An adaptive control system for chemical production with process quality detection

Abstract

The invention discloses a chemical production adaptive control system for process quality detection, which relates to the technical field of production control. The system comprises: a fermentation record retrieval module: retrieval of process records of continuous multi-stage fermentation of target chemical raw materials by serially connecting fermentation tanks; a first record data extraction module: extraction of fermentation state data and control data in fermentation records; a fermentation control evaluation module: introduction of evaluation function to analyze control data and obtain production fitness; a prediction model construction module: training a production fitness prediction model based on fermentation state data and fitness; a production fitness acquisition module: using a model to predict real-time fermentation state and obtain predicted production fitness; a control instruction generation module: if the predicted fitness does not meet a threshold, a control instruction is issued; and a fermentation production adjustment module: adjusting the fermentation production process according to the control instruction. Thus, the technical effect of improving the control responsiveness and control efficiency and improving the stability of fermentation quality is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of production control, and particularly to an adaptive control system for chemical production with process quality detection. Background Art

[0002] In the process of chemical production, the fermentation link is a key step in the production of many chemical products, and its quality control has an important impact on the performance and yield of the final product. Traditional fermentation process control usually relies on manual experience or preset fixed parameters, by monitoring and adjusting the parameters of the fermentation tank. There are mainly the following technical drawbacks: on the one hand, manual experience control lacks accurate grasp of the complex dynamic characteristics of the fermentation process, and it is difficult to adapt to the changes of raw material characteristics and environmental conditions in real time, resulting in unstable fermentation quality; on the other hand, fixed parameter control cannot dynamically adjust fermentation parameters according to real-time monitoring data, and it is difficult to effectively respond to sudden situations and abnormal fluctuations in the fermentation process. In addition, traditional control methods also have deficiencies in regulation responsiveness and regulation efficiency, and cannot optimize and adjust the fermentation process in a timely and accurate manner, thus affecting the overall efficiency and product quality of chemical production. Summary of the Invention

[0003] The present invention provides an adaptive control system for chemical production with process quality detection to solve the technical problems of low regulation responsiveness and regulation efficiency and unstable fermentation quality in the prior art, and to achieve the technical effects of improving regulation responsiveness and regulation efficiency and enhancing the stability of fermentation quality.

[0004] An adaptive control system for chemical production with process quality detection provided by the present invention includes:

[0005] A fermentation record retrieval module for retrieving fermentation records, where the fermentation records refer to the records of continuous multi-stage fermentation of target chemical raw materials through a series of fermentation tanks.

[0006] A first record data extraction module for extracting first record data from the fermentation records, where the first record data includes first fermentation state data and first fermentation control data.

[0007] A fermentation control evaluation module for evaluating and analyzing the first fermentation control data by introducing a fermentation control evaluation function to obtain a first production fitness.

[0008] A prediction model construction module for performing machine supervised learning on a first data set composed of the first fermentation state data and the first production fitness to obtain a production fitness prediction model.

[0009] A production fitness acquisition module, configured to perform predictive analysis on real-time fermentation state data of the target chemical raw material dynamically monitored through the production fitness prediction model to obtain a predicted real-time production fitness.

[0010] A control instruction generation module, configured to issue a first adaptive control instruction if the predicted real-time production fitness does not meet a predetermined fitness threshold.

[0011] A fermentation production adjustment module, configured to adjust the fermentation production of the target chemical raw material based on the first adaptive control instruction.

[0012] In a feasible implementation manner, the execution steps of the system include:

[0013] Set up a preheating tower - flash tank dual device to preheat the chemical raw material, and use secondary steam to heat the waste liquid to obtain preheated pre-production materials.

[0014] Read the liquefaction plan, and perform liquefaction on the preheated pre-production materials according to the liquefaction plan to obtain the target chemical raw material, where the target chemical raw material refers to the pre-treated chemical raw material.

[0015] In a feasible implementation manner, the expression of the fermentation control evaluation function is as follows:

[0016] ;

[0017] Where F refers to the first production fitness, E refers to the first fermentation efficiency in the first fermentation control data, refers to the maximum possible value of the fermentation efficiency, P refers to the first ethanol purity in the first fermentation control data, refers to the maximum possible value of the ethanol purity, C refers to the first fermentation energy consumption in the first fermentation control data, and are the weight coefficients of the fermentation efficiency, ethanol purity, fermentation energy consumption and the comprehensive efficiency purity energy consumption ratio respectively, and .

[0018] In a feasible implementation manner, performing machine supervised learning on a first data set formed based on the first fermentation state data and the first production fitness to obtain a production fitness prediction model, including:

[0019] Traverse the first feature in the predetermined fermentation state features in the first fermentation state data to obtain a first state parameter.

[0020] When the first state parameter is within the first predetermined parameter threshold of the first feature, add the first state parameter to the first data set.

[0021] Among them, the described predetermined fermentation state characteristics include fermentation temperature, pH value, sugar concentration, yeast concentration, and the rate of miscellaneous bacteria.

[0022] In a feasible implementation manner, when the first state parameter is not within the first predetermined parameter threshold, an abnormal control warning is given for the first characteristic.

[0023] In a feasible implementation manner, after predicting and analyzing the real-time fermentation state data of the dynamically monitored target chemical raw material through the production fitness prediction model to obtain the predicted real-time production fitness, it further includes:

[0024] If the predicted real-time production fitness meets the predetermined fitness threshold, the real-time distillation state data of the target chemical raw material is dynamically monitored.

[0025] Traverse the real-time distillation state data in the differential pressure distillation database to obtain the most similar distillation state data, and obtain the most similar distillation control data corresponding to the most similar distillation state data.

[0026] Read the predetermined distillation control characteristics, and perform feature matching on the most similar distillation control data based on the predetermined distillation control characteristics to obtain distillation control characteristic parameters.

[0027] Perform normalized weighted calculation on the distillation control characteristic parameters to obtain the distillation fitness.

[0028] If the distillation fitness does not meet the predetermined fitness threshold, a second adaptive control instruction is issued.

[0029] Adjust the differential pressure distillation of the target chemical raw material based on the second adaptive control instruction.

[0030] In a feasible implementation manner, traversing the real-time distillation state data in the differential pressure distillation database to obtain the most similar distillation state data, and obtaining the most similar distillation control data corresponding to the most similar distillation state data, includes:

[0031] Extract any data group in the differential pressure distillation database.

[0032] Successively perform vectorization processing on the real-time distillation state data and any distillation state data in the any data group to respectively obtain a real-time distillation state vector and an any distillation state vector.

[0033] Calculate any similarity between the real-time distillation state vector and the any distillation state vector.

[0034] When any of the similarities meets a predetermined traversal constraint, use the any distillation state data as the most similar distillation state data.

[0035] Use any distillation control data in the any data group as the most similar distillation control data.

[0036] In a feasible implementation manner, the predetermined distillation control features at least include distillation efficiency, steam consumption, and ethanol purity.

[0037] The present invention discloses an adaptive control system for chemical production with process quality detection, including: a fermentation record retrieval module for retrieving fermentation records, where the records are process records of continuously multi-stage fermenting a target chemical raw material through a series of fermenters; a first record data extraction module for extracting first record data from the fermentation records, including first fermentation state data and first fermentation control data; a fermentation control evaluation module for introducing a fermentation control evaluation function to evaluate and analyze the first fermentation control data to obtain a first production fitness; a prediction model construction module for constructing a first data group based on the first fermentation state data and the first production fitness and training a production fitness prediction model using a machine supervised learning method; a production fitness acquisition module for predicting and analyzing real-time fermentation state data of the dynamically monitored target chemical raw material through the production fitness prediction model to obtain a predicted real-time production fitness; a control instruction generation module for issuing a first adaptive control instruction if the predicted real-time production fitness does not meet a predetermined fitness threshold; and a fermentation production adjustment module for adjusting the fermentation production process of the target chemical raw material based on the first adaptive control instruction. The adaptive control system for chemical production with process quality detection disclosed by the present invention solves the technical problems of low regulation responsiveness and regulation efficiency and unstable fermentation quality, and achieves the technical effects of improving regulation responsiveness and regulation efficiency and enhancing the stability of fermentation quality. Description of the Drawings

[0038] Figure 1 It is a schematic structural diagram of an adaptive control system for chemical production with process quality detection according to the present invention;

[0039] Figure 2 It is a schematic flow diagram of obtaining the most similar distillation control data in an adaptive control system for chemical production with process quality detection according to the present invention.

[0040] Description of the reference numerals: fermentation record retrieval module 11, first record data extraction module 12, fermentation control evaluation module 13, prediction model construction module 14, production fitness acquisition module 15, control instruction generation module 16, fermentation production adjustment module 17. Detailed Embodiments

[0041] The above technical solution will be described in detail below in conjunction with the specification drawings and specific embodiments to better understand the above technical solution. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments only for explaining the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention. In addition, it should be noted that for the sake of convenience of description, only the parts related to the present invention are shown in the drawings, rather than all of them.

[0042] Embodiment Figure 1 is a schematic flowchart of an adaptive control system for chemical production of process quality detection according to the present invention. Among them, the system includes:

[0043] A fermentation record retrieval module 11, configured to retrieve fermentation records, where the fermentation records refer to the records of continuous multi-stage fermentation of target chemical raw materials through a series of fermentation tanks.

[0044] Specifically, first, retrieve and obtain data records related to the fermentation process from the storage system of the production management end of the target scenario. The fermentation records refer to the data records generated by continuously multi-stage fermenting target chemical raw materials through multiple series-connected fermentation tanks during the chemical production process, covering key information during the fermentation process; Exemplarily, it usually includes information such as control parameters, control operations, and timestamps during the fermentation process, such as changes in the temperature, pH value, stirring speed, sugar concentration, yeast concentration, etc. of the fermentation tank, providing basic data for subsequent analysis and processing.

[0045] By retrieving the fermentation records, the system can obtain comprehensive and detailed fermentation process data, providing a rich information basis for subsequent fermentation control evaluation and prediction model construction.

[0046] A first record data extraction module 12, configured to extract first record data from the fermentation records, where the first record data includes first fermentation state data and first fermentation control data.

[0047] Specifically, the first record data refers to the key data selected from the retrieved fermentation records that are specific and related to the fermentation process state and control operations, such as the data with the highest frequency of occurrence of working conditions or the best quality stability. Among them, the first fermentation state data refers to the parameter data reflecting the current operating state of the fermentation process, such as the temperature, pH value, sugar concentration, yeast concentration, etc. in the fermentation tank; the first fermentation control data refers to the operating parameters used to control the fermentation conditions during the fermentation process, such as the stirring intensity, ventilation volume, types and amounts of added nutrients, etc.

[0048] The function of extracting the first record data is to provide accurate data support for the evaluation and prediction of the fermentation process. By screening out key representative fermentation state data and control data, the system can more accurately evaluate the operation of the fermentation process, analyze the effectiveness of fermentation control operations, and provide high-quality input data for the subsequent construction of a production fitness prediction model.

[0049] The fermentation control evaluation module 13 is used to introduce a fermentation control evaluation function to evaluate and analyze the first fermentation control data to obtain the first production fitness.

[0050] Specifically, the fermentation control evaluation function is a pre-defined function, which is used to map the multi-dimensional and multi-dimensional parameters in the first fermentation control data into a comprehensive and intuitive numerical evaluation value, that is, the first production fitness, so as to quantify the control effect of the fermentation process and facilitate the comparison and discrimination of the fermentation production levels under different states.

[0051] The above quantitative evaluation path not only improves the objectivity and accuracy of the fermentation process evaluation, but also provides high-quality training data for the subsequent construction of the prediction model. By calculating the first production fitness, the system can more accurately identify the advantages and disadvantages in the fermentation process, so as to provide a scientific basis for adaptive control.

[0052] In some embodiments, the expression of the fermentation control evaluation function is as follows:

[0053] ;

[0054] Among them, F refers to the first production fitness, E refers to the first fermentation efficiency in the first fermentation control data, refers to the maximum possible value of the fermentation efficiency, P refers to the first ethanol purity in the first fermentation control data, refers to the maximum possible value of the ethanol purity, C refers to the first fermentation energy consumption in the first fermentation control data, and are the weight coefficients of the fermentation efficiency, ethanol purity, fermentation energy consumption and the comprehensive efficiency purity energy consumption ratio respectively, and .

[0055] Specifically, the fermentation control evaluation function includes multiple sub-items and corresponding weight coefficients for evaluating the fermentation efficiency, product purity, fermentation energy consumption and energy consumption ratio efficiency. Among them, the sum of the weight coefficients is 1, ensuring the balance of the evaluation function.

[0056] Specifically, is used to evaluate the fermentation efficiency of the first fermentation control data, where is the maximum possible value of the fermentation efficiency, which can be set based on experimental data or theoretical analysis, representing the optimal fermentation efficiency. The closer the first fermentation efficiency in the first fermentation control data is to , the better it can be considered in terms of efficiency, and the closer the value is to 1.

[0057] Specifically, is used to evaluate the product purity of the first fermentation control data (i.e., the purity of the produced ethanol). Among them, is the maximum possible value of the ethanol purity, which is also set based on process design or experiments. The closer the first ethanol purity in the first fermentation control data is to , the better it can be considered in terms of efficiency, and the closer the value is to 1.

[0058] Specifically, is used to evaluate the first fermentation energy consumption of the first fermentation control data, that is, the evaluation of the absolute value of the energy consumption. The lower the energy consumption, the larger the value of this sub-item; is the evaluation of the energy consumption efficiency of the first fermentation control data, that is, the energy consumption ratio efficiency. The higher the fermentation efficiency and product purity generated per unit energy consumption, the higher the comprehensive efficiency of the fermentation process can be considered, and the larger the value of this sub-item.

[0059] By using the fermentation control evaluation function, the system can quantify the performance of each key fermentation control data and calculate the comprehensive fitness F according to the deviation degree of each data; it ensures the balance of each process condition, avoids the excessive influence of a single index on the production result. At the same time, it provides accurate input data for the prediction model and adaptive control, thereby improving the overall quality control level and production efficiency of the fermentation process.

[0060] The prediction model construction module 14 is used to perform machine supervised learning on the first data set composed of the first fermentation state data and the first production fitness to obtain a production fitness prediction model.

[0061] Specifically, by using the first fermentation state data marked with the first production fitness as training data, training the production fitness prediction model based on machine learning, enabling it to obtain the mapping relationship between the input data (the first fermentation state data) and the output target (the first production fitness), so as to have the ability to quickly predict the production fitness of the real-time fermentation process according to the input real-time fermentation state data, providing a basis for subsequent adaptive control, and helping to timely discover potential problems in the fermentation process and dynamically adjust to the problems.

[0062] In some embodiments, the execution steps of the prediction model construction module 14 include:

[0063] Traverse the first feature among the predetermined fermentation state features in the first fermentation state data to obtain a first state parameter; when the first state parameter is within the first predetermined parameter threshold of the first feature, add the first state parameter to the first data group; wherein, the predetermined fermentation state features include fermentation temperature, pH value, sugar concentration, yeast concentration, and contamination rate.

[0064] Specifically, the predetermined fermentation state features refer to the key parameters preset during the fermentation process, such as fermentation temperature, pH value, sugar concentration, yeast concentration, and contamination rate, etc. They are the core indicators for monitoring and controlling the fermentation process and have an important impact on the quality and efficiency of the fermentation process; the first feature is any specific parameter selected from the predetermined fermentation state features.

[0065] Specifically, the first state parameter refers to the value corresponding to the first feature extracted from the first fermentation state data, such as the fermentation temperature value or pH value at a certain time point; the first predetermined parameter threshold is a reasonable range or standard value set for the first state parameter, used to determine whether the parameter meets the requirements of the fermentation process for a preliminary screening of the traversed first state parameters.

[0066] Specifically, first, select a first feature (such as fermentation temperature) from the predetermined fermentation state features, then traverse this feature in the first fermentation state data and extract the corresponding first state parameter (such as the fermentation temperature value at each time point); then, determine whether these first state parameters are within the first predetermined parameter threshold range. If a certain first state parameter meets the threshold condition, add it to the first data group, so as to screen out the key state parameters that meet the requirements of the fermentation process, ensure that the data used for training the prediction model is of high quality and representative, and further improve the accuracy and reliability of the model, enabling it to better predict the production fitness. Among them, the first data group is the basic data set for subsequent machine supervised learning, containing the fermentation state parameters that meet the requirements and the corresponding first production fitness.

[0067] In some embodiments, the execution steps of the prediction model construction module 14 further include: when the first state parameter is not within the first predetermined parameter threshold, perform an abnormal control warning on the first feature.

[0068] Specifically, if the first state parameter is not within the first predetermined parameter threshold, it means that the current first state parameter significantly deviates from the preset normal range. The system issues an alarm or prompt accordingly to remind the operator or the automated control system to pay attention to this abnormal situation, so as to timely discover and handle potential problems, prevent the fermentation process from further deviating from the normal state, and avoid a decline in product quality or a reduction in production efficiency.

[0069] Specifically, triggering the exception control warning mechanism for exception control warning includes generating alarm signals (such as sound alarms, visual cues, or system logging) and sending relevant information to the operator or the automated control system.

[0070] The production fitness acquisition module 15 is used to perform predictive analysis on the real-time fermentation state data of the dynamically monitored target chemical raw materials through the production fitness prediction model to obtain the predicted real-time production fitness.

[0071] Specifically, during the fermentation process, the fermentation state data of the target chemical raw materials is collected in real-time and continuously. This real-time fermentation state data reflects the real-time operation of the fermentation process, including various key parameters during the fermentation process, such as fermentation temperature, pH value, sugar concentration, yeast concentration, etc.; further, through predictive analysis of the real-time fermentation state data by the production fitness prediction model, the predicted real-time production fitness can be obtained, that is, the production fitness value predicted by the model based on the current fermentation state, which is used to evaluate whether the fermentation process is in an ideal state.

[0072] The role of this process is to apply the prediction model to the actual fermentation process to achieve real-time monitoring and evaluation of the fermentation process; through the predictive analysis of the model, the system can quickly determine whether the current fermentation process meets the expected production fitness requirements, thereby providing timely and accurate basis for subsequent adaptive control, helping to timely detect potential problems in the fermentation process, and taking corresponding adjustment measures to ensure the stability of the fermentation process and product quality.

[0073] In some embodiments, the execution steps of the production fitness acquisition module 15 include:

[0074] If the predicted real-time production fitness meets the predetermined fitness threshold, dynamically monitor the real-time distillation state data of the target chemical raw materials; traverse the real-time distillation state data in the differential pressure distillation database to obtain the most similar distillation state data, and obtain the most similar distillation control data corresponding to the most similar distillation state data; read the predetermined distillation control characteristics, and perform feature matching on the most similar distillation control data based on the predetermined distillation control characteristics to obtain the distillation control characteristic parameters; perform normalized weighted calculation on the distillation control characteristic parameters to obtain the distillation fitness; if the distillation fitness does not meet the predetermined fitness threshold, issue a second adaptive control instruction; adjust the differential pressure distillation of the target chemical raw materials based on the second adaptive control instruction.

[0075] Specifically, the differential pressure distillation database is a database that stores a large amount of historical distillation state data and corresponding control data, and is used to provide reference data; the most similar distillation state data refers to the data record in the above differential pressure distillation database that is closest to the current real-time distillation state data; the predetermined distillation control feature refers to the key control parameters preset during the distillation process, such as distillation efficiency, steam consumption, ethanol purity, etc.; the distillation fitness is a comprehensive evaluation index used to measure whether the control effect of the current distillation process meets the expectations.

[0076] Specifically, the real-time distillation state data includes: distillation temperature, which directly affects the separation efficiency of ethanol. Too high a temperature may cause ethanol volatilization loss, while too low a temperature will affect the separation effect; distillation pressure, the pressure settings of different distillation towers in the differential pressure distillation technology will affect the utilization efficiency of steam and the purity of ethanol; reflux ratio, which refers to the ratio of the amount of condensed liquid returned to the tower at the top of the tower to the amount of product withdrawn at the top of the tower. The size of the reflux ratio will affect the purity and output of ethanol; steam flow rate, the amount of steam flow directly affects the speed and efficiency of distillation; ethanol concentration, the change of ethanol concentration during the distillation process can reflect whether the distillation effect is good.

[0077] Specifically, when the predicted real-time production fitness meets the predetermined fitness threshold, the system dynamically monitors the real-time distillation state data of the target chemical raw material through a pre-set sensing network; then, according to the obtained real-time distillation state data, it traverses the differential pressure distillation database to find the distillation state data most similar to the current state, and obtains the corresponding most similar distillation control data; then, reads the predetermined distillation control feature, performs feature matching on the most similar distillation control data, extracts the distillation control feature parameters, and performs normalized weighted calculation on the extracted parameters to obtain the distillation fitness. If the distillation fitness does not meet the predetermined fitness threshold, a second adaptive control instruction is issued to adjust the differential pressure distillation process until the distillation fitness meets the predetermined fitness threshold.

[0078] Specifically, if the distillation fitness meets the predetermined fitness threshold, it can be considered that the current distillation control feature meets the requirements and no adjustment is required. At this time, the system continuously monitors and collects the distillation process according to the predetermined monitoring granularity, and repeats the above production fitness evaluation process.

[0079] The role of the above process is to combine the monitoring of the fermentation process with the monitoring of the distillation process to achieve comprehensive monitoring and dynamic adjustment of the entire chemical production process. By matching with historical data, it can be adjusted more accurately according to past successful operating conditions, avoiding the deviation caused by over-reliance on static parameter settings; at the same time, guided by the adaptive control instruction, the control efficiency of the distillation process is improved, the energy consumption can be significantly reduced and the product quality can be improved, ensuring that the entire production process remains coordinated and efficient in multiple process steps.

[0080] In some implementations, the predetermined distillation control features at least include distillation efficiency, steam consumption, and ethanol purity.

[0081] In some implementations, as Figure 2 shown, traversing the real-time distillation state data in the differential pressure distillation database to obtain the most similar distillation state data, and acquiring the most similar distillation control data corresponding to the most similar distillation state data, includes:

[0082] Extracting any data group from the differential pressure distillation database; sequentially performing vectorization processing on the real-time distillation state data and any distillation state data in the any data group to respectively obtain a real-time distillation state vector and an arbitrary distillation state vector; calculating any similarity between the real-time distillation state vector and the arbitrary distillation state vector; when the arbitrary similarity meets the predetermined traversal constraint, regarding the arbitrary distillation state data as the most similar distillation state data; and regarding the arbitrary distillation control data in the any data group as the most similar distillation control data.

[0083] Specifically, first, extract any group of data from the differential pressure distillation database, including distillation state data and corresponding distillation control data; then, perform vectorization processing on the real-time monitored distillation state data and any distillation state data in the database respectively, that is, convert the distillation state data including multiple-dimensional state features into vectors in a multi-dimensional space to obtain a real-time distillation state vector and an arbitrary distillation state vector, which is convenient for mathematical calculation and similarity comparison; then, calculate the similarity between these two vectors. If the similarity meets the predetermined traversal constraint condition, it indicates that the similarity between the current real-time distillation state and a certain historical data group is high enough, and this group of historical data can be used as a reference for the current distillation state. Furthermore, mark the distillation state data in the database as the most similar distillation state data, and mark the corresponding distillation control data as the most similar distillation control data.

[0084] Specifically, the similarity calculation can be based on, for example, Euclidean distance, cosine similarity, etc., so as to provide a quantitative basis for determining which historical data in the history can best represent the current distillation process.

[0085] The function of the above process is to find the historical data most similar to the current distillation state through data matching, so as to provide a reference for subsequent distillation control. In this way, the system can draw on historical experience, optimize the current distillation control strategy, and improve the stability and efficiency of the distillation process.

[0086] The control instruction generation module 16 is used to issue a first adaptive control instruction if the predicted real-time production fitness does not meet the predetermined fitness threshold.

[0087] Specifically, if the predicted real-time production fitness does not meet the predetermined fitness threshold, it can be considered that there is a risk in the current production process and regulation is required. Further, a first adaptive control instruction is generated to dynamically adjust the fermentation process to optimize the fermentation conditions.

[0088] The fermentation production adjustment module 17 is used to adjust the fermentation production of the target chemical raw material based on the first adaptive control instruction.

[0089] Exemplarily, to adjust the fermentation production of the target chemical raw material, first, the system determines the fermentation parameters to be adjusted (such as temperature, pH value, stirring speed, etc.) according to the first adaptive control instruction; then, in combination with an optimization algorithm (such as genetic algorithm, particle swarm optimization algorithm, etc.), under the guidance of the production fitness prediction model (i.e., taking the production fitness prediction model as the cost function), the previously determined fermentation parameters are iteratively optimized and adjusted. Among them, the optimization algorithm dynamically adjusts the fermentation parameters according to the output of the prediction model (i.e., the predicted production fitness) to find the optimal parameter combination.

[0090] The role of the above process is to optimize the fermentation process by dynamically adjusting the fermentation parameters, ensuring the stability and efficiency of the fermentation process. Among them, in combination with the optimization algorithm and the production fitness prediction model, the system can reduce manual intervention, improve the automation level of production, more accurately adjust the fermentation parameters, improve the fermentation efficiency, reduce energy consumption, and improve the product quality.

[0091] In some embodiments, the execution steps of the system include:

[0092] Set up a preheating tower - flash tank dual device to preheat the chemical raw material, and use secondary steam to heat the waste liquid to obtain preheated and pre-produced materials; read the liquefaction plan, and liquefy the preheated and pre-produced materials according to the liquefaction plan to obtain the target chemical raw material, where the target chemical raw material refers to the pre-treated chemical raw material.

[0093] Specifically, the preheating tower - flash tank dual device is a combination of equipment for preheating chemical raw materials. Through the coordinated action of the preheating tower and the flash tank, secondary steam is used to heat the raw materials to improve energy utilization efficiency; the preheated chemical raw material is called the preheated and pre-produced material.

[0094] Specifically, the liquefaction plan refers to a specific plan for liquefying the preheated and pre-produced materials in advance, including parameters such as liquefaction method, temperature, enzyme addition amount, etc. Exemplarily, the liquefaction plan adopts the one-time enzyme addition and one-time jet liquefaction method, and improves the liquefaction efficiency by adjusting the liquefaction tank capacity and liquefaction temperature (above 87°C) to solve the problems of low enzyme activity and difficult liquefaction.

[0095] Through the above steps, by optimizing the pretreatment steps, the liquefaction efficiency and quality of chemical raw materials are improved, providing high-quality raw materials for the subsequent fermentation process, ensuring that the raw materials are in good condition when entering the fermentation link, thereby improving the fermentation efficiency and product quality.

[0096] In summary, the self-adaptive control system for chemical production with process quality detection provided by the present invention has the following technical effects:

[0097] First, by introducing a production fitness prediction model constructed by machine supervised learning, it is possible to quickly and accurately predict and analyze real-time fermentation state data, thereby realizing real-time monitoring and dynamic adjustment of the fermentation process. The above data-driven prediction and analysis can effectively overcome the problem of regulation lag caused by insufficient manual experience or unreasonable fixed parameter settings in traditional control methods, and significantly improve the regulation responsiveness. Secondly, the self-adaptive control system can dynamically generate control instructions according to the prediction results, timely adjust the fermentation parameters, optimize the fermentation process, thereby improving the regulation efficiency and ensuring the stability of the fermentation process and the reliability of product quality. At the same time, it can also adapt to the characteristics of different batches of raw materials and changes in the fermentation environment, with strong versatility and adaptability, providing strong support for the intelligent control of the chemical production process. Generally speaking, the present invention achieves the technical effects of improving regulation responsiveness and regulation efficiency and improving the stability of fermentation quality.

[0098] It should be understood that the disclosed embodiments of the present invention and the above descriptions enable those skilled in the art to implement the present invention using the present invention. At the same time, the present invention is not limited to the above-mentioned part of the embodiments. It should be understood that those of ordinary skill in the art can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A chemical production adaptive control system for process quality detection, characterized in that: include: A fermentation record retrieval module, used to retrieve fermentation records, wherein the fermentation records refer to records of continuous multi-stage fermentation of target chemical raw materials through serially connected fermentation tanks; A first record data extraction module, used to extract first record data in the fermentation record, wherein the first record data includes first fermentation state data and first fermentation control data; A fermentation control evaluation module, used for introducing a fermentation control evaluation function to evaluate and analyze the first fermentation control data to obtain a first production fitness; A prediction model building module, used for performing machine supervised learning on a first data set formed based on the first fermentation state data and the first production fitness to obtain a production fitness prediction model; A production fitness acquisition module is used to predict and analyze the real-time fermentation state data of the target chemical raw material dynamically monitored through the production fitness prediction model to obtain a predicted real-time production fitness; A control instruction generating module, configured to issue a first adaptive control instruction if the predicted real-time production fitness does not meet a predetermined fitness threshold; A fermentation production adjustment module, used for adjusting the fermentation production of the target chemical raw material based on the first adaptive control instruction; The expression of the fermentation control evaluation function is as follows: Wherein, F refers to the first production fitness, E refers to the first fermentation efficiency in the first fermentation control data, and E max refers to the maximum possible value of the fermentation efficiency, P refers to the first ethanol purity in the first fermentation control data, and P max refers to the maximum possible value of ethanol purity, C refers to the first fermentation energy consumption in the first fermentation control data, ω1, ω2, ω3 and ω4 are weight coefficients of fermentation efficiency, ethanol purity, fermentation energy consumption and comprehensive efficiency-purity energy consumption ratio, respectively, and ω1+ω2+ω3+ω4=1; After predicting and analyzing the real-time fermentation state data of the target chemical raw material monitored dynamically through the production fitness prediction model to obtain the predicted real-time production fitness, the method further includes: If the predicted real-time production fitness meets the predetermined fitness threshold, dynamically monitoring the real-time distillation state data of the target chemical raw material; Traversing the real-time distillation state data in a differential pressure distillation database to obtain the most similar distillation state data, and acquiring the most similar distillation control data corresponding to the most similar distillation state data; Reading a predetermined distillation control feature, and performing feature matching on the most similar distillation control data based on the predetermined distillation control feature to obtain a distillation control feature parameter; Performing normalized weighted calculation on the distillation control characteristic parameters to obtain distillation fitness; If the distillation fitness does not meet the predetermined fitness threshold, issuing a second adaptive control instruction; The differential pressure distillation of the target chemical raw material is adjusted based on the second adaptive control instruction.

2. According to the chemical production adaptive control system for process quality detection according to claim 1, it is characterized in that: include: A preheating tower-flash tank dual device is set up to preheat the chemical raw materials, and the waste liquid is heated by secondary steam to obtain preheated pre-production materials; The liquefaction plan is read, and the preheated and pre-produced materials are liquefied according to the liquefaction plan to obtain the target chemical raw materials, wherein the target chemical raw materials refer to the chemical raw materials after pretreatment.

3. According to the chemical production adaptive control system for process quality detection according to claim 1, it is characterized in that: Performing machine supervised learning on a first data set formed based on the first fermentation state data and the first production fitness to obtain a production fitness prediction model, including: Traversing a first feature of the predetermined fermentation state features in the first fermentation state data to obtain a first state parameter; When the first state parameter is within a first predetermined parameter threshold of the first feature, adding the first state parameter to the first data set; The predetermined fermentation state characteristics include fermentation temperature, pH value, sugar concentration, yeast concentration and foreign bacteria rate.

4. According to the chemical production adaptive control system for process quality detection according to claim 3, it is characterized in that: When the first state parameter is not within the first predetermined parameter threshold, an abnormal control warning is issued for the first feature.

5. According to the chemical production adaptive control system for process quality detection of claim 1, it is characterized in that: Traversing the real-time distillation state data in the differential pressure distillation database to obtain the most similar distillation state data, and obtaining the most similar distillation control data corresponding to the most similar distillation state data, including: Extracting any data set in the differential pressure distillation database; Sequentially performing vectorization processing on the real-time distillation state data and any distillation state data in the arbitrary data group to obtain a real-time distillation state vector and an arbitrary distillation state vector respectively; Calculate and obtain any similarity between the real-time distillation state vector and the arbitrary distillation state vector; When any similarity meets the predetermined traversal constraint, taking any distillation state data as the most similar distillation state data; Any distillation control data in the arbitrary data group is used as the most similar distillation control data.

6. According to the chemical production adaptive control system for process quality detection of claim 1, it is characterized in that: The predetermined distillation control characteristics include at least distillation efficiency, steam usage and ethanol purity.

Images