Digital regulation and control method and system for disinfectant production

Abstract

The invention discloses a disinfectant production-oriented digital regulation and control method and system, and belongs to the technical field of digital production, and the method comprises the steps: receiving a disinfectant production task, and building a disinfectant production decision space; setting a disinfectant production optimizing factor; activating a disinfectant production prediction multichannel to generate a disinfectant production regime domain; based on the disinfectant production optimization factors, constructing a disinfectant production fitness evaluation network, and performing optimization analysis on a disinfectant production scheme domain to obtain a disinfectant production digital strategy; and the disinfectant is produced according to the disinfectant production raw materials and the disinfectant production digital strategy. The problems that in the prior art, the production efficiency is low, the product quality is unstable and byproducts are difficult to control due to the fact that the disinfectant production process depends on artificial experience and lacks an accurate digital regulation and control means are solved.

Description

Technical Field

[0001] The present invention relates to the field of digital production technology, and in particular to a digital control method and system for disinfectant production. Background Art

[0002] With the continuous development of industrial automation and intelligent manufacturing technology, digital control methods have been widely used in various production processes, especially in the fields of chemical, pharmaceutical, food, etc. Digital production control has become a key means to improve production efficiency, ensure product quality and reduce costs. Disinfectants are essential products in daily life, and their production process requires precise control of the ratio of various raw materials, reaction conditions and the content of disinfectant ingredients in the final product.

[0003] At present, the disinfectant production process usually relies on manual control and empirical data, lacking effective digital management and intelligent decision-making systems. This leads to low production efficiency, difficulty in handling by-products, and inability to optimize production strategies in real time, affecting the flexibility and sustainability of production. With the increasing demand for the purity of disinfectant ingredients, the ease of by-product purification, and disinfection performance, the traditional production model can no longer meet the requirements of efficient, environmentally friendly, and high-quality production. In order to solve this problem, it is urgently necessary to use a digital control method and system for disinfectant production to solve the problem that the disinfectant production process in the prior art relies on manual experience and lacks precise digital control means, resulting in low production efficiency, unstable product quality, and difficult to control by-products. Summary of the invention

[0004] This application provides a digital control method and system for disinfectant production, aiming to solve the problems in the prior art that the disinfectant production process relies on manual experience and lacks precise digital control means, resulting in low production efficiency, unstable product quality and difficult to control by-products.

[0005] In view of the above problems, the present application provides a digital control method and system for disinfectant production.

[0006] The first aspect disclosed in the present application provides a digital control method for disinfectant production, which includes receiving a disinfectant production task according to a disinfectant digital production terminal, wherein the disinfectant production task includes disinfectant production raw materials and disinfectant component expectations; loading disinfectant raw material information corresponding to the disinfectant production raw materials, performing digital control decisions on the disinfectant production raw materials in combination with the disinfectant component expectations, and establishing a disinfectant production decision space; setting disinfectant production optimization factors, wherein the disinfectant production optimization factors include disinfectant component purity, by-product purification ease, disinfection performance, and disinfectant production efficiency; activating disinfectant production prediction multi-channels, performing multilateral joint optimization on the disinfectant production decision space in combination with the disinfectant production optimization factors, and generating a disinfectant production solution domain; constructing a disinfectant production fitness evaluation network based on the disinfectant production optimization factors, and performing optimization analysis on the disinfectant production solution domain according to the disinfectant production fitness evaluation network to obtain a disinfectant production digital strategy; sending the disinfectant production digital strategy to the disinfectant digital production terminal, and the disinfectant digital production terminal performs disinfectant production according to the disinfectant production raw materials and the disinfectant production digital strategy.

[0007] Another aspect disclosed in the present application provides a digital control system for disinfectant production, the system comprising a production task receiving module, for receiving a disinfectant production task according to a disinfectant digital production terminal, wherein the disinfectant production task includes disinfectant production raw materials and disinfectant component expectations; a production decision space establishment module, for loading disinfectant raw material information corresponding to the disinfectant production raw materials, making digital control decisions on the disinfectant production raw materials in combination with the disinfectant component expectations, and establishing a disinfectant production decision space; a production optimization factor setting module, for setting disinfectant production optimization factors, wherein the disinfectant production optimization factors include disinfectant component purity, by-product purification ease, disinfection performance, and disinfectant production efficiency. rate; a production plan domain generation module, used to activate the disinfectant production prediction multi-channel, combine the disinfectant production optimization factor to perform multilateral joint optimization on the disinfectant production decision space, and generate a disinfectant production plan domain; a digital strategy acquisition module, used to construct a disinfectant production fitness evaluation network based on the disinfectant production optimization factor, and perform optimization analysis on the disinfectant production plan domain according to the disinfectant production fitness evaluation network to obtain a disinfectant production digital strategy; a disinfectant production module, used to send the disinfectant production digital strategy to the disinfectant digital production end, and the disinfectant digital production end produces disinfectants according to the disinfectant production raw materials and the disinfectant production digital strategy.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: The digital control and intelligent optimization technology for disinfectant production is adopted. By loading the information of disinfectant production raw materials and the expected disinfectant ingredients, the production process is precisely controlled in combination with multi-channel prediction and optimization factors, thus solving the problem that the disinfectant production process in the existing technology relies on manual experience and lacks precise digital control methods, resulting in low production efficiency, unstable product quality and difficult to control by-products. Through automated decision-making and real-time optimization, this solution significantly improves production efficiency, product stability and disinfection performance, while reducing the generation of by-products, achieving the technical effect of improving the controllability of the production process.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart of a digital control method for disinfectant production is provided for an embodiment of the present application.

[0011] Figure 2 A structural schematic diagram of a digital control system for disinfectant production is provided for the embodiment of the present application.

[0012] Explanation of the accompanying drawings: production task receiving module 11, production decision space establishing module 12, production optimization factor setting module 13, production plan domain generating module 14, digital strategy obtaining module 15, disinfectant production module 16. DETAILED DESCRIPTION

[0013] The overall idea of ​​the technical solution provided by this application is as follows: The embodiments of the present application provide a digital control method and system for disinfectant production. By constructing a digital control system for disinfectant production, combined with production raw material information and disinfection component expectations, intelligent management of the disinfectant production process is achieved. This solution loads raw material information and component expectations, and uses multi-channel prediction models and optimization factors to digitally control production decisions, thereby optimizing production plans, improving production efficiency, ensuring stable product quality, and effectively controlling the generation of by-products. Through this optimization method, the accuracy and controllability of the disinfectant production process are improved.

[0014] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0015] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a digital control method for disinfectant production, the method comprising: Step S100: receiving a disinfectant production task according to a disinfectant digital production terminal, wherein the disinfectant production task includes disinfectant production raw materials and disinfectant component expectations.

[0016] Specifically, the digital production end of disinfectants refers to a system or platform that manages the production of disinfectants through digital technology. It integrates information and control methods from various aspects such as production process, raw material management, ingredient control, and quality monitoring to achieve efficient production scheduling and management. The disinfectant production task refers to the specific production instructions received by the system during the disinfectant production process, which usually includes the type of disinfectant to be produced, the required raw material ratio, the target disinfection component and other requirements. Disinfectant production raw materials refer to various raw materials used to produce disinfectants, including chemical raw materials, additives, solvents, etc. For example, chlorides, alcohols, spices, etc. Disinfectant component expectations refer to the expected target values ​​of each key component in the disinfectant (such as the concentration of disinfectant active ingredients, ingredient ratio, etc.). For example, the effective chlorine content and bactericidal performance in the disinfectant.

[0017] The disinfectant digital production end first receives a disinfectant production task, which includes two main information items: disinfectant production raw materials and disinfectant component expectations. Specifically, the production end receives production requirements from a digital control platform, including: disinfectant production raw materials, disinfectant component expectations.

[0018] Based on this information, the disinfectant digital production end analyzes and creates a production decision space through algorithmic tools (such as production scheduling systems, optimization models, etc.). At this point, the system will decide which raw materials need to be put into production and adjust the raw material ratio and processing conditions according to the disinfectant component expectations.

[0019] Through this step, the digital control end of disinfectant production can accurately obtain the core requirements of the production task (raw materials and ingredient expectations) and make data-driven production decisions based on this information. Compared with the traditional manual control method, the digital production end can achieve refined management of the production process, reduce human errors, improve production efficiency, and ensure that the quality and disinfection effect of the disinfectant meet the standard requirements.

[0020] Step S200: Load the disinfectant raw material information corresponding to the disinfectant production raw material, make digital control decisions on the disinfectant production raw material in combination with the disinfectant component expectations, and establish a disinfectant production decision space.

[0021] Specifically, digital control decision-making refers to real-time monitoring and optimization of the production process through computer algorithms and data analysis tools, so as to formulate the most appropriate production plan based on the expectations of disinfectant ingredients and production raw material information. Digital control includes automated raw material ratios, production condition adjustments, and quality control. The disinfectant production decision space refers to the set of all feasible production plans generated after considering all production constraints (such as raw material characteristics, ingredient requirements, production equipment limitations, etc.). It represents production paths and options, helping decision makers to optimize among various options.

[0022] The disinfectant production end first loads the disinfectant production raw material information, that is, a detailed description of the properties of each raw material used to produce disinfectants (such as alcohol, chloride, hydrogen peroxide, etc.). For example, the purity of alcohol is 70%, and the purity of chloride is 99%. This information will be entered into the production system database. The system will analyze and make decisions based on the information of these raw materials and the expectations of the disinfectant ingredients (for example, the purity of alcohol in the final product should reach 90%, and the purification ease of the disinfectant ingredients should be at least 95%).

[0023] Next, the disinfectant production end uses digital control and decision-making tools (such as optimization algorithms, mathematical models, prediction tools, etc.) to make digital control decisions based on raw material information and ingredient expectations. These tools will adjust the raw material usage ratio, ingredient order, reaction temperature and other parameters based on the expected disinfectant ingredients and the characteristics of the production raw materials, thereby ensuring that the disinfectant produced meets the requirements.

[0024] Through these decisions, the system will establish a disinfectant production decision space, that is, a series of production plans generated according to different production constraints (such as raw material availability, cost, disinfection effect, etc.).

[0025] Through this step, the digital control of the disinfectant production process realizes the automation and intelligence of production decisions. Digital control can generate accurate production plans based on the disinfectant ingredient expectations and raw material information, thereby optimizing the production process to the greatest extent, reducing human errors and reducing production costs. In addition, by establishing a decision-making space, the production end can flexibly respond to different production environments and task requirements, select the best solution, and ensure the quality stability and production efficiency of the disinfectant.

[0026] Step S300: Setting disinfectant production optimization factors, wherein the disinfectant production optimization factors include the purity of disinfectant ingredients, ease of by-product purification, disinfection performance and disinfectant production efficiency.

[0027] Specifically, the purity of disinfectant ingredients refers to the concentration or percentage of active ingredients in disinfectants. The ease of by-product purification refers to the difficulty of purifying by-products produced during the production of disinfectants. Disinfection performance refers to the ability of disinfectants to kill bacteria, viruses and other pathogens in actual applications. Disinfection performance is usually evaluated by testing indicators such as the bactericidal effect and disinfection breadth of disinfectants within a specific period of time. Disinfectant production efficiency refers to the ratio of resource consumption required to produce disinfectants to the final output per unit time. High production efficiency means low production process costs and high resource utilization.

[0028] First, we need to set the optimization factors for disinfectant production, that is, to quantify the key factors that affect the production process and use them as optimization targets. These factors include: purity of disinfectant ingredients, ease of by-product purification, disinfection performance, and disinfectant production efficiency. By determining these factors, the system can optimize for different production goals to ensure that the production process meets quality, efficiency, and environmental protection requirements.

[0029] Specifically, it includes: defining optimization factors, defining and quantifying factors such as the purity of disinfectant ingredients, the ease of by-product purification, disinfection performance and production efficiency. For example, the purity of disinfectant ingredients can be evaluated by measuring the proportion of active ingredients in each batch of disinfectant; the ease of by-product purification can be measured based on the required post-processing cost and time; disinfection performance is usually evaluated through standard microbial kill tests; and production efficiency is calculated by the ratio of resource consumption to output. Set optimization goals. According to different production task requirements, the system sets these factors as optimization goals. Multi-objective optimization algorithms or genetic algorithms are usually used for multi-factor optimization. By inputting different optimization factor data, the system can automatically analyze the relationship between the factors and search for the optimal solution under the constraints of these factors.

[0030] After setting the optimization goal, the system calculates the effects of different production plans through simulation and prediction based on existing production data (such as raw material composition, production conditions, etc.).

[0031] By setting disinfectant production optimization factors and optimizing them, the production process can find a balance between multiple objectives, ensuring the disinfection effect of the final product, minimizing by-products, and improving production efficiency.

[0032] Step S400: Activate the disinfectant production prediction multi-channel, combine the disinfectant production optimization factor to perform multilateral joint optimization on the disinfectant production decision space, and generate a disinfectant production solution domain.

[0033] Specifically, the multi-channel prediction of disinfectant production refers to the prediction of different factors in the disinfectant production process through multiple independent prediction models (i.e., multiple "channels") to provide multi-dimensional results. Multilateral joint optimization refers to the process of optimizing multiple objectives or factors at the same time. In the disinfectant production process, the objectives are often multidimensional, such as optimizing the purity of disinfectant ingredients and the ease of by-product purification. Multilateral joint optimization finds an optimal solution by considering the relationship between various objectives. The disinfectant production solution domain refers to a set of optimal production solutions generated by the optimization process. These solutions can meet all optimization objectives (such as the purity of disinfectant ingredients, production efficiency, etc.) and balance the needs of various objectives.

[0034] First, it is necessary to activate the disinfectant production prediction multi-channel, and use multiple independent prediction models to predict different disinfectant production factors. These prediction models will be trained and optimized for different optimization factors, thereby providing multi-dimensional information for decision-making. Specifically, the purity of disinfectant ingredients and the ease of by-product purification are predicted through machine learning models. Each prediction channel will independently calculate its own prediction results.

[0035] Next, these disinfectant production optimization factors are combined to perform multilateral joint optimization on the disinfectant production decision space. That is, the output results of the prediction channel are used to optimize the production decision space according to the optimization objectives of each factor (such as minimizing the ease of byproduct purification while maximizing disinfection performance and production efficiency). This process usually relies on multi-objective optimization algorithms, such as genetic algorithms or particle swarm optimization (PSO), to balance and optimize the relationship between various objectives.

[0036] Through this process, the system will generate a disinfectant production solution domain, which is a set of production solutions that meet all optimization goals. Within this solution domain, each solution has been optimized in multiple dimensions to ensure the best production efficiency and quality.

[0037] By activating multiple channels for disinfectant production prediction and combining multilateral joint optimization, all key factors in the production process have been fully optimized. This not only improves the quality and production efficiency of disinfectants, but also effectively reduces the generation and treatment costs of by-products. The automation and intelligence of the production process are realized, and the accuracy and efficiency of production are improved.

[0038] Step S500: Based on the disinfectant production optimization factor, a disinfectant production fitness evaluation network is constructed, and the disinfectant production solution domain is optimized according to the disinfectant production fitness evaluation network to obtain a disinfectant production digitalization strategy.

[0039] Specifically, the disinfectant production fitness evaluation network is an evaluation system built on the above optimization factors, which can comprehensively consider the influence of various factors, evaluate different production plans, and finally calculate the "fitness" of each plan, that is, the degree of excellence of the plan under a specific goal. The fitness evaluation network is usually implemented through machine learning or multi-objective optimization algorithms.

[0040] The digital strategy for disinfectant production is an optimization solution generated by digital technologies (such as machine learning, data analysis, etc.). It comprehensively considers various factors in the disinfectant production process and formulates the best strategy for the production process based on these factors.

[0041] First, a fitness evaluation network is constructed based on the optimization factors of disinfectant production. The main task of this network is to calculate the performance of each factor based on the input of the production plan and comprehensively evaluate the fitness of the plan. Multi-objective optimization algorithms (such as genetic algorithms and particle swarm optimization) can be used to optimize the evaluation process.

[0042] After constructing the fitness evaluation network, the effect of each production plan is evaluated by performing optimization analysis on the disinfectant production plan domain. Each plan in the production plan domain represents a production path, and the fitness evaluation network finds the optimal plan by calculating the contribution of each factor to the target. Common optimization methods such as particle swarm optimization (PSO) and genetic algorithm (GA) can be used in this process. Based on the results of the evaluation analysis, the optimization process will generate a digital strategy for disinfectant production, that is, a set of optimized production plans based on data and models.

[0043] By building a disinfectant production fitness evaluation network and optimizing the production solution domain, the best digital production strategy can be accurately designed for the production process. This strategy not only improves production efficiency and reduces resource waste, but also ensures the consistency of product quality.

[0044] Step S600: Send the disinfectant production digitalization strategy to the disinfectant digitalization production end, and the disinfectant digitalization production end produces disinfectants according to the disinfectant production raw materials and the disinfectant production digitalization strategy.

[0045] Specifically, first, the disinfectant production digital strategy is obtained through computational optimization and sent to the disinfectant digital production end through digital transmission. The production end automatically adjusts the production parameters and controls every link of the production process based on the received strategy and real-time data (such as raw material information, temperature, humidity, concentration, etc.). This process usually relies on automated control systems and production management software, combined with real-time data collection and feedback adjustment mechanisms.

[0046] This step significantly improves production efficiency and reduces errors caused by human intervention through digital decision-making and automated production control, ensures product quality and consistency, reduces the generation of by-products, and improves the controllability and stability of the production process.

[0047] Furthermore, the disinfectant production prediction multi-channel is activated, and the disinfectant production decision space is subjected to multilateral joint optimization in combination with the disinfectant production optimization factor to generate a disinfectant production solution domain, including: setting multilateral joint optimization rules according to the disinfectant production optimization factor, wherein the multilateral joint optimization rules include the expected disinfectant component purity, the expected by-product purification ease, the expected disinfection performance and the expected disinfectant production efficiency; extracting the first disinfectant production decision according to the disinfectant production decision space; based on the disinfectant production prediction multi-channel, optimizing the disinfectant production decision space according to the first disinfectant production decision; The first disinfectant production prediction is performed on the material to obtain a first disinfectant production prediction result; whether the first disinfectant production prediction result satisfies the multilateral joint optimization rule is determined; if the first disinfectant production prediction result satisfies the multilateral joint optimization rule, the first disinfectant production decision is set as the first disinfectant production plan; if the first disinfectant production prediction result does not satisfy the multilateral joint optimization rule, the first disinfectant production decision is eliminated; according to the disinfectant production prediction multi-channel and the multilateral joint optimization rule, the disinfectant production decision space is continued to be optimized and analyzed to construct the disinfectant production plan domain.

[0048] Specifically, first, according to the optimization factors of disinfectant production, multilateral joint optimization rules are set. This step guides the entire optimization process by defining multiple optimization objectives, such as the desired purity of disinfectant ingredients (for example, set to 95%), the ease of by-product purification (requiring a simple by-product treatment process), disinfection performance (for example, the disinfectant must kill 99% of bacteria) and disinfectant production efficiency (producing more than 20 kilograms per hour).

[0049] Next, the first disinfectant production decision is extracted based on the disinfectant production decision space. Here, the decision space includes various raw material ratios, production conditions, etc. By exploring these variables, a preliminary production decision plan is extracted.

[0050] Based on the activated disinfectant production prediction multiple channels, for example, for the disinfectant component purity prediction channel, the byproduct purification ease prediction channel, the disinfection performance prediction channel and the production efficiency prediction channel, the first disinfectant production prediction result is obtained by inputting production decisions and raw material information. These prediction results provide expected values ​​for various aspects such as the disinfectant component purity and disinfection effect.

[0051] Next, determine whether the prediction result of the first disinfectant production meets the multilateral joint optimization rule. For example, if the expected purity of the disinfectant component is 95%, and the prediction result is 96%, then this rule is met. If it does not meet the rule, the production decision is eliminated and returned to the decision space for the next round of optimization. If it meets the rule, the production decision is used as the first disinfectant production plan.

[0052] Through this process, the optimization analysis of the disinfectant production decision space is continued, that is, through multiple rounds of iterative optimization, combined with the disinfectant production prediction multi-channel and multilateral joint optimization rules, new and optimized production plans are continuously generated. Finally, the generated disinfectant production plan domain contains a set of optimal production plans that meet all optimization goals for actual production use.

[0053] By setting multilateral joint optimization rules and activating multiple channels for disinfectant production prediction, this method can optimize multiple production goals at the same time to ensure the high quality and efficiency of disinfectants. After multiple rounds of optimization decisions, the generated disinfectant production solution domain provides manufacturers with a series of feasible optimal solutions, which can effectively improve production accuracy, reduce production costs, and optimize resource use, ensuring that the final disinfectant product can achieve the best balance in terms of quality, production efficiency and environmental protection.

[0054] Further, based on the disinfectant production prediction multi-channel, the production prediction of the disinfectant production raw material is performed according to the first disinfectant production decision to obtain a first disinfectant production prediction result, including: the disinfectant production prediction multi-channel includes a disinfection component purity prediction channel, a by-product purification ease prediction channel, a disinfection performance prediction channel and a disinfectant production efficiency prediction channel; the first disinfectant production decision and the disinfectant raw material information are input into the disinfection component purity prediction channel to obtain a first predicted disinfection component purity; the first disinfectant production decision and the disinfectant raw material information are input into the by-product purification ease prediction channel to obtain a first predicted by-product purification ease; the first disinfectant production decision and the disinfectant raw material information are input into the disinfection performance prediction channel to obtain a first disinfection performance prediction coefficient; the first disinfectant production decision and the disinfectant raw material information are input into the disinfection production efficiency prediction channel to obtain a first predicted disinfectant production efficiency; the first predicted disinfection component purity, the first predicted by-product purification ease, the first disinfection performance prediction coefficient and the first predicted disinfectant production efficiency are output as the first disinfectant production prediction result.

[0055] Specifically, the disinfectant component purity prediction channel is responsible for predicting the purity level of the main disinfectant components (such as hypochlorous acid, alcohol, etc.) in the disinfectant. After inputting production decisions and raw material information, the channel predicts the component purity of the generated disinfectant based on the data model.

[0056] The byproduct purification ease prediction channel predicts the difficulty of purifying byproducts (such as reaction byproducts, impurities, etc.) during the disinfectant production process. The disinfection performance prediction channel predicts the disinfection effect of the disinfectant, usually measured by the disinfection performance prediction coefficient. The disinfectant production efficiency prediction channel is used to predict the production efficiency of the disinfectant, usually based on the disinfectant dosage produced per hour. Predict the speed of disinfectant production based on production decisions and raw material input.

[0057] First, the disinfectant production forecast multi-channel is used to evaluate the first disinfectant production decision. This decision is based on the production plan made based on the disinfectant production raw materials and production conditions.

[0058] The first disinfectant production decision and related disinfectant raw material information (such as raw material type, component ratio, etc.) are input into the disinfectant component purity prediction channel. The task of this channel is to predict the purity of the disinfectant component in the final disinfectant product based on historical data and prediction models.

[0059] At the same time, the first disinfectant production decision and disinfectant raw material information will be input into the by-product purification ease prediction channel, which will predict the purification difficulty of the by-product based on the raw material characteristics and production process.

[0060] Next, the first disinfectant production decision and raw material information will be input into the disinfection performance prediction channel, and the system predicts the effect of the disinfectant by calculating the disinfection performance prediction coefficient.

[0061] Finally, all production decisions and raw material information will be input into the disinfectant production efficiency prediction channel to estimate production efficiency. This prediction value is usually expressed in terms of disinfectant production per hour, for example, it is expected that 30 kg of disinfectant can be produced per hour.

[0062] The prediction results of the above four channels - the purity of disinfectant ingredients, the ease of by-product purification, the disinfection performance prediction coefficient and the disinfectant production efficiency - are outputted comprehensively to form a complete prediction result for the production of the first disinfectant.

[0063] Through multi-channel analysis based on disinfectant production prediction, the performance indicators of disinfectants under different production decisions can be comprehensively evaluated. This multi-channel prediction method can significantly improve the accuracy of predictions, help decision makers optimize production plans, reduce raw material waste, and ensure that the disinfectants produced achieve the best balance in quality, efficiency, and environmental protection.

[0064] Furthermore, the steps of constructing the disinfectant production prediction multi-channel include: Load the disinfectant production decision sample set, the disinfectant raw material information sample set, the disinfectant component purity sample set, the by-product purification ease sample set, the disinfection performance coefficient sample set and the disinfectant production efficiency sample set; activate the predetermined learning model and the prediction channel training convergence condition; use the disinfectant production decision sample set and the disinfectant raw material information sample set as input information, and use the disinfectant component purity sample set as output information to perform supervised training on the predetermined learning model, and construct the disinfectant component purity prediction channel that meets the prediction channel training convergence condition; according to the disinfectant production decision sample set, the disinfectant raw material information sample set and the by-product purification ease sample set, supervised learning is performed on the predetermined learning model to establish a prediction channel that meets the prediction channel training convergence condition. The by-product purification ease prediction channel; according to the disinfectant production decision sample set, the disinfectant raw material information sample set and the disinfection performance coefficient sample set, the predetermined learning model is supervised and trained to generate the disinfection performance prediction channel that meets the prediction channel training convergence conditions; according to the disinfectant production decision sample set, the disinfectant raw material information sample set and the disinfectant production efficiency sample set, the predetermined learning model is supervised and learned to establish the disinfectant production efficiency prediction channel that meets the prediction channel training convergence conditions; the disinfection ingredient purity prediction channel, the by-product purification ease prediction channel, the disinfection performance prediction channel and the disinfectant production efficiency prediction channel are connected to generate the disinfectant production prediction multi-channel.

[0065] Specifically, the predetermined learning model is a machine learning model used for training, usually a supervised learning algorithm (such as a regression model, a neural network, etc.). By learning sample data, the model can predict the relevant disinfectant performance based on the input production decisions and raw material information.

[0066] First, a supervised learning model needs to be prepared for each prediction channel (i.e., disinfection component purity, byproduct purification ease, disinfection performance, and production efficiency) and trained with the given sample data. The specific process is as follows: First, load different sample data sets, including disinfectant production decision sample set, disinfectant raw material information sample set, disinfectant component purity sample set, by-product purification ease sample set, disinfection performance coefficient sample set, and disinfectant production efficiency sample set. These data will be used to train models for multiple prediction channels.

[0067] Next, the pre-defined learning model is activated and the training convergence conditions for each prediction channel are set. These conditions include minimizing the training error or the loss function reaching a certain preset value, etc., to ensure the prediction accuracy of the model.

[0068] The learning model is supervised and trained using the disinfectant production decision sample set and the disinfectant raw material information sample set as input and the disinfectant component purity sample set as output. The training process adjusts the model parameters until the training convergence conditions are met, and finally generates a channel that can predict the purity of disinfectant components.

[0069] The model is trained using the disinfectant production decision sample set, disinfectant raw material information sample set, and by-product purification ease sample set to construct a by-product purification ease prediction channel. The model will predict the purification difficulty of by-products based on different production decisions.

[0070] Similarly, the disinfectant production decision sample set, the disinfectant raw material information sample set, and the disinfection performance coefficient sample set are used for training to generate a prediction channel that can predict disinfection performance (such as bactericidal efficiency).

[0071] Finally, the disinfectant production decision sample set, disinfectant raw material information sample set and disinfectant production efficiency sample set are used to train the model and establish a disinfectant production efficiency prediction channel.

[0072] After all prediction channels have completed training and met convergence conditions, they are connected to form a complete disinfectant production prediction multi-channel system that can perform predictive analysis on multiple important aspects of the disinfectant production process.

[0073] By building a multi-channel prediction system for disinfectant production, we can comprehensively and accurately predict the various properties of disinfectants, such as purity, byproduct purification difficulty, disinfection effect, and production efficiency. This not only improves the accuracy and efficiency of production decisions, but also enables rapid adjustments in the early stages of production to avoid unnecessary waste of resources.

[0074] Furthermore, based on the disinfectant production optimization factor, a disinfectant production fitness evaluation network is constructed, including: having multiple disinfectant production enterprises score the importance of the disinfectant production optimization factor to obtain multiple indicator importance scoring sets; based on the multiple indicator importance scoring sets, respectively calculating the importance score concentration value of each indicator in the disinfectant production optimization factor to obtain the importance characteristic value of disinfectant ingredient purity, the importance characteristic value of by-product purification ease, the importance characteristic value of disinfection performance and the importance characteristic value of disinfectant production efficiency; according to the importance characteristic value of disinfectant ingredient purity, the importance characteristic value of by-product purification ease, the importance characteristic value of disinfection performance and the importance characteristic value of disinfectant production efficiency, the disinfectant production optimization factor is weighted to obtain the disinfectant production fitness evaluation network.

[0075] Specifically, the indicator importance score set is the result of multiple disinfectant manufacturers or experts scoring the importance of the impact of each production factor. Each enterprise or expert scores each factor based on their own experience and data, thus forming a score set about the importance of each factor. The importance score concentration value is calculated by statistically analyzing the scores of multiple enterprises or experts to calculate the score concentration trend (such as mean, median, etc.) of each factor. This concentration value reflects the relative importance of each factor in the optimization process. The importance characteristic value refers to the value calculated based on the score concentration value, which represents the relative importance characteristics of each disinfectant production factor. The disinfectant production fitness evaluation network is a system that performs comprehensive evaluation based on the weight distribution of each factor. The network is used to evaluate the fitness of each production plan, comprehensively consider the relative importance of different factors, and assign a fitness value to each plan based on the calculation results.

[0076] First, teams from different disinfectant manufacturers or experts will rate the importance of each indicator of disinfectant production optimization factor (such as the purity of disinfectant ingredients, the ease of by-product purification, etc.). These scores reflect the views of each company or expert on different factors. The score of each factor will come from multiple evaluators to form an indicator importance score set.

[0077] For each factor (such as the purity of disinfectant ingredients, the ease of by-product purification, etc.), we will conduct statistical analysis based on the scores from multiple companies or experts. By calculating the central value of the importance score, we can obtain the central tendency value of each factor. For example, assuming that 10 experts score the purity of disinfectant ingredients at 80, 85, 90, 95, 88, etc., respectively, calculating the average or median of these scores will give a central value reflecting the importance of the factor.

[0078] Based on the importance score concentration values ​​calculated above, the system assigns weights to each factor (such as disinfectant ingredient purity, byproduct purification ease, disinfection performance, etc.). The weight assignment is adjusted according to the relative importance characteristic value of each factor. For example, if the disinfectant ingredient purity is considered to be the most critical factor, its weight will be higher, while the byproduct purification ease will have a lower weight. After the weight assignment is completed, the weights of all factors will be integrated into a disinfectant production fitness assessment network.

[0079] After the disinfectant production fitness evaluation network is built, the network can evaluate the fitness of each plan based on the input production plan and the weight value of each factor. The fitness evaluation network will generate a comprehensive score for each production plan, which represents the overall pros and cons of the plan under all evaluation factors.

[0080] By scoring multiple disinfectant manufacturers and calculating the central value of each factor, the accuracy and breadth of the disinfectant production fitness evaluation network can be ensured. This method combines expert experience and data analysis to provide an objective and reliable optimization solution. In addition, since the network can comprehensively consider the weights of multiple factors, it can balance various factors during the optimization process, thereby generating the optimal production strategy that meets actual needs and ensuring the efficiency of the disinfectant production process and product quality.

[0081] Furthermore, the disinfectant production scheme domain is optimized and analyzed according to the disinfectant production fitness evaluation network to obtain a disinfectant production digitalization strategy, including: extracting the Kth disinfectant production scheme according to the disinfectant production scheme domain, where K is a positive integer; performing normalization processing on the Kth disinfectant production prediction result corresponding to the Kth disinfectant production scheme to obtain the Kth disinfectant production feature prediction result, and inputting the Kth disinfectant production feature prediction result into the disinfectant production fitness evaluation network to generate the Kth disinfectant production fitness; extracting the Kth disinfectant production scheme domain according to the disinfectant production scheme domain, wherein .... K+1 disinfectant production plan, and in combination with the disinfectant production fitness evaluation network, calculate the K+1th disinfectant production fitness; based on the K+1th disinfectant production fitness and the Kth disinfectant production fitness, perform current optimization on the K+1th disinfectant production plan and the Kth disinfectant production plan to obtain the current optimized disinfectant production plan; based on the disinfectant production fitness evaluation network and the disinfectant production plan, continue to iteratively optimize the current optimized disinfectant production plan until the number of iterative optimizations meets the iterative optimization number constraint, and generate the disinfectant production digitalization strategy.

[0082] Specifically, the disinfectant production prediction result is the result generated by the disinfectant production prediction multi-channel, which represents the relevant production characteristics predicted according to a certain production plan. Each prediction result is usually calculated by the prediction model based on the input production decision and raw material information. Normalization processing refers to the process of converting data into a certain range (such as [0,1]) so that data of different scales can be compared. Through normalization processing, the influence of different data magnitudes can be eliminated, so that the disinfectant production prediction results can be more fair and unified during evaluation. The disinfectant production fitness is the score obtained by the disinfectant production plan in the fitness evaluation network, which indicates the pros and cons of the plan. Current optimization refers to the process of selecting the best plan for adjustment and improvement by comparing the fitness of the current plan with the previous plan in one round of iteration. Iterative optimization refers to the process of gradually finding the best plan by repeatedly evaluating, adjusting and optimizing multiple production plans.

[0083] First, the K-th production scheme is extracted from the disinfectant production scheme domain, where K is a positive integer, representing the K-th production scheme to be evaluated. Each production scheme corresponds to a different production configuration (such as raw materials, processes, etc.) and has corresponding prediction characteristics such as the purity of disinfectant components and disinfection performance. For the extracted K-th disinfectant production scheme, its production prediction results are normalized. The purpose of normalization is to convert prediction results of different scales into standardized values ​​(such as the [0,1] interval) to facilitate fair comparison. After that, the normalized production prediction results are input into the disinfectant production fitness evaluation network to evaluate the fitness of the scheme. Similarly, the K+1-th production scheme is extracted from the disinfectant production scheme domain, and the fitness of the scheme is calculated using the same method. This step ensures that each scheme has received a corresponding fitness evaluation.

[0084] Compare the fitness of the Kth disinfectant production scheme and the K+1th disinfectant production scheme. If the fitness of the K+1th scheme is higher, then select the K+1th scheme as the current optimized production scheme. This process can be understood as finding the best current scheme among all candidate schemes.

[0085] Through the iterative process, the current optimal disinfectant production plan is continuously optimized. Each round of iteration compares the fitness of the current plan with the production plan of the previous round, and further optimizes it through the disinfectant production fitness evaluation network. This process continues until the predetermined number of iterations is met (for example, the maximum number of iterations is reached or the fitness reaches a certain threshold).

[0086] Finally, after multiple iterations of optimization, the system will generate the final disinfectant production digital strategy. This strategy represents the optimal disinfectant production process and configuration based on the optimized production plan under the current production environment.

[0087] Through the optimization analysis method based on the fitness evaluation network, the efficiency and accuracy of the disinfectant production process can be ensured. Each production plan is strictly evaluated and optimized to maximize the production goals.

[0088] Furthermore, the disinfectant raw material information corresponding to the disinfectant production raw material is loaded, and a digital regulation and control decision is made on the disinfectant production raw material in combination with the disinfectant component expectation to establish a disinfectant production decision space, including: taking the disinfectant raw material information as the first constraint for disinfectant production retrieval, and taking the disinfectant component expectation as the second constraint for disinfectant production retrieval; performing a disinfectant production plan search on the disinfectant digital production end according to the first constraint for disinfectant production retrieval and the second constraint for disinfectant production retrieval to obtain a set of sample disinfectant production plans; performing regulation trigger interval feature identification according to the sample disinfectant production plan set to establish a disinfectant production regulation and control constraint domain, wherein the disinfectant production regulation and control constraint domain includes multiple disinfectant production regulation and control trigger intervals; taking the disinfectant component expectation as the disinfectant production target, and combining the disinfectant production regulation and control constraint domain to make a production decision on the disinfectant production raw material to obtain the disinfectant production decision space.

[0089] Specifically, in the first and second constraints of disinfectant production retrieval, the first constraint (disinfectant raw material information) refers to the constraints of all raw materials in production, such as availability, price, quality, etc.; the second constraint (disinfectant ingredient expectations) refers to the target requirements for disinfectant ingredients in the production process, such as purity, purification effect, etc. These two constraints work together to ensure that the production plan meets the established standards. The disinfectant production plan set refers to a series of disinfectant production plans retrieved by the system based on the constraints. Disinfectant production control constraint domain and control trigger interval, the control constraint domain refers to a set of a series of constraints that must be followed during the production process, including multiple trigger intervals (such as raw material ratio, temperature, reaction time, etc.), which represent the operating range that needs to be maintained during the production process.

[0090] First, the system sets the first constraint and the second constraint based on the raw material information and disinfectant component expectations in the received disinfectant production task. The first constraint is related to the raw materials, such as the concentration of alcohol, the content of chloride, etc.; the second constraint is about the disinfection effect requirements of the final product, such as the purity of the disinfectant component or the degree of purification of the by-product. These two constraints are used as input information to retrieve the production plan through the digital production end.

[0091] During the retrieval process, the system uses optimization algorithms or machine learning models to screen feasible production plans, and combines these constraints (first and second constraints) to generate a sample disinfectant production plan set. For example, if the production task requires an alcohol purity of 90%, the system will calculate the ratio of different alcohol concentrations to other raw materials to obtain a production plan set that meets this standard.

[0092] Then, the system identifies the characteristics of the control trigger interval, determines which variables (such as temperature, time, and reaction conditions) need to be strictly controlled during the production process through data analysis, and identifies the appropriate operating interval. Through this process, the disinfectant production control constraint domain is established, which includes a range of multiple constraints to ensure that the production process operates under these conditions.

[0093] On this basis, the system takes the disinfection component expectation as the final production goal, combines the disinfectant production control constraint domain, makes decisions on production raw materials, and thus obtains the optimal disinfectant production decision space. This decision space contains all production plans that meet the production task requirements, and each plan takes into account the characteristics of the raw materials, the disinfection component expectations, and the feasibility of production.

[0094] Through this process, the disinfectant production system can achieve more precise production control, automatically generate multiple production plans, and select the best plan under multiple constraints. By reasonably adjusting the production raw material ratio, production process conditions, etc., the disinfectant production process can be highly intelligent, further improving the flexibility and adaptability of production, and providing enterprises with higher production accuracy and optimization space.

[0095] In summary, the digital control method for disinfectant production provided in the embodiments of the present application has the following technical effects: 1. By digitally controlling the raw materials for disinfectant production and combining the expected disinfectant ingredients to make intelligent decisions on disinfectant production, it helps to improve the accuracy of the production process. By loading the disinfectant raw material information and disinfectant ingredient expectations, the raw material ratio and production plan can be optimized, thereby achieving efficient and low-cost disinfectant production, while ensuring the purity and effectiveness of the disinfectant ingredients, improving the consistency and reliability of production, and meeting a variety of needs.

[0096] 2. By establishing a decision space for disinfectant production, this method achieves multi-dimensional optimization in the production process. Combined with the digital control of production raw materials and disinfectant component expectations, the accuracy and optimization space of disinfectant production are effectively improved. The setting of multiple constraints enables the production plan to meet quality requirements while avoiding waste of raw materials, and can quickly adapt to market changes, improving production flexibility and efficiency.

[0097] 3. Through the construction and optimization analysis of the disinfectant production fitness evaluation network, this method can comprehensively evaluate the advantages and disadvantages of different production plans. Combined with the weighted evaluation of multiple disinfectant production factors (such as purity, by-product purification, etc.), it can ensure the optimization of the comprehensive performance of the disinfectant production process. Through the continuous evaluation and optimization of the production process, the efficient selection of production plans is achieved, which effectively improves the competitiveness and production efficiency of disinfectant products.

[0098] Embodiment 2, based on the same inventive concept as the digital control method for disinfectant production in the above embodiment, Figure 2 As shown, the embodiment of the present application provides a digital control system for disinfectant production, the system comprising: The production task receiving module 11 is used to receive the disinfectant production task according to the disinfectant digital production terminal, wherein the disinfectant production task includes the disinfectant production raw materials and the disinfectant component expectations; the production decision space establishment module 12 is used to load the disinfectant raw material information corresponding to the disinfectant production raw materials, and make digital control decisions on the disinfectant production raw materials in combination with the disinfectant component expectations to establish the disinfectant production decision space; the production optimization factor setting module 13 is used to set the disinfectant production optimization factor, wherein the disinfectant production optimization factor includes the disinfectant component purity, by-product purification ease, disinfection performance and disinfectant production efficiency; the production plan domain generation module 14 is used to activate The disinfectant production prediction multi-channel combines the disinfectant production optimization factors to perform multilateral joint optimization on the disinfectant production decision space to generate a disinfectant production solution domain; a digital strategy acquisition module 15 is used to construct a disinfectant production fitness evaluation network based on the disinfectant production optimization factors, and perform optimization analysis on the disinfectant production solution domain according to the disinfectant production fitness evaluation network to obtain a disinfectant production digital strategy; a disinfectant production module 16 is used to send the disinfectant production digital strategy to the disinfectant digital production end, and the disinfectant digital production end produces disinfectants according to the disinfectant production raw materials and the disinfectant production digital strategy.

[0099] Furthermore, the production plan domain generating module 14 is further configured to perform the following steps: According to the disinfectant production optimization factor, a multilateral joint optimization rule is set, wherein the multilateral joint optimization rule includes the expected disinfectant component purity, the expected by-product purification ease, the expected disinfection performance and the expected disinfectant production efficiency; according to the disinfectant production decision space, a first disinfectant production decision is extracted; based on the disinfectant production prediction multi-channel, the production prediction of the disinfectant production raw material is performed according to the first disinfectant production decision to obtain a first disinfectant production prediction result; it is determined whether the first disinfectant production prediction result satisfies the multilateral joint optimization rule; if the first disinfectant production prediction result satisfies the multilateral joint optimization rule, the first disinfectant production decision is set as the first disinfectant production plan; if the first disinfectant production prediction result does not satisfy the multilateral joint optimization rule, the first disinfectant production decision is eliminated; according to the disinfectant production prediction multi-channel and the multilateral joint optimization rule, the disinfectant production decision space is continued to be optimized and analyzed to construct the disinfectant production plan domain.

[0100] Furthermore, the production plan domain generating module 14 is further configured to perform the following steps: The disinfectant production prediction multi-channel includes a disinfection component purity prediction channel, a by-product purification ease prediction channel, a disinfection performance prediction channel and a disinfectant production efficiency prediction channel; the first disinfectant production decision and the disinfectant raw material information are input into the disinfection component purity prediction channel to obtain a first predicted disinfection component purity; the first disinfectant production decision and the disinfectant raw material information are input into the by-product purification ease prediction channel to obtain a first predicted by-product purification ease; the first disinfectant production decision and the disinfectant raw material information are input into the disinfection performance prediction channel to obtain a first disinfection performance prediction coefficient; the first disinfectant production decision and the disinfectant raw material information are input into the disinfection efficiency prediction channel to obtain a first predicted disinfectant production efficiency; the first predicted disinfection component purity, the first predicted by-product purification ease, the first disinfection performance prediction coefficient and the first predicted disinfectant production efficiency are output as the first disinfectant production prediction result.

[0101] Furthermore, the production plan domain generating module 14 is further configured to perform the following steps: Load the disinfectant production decision sample set, the disinfectant raw material information sample set, the disinfectant component purity sample set, the by-product purification ease sample set, the disinfection performance coefficient sample set and the disinfectant production efficiency sample set; activate the predetermined learning model and the prediction channel training convergence condition; use the disinfectant production decision sample set and the disinfectant raw material information sample set as input information, and use the disinfectant component purity sample set as output information to perform supervised training on the predetermined learning model, and construct the disinfectant component purity prediction channel that meets the prediction channel training convergence condition; according to the disinfectant production decision sample set, the disinfectant raw material information sample set and the by-product purification ease sample set, supervised learning is performed on the predetermined learning model to establish a prediction channel that meets the prediction channel training convergence condition. The by-product purification ease prediction channel; according to the disinfectant production decision sample set, the disinfectant raw material information sample set and the disinfection performance coefficient sample set, the predetermined learning model is supervised and trained to generate the disinfection performance prediction channel that meets the prediction channel training convergence conditions; according to the disinfectant production decision sample set, the disinfectant raw material information sample set and the disinfectant production efficiency sample set, the predetermined learning model is supervised and learned to establish the disinfectant production efficiency prediction channel that meets the prediction channel training convergence conditions; the disinfection ingredient purity prediction channel, the by-product purification ease prediction channel, the disinfection performance prediction channel and the disinfectant production efficiency prediction channel are connected to generate the disinfectant production prediction multi-channel.

[0102] Furthermore, the digital strategy obtaining module 15 is further configured to perform the following steps: A plurality of disinfectant manufacturers assign importance scores to the disinfectant production optimization factors to obtain a plurality of indicator importance score sets; based on the plurality of indicator importance score sets, the importance score concentration value is calculated for each indicator in the disinfectant production optimization factors to obtain importance characteristic values ​​of disinfectant ingredient purity, importance characteristic values ​​of by-product purification ease, importance characteristic values ​​of disinfection performance and importance characteristic values ​​of disinfectant production efficiency; weights are assigned to the disinfectant production optimization factors according to the importance characteristic values ​​of disinfectant ingredient purity, the importance characteristic values ​​of by-product purification ease, the importance characteristic values ​​of disinfection performance and the importance characteristic values ​​of disinfectant production efficiency to obtain the disinfectant production fitness evaluation network.

[0103] Furthermore, the digital strategy obtaining module 15 is further configured to perform the following steps: According to the disinfectant production scheme domain, extract the Kth disinfectant production scheme, where K is a positive integer; perform normalization processing on the Kth disinfectant production prediction result corresponding to the Kth disinfectant production scheme to obtain the Kth disinfectant production feature prediction result, and input the Kth disinfectant production feature prediction result into the disinfectant production fitness evaluation network to generate the Kth disinfectant production fitness; according to the disinfectant production scheme domain, extract the K+1th disinfectant production scheme, and calculate the K+1th disinfectant production fitness in combination with the disinfectant production fitness evaluation network; perform current optimization on the K+1th disinfectant production scheme and the Kth disinfectant production scheme based on the K+1th disinfectant production fitness and the Kth disinfectant production fitness to obtain the current optimized disinfectant production scheme; continue to iteratively optimize the current optimized disinfectant production scheme based on the disinfectant production fitness evaluation network and the disinfectant production scheme until the number of iterative optimizations meets the iterative optimization number constraint, and generate the disinfectant production digitalization strategy.

[0104] Furthermore, the production decision space establishment module 12 is also used to perform the following steps: The disinfectant raw material information is used as the first constraint for disinfectant production retrieval, and the disinfectant component expectation is used as the second constraint for disinfectant production retrieval; according to the first disinfectant production retrieval constraint and the second disinfectant production retrieval constraint, the disinfectant production plan is retrieved for the disinfectant digital production end to obtain a sample disinfectant production plan set; according to the sample disinfectant production plan set, the control trigger interval feature is identified to establish a disinfectant production control constraint domain, wherein the disinfectant production control constraint domain includes multiple disinfectant production control trigger intervals; with the disinfectant component expectation as the disinfectant production target, a production decision is made on the disinfectant production raw material in combination with the disinfectant production control constraint domain to obtain the disinfectant production decision space.

[0105] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0106] Furthermore, the first or second mentioned above not only represents an order relationship, but also represents a specific concept, and / or refers to the selection of multiple elements individually or in whole. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application intends to include these modifications and variations.

Claims

1. A digital control method for disinfectant production, characterized in that: The method comprises: According to the disinfectant digital production terminal, receiving a disinfectant production task, wherein the disinfectant production task includes disinfectant production raw materials and disinfectant component expectations; Load the disinfectant raw material information corresponding to the disinfectant production raw material, make digital control decisions on the disinfectant production raw material in combination with the disinfectant component expectation, and establish a disinfectant production decision space; Setting disinfectant production optimization factors, wherein the disinfectant production optimization factors include disinfectant component purity, by-product purification ease, disinfection performance and disinfectant production efficiency; Activate the disinfectant production prediction multi-channel, combine the disinfectant production optimization factor to perform multilateral joint optimization on the disinfectant production decision space, and generate a disinfectant production solution domain; Based on the disinfectant production optimization factor, a disinfectant production fitness evaluation network is constructed, and the disinfectant production solution domain is optimized according to the disinfectant production fitness evaluation network to obtain a disinfectant production digitalization strategy; The disinfectant production digitalization strategy is sent to the disinfectant digitalization production end, and the disinfectant digitalization production end produces disinfectants according to the disinfectant production raw materials and the disinfectant production digitalization strategy.

2. The digital control method for disinfectant production according to claim 1, characterized in that: Activate the disinfectant production prediction multi-channel, combine the disinfectant production optimization factor to perform multilateral joint optimization on the disinfectant production decision space, and generate the disinfectant production solution domain, including: According to the optimization factor for disinfectant production, a multilateral joint optimization rule is set, wherein the multilateral joint optimization rule includes the expected purity of disinfectant components, the expected ease of by-product purification, the expected disinfection performance and the expected disinfectant production efficiency; Extracting a first disinfectant production decision according to the disinfectant production decision space; Based on the disinfectant production prediction multi-channel, the production prediction of the disinfectant production raw material is performed according to the first disinfectant production decision to obtain a first disinfectant production prediction result; Determining whether the first disinfectant production prediction result satisfies the multilateral joint optimization rule; If the first disinfectant production prediction result satisfies the multilateral joint optimization rule, setting the first disinfectant production decision as the first disinfectant production plan; If the first disinfectant production prediction result does not satisfy the multilateral joint optimization rule, the first disinfectant production decision is eliminated; The disinfectant production decision space is continuously optimized and analyzed according to the disinfectant production prediction multi-channel and the multilateral joint optimization rule to construct the disinfectant production solution domain.

3. The digital control method for disinfectant production according to claim 2, characterized in that: Based on the disinfectant production prediction multi-channel, the production prediction of the disinfectant production raw material is performed according to the first disinfectant production decision to obtain a first disinfectant production prediction result, including: The disinfectant production prediction multi-channel includes a disinfectant component purity prediction channel, a by-product purification ease prediction channel, a disinfection performance prediction channel and a disinfectant production efficiency prediction channel; Inputting the first disinfectant production decision and the disinfectant raw material information into the disinfectant component purity prediction channel to obtain a first predicted disinfectant component purity; Inputting the first disinfectant production decision and the disinfectant raw material information into the by-product purification ease prediction channel to obtain a first predicted by-product purification ease; Inputting the first disinfectant production decision and the disinfectant raw material information into the disinfection performance prediction channel to obtain a first disinfection performance prediction coefficient; Inputting the first disinfectant production decision and the disinfectant raw material information into the disinfectant production efficiency prediction channel to obtain a first predicted disinfectant production efficiency; The first predicted disinfection component purity, the first predicted by-product purification ease, the first disinfection performance prediction coefficient and the first predicted disinfectant production efficiency are output as the first disinfectant production prediction result.

4. The digital control method for disinfectant production according to claim 3, characterized in that: The steps of constructing the disinfectant production prediction multi-channel include: Loading disinfectant production decision sample set, disinfectant raw material information sample set, disinfectant component purity sample set, by-product purification ease sample set, disinfection performance coefficient sample set and disinfectant production efficiency sample set; Activate the predefined learning model and predict channel training convergence conditions; Taking the disinfectant production decision sample set and the disinfectant raw material information sample set as input information and the disinfectant component purity sample set as output information, the predetermined learning model is supervised trained to construct the disinfectant component purity prediction channel that meets the prediction channel training convergence condition; According to the disinfectant production decision sample set, the disinfectant raw material information sample set and the by-product purification ease sample set, supervised learning is performed on the predetermined learning model to establish the by-product purification ease prediction channel that meets the prediction channel training convergence condition; According to the disinfectant production decision sample set, the disinfectant raw material information sample set and the disinfection performance coefficient sample set, the predetermined learning model is supervised trained to generate the disinfection performance prediction channel that meets the prediction channel training convergence condition; According to the disinfectant production decision sample set, the disinfectant raw material information sample set and the disinfectant production efficiency sample set, supervised learning is performed on the predetermined learning model to establish the disinfectant production efficiency prediction channel that meets the prediction channel training convergence condition; The disinfectant production prediction multi-channel is generated by connecting the disinfection component purity prediction channel, the by-product purification ease prediction channel, the disinfection performance prediction channel and the disinfectant production efficiency prediction channel.

5. The digital control method for disinfectant production according to claim 1, characterized in that: Based on the disinfectant production optimization factor, a disinfectant production fitness evaluation network is constructed, including: A plurality of disinfectant production enterprises perform importance scoring on the disinfectant production optimization factors to obtain a plurality of indicator importance scoring sets; Based on the plurality of indicator importance scoring sets, the importance score concentration value of each indicator in the disinfectant production optimization factor is calculated respectively to obtain the importance characteristic value of the disinfectant component purity, the importance characteristic value of the by-product purification ease, the importance characteristic value of the disinfection performance and the importance characteristic value of the disinfectant production efficiency; According to the importance characteristic value of the disinfection component purity, the importance characteristic value of the by-product purification ease, the importance characteristic value of the disinfection performance and the importance characteristic value of the disinfectant production efficiency, the disinfectant production optimization factors are weighted to obtain the disinfectant production fitness evaluation network.

6. The digital control method for disinfectant production according to claim 1, characterized in that: The disinfectant production solution domain is optimized and analyzed according to the disinfectant production fitness evaluation network to obtain a disinfectant production digitalization strategy, including: According to the disinfectant production plan domain, extract the Kth disinfectant production plan, where K is a positive integer; Performing normalization processing on the Kth disinfectant production prediction result corresponding to the Kth disinfectant production scheme to obtain a Kth disinfectant production feature prediction result, and inputting the Kth disinfectant production feature prediction result into the disinfectant production fitness evaluation network to generate a Kth disinfectant production fitness; According to the disinfectant production scheme domain, extract the K+1 disinfectant production scheme, and calculate the K+1 disinfectant production fitness in combination with the disinfectant production fitness evaluation network; Based on the K+1th disinfectant production fitness and the Kth disinfectant production fitness, the K+1th disinfectant production scheme and the Kth disinfectant production scheme are currently optimized to obtain a current optimized disinfectant production scheme; The current optimal disinfectant production scheme is continuously iterated and optimized based on the disinfectant production fitness evaluation network and the disinfectant production scheme until the number of iterative optimizations meets the iterative optimization number constraint, thereby generating the disinfectant production digitalization strategy.

7. The digital control method for disinfectant production according to claim 1, characterized in that: Load the disinfectant raw material information corresponding to the disinfectant production raw material, make digital control decisions on the disinfectant production raw material in combination with the disinfectant component expectation, and establish a disinfectant production decision space, including: The disinfectant raw material information is used as the first constraint for disinfectant production retrieval, and the disinfectant component expectation is used as the second constraint for disinfectant production retrieval; According to the first disinfectant production search constraint and the second disinfectant production search constraint, the disinfectant digital production end is searched for a disinfectant production plan to obtain a sample disinfectant production plan set; Performing control trigger interval feature identification according to the sample disinfectant production plan set, and establishing a disinfectant production control constraint domain, wherein the disinfectant production control constraint domain includes multiple disinfectant production control trigger intervals; The disinfectant production target is taken as the disinfectant component expectation, and the production decision of the disinfectant production raw materials is made in combination with the disinfectant production regulation and control constraint domain to obtain the disinfectant production decision space.

8. A digital control system for disinfectant production, characterized in that: Used to execute the digital control method for disinfectant production according to any one of claims 1 to 7, the system comprising: A production task receiving module, used for receiving a disinfectant production task according to a disinfectant digital production terminal, wherein the disinfectant production task includes disinfectant production raw materials and disinfectant component expectations; A production decision space establishment module is used to load the disinfectant raw material information corresponding to the disinfectant production raw material, make digital control decisions on the disinfectant production raw material in combination with the disinfectant component expectation, and establish a disinfectant production decision space; A production optimization factor setting module, used to set the disinfectant production optimization factor, wherein the disinfectant production optimization factor includes the purity of the disinfectant component, the ease of by-product purification, the disinfection performance and the disinfectant production efficiency; A production plan domain generation module is used to activate the disinfectant production prediction multi-channel, combine the disinfectant production optimization factor to perform multilateral joint optimization on the disinfectant production decision space, and generate a disinfectant production plan domain; A digital strategy acquisition module is used to construct a disinfectant production fitness evaluation network based on the disinfectant production optimization factor, and perform optimization analysis on the disinfectant production solution domain according to the disinfectant production fitness evaluation network to obtain a disinfectant production digital strategy; The disinfectant production module is used to send the disinfectant production digitalization strategy to the disinfectant digitalization production end, and the disinfectant digitalization production end produces disinfectants according to the disinfectant production raw materials and the disinfectant production digitalization strategy.

Images