnormal situation, quickly control the equipment temperature within the normal range, reduce equipment failures and production interruptions caused by excessive temperature, ensure the continuity and stability of chemical production, and at the same time help to extend the service life of the equipment and reduce the equipment maintenance cost.

[0053] Preferably, step S43 includes the following steps:

[0054] Step S431: Detect the jitter frequency of the equipment abnormal jitter data to obtain the abnormal jitter frequency value; Measure the equipment operating speed of the chemical production equipment according to the abnormal jitter frequency value to generate the jitter equipment operating speed data;

[0055] Step S432: Monitor the equipment load condition of the jitter equipment operating speed data to obtain the jitter equipment load data; Record the abnormal load of the jitter equipment load data to generate the equipment abnormal load data;

[0056] Step S433: Extract the rotational speed load value from the equipment abnormal load data to obtain the rotational speed load abnormal value; Reduce the equipment gear transmission speed of the chemical production equipment based on the rotational speed load abnormal value to generate the gear speed adjustment data;

[0057] Step S434: Reduce the equipment centrifugal speed of the chemical production equipment based on the rotational speed load abnormal value to generate the centrifugal speed adjustment data;

[0058] Step S435: Control the equipment abnormal jitter response of the chemical production equipment according to the gear speed adjustment data and the centrifugal speed adjustment data to obtain the equipment abnormal jitter response measures.

[0059] The present invention detects the jitter frequency of abnormal jitter data of equipment, clarifying the specific frequency characteristics of equipment jitter. Based on the abnormal jitter frequency value, the operating speed of chemical production equipment is measured, correlating the jitter frequency with the equipment operating speed, providing key data for subsequent analysis of the jitter cause and formulation of corresponding control measures. The load condition of the jittering equipment is monitored based on the operating speed data of the jittering equipment, reflecting the load condition of the equipment in the jitter state. Abnormal load records are made for the load data of the jittering equipment, generating equipment abnormal load data and screening out the load data beyond the normal range. Further focusing on the impact of abnormal load on equipment jitter provides a basis for subsequent targeted adjustment of equipment operating parameters to reduce jitter and enhance the stability of equipment operation. The rotational speed load value is extracted from the equipment abnormal load data, quantifying the rotational speed performance under abnormal load conditions. Based on the abnormal rotational speed load value, the rotational speed of the gear drive of chemical production equipment is reduced, achieving precise adjustment of the rotational speed of the gear drive system. This can effectively reduce equipment jitter caused by excessive rotational speed, reduce gear wear, ensure the stable operation of the gear drive system, and extend the service life of the equipment. Based on the abnormal rotational speed load value, the centrifugal rotational speed of chemical production equipment is reduced, optimizing the control of the rotational speed of centrifugal equipment. This helps to reduce the jitter impact caused by centrifugal force on the equipment, reduce the mechanical stress of the equipment during high-speed operation, reduce the risk of equipment damage, and is also beneficial to improving product quality and production continuity, ensuring the stable progress of chemical production. According to the gear rotational speed adjustment data and the centrifugal rotational speed adjustment data, the equipment abnormal jitter response control is carried out on chemical production equipment, and the obtained equipment abnormal jitter response measures can comprehensively and effectively address the equipment abnormal jitter problem, making adjustments and controls simultaneously from multiple key links, quickly suppressing the equipment jitter within a reasonable range, reducing production efficiency decline and equipment failures caused by jitter, and ensuring the efficient and stable operation of chemical production.

[0060] In this specification, a chemical production control model generation system is provided for performing the above-mentioned chemical production control model generation method. The chemical production control model generation system includes:

[0061] A chemical production data acquisition module for obtaining chemical production process products; collecting original production data of the chemical production process products to obtain chemical production original data; and preprocessing the chemical production original data to obtain standard chemical production data;

[0062] A chemical reaction index analysis module for dividing the production stage of the standard chemical production data to obtain chemical production stage data; determining chemical reaction condition indexes for the chemical production stage data to generate chemical reaction condition indexes; and detecting production index offsets for the chemical reaction condition indexes to obtain production index offset data;

[0063] The device abnormal operation detection module is used to extract the operation parameters of production equipment from the standardized chemical production data to obtain the operation data of production equipment; map the operation state of the production equipment according to the production index offset data to generate the equipment operation state data; detect the abnormal operation of the equipment on the equipment operation state data to obtain the equipment abnormal operation data;

[0064] The chemical production control model generation module is used to perform production offset optimization control on the products in the chemical production process according to the production index offset data to obtain production offset optimization measures; perform production equipment operation response control on the equipment abnormal operation data to obtain equipment abnormal operation response measures; generate a chemical production control model based on the production offset optimization measures and the equipment abnormal operation response measures to obtain a chemical production control model.

[0065] Through the chemical production data collection module, the original production data of the products in the chemical production process is collected and preprocessed to obtain standard chemical production data, which can ensure that the data for subsequent analysis and processing has a unified format and quality, providing a reliable data basis for the precise control of chemical production and avoiding production control errors caused by non-standard and inaccurate data. Through the chemical reaction index analysis module, the standard chemical production data is divided into production stages to obtain chemical production stage data, and then the chemical reaction condition indicators are determined and production index deviation detection is carried out to obtain production index deviation data. This process realizes the refined management and monitoring of each stage of chemical production, can timely detect the subtle changes in chemical reaction conditions during the production process, provides a basis for subsequent targeted optimization control, and improves the quality and production efficiency of chemical products. Through the equipment abnormal operation detection module, the operation parameters of the production equipment are extracted from the standard chemical production data to obtain production equipment operation data, the equipment operation status data is mapped and generated based on the production index deviation data, and equipment abnormal operation detection is carried out to obtain equipment abnormal operation data. This makes the operation status of the production equipment closely related to the production index, can accurately locate the impact of equipment abnormalities on the production index deviation, facilitates taking measures in advance to prevent equipment failures, ensures the stable operation of the production equipment, and reduces production interruptions and defective products caused by equipment problems. Through the chemical production control model generation module, according to the production index deviation data, production deviation optimization control is carried out on the products in the chemical production process to obtain production deviation optimization measures. At the same time, production equipment operation response control is carried out on the equipment abnormal operation data to obtain equipment abnormal operation response measures, and a chemical production control model is generated based on the two. This model comprehensively considers the production index and the equipment operation status, realizes the closed-loop control of chemical production, can adjust the process parameters and equipment operation strategies in real time during the production process, makes the chemical production process always in the optimal state, and effectively improves the overall efficiency and safety of chemical production. Therefore, through data analysis technology, pattern recognition technology and automation control technology, the present invention realizes the detection of production index deviation amounts in each stage of chemical product production, and uses the production index deviation amounts to identify abnormalities in the operation of chemical production equipment, thereby improving the accuracy of chemical production control and the production efficiency of chemical products.

[0066] A computer-readable storage medium stores a computer program, wherein the computer program is used to execute the chemical production control model generation method described above. Brief Description of the Drawings

[0067] Figure 1 It is a schematic flow chart of the steps of a chemical production control model generation method;

[0068] Figure 2 is Figure 1 a detailed implementation step flow chart of step S4 in

[0069] Figure 3 For Figure 2 the detailed implementation step flow diagram of step S42 in

[0070] The realization, functional features and advantages of the present invention will be further described with reference to the embodiments and the accompanying drawings. Specific implementation manners

[0071] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0072] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus the repeated description thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0073] It should be understood that although the terms "first", "second", etc. are used here to describe each unit, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit can be called the second unit, and similarly the second unit can be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed related items.

[0074] To achieve the above object, please refer to Figures 1 to 3 , a method for generating a chemical production control model, the method comprising the following steps:

[0075] Step S1: Obtain chemical production process products; collect raw production data of the chemical production process products to obtain raw chemical production data; perform data preprocessing on the raw chemical production data to obtain standard chemical production data;

[0076] Step S2: Divide the standard chemical production data into production stages to obtain chemical production stage data; determine chemical reaction condition indicators for the chemical production stage data to generate chemical reaction condition indicators; perform production index offset detection on the chemical reaction condition indicators to obtain production index offset data;

[0077] Step S3: Extract the operating parameters of the production equipment from the standardized chemical production data to obtain the production equipment operation data; map the equipment operation status according to the production index deviation data to generate the equipment operation status data; perform equipment abnormal operation detection on the equipment operation status data to obtain the equipment abnormal operation data;

[0078] Step S4: Perform production deviation optimization control on the chemical production process products according to the production index deviation data to obtain production deviation optimization measures; perform production equipment operation response control on the equipment abnormal operation data to obtain equipment abnormal operation response measures; generate a chemical production control model based on the production deviation optimization measures and the equipment abnormal operation response measures to obtain the chemical production control model.

[0079] The present invention collects the original data of the production process of chemical products during the chemical production process, preprocesses the data, and obtains standard chemical production data, which can ensure that the data for subsequent analysis and processing has a unified format and quality, provides a reliable data basis for the precise control of chemical production, and avoids production control errors caused by non-standard and inaccurate data. The standard chemical production data is divided into production stages to obtain chemical production stage data, and then the chemical reaction condition indicators are determined and production index deviation detection is carried out to obtain production index deviation data. This process realizes the refined management and monitoring of each stage of chemical production, can timely detect the slight changes in chemical reaction conditions during the production process, provides a basis for subsequent targeted optimization control, and improves the quality and production efficiency of chemical products. The operating parameters of production equipment are extracted from the standard chemical production data to obtain production equipment operation data, the equipment operation status data is generated by mapping according to the production index deviation data, and equipment abnormal operation detection is carried out to obtain equipment abnormal operation data. This makes the operating status of production equipment closely related to production indicators, can accurately locate the impact of equipment abnormalities on production index deviations, facilitates taking measures in advance to prevent equipment failures, ensures the stable operation of production equipment, and reduces production interruptions and defective products caused by equipment problems. According to the production index deviation data, production deviation optimization control is carried out on the chemical production process products to obtain production deviation optimization measures. At the same time, production equipment operation response control is carried out on the equipment abnormal operation data to obtain equipment abnormal operation response measures, and a chemical production control model is generated based on the two. This model comprehensively considers production indicators and equipment operation status, realizes the closed-loop control of chemical production, can adjust process parameters and equipment operation strategies in real time during the production process, keeps the chemical production process in the optimal state all the time, and effectively improves the overall efficiency and safety of chemical production. Therefore, the present invention realizes the detection of production index deviation amounts in each stage of chemical product production through data analysis technology, pattern recognition technology, and automation control technology, and identifies abnormalities in the operation of chemical production equipment based on the production index deviation amounts, thereby improving the accuracy of chemical production control and the production efficiency of chemical products.

[0080] In an embodiment of the present invention, as shown in Figure 1 The method for generating the chemical production control model includes the following steps:

[0081] Step S1: Obtain chemical products during the chemical production process; collect the original data of the production process of chemical products during the chemical production process to obtain chemical production original data; preprocess the chemical production original data to obtain standard chemical production data;

[0082] In the embodiments of the present invention, various sensors deployed at the chemical production site, such as temperature sensors, pressure sensors, flow sensors, etc., are used to obtain the relevant data of the products in different production links during the chemical production process in real time. These sensors convert the collected signals into electrical signals, and then through a data acquisition card or data acquisition module, at a certain sampling frequency, such as 10 times per second, the electrical signals are converted into digital signals, so as to obtain the original production process data of the products in the chemical production process, including data of parameters such as product density, product content, moisture content, acidity, feed flow rate, discharge flow rate, feed pressure, discharge pressure, feed temperature, discharge temperature, reaction temperature, purity, reaction rate, pH value, liquid level, material concentration, etc. Then, the collected original chemical production data is transmitted to a data processing server or a computer system, and data preprocessing software or a data processing library in a programming language, such as the Pandas library of Python, is used to clean the data. Specifically, missing values are identified and processed. For the missing data, methods such as linear interpolation or mean filling can be used to supplement it according to the data at adjacent time points; outliers are screened and removed. By calculating the statistical quantities of the data, such as the average value, standard deviation, etc., a reasonable threshold is set, and the data outside the threshold range is determined as an outlier and deleted; for the product content data, if its average value is 80% and the standard deviation is 2%, then the data with a content lower than 76% or higher than 84% can be regarded as outliers and removed. Then, the cleaned data is standardized. Using the Z-score standardization method, each data point is subtracted by the average value of the data set and then divided by the standard deviation, so that the processed data conforms to a normal distribution with a mean of 0 and a standard deviation of 1.

[0083] Step S2: Divide the standardized chemical production data into production stages to obtain chemical production stage data; determine the chemical reaction condition indicators for the chemical production stage data to generate chemical reaction condition indicators; detect the production index deviation for the chemical reaction condition indicators to obtain production index deviation data;

[0084] In the embodiments of the present invention, the clustering algorithm in data mining technology is used to divide the standard chemical production data into production stages. The specific operation is as follows: The data of parameters such as product density, product content, moisture content, acidity, feed flow rate, discharge flow rate, feed pressure, discharge pressure, feed temperature, discharge temperature, reaction temperature, purity, reaction rate, pH value, liquid level, and material concentration in the standard chemical production data are used as input features. An appropriate number of clustering centers is selected, for example, set to 3. By calculating the distance between each data point and the clustering center, the data points are divided into the production stages represented by the nearest clustering center, thereby obtaining the chemical production stage data. Then, for each chemical production stage data, a statistical analysis method is used to determine the chemical reaction condition indicators. Taking the reaction temperature as an example, statistical quantities such as the average value, maximum value, minimum value, and standard deviation of the reaction temperature data within each production stage are calculated, and these statistical quantities are used as the chemical reaction condition indicators for this stage, generating a chemical reaction condition indicator data set, which contains the chemical reaction condition indicators corresponding to each production stage. Then, production index offset detection is performed on the chemical reaction condition indicator data set. The normal range threshold of each chemical reaction condition indicator is set. For example, the normal range of the reaction temperature is 80°C - 120°C. By comparing the actual chemical reaction condition indicator with the normal range threshold, if the actual indicator exceeds the normal range, the offset value of the indicator is recorded, that is, the difference between the actual value and the normal range threshold, thereby obtaining the production index offset data.

[0085] Step S3: Extract the production equipment operation parameters from the standard chemical production data to obtain the production equipment operation data; map the production equipment operation data according to the production index offset data to generate the equipment operation status data; perform equipment abnormal operation detection on the equipment operation status data to obtain the equipment abnormal operation data;

[0086] In the embodiments of the present invention, production equipment operation parameters are extracted from standardized chemical production data by using data extraction technology. The specific operation is to screen out the operation parameters directly related to the production equipment, such as the vibration frequency of the equipment, the motor current, and the equipment operation duration, from the standardized chemical production data containing parameters such as product density, product content, moisture content, acidity, feed flow rate, discharge flow rate, feed pressure, discharge pressure, feed temperature, discharge temperature, reaction temperature, purity, reaction rate, pH value, liquid level, and material concentration, so as to obtain the production equipment operation data. Then, the equipment operation state mapping is performed on the production equipment operation data according to the production index offset data. The specific operation is to perform correlation analysis on the offset value in the production index offset data and the corresponding parameters in the production equipment operation data. By setting mapping rules, such as when the production index offset value exceeds a certain threshold, the corresponding parameters in the production equipment operation data are marked as abnormal states. For example, if the production index offset value of the reaction temperature exceeds 5°C, the vibration frequency parameter in the production equipment operation data related to the reaction temperature is marked as an abnormal state, which includes information such as equipment ID, parameter name, parameter value, and operation state. The equipment abnormal operation detection is performed on the equipment operation state data. Specifically, machine learning algorithms, such as support vector machines, are used to perform classification analysis on the equipment operation state data. The normal state data in the equipment operation state data is used as the training set, and the abnormal state data is used as the test set to train the machine learning model. The abnormal conditions in the equipment operation state data are predicted through the model. If the model prediction result is abnormal, the data is recorded as equipment abnormal operation data, which includes information such as equipment ID, abnormal parameter name, abnormal parameter value, and abnormal time. The SVM algorithm in the Scikit-learn library of Python is used to train and predict the equipment operation state data to obtain the equipment abnormal operation data.

[0087] Step S4: Perform production offset optimization control on the chemical production process products according to the production index offset data to obtain production offset optimization measures; perform production equipment operation response control on the equipment abnormal operation data to obtain equipment abnormal operation response measures; generate a chemical production control model based on the production offset optimization measures and the equipment abnormal operation response measures to obtain a chemical production control model.

[0088] In the embodiments of the present invention, production offset optimization control is performed on chemical production process products according to production index offset data. The specific operation is to use an association rule mining algorithm, such as the Apriori algorithm, to analyze the production index offset data, calculate the support and confidence between various indicators, and thus generate production offset optimization rules. For example, setting the minimum support to 0.5 and the minimum confidence to 0.6, it is found through calculation that when the reaction temperature offset value exceeds 5°C and the feed flow rate offset value exceeds 10%, adjusting the stirring speed of the reaction kettle can improve the product purity, and corresponding production offset optimization measures are generated, including information such as the parameter name to be adjusted, the adjustment range, and the adjustment time. Then, production equipment operation response control is performed on the equipment abnormal operation data. Specifically, the decision tree algorithm in the machine learning algorithm is used to classify and analyze the equipment abnormal operation data, and according to information such as the equipment ID, abnormal parameter name, abnormal parameter value, and abnormal time in the equipment abnormal operation data, equipment abnormal operation response rules are generated. For example, when the equipment vibration frequency is abnormal and the motor current is abnormal, the equipment operation is immediately stopped and repaired, and equipment abnormal operation response measures are generated, including information such as the response equipment ID, response measure description, and response time. Then, a chemical production control model is generated based on the production offset optimization measures and the equipment abnormal operation response measures. Specifically, the production offset optimization measures and the equipment abnormal operation response measures are integrated into a control strategy table, which contains various parameters in the production process, the corresponding optimization measures or response measures, and the trigger conditions. Through the automated control system, various parameters in the production process are monitored in real time. When the parameters reach the trigger conditions, the corresponding optimization measures or response measures are automatically executed, thereby realizing the automatic control of the chemical production process and obtaining a chemical production control model.

[0089] Preferably, step S2 includes the following steps:

[0090] Step S21: Extract the production stage timestamp from the standard chemical production data to obtain the production stage timestamp; mark the standard chemical production data according to the production stage timestamp to generate production stage identification data;

[0091] Step S22: Classify the production stage identification data to obtain the production stage identification category; divide the chemical production stage through the production stage identification category to obtain chemical production stage data;

[0092] Step S23: Identify the chemical production stage state of the chemical production stage data to obtain chemical production stage state data; detect the chemical reaction conditions of the chemical products for the chemical production stage state data to generate stage chemical reaction data;

[0093] Step S24: Judge the production stage reaction condition indexes for the stage chemical reaction data to generate chemical reaction condition indexes; determine the production stage chemical reaction index benchmarks according to the chemical reaction condition indexes to obtain the stage chemical reaction index benchmarks;

[0094] Step S25: Detect the anomalies of the stage chemical reaction indexes for the stage chemical reaction data to obtain reaction index anomaly data; measure the production index offset for the reaction index anomaly data according to the stage chemical reaction index benchmarks to obtain production index offset data.

[0095] In the embodiments of the present invention, data processing technology is used to extract production stage timestamps from standardized chemical production data. The specific operation is to screen out time-related fields, such as "production start time", "production end time", etc., from the standardized chemical production data containing parameters such as product density, product content, moisture content, acidity, feed flow rate, discharge flow rate, feed pressure, discharge pressure, feed temperature, discharge temperature, reaction temperature, purity, reaction rate, pH value, liquid level, material concentration, etc. through a data processing script or a database query statement. Then, the standardized chemical production data is marked with production stages according to the production stage timestamps to generate production stage identification data, which includes the start time, end time, and corresponding production data of each production stage. The production stage identification data is classified by stage identification. The specific operation is to use a data classification algorithm, such as the K-Means clustering algorithm, to classify the production stage identification data according to the similarity of timestamps to obtain production stage identification categories. For example, when setting the number of clustering centers to 3, the data points are divided into the production stage categories represented by the nearest clustering centers by calculating the distance between each production stage identification data and the clustering centers. Then, the production stages are divided by the production stage identification categories, and each stage includes all relevant production data within that stage. The state of the chemical production stage data is identified for the chemical production stage. Specifically, the decision tree algorithm in the machine learning algorithm is used to classify and analyze the chemical production stage data, and the state of each production stage is identified according to parameters such as the vibration frequency of the equipment, the motor current, and the equipment operation duration. The chemical reaction conditions of the chemical products are detected for the chemical production stage state data, which includes the chemical reaction conditions of each production stage, such as reaction temperature, reaction pressure, reactant concentration, etc. The reaction conditions indicators of the production stage are judged for the stage chemical reaction data. Specifically, by setting thresholds, such as the normal range of reaction temperature is 80°C - 120°C, it is judged whether the chemical reaction conditions of each production stage are within the normal range. The chemical reaction index benchmarks of the production stage are determined according to the chemical reaction conditions indicators, which includes the chemical reaction index benchmark values of each production stage, such as the reaction temperature benchmark value, the reaction pressure benchmark value, etc. The abnormal detection of the stage chemical reaction index is carried out for the stage chemical reaction data. Specifically, statistical analysis methods, such as standard deviation analysis, are used to calculate the deviation between the chemical reaction index of each production stage and the stage chemical reaction index benchmark value. The production index offset amount is measured for the reaction index abnormal data according to the stage chemical reaction index benchmark, which includes the offset amount of each abnormal data, such as the reaction temperature offset amount, the reaction pressure offset amount, etc.

[0096] Preferably, step S3 includes the following steps:

[0097] Step S31: Identify the characteristics of chemical production equipment from the standardized chemical production data to obtain chemical production equipment; extract the equipment operation parameters of the chemical production equipment to obtain production equipment operation data;

[0098] Step S32: Determine the production stage where the production index deviation data is located to obtain the data of the deviation location stage; match the stage equipment operation characteristics with the production equipment operation data according to the data of the deviation location stage to generate stage equipment operation data;

[0099] Step S33: Identify the operation working mode from the stage equipment operation data to obtain operation working mode data; map the operation working mode data to the equipment operation working state to generate equipment operation state data;

[0100] Step S34: Detect the abnormal operation of the equipment from the equipment operation state data to obtain equipment abnormal operation data.

[0101] In the embodiments of the present invention, image recognition and sensor data fusion technology are used to identify the characteristics of production equipment for standard chemical production data. Specifically, through intelligent cameras and various sensors installed at the production site, such as temperature sensors, pressure sensors, flow sensors, etc., images and operation parameter data of production equipment are collected in real time; using image processing algorithms, such as edge detection, feature extraction, etc., the contours and key components of production equipment are identified from the images collected by the cameras, and at the same time, combined with sensor data, the operation parameters of production equipment are extracted, such as the vibration frequency of the equipment, motor current, equipment operation duration, etc. Then, equipment operation parameters are extracted from these characteristic data, which include information such as equipment ID, parameter name, parameter value, acquisition time, etc. To determine the production stage of production index offset data, specifically through the timestamp matching algorithm, the timestamp in the production index offset data is compared with the production stage timestamp in the standard chemical production data to determine the production stage where each offset data is located; according to the data in the offset stage, the operation characteristics of the equipment in the stage are matched with the operation data of the production equipment. Specifically, the association rule mining algorithm, such as the Apriori algorithm, is used to analyze the association relationship between the data in the offset stage and the operation data of the production equipment; if the reaction temperature offset value exceeds 5°C in a certain production stage, then the operation data of the equipment vibration frequency and motor current in this stage are matched, which includes information such as equipment ID, production stage, matching parameter name, matching parameter value, etc. To identify the operation working mode of the equipment operation data in the stage, specifically using the clustering algorithm in machine learning algorithms, such as the K-Means algorithm, to classify and analyze the equipment operation data in the stage, and according to parameters such as the vibration frequency of the equipment, motor current, equipment operation duration, etc., identify the operation working mode of the equipment in each production stage; for example, set the number of clustering centers to 3, and by calculating the distance between the equipment operation data in each stage and the clustering center, divide the data points into the operation working mode categories represented by the nearest clustering center; map the operation working mode data to the equipment operation working state, specifically by setting mapping rules, such as mapping a certain operation working mode to the normal operation state, and another mode to the standby state, etc., to generate equipment operation state data, which includes information such as equipment ID, production stage, operation working mode, operation working state, etc. To detect abnormal operation of the equipment based on the equipment operation state data. Specifically, statistical analysis methods, such as standard deviation analysis, are used to calculate the deviation between the equipment operation parameters in each production stage and the normal operation parameters to obtain equipment abnormal operation data. For example, if the deviation of the equipment vibration frequency exceeds the set threshold, such as exceeding 10% of the normal value, it is determined that the equipment has abnormal operation in this production stage and is recorded as equipment abnormal operation data.

[0102] Preferably, step S34 includes the following steps:

[0103] Step S341: Classify the device operation status data according to the devices in the operation stage to obtain device type data; Correspond the device type data to the devices in the chemical production stage to generate stage-corresponding device data;

[0104] Step S342: Determine the chemical production process operations for the stage-corresponding device data to obtain device process operation data; Identify the chemical device temperature for the device process operation data to obtain chemical device temperature data;

[0105] Step S343: Locate the abnormal temperature area of the device for the chemical device temperature data to obtain the abnormal temperature area of the device; Detect the parameters of the chemical rotating centrifugal device according to the abnormal temperature area of the device for the device operation status data to generate rotating centrifugal device parameters;

[0106] Step S344: Detect the abnormal centrifugal speed of the device for the rotating centrifugal device parameters to obtain the parts of the device with abnormal speed; Identify the abnormal jitter state of the device for the parts of the device with abnormal speed to generate device abnormal jitter data;

[0107] Step S345: Integrate the abnormal temperature area of the device and the device abnormal jitter data to obtain device abnormal operation data.

[0108] In the embodiments of the present invention, data classification technology is used to classify equipment in the operation stage according to the operation status data of the equipment. Specifically, through the decision tree algorithm in machine learning algorithms, the equipment in the equipment operation status data is classified according to features such as the model, production capacity, and maintenance records of the equipment. For example, the equipment is classified into types such as reaction kettles, centrifuges, and compressors; the equipment type data is corresponded to the equipment in the chemical production stage. Specifically, through the timestamp matching and equipment type matching algorithms, the equipment type data is corresponded to the production stage in the standard chemical production data, which includes information such as equipment ID, equipment type, production stage, and operation status; the equipment data corresponding to the stage is used to determine the chemical production process operations. Specifically, through the process flow analysis algorithm, according to the process steps and equipment functions in the chemical production process, the process operations of each stage corresponding equipment are determined to obtain equipment process operation data. For example, the process operation of a reaction kettle in a certain production stage is heating reaction, and the process operation of a centrifuge is separation and purification. Then, the chemical equipment temperature is identified from the equipment process operation data. The specific operation is to collect the temperature data of the equipment during the process operation through a temperature sensor, and combine the process operation requirements to identify the temperature change of the equipment to obtain chemical equipment temperature data, which includes information such as equipment ID, production stage, process operation, and temperature value. The abnormal temperature area of the chemical equipment is located from the chemical equipment temperature data. Specifically, through thermal imaging technology or temperature distribution analysis algorithm, according to the temperature data of the equipment and the normal operating temperature range, the abnormal temperature area on the surface or inside of the equipment is located to obtain the abnormal temperature area of the equipment; if the temperature of a local area of a reaction kettle rises abnormally, the area can be accurately located through a thermal imaging map. Then, the chemical rotation centrifuge equipment parameters are detected according to the abnormal temperature area of the equipment from the equipment operation status data. The specific operation is that for a rotating centrifuge equipment, through a vibration sensor and a speed sensor, the operation parameters of the equipment in the abnormal temperature area, such as vibration amplitude and speed, are detected to generate rotating centrifuge equipment parameters. The abnormal centrifugal speed of the rotating centrifuge equipment is detected from the rotating centrifuge equipment parameters. By setting a speed threshold, such as the normal speed range is 1000 - 1500 revolutions per minute, it is detected whether the actual speed of the rotating centrifuge equipment exceeds the normal range. For example, if the actual speed of a centrifuge is 1600 revolutions per minute, exceeding the normal range, it is determined that there is a speed abnormality in this equipment part. Then, the abnormal jitter state of the equipment part with abnormal speed is identified. The vibration data of the equipment part with abnormal speed is collected through a vibration sensor, and the vibration frequency and amplitude are analyzed to identify the abnormal jitter state of the equipment to generate equipment abnormal jitter data. Through data fusion technology, the equipment abnormal temperature area data and the equipment abnormal jitter data are integrated to generate equipment abnormal operation data, which includes information such as equipment ID, production stage, abnormal type (temperature abnormality or jitter abnormality), abnormal part, and abnormal parameter value.

[0109] As an example of the present invention, refer toFigure 2 As shown in the figure, in this example, step S4 includes:

[0110] Step S41: Determine the offset index type for the production index offset data to obtain the offset index type data; perform production offset optimization control on the chemical production process products according to the offset index type data to obtain production offset optimization measures;

[0111] Step S42: Perform equipment temperature anomaly response control on the equipment abnormal temperature area to obtain equipment temperature anomaly response measures;

[0112] Step S43: Perform equipment abnormal jitter response control on the equipment abnormal jitter data to obtain equipment abnormal jitter response measures;

[0113] Step S44: Perform chemical production control on the chemical production equipment according to the production offset optimization measures and the equipment abnormal operation response measures to obtain chemical production control data; construct a chemical production control model based on the chemical production control data to obtain a chemical production control pre-model;

[0114] Step S45: Use the production offset optimization measures and the equipment abnormal operation response measures to train the chemical production control pre-model to obtain a chemical production control training model;

[0115] Step S46: Perform model cross-validation evaluation on the chemical production control training model to obtain chemical production control model evaluation data; adjust the model parameters of the chemical production control training model through the chemical production control model evaluation data to obtain a chemical production control model.

[0116] In the embodiments of the present invention, data classification technology is used to determine the types of offset indicators for production indicator offset data. Specifically, through the decision tree algorithm in machine learning algorithms, according to features such as indicator names, offsets, and offset times in the production indicator offset data, the offset indicators are classified. For example, the offset indicators are classified into types such as temperature offset, pressure offset, and flow offset. Then, production offset optimization control is performed on the products in the chemical production process according to the offset indicator type data. Specifically, through the PID control algorithm, the corresponding production parameters are adjusted according to the offset indicator type and the offset amount. If the temperature offset exceeds 5°C, the power of the heater is adjusted to bring the temperature back to the normal range, including information such as the parameter name to be adjusted, the adjustment amplitude, and the adjustment time. Equipment temperature anomaly response control is performed on the equipment abnormal temperature area. Specifically, through the temperature control system, according to the data of the equipment abnormal temperature area, such as the location of the abnormal area and the temperature value, the corresponding cooling or heating device is started. For example, if the temperature of a local area of a certain equipment rises abnormally, the cooling water circulation system is started to lower the temperature of this area, and equipment temperature anomaly response measures are generated, including information such as the response equipment ID, the description of the response measure, and the response time. Equipment abnormal vibration response control is performed on the equipment abnormal vibration data. Specifically, through the vibration control system, according to parameters such as the vibration frequency and vibration amplitude in the equipment abnormal vibration data, the operating parameters of the equipment are adjusted, such as adjusting the balance device or shock absorption device of the equipment, and equipment abnormal vibration response measures are obtained. For example, if the vibration amplitude of the equipment exceeds the set threshold, the shock pads of the equipment are adjusted to reduce the vibration amplitude. Chemical production control is performed on the chemical production equipment according to the production offset optimization measures and the equipment abnormal operation response measures. The specific operation is to integrate the production offset optimization measures and the equipment abnormal operation response measures into the control strategy through the automation control system, and monitor various parameters in the production process in real time. When the parameters reach the trigger conditions, the corresponding optimization measures or response measures are automatically executed. Then, a chemical production control model is constructed based on the chemical production control data. The specific operation is to use data modeling technology to take the chemical production control data as input and construct a chemical production control model. The production offset optimization measures and the equipment abnormal operation response measures are used to train the chemical production control pre-model. Specifically, the production offset optimization measures and the equipment abnormal operation response measures are used as training data to train the chemical production control pre-model, and a chemical production control training model is obtained, which contains information such as the weights, biases, and classification surfaces of the model. Model cross-validation evaluation is performed on the chemical production control training model. The specific operation is to evaluate the chemical production control training model on the test data through cross-validation methods such as K-fold cross-validation, and obtain chemical production control model evaluation data, which contains indicators such as the accuracy, recall rate, and F1 value of the model. Then, the model parameters of the chemical production control training model are adjusted according to the chemical production control model evaluation data.Specific operations are as follows: According to the metrics in the evaluation data, adjust the parameters of the model, such as the learning rate, the number of iterations, the regularization coefficient, etc., to obtain a chemical production control model, which includes the optimized model parameters and structure.

[0117] Preferably, step S41 includes the following steps:

[0118] Step S411: Determine the deviation index type of the production index deviation data to obtain deviation index type data, where the deviation index type data includes reaction conversion rate deviation data and product quality deviation data;

[0119] Step S412: Determine the reaction catalyst for the reaction conversion rate deviation data to obtain reaction catalyst data; Detect the dosage of the reaction catalyst data to produce the reaction catalyst dosage;

[0120] Step S413: Measure the conversion rate deviation of the reaction conversion rate deviation data to produce the conversion rate deviation; Determine the addition amount of the chemical production catalyst for the reaction catalyst dosage according to the conversion rate deviation to obtain the production catalyst addition amount;

[0121] Step S414: Control the chemical catalyst dosage of the chemical production process product according to the production catalyst addition amount to obtain the chemical catalyst dosage addition data;

[0122] Step S415: Determine the product impurity type of the product quality deviation data to obtain product impurity type data; Measure the content of the impurity type of the product impurity type data to generate the impurity type content; Put the impurity neutralizer into the chemical production process product according to the impurity type content to obtain the impurity neutralizer addition data;

[0123] Step S416: Use the chemical catalyst dosage addition data and the impurity neutralizer addition data to perform chemical production deviation optimization control on the chemical production process product to obtain the production deviation optimization measures.

[0124] In the embodiments of the present invention, data classification technology is used to determine the types of offset indicators for production indicator offset data. Specifically, through the decision tree algorithm in machine learning algorithms, according to features such as indicator names, offsets, and offset times in the production indicator offset data, the offset indicators are classified to obtain offset indicator type data, where the offset indicator type data includes reaction conversion rate offset data and product quality offset data. For example, by analyzing the labels and value ranges in the data, the reaction conversion rate offset data and product quality offset data are respectively marked out; the reaction catalyst for the reaction conversion rate offset data is determined. The specific operation is to determine the catalyst type related to the reaction conversion rate offset by analyzing the chemical reaction mechanism and combining the catalyst usage records in the production process. Then, the dosage of the reaction catalyst data is detected, and the actual dosage of the catalyst is measured through an on-line analyzer or laboratory analysis method. For example, a spectral analyzer is used to detect the concentration of the catalyst to obtain specific dosage values. The conversion rate offset amount of the reaction conversion rate offset data is determined. Specifically, the actual conversion rate is compared with the target conversion rate, and the offset amount of the conversion rate is calculated to generate the conversion rate offset amount. The addition amount of the chemical production catalyst is determined for the reaction catalyst dosage according to the conversion rate offset amount. Specifically, through the chemical reaction kinetics model and combining the conversion rate offset amount, the addition amount of the catalyst that needs to be adjusted is calculated to obtain the production catalyst addition amount. For example, if the conversion rate offset amount is -5%, it is calculated according to the model that 10% more catalyst dosage is needed. The chemical production process product is controlled for the chemical catalyst dosage according to the production catalyst addition amount. Specifically, through an automated control system, according to the calculated catalyst addition amount, the catalyst supply system is adjusted. For example, the flow rate of the catalyst supply pump is adjusted, and the addition data is recorded. The product impurity type of the product quality offset data is determined. The specific operation is to analyze the impurity components in the product quality offset data through a quality analyzer, such as a chromatograph or a mass spectrometer, to obtain the product impurity type data. Then, the content of the impurity type in the product impurity type data is determined, and the specific content of the impurity is measured through a quantitative analysis method to generate the impurity type content. The impurity neutralizer is added to the chemical production process product according to the impurity type content. The specific operation is to select a suitable neutralizer according to the impurity type and content, and through an automated control system, the neutralizer is accurately added to obtain the impurity neutralizer addition data. For example, if it is detected that the product contains excessive acidic impurities, the corresponding alkaline neutralizer is added, and the addition data is recorded. The chemical production offset optimization control is performed on the chemical production process product with the chemical catalyst dosage addition data and the impurity neutralizer addition data. The specific operation is to integrate the catalyst dosage addition data and the impurity neutralizer addition data into the production control strategy through an integrated automated control system, and monitor various parameters in the production process in real time. When the parameters reach the trigger conditions, the corresponding optimization measures are automatically executed to obtain the production offset optimization measures.

[0125] As an example of the present invention, refer to Figure 3 As shown, in this example, step S42 includes:

[0126] Step S421: Perform equipment area thermal imaging processing on the abnormal temperature area of the equipment to obtain an equipment thermal imaging map; identify the abnormal temperature distribution of the equipment thermal imaging map to generate temperature abnormal distribution data;

[0127] Step S422: Perform temperature-affected equipment detection on the chemical production equipment according to the temperature abnormal distribution data to obtain temperature abnormal influence data;

[0128] Step S423: Identify the structural position of the affected equipment for the temperature abnormal influence data to generate the structural position data of the affected equipment; judge the degree of temperature influence on the structural position data of the affected equipment to obtain the degree of temperature influence;

[0129] Step S424: Start the equipment position cooling system for the chemical production equipment based on the structural position data of the affected equipment to obtain cooling system start data; control the gear of the equipment cooling system for the chemical production equipment based on the degree of temperature influence to generate equipment cooling control data;

[0130] Step S425: Perform equipment temperature abnormal response control according to the cooling system start data and the equipment cooling control data to obtain equipment temperature abnormal response measures.

[0131] In the embodiment of the present invention, thermal imaging processing of the equipment area is performed on the abnormal temperature area of the equipment. The specific operation is to use a thermal imaging camera to scan the abnormal temperature area of the equipment to generate an equipment thermal imaging map. The thermal imaging camera detects the temperature distribution on the surface of the equipment through infrared rays, converts the temperature data into an image form, and obtains the equipment thermal imaging map. Then, the abnormal temperature distribution in the equipment thermal imaging map is identified. The specific operation is to identify the areas with abnormal temperatures in the map through image processing algorithms such as edge detection and region segmentation, and generate abnormal temperature distribution data, which includes information such as the positions and temperature values of the abnormal areas. Equipment detection affected by temperature is performed on the chemical production equipment according to the abnormal temperature distribution data. The specific operation is to determine the equipment affected by temperature through the equipment management system, combining the positions and temperature values in the abnormal temperature distribution data, and obtain the temperature abnormal influence data. For example, if the temperature of a local area of a certain equipment rises abnormally, query the equipment corresponding to this area through the equipment management system and record it as the equipment affected by temperature. Identification of the structural positions of the equipment affected by the temperature abnormal influence data is performed. The specific operation is to determine the specific structural positions of the equipment affected by combining the position information in the temperature abnormal influence data with the three-dimensional model or drawings of the equipment. Then, judgment of the degree of influence of temperature on the structural position data of the equipment affected is performed. The specific operation is to judge the degree of influence of temperature on the equipment through the relationship model between temperature and equipment performance, combining the temperature values in the structural position data of the equipment affected, and obtain the degree of influence of temperature. For example, if the temperature of a certain component of an equipment exceeds 20% of its normal operating temperature range, it is judged that the degree of influence of this component by temperature is severe. Starting of the equipment position cooling system is performed on the chemical production equipment based on the structural position data of the equipment affected. Specifically, through the automatic control system, the corresponding cooling system is started according to the structural position data of the equipment affected. For example, if the temperature of a certain component of an equipment is abnormal, start the cooling fan or cooling water circulation system near this component, and record the start time and status of the cooling system. Control of the gear position of the equipment cooling system is performed on the chemical production equipment based on the degree of influence of temperature. The specific operation is to adjust the gear position of the cooling system according to the degree of influence of temperature. For example, if the degree of influence of the equipment by temperature is severe, adjust the gear position of the cooling system to the highest, and record the adjusted gear position and time. Equipment temperature abnormal response control is performed according to the cooling system start data and the equipment cooling control data. The specific operation is to integrate the cooling system start data and the equipment cooling control data into the control strategy through the automatic control system, and monitor the temperature change of the equipment in real time. When the temperature reaches the set safe range, automatically adjust the operating state of the cooling system to obtain the equipment temperature abnormal response measures. For example, when the equipment temperature drops to the normal range, automatically reduce the gear position of the cooling system or stop the cooling system, and record the execution time and effect of the response measures.

[0132] Preferably, step S43 includes the following steps:

[0133] Step S431: Detect the jitter frequency of the abnormal jitter data of the equipment to obtain the abnormal jitter frequency value; measure the operating speed of the chemical production equipment according to the abnormal jitter frequency value, and generate the operating speed data of the jitter equipment;

[0134] Step S432: Monitor the equipment load condition of the operating speed data of the jitter equipment to obtain the load data of the jitter equipment; record the abnormal load of the load data of the jitter equipment to generate the abnormal load data of the equipment;

[0135] Step S433: Extract the rotational speed load value from the abnormal load data of the equipment to obtain the abnormal rotational speed load value; reduce the rotational speed of the equipment gear transmission of the chemical production equipment based on the abnormal rotational speed load value, and generate the gear rotational speed adjustment data;

[0136] Step S434: Reduce the centrifugal rotational speed of the chemical production equipment based on the abnormal rotational speed load value, and generate the centrifugal rotational speed adjustment data;

[0137] Step S435: Control the abnormal jitter response of the chemical production equipment according to the gear rotational speed adjustment data and the centrifugal rotational speed adjustment data to obtain the abnormal jitter response measures of the equipment.

[0138] In the embodiments of the present invention, for the abnormal jitter data of the device, the jitter frequency is detected. Specifically, a vibration sensor is used to collect the vibration signal of the device, and the time-domain signal is converted into a frequency-domain signal through Fourier transform. For example, a spectrum analyzer is used to analyze the vibration signal to determine the main jitter frequency components. The operating speed of the chemical production equipment is measured according to the abnormal jitter frequency value. Specifically, through a speed sensor or an encoder, the operating speed of the device is measured to generate the operating speed data of the jitter device. For example, for a rotating device, its rotational speed is measured by an encoder and recorded as the operating speed data of the jitter device. The load condition of the jitter device during operation is monitored for the operating speed data of the jitter device. Specifically, through a current sensor or a torque sensor, the load condition of the device during operation is monitored. For example, the current of the motor is measured by a current sensor to estimate the load of the device. Abnormal load records are made for the load data of the jitter device. Specifically, a load threshold is set, and when the device load exceeds the threshold, it is recorded as abnormal load data. If the current during normal operation of the device is 10 A and the set threshold is 12 A, when the current exceeds 12 A, it is recorded as abnormal load data. The rotational speed load value is extracted from the abnormal load data of the device. Specifically, the load value related to the rotational speed is extracted from the abnormal load data to obtain the abnormal rotational speed load value. For example, the rotational speed and the corresponding current value of the device under abnormal load are recorded. Based on the abnormal rotational speed load value, the rotational speed of the gear drive of the chemical production equipment is reduced. The specific operation is to reduce the rotational speed of the gear drive of the device through a frequency converter or a speed governor according to the abnormal rotational speed load value to generate gear rotational speed adjustment data. For example, if the abnormal rotational speed load value indicates that the device rotational speed is too high, the rotational speed is reduced through a frequency converter, and the adjusted rotational speed and time are recorded. Based on the abnormal rotational speed load value, the centrifugal rotational speed of the chemical production equipment is reduced. The specific operation is that for a centrifugal device, by adjusting the control parameters of the centrifuge, such as voltage or frequency, the centrifugal rotational speed is reduced. For example, if the abnormal rotational speed load value of the centrifuge indicates that the rotational speed needs to be reduced, the rotational speed is reduced by adjusting the power supply frequency, and the adjusted rotational speed and time are recorded. According to the gear rotational speed adjustment data and the centrifugal rotational speed adjustment data, the abnormal jitter response control of the chemical production equipment is performed. Specifically, through an automated control system, the gear rotational speed adjustment data and the centrifugal rotational speed adjustment data are integrated into the control strategy to monitor the jitter condition of the device in real time. When the jitter frequency or load returns to normal, the operating state of the device is automatically adjusted to obtain the abnormal jitter response measures of the device. For example, when the jitter frequency of the device drops to the normal range, the rotational speed and load of the device are automatically adjusted, and the execution time and effect of the response measures are recorded.

[0139] In this specification, a chemical production control model generation system is also provided for performing the above-mentioned chemical production control model generation method. The chemical production control model generation system includes:

[0140] A chemical production data acquisition module, which is used to obtain products in the chemical production process; collect the original production data of the products in the chemical production process to obtain the original chemical production data; and perform data preprocessing on the original chemical production data to obtain the standard chemical production data.

[0141] A chemical reaction index analysis module, which is used to divide the production stages of the standard chemical production data to obtain the chemical production stage data; determine the chemical reaction condition indexes for the chemical production stage data to generate the chemical reaction condition indexes; and perform production index offset detection on the chemical reaction condition indexes to obtain the production index offset data.

[0142] An equipment abnormal operation detection module, which is used to extract the operation parameters of the production equipment from the standard chemical production data to obtain the production equipment operation data; map the operation state of the production equipment according to the production index offset data to generate the equipment operation state data; and perform equipment abnormal operation detection on the equipment operation state data to obtain the equipment abnormal operation data.

[0143] A chemical production control model generation module, which is used to perform production offset optimization control on the products in the chemical production process according to the production index offset data to obtain the production offset optimization measures; perform production equipment operation response control on the equipment abnormal operation data to obtain the equipment abnormal operation response measures; and generate a chemical production control model based on the production offset optimization measures and the equipment abnormal operation response measures to obtain the chemical production control model.

[0144] Through the chemical production data collection module, the original production data of products in the chemical production process is collected and preprocessed to obtain standard chemical production data, which can ensure that the data for subsequent analysis and processing has a unified format and quality, providing a reliable data basis for the precise control of chemical production and avoiding production control errors caused by non-standard and inaccurate data. Through the chemical reaction index analysis module, the standard chemical production data is divided into production stages to obtain chemical production stage data, and then the chemical reaction condition indicators are determined and production index deviation detection is carried out to obtain production index deviation data. This process realizes the refined management and monitoring of each stage of chemical production, can timely detect the small changes in chemical reaction conditions during the production process, provides a basis for subsequent targeted optimization control, and improves the quality and production efficiency of chemical products. Through the equipment abnormal operation detection module, the operation parameters of production equipment are extracted from the standard chemical production data to obtain production equipment operation data, the equipment operation status data is mapped and generated based on the production index deviation data, and equipment abnormal operation detection is carried out to obtain equipment abnormal operation data. This makes the operation status of production equipment closely related to production indicators, can accurately locate the impact of equipment abnormalities on production index deviation, facilitates taking measures in advance to prevent equipment failures, ensures the stable operation of production equipment, and reduces production interruptions and defective products caused by equipment problems. Through the chemical production control model generation module, production deviation optimization control is carried out on the products in the chemical production process according to the production index deviation data to obtain production deviation optimization measures, and at the same time, production equipment operation response control is carried out on the equipment abnormal operation data to obtain equipment abnormal operation response measures, and a chemical production control model is generated based on the two. This model comprehensively considers production indicators and equipment operation status, realizes the closed-loop control of chemical production, can adjust process parameters and equipment operation strategies in real time during the production process, makes the chemical production process always in the optimal state, and effectively improves the overall efficiency and safety of chemical production. Therefore, through data analysis technology, pattern recognition technology and automation control technology, the present invention realizes the detection of production index deviation amounts at each stage of chemical product production, and the abnormal operation of the chemical production equipment is identified by the production index deviation amount, thereby improving the accuracy of chemical production control and the production efficiency of chemical products.

[0145] A computer-readable storage medium stores a computer program, wherein the computer program is used to execute the above-mentioned chemical production control model generation method.

[0146] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes falling within the meaning and scope of the equivalent elements of the application documents within the present invention.

[0147] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating a chemical production control model, characterized in that: The following steps are involved: Step S1: Acquire chemical production process products; collect original data of the production process of the chemical production process products to obtain original chemical production data; Preprocess the raw data of chemical production to obtain standardized chemical production data; Step S2: dividing the standardized chemical production data into production stages to obtain chemical production stage data; Determine the chemical reaction condition index for the chemical production stage data to generate the chemical reaction condition index; perform production index deviation detection on the chemical reaction condition index to obtain production index deviation data; Step S3: extracting production equipment operation parameters from the standardized chemical production data to obtain production equipment operation data; Mapping the equipment operation status to the production equipment operation data according to the production index offset data to generate the equipment operation status data; Performing equipment abnormal operation detection on equipment operation status data to obtain equipment abnormal operation data; Step S4: performing production deviation optimization control on the chemical production process products according to the production index deviation data to obtain production deviation optimization measures; The production equipment operation response control is performed on the equipment abnormal operation data to obtain the equipment abnormal operation response measures; the chemical production control model is generated based on the production deviation optimization measures and the equipment abnormal operation response measures to obtain the chemical production control model.

2. The chemical production control model generation method according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: extracting the production stage timestamp of the standardized chemical production data to obtain the production stage timestamp; marking the production stage of the standardized chemical production data according to the production stage timestamp to generate production stage identification data; Step S22: classifying the production stage identification data into stage identification categories to obtain production stage identification categories; dividing the production stages into production stages according to the production stage identification categories to obtain chemical production stage data; Step S23: performing chemical production stage status identification on the chemical production stage data to obtain chemical production stage status data; performing chemical product chemical reaction condition detection on the chemical production stage status data to generate stage chemical reaction data; Step S24: judging the reaction condition index of the production stage on the stage chemical reaction data to generate the chemical reaction condition index; determining the production stage chemical reaction index benchmark according to the chemical reaction condition index to obtain the stage chemical reaction index benchmark; Step S25: performing stage chemical reaction index abnormality detection on the stage chemical reaction data to obtain reaction index abnormality data; performing production index offset measurement on the reaction index abnormal data according to the stage chemical reaction index benchmark to obtain production index offset data.

3. The chemical production control model generation method according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing production equipment feature recognition on the standardized chemical production data to obtain chemical production equipment; performing equipment operation parameter extraction on the chemical production equipment to obtain production equipment operation data; Step S32: determining the production stage of the production index offset data to obtain the stage data of the offset; matching the stage equipment operation characteristics of the production equipment operation data according to the stage data of the offset to generate the stage equipment operation data; Step S33: performing operation mode identification on the stage equipment operation data to obtain operation mode data; mapping the operation mode data to the equipment operation state to generate equipment operation state data; Step S34: Perform equipment abnormal operation detection on the equipment operation status data to obtain equipment abnormal operation data.

4. The chemical production control model generation method according to claim 3, characterized in that: Step S34 includes the following steps: Step S341: classify the equipment in the operation stage according to the equipment operation status data to obtain equipment type data; match the equipment type data with the equipment in the chemical production stage to generate equipment data corresponding to the stage; Step S342: performing chemical production process operation determination on the equipment data corresponding to the stage to obtain equipment process operation data; performing chemical equipment temperature identification on the equipment process operation data to obtain chemical equipment temperature data; Step S343: locate the abnormal temperature area of ​​the chemical equipment temperature data to obtain the abnormal temperature area of ​​the equipment; perform chemical rotary centrifugal equipment parameter detection on the equipment operation status data according to the abnormal temperature area of ​​the equipment to generate the rotary centrifugal equipment parameters; Step S344: performing abnormal centrifugal speed detection on the parameters of the rotating centrifugal equipment to obtain the equipment part with abnormal speed; performing abnormal jitter state identification on the equipment part with abnormal speed to generate abnormal jitter data of the equipment; Step S345: integrating the abnormal temperature area of ​​the device and the abnormal jitter data of the device into the abnormal operation data of the device to obtain the abnormal operation data of the device.

5. The chemical production control model generation method according to claim 4, characterized in that: Step S4 includes the following steps: Step S41: determining the offset indicator type of the production indicator offset data to obtain offset indicator type data; performing production offset optimization control on the chemical production process product according to the offset indicator type data to obtain production offset optimization measures; Step S42: performing device temperature abnormality response control on the device abnormal temperature area to obtain device temperature abnormality response measures; Step S43: performing device abnormal jitter response control on the device abnormal jitter data to obtain device abnormal jitter response measures; Step S44: performing chemical production control on chemical production equipment according to the production deviation optimization measures and the equipment abnormal operation response measures to obtain chemical production control data; constructing a chemical production control model based on the chemical production control data to obtain a chemical production control pre-model; Step S45: training the chemical production control pre-model by using the production deviation optimization measures and the equipment abnormal operation response measures to obtain a chemical production control training model; Step S46: Perform model cross-validation evaluation on the chemical production control training model to obtain chemical production control model evaluation data; adjust model parameters of the chemical production control training model using the chemical production control model evaluation data to obtain a chemical production control model.

6. The chemical production control model generation method according to claim 5, characterized in that: Step S41 includes the following steps: Step S411: determining the offset indicator type of the production indicator offset data to obtain offset indicator type data, wherein the offset indicator type data includes reaction conversion rate offset data and product quality offset data; Step S412: determining the reaction catalyst for the reaction conversion rate deviation data to obtain reaction catalyst data; performing dosage detection on the reaction catalyst data to produce the reaction catalyst amount; Step S413: measuring the conversion rate offset of the reaction conversion rate offset data to produce the conversion rate offset; determining the amount of chemical production catalyst added to the reaction catalyst amount according to the conversion rate offset to obtain the production catalyst added amount; Step S414: Controlling the amount of chemical catalyst for the chemical production process product according to the amount of production catalyst added to obtain chemical catalyst amount addition data; Step S415: determining the product impurity type of the product quality deviation data to obtain product impurity type data; determining the impurity type content of the product impurity type data to generate the impurity type content; and adding an impurity neutralizer to the product of the chemical production process according to the impurity type content to obtain impurity neutralizer addition data; Step S416: Use the chemical catalyst addition data and the impurity neutralizer dosage data to perform chemical production deviation optimization control on the chemical production process products to obtain production deviation optimization measures.

7. The chemical production control model generation method according to claim 5, characterized in that: Step S42 includes the following steps: Step S421: performing device area thermal imaging processing on the device abnormal temperature area to obtain a device thermal imaging map; performing abnormal temperature distribution recognition on the device thermal imaging map to generate temperature abnormality distribution data; Step S422: performing temperature-affected equipment detection on chemical production equipment according to the temperature anomaly distribution data to obtain temperature anomaly impact data; Step S423: identifying the affected device structure position of the temperature abnormality impact data to generate the affected device structure position data; determining the temperature impact degree of the affected device structure position data to obtain the temperature impact degree; Step S424: based on the affected equipment structure position data, the equipment position cooling system of the chemical production equipment is started to obtain cooling system start-up data; based on the degree of temperature influence, the equipment cooling system gear position control of the chemical production equipment is performed to generate equipment cooling control data; Step S425: Perform equipment temperature abnormality response control according to the cooling system startup data and the equipment cooling control data to obtain equipment temperature abnormality response measures.

8. The method for generating a chemical production control model according to claim 5, characterized in that: Step S43 also includes the following steps: Step S431: performing jitter frequency detection on abnormal jitter data of the equipment to obtain an abnormal jitter frequency value; measuring the equipment operating speed of the chemical production equipment according to the abnormal jitter frequency value to generate jitter equipment operating speed data; Step S432: monitoring the equipment load condition of the jitter equipment running speed data to obtain the jitter equipment load data; recording the abnormal load of the jitter equipment load data to generate the equipment abnormal load data; Step S433: extracting the speed load value from the abnormal load data of the equipment to obtain the abnormal speed load value; reducing the gear transmission speed of the chemical production equipment based on the abnormal speed load value to generate gear speed adjustment data; Step S434: reducing the centrifugal speed of the chemical production equipment based on the abnormal speed load value, and generating centrifugal speed adjustment data; Step S435: performing equipment abnormal vibration response control on the chemical production equipment according to the gear speed adjustment data and the centrifugal speed adjustment data, and obtaining equipment abnormal vibration response measures.

9. A chemical production control model generation system, characterized in that: Used to execute the chemical production control model generation method as claimed in claim 1, the chemical production control model generation system comprises: The chemical production data acquisition module is used to obtain chemical production process products; collect the original data of the chemical production process products to obtain the original data of chemical production; pre-process the original data of chemical production to obtain standardized chemical production data; The chemical reaction index analysis module is used to divide the standardized chemical production data into production stages to obtain chemical production stage data; determine the chemical reaction condition index of the chemical production stage data to generate the chemical reaction condition index; perform production index deviation detection on the chemical reaction condition index to obtain production index deviation data; The equipment abnormal operation detection module is used to extract the production equipment operation parameters from the standardized chemical production data to obtain the production equipment operation data; map the production equipment operation data to the equipment operation status according to the production index offset data to generate the equipment operation status data; perform equipment abnormal operation detection on the equipment operation status data to obtain the equipment abnormal operation data; The chemical production control model generation module is used to perform production deviation optimization control on chemical production process products according to production index deviation data to obtain production deviation optimization measures; perform production equipment operation response control on equipment abnormal operation data to obtain equipment abnormal operation response measures; generate a chemical production control model based on production deviation optimization measures and equipment abnormal operation response measures to obtain a chemical production control model.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed, the chemical production control model generation method as described in any one of claims 1 to 8 is implemented.

Images