Monitoring control management system for production process of sodium dibutyryladenosine cyclophosphate

Abstract

The invention belongs to the technical field of biological medicine production control, and particularly discloses a sodium dibutyryladenosine cyclophosphate production process monitoring control management system which comprises a production data monitoring module, an equipment data import module, a process production analysis module, a process adjustment confirmation module and a process control execution terminal. The production data monitoring module is arranged to collect parameters in real time, the equipment data import module introduces equipment state data, the process production analysis module judges whether production control change needs to be carried out or not, and production change is responded in time. The process adjustment confirmation module defines change content, the trigger adjustment analysis module accurately locks adjustment processes and indexes, all the modules cooperate closely, the flexibility, stability and high efficiency of production are remarkably improved, the product quality is guaranteed, meanwhile, the cost is reduced, the adaptability of a production line to complex working conditions is enhanced, and the production efficiency is improved. And the refinement level and the flexibility of production management are greatly improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of biopharmaceutical production control. Specifically, it relates to a monitoring, control and management system for the production process of sodium dibutyryl cyclic adenosine phosphate. Background Art

[0002] Sodium dibutyryl cyclic adenosine phosphate appears as a white or almost white crystalline powder, is readily soluble in water, and slightly soluble in methanol and ethanol; it is mainly used to improve energy metabolism disorders and microcirculation disorders in cardiovascular diseases. Its production process mainly involves mixing, reaction and separation, etc. The production is usually a continuous and large-scale production process. It is crucial for the production line to operate stably after startup. Restarting after a mid-course shutdown will cause economic losses and trigger safety and quality problems. Therefore, it is extremely necessary to monitor, control and manage the linkage of the production line processes.

[0003] The prior art, such as a full-process online monitoring and management system for a chemical production process disclosed in a Chinese patent application with the application number 202411230708.6, ensures that the reaction process is in the best conditions by real-time regulating the process parameters of the neutralization reaction and the polymerization reaction. The system dynamically optimizes the initial parameter settings of the next batch based on historical batch data, and continuously improves the supervision efficiency of the production line and the scientificity of production decision-making through multi-round iterative evaluation of the preparation optimization effectiveness coefficient. This technology realizes the adaptive optimization of the production process and strengthens the monitoring and management ability of the chemical process.

[0004] Another example of the prior art is a smart monitoring and management method and system for the sodium hypochlorite production process disclosed in a Chinese patent application with the application number 202410171804.1. It innovatively constructs an intermediate sodium hypochlorite concentration model, and accurately controls the reaction conditions of sodium hydroxide solution and chlorine gas by collecting the initial concentration and the volume of the mixed solution output by the electrolysis device, combined with the target concentration set manually. This technology not only improves the utilization rate of raw materials, but also realizes the full-process resource utilization of the electrolysis by-product chlorine gas by adding a chlorine gas conversion process and establishing a reaction kinetics model, significantly improving the economy and environmental protection of the production process. Both patents focus on the real-time monitoring and intelligent optimization of chemical production, and promote the efficient operation of the production system through data iterative analysis and reaction process modeling respectively.

[0005] Regarding the above technical solutions, obviously, there are still the following deficiencies in the current monitoring, control and management of the production line processes: 1. There are mutual influences and interferences between the processes during the production process. Currently, more emphasis is placed on the independent monitoring and analysis between processes or the comprehensive analysis of the overall process, and the linkage monitoring and analysis between processes is not carried out, resulting in limited coordination between processes and the adaptive ability of management.

[0006] 2. At present, it is difficult to comprehensively evaluate the impact of equipment status on production, and there is no data-based and targeted detailed management, making it difficult to dynamically adapt to changes in the production process. Summary of the Invention

[0007] In view of this, to solve the problems raised in the above-mentioned background technology, a monitoring, control and management system for the production process of sodium dibutyryl adenosine cyclophosphate is proposed.

[0008] The object of the present invention can be achieved by the following technical solutions: The present invention provides a monitoring, control and management system for the production process of sodium dibutyryl adenosine cyclophosphate, which system includes: a production data monitoring module for collecting production parameters of the corresponding mixing process, reaction process and separation process of the current production line.

[0009] An equipment data import module for importing the nuclear inspection record form of production equipment.

[0010] A process production analysis module for performing production self-adaptation analysis and process linkage analysis based on the production parameters and the nuclear inspection record form, outputting the production state compliance degree and process linkage compliance degree of the mixing, reaction and separation processes, and judging whether process control changes are required accordingly.

[0011] A process adjustment confirmation module for, when process control changes are required, judging and outputting adjustment categories based on preset adjustment judgment rules, and confirming production control indicators based on the adjustment categories.

[0012] A process control execution terminal for performing corresponding control based on the analysis result of the process adjustment confirmation module.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) By setting a production data monitoring module to collect parameters in real time, an equipment data import module to introduce equipment status data, and a process production analysis module to judge whether process control changes are required, the present invention can respond to production changes in a timely manner. The process adjustment confirmation module clarifies the change content, triggers the adjustment analysis module to accurately lock the adjustment process and indicators, and each module cooperates closely, significantly improving the flexibility, stability and efficiency of production, ensuring product quality while reducing costs, enhancing the adaptability of the production line to complex working conditions, and greatly improving the refinement level of production management.

[0014] (2) By performing production self-adaptation analysis and process linkage analysis, the present invention solves the problem that the current production process does not conduct linkage monitoring and analysis between processes, can monitor and adjust the mutual influence and interference between processes in real time, and improve the coordination between processes and the self-adaptation ability of management. At the same time, it can optimize production efficiency, reduce resource waste, and can also timely discover and solve potential problems to ensure the stability of the production process.

[0015] (3) The present invention solves the problem of the current difficulty in comprehensively evaluating the impact of equipment status on production by judging and adjusting categories and confirming the adjusted production control indicators, realizes specific, data-based and targeted production management, and can dynamically adapt to changes in the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a schematic diagram of the connection of the system modules of the present invention.

[0018] Figure 2 It is a schematic diagram of the overall implementation step flow of the present invention.

[0019] Figure 3 It is a schematic diagram of the process control change judgment flow of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. 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.

[0021] Please refer to Figure 1 and Figure 2 As shown, the present invention provides a monitoring and control management system for the production process of sodium dibutyryl cyclic adenosine phosphate, which includes: a production data monitoring module, an equipment data import module, a process production analysis module, a process adjustment confirmation module, and a process control execution terminal.

[0022] Among the above, the process production analysis module is respectively connected to the production data monitoring module, the equipment data import module, and the process adjustment confirmation module, and the process adjustment confirmation module is also connected to the process control execution terminal.

[0023] The production data monitoring module is used to collect the production parameters of the corresponding mixing process, reaction process, and separation process of the current production line.

[0024] In a specific embodiment, each process may specifically consist of a mixing process, a reaction process, a separation process, etc. The embodiments of the present invention use the mixing process, the reaction process, and the separation process as specific examples for information supplementation, as shown in Table 1 specifically.

[0025] Example of Partial Information for Each Process in Table 1

[0026]

[0027] The device data import module is used to import the inspection record form of production equipment.

[0028] It should be added that the inspection record form records basic equipment information such as equipment number, name, model, etc. Inspection items include various performance indicators and operating parameters of the equipment, etc. The inspection time is accurate to the specific date and time. Multiple pieces of information such as the information of the inspection personnel are manually imported independently.

[0029] The process production analysis module is used to perform production self - adaptation analysis and process linkage analysis based on the production parameters and the inspection record form, and output the production status compliance degree and process linkage compliance degree of the mixing, reaction, and separation processes, and accordingly judge whether process control changes are required.

[0030] Through production self - adaptation analysis and process linkage analysis in the embodiments of the present invention, the problem of lack of linkage monitoring and analysis between processes is solved. It can monitor and adjust the mutual influence and interference between processes in real time, improve the coordination between processes and the self - adaptation ability of management. At the same time, it can optimize production efficiency, reduce resource waste, and can also timely discover and solve potential problems to ensure the stability of the production process.

[0031] Specifically, performing production self - adaptation analysis includes: A1. Extract the initial set mixing duration, current mixing duration, real - time monitored temperature, and the content of each material component at each monitoring position in the production parameters of the mixing process, and statistically calculate the production status compliance degree of the mixing process.

[0032] A2. Extract the current reaction duration, reaction temperature, reaction pressure, product concentration and their corresponding target values from the production parameters of the reaction process, calculate the temperature, pressure, product concentration deviation and reaction rate, and after normalization, perform weighted summation to obtain the production status compliance degree of the reaction process.

[0033] A3. Extract the current separation duration, product purity, recovery rate and their corresponding target values from the production parameters of the separation process, calculate the purity and recovery rate deviation, and after normalization, perform weighted summation to obtain the production status compliance degree of the separation process.

[0034] A4. Take the production status compliance degrees of the mixing, reaction, and separation processes as the production self - adaptation analysis results.

[0035] Understandably, production is usually a continuous process. From the input of raw materials to the output of the final product, each process is closely linked. For example, in pharmaceutical and chemical production, raw materials need to go through a series of continuous processes such as atmospheric and vacuum distillation, catalytic cracking, and hydrofining before they can be converted into products. This continuity requires that the production process cannot be easily interrupted, otherwise it may lead to a decline in product quality, equipment damage, and economic losses. At the same time, there is a close interrelationship between the various processes in the production line. The output of one process is often the input of the next process, and the process parameters and product quality of the previous process will affect the subsequent processes. Therefore, it is necessary to comprehensively manage and coordinate the processes of the entire production line to ensure the smooth progress of production. Therefore, the present invention selects the coordination situation of process linkage and the production status of each process as the main entry points for analysis to ensure the coherence and reliability of the overall production.

[0036] Further, in step A1, the production status compliance of the mixing process is statistically analyzed, including: A11. Select the maximum temperature from the real-time monitored temperatures, calculate the temperature change rate, and at the same time, calculate the proportion of each material component based on the content of each material component.

[0037] A12. For the same material component, calculate the standard deviation of its content at different monitoring positions, denoted as the content difference degree, and select the maximum content difference degree.

[0038] A13. Calculate the ratio of the current mixing duration to the initially set mixing duration, denoted as the current mixing progress ratio. According to the mixing progress ratio, locate the reference temperature range, reference temperature change rate range, and reference proportion of each material component from the pre-set mixing reference data table.

[0039] A14. If the maximum temperature exceeds the reference temperature range or the temperature change rate exceeds the safe temperature change rate range, assign the temperature status compliance value to 0. If both are within the corresponding reference ranges, assign the temperature status compliance value to 1.

[0040] A15. Input the proportion of the material components, the reference proportion, and the maximum content difference degree at each monitoring position into the multi-layer perceptron model to output the mixing status compliance.

[0041] A16. Integrate the temperature status compliance and the mixing status compliance through a weighted model to obtain the production status compliance of the mixing process.

[0042] Understandably, calculate the ratio of the current cumulative mixing duration to the initially set mixing duration, denoted as the current mixing progress ratio. The purpose of this step is to measure the stage at which the current mixing process is within the entire preset mixing time range. For example, if the initially set mixing duration is 10 hours and the current cumulative mixing is 3 hours, then the current mixing progress ratio is 0.3. Then, locate the reference temperature range, the safe temperature change rate range, and the reference proportions of each material component at the current mixing progress ratio from the pre-set mixing monitoring data table. This mixing monitoring data table is summarized based on a large amount of experimental data and production experience. It details the reasonable temperature range, the temperature change rate range, and the proportions of each material component that the mixing process should exhibit at different mixing progress ratios and serves as reference data.

[0043] It should be noted that for the sake of concise explanation, the multi-layer perceptron model is denoted as MLP. The MLP consists of an input layer, multiple hidden layers, and an output layer. The input layer receives the proportion and content difference data of each material component. The hidden layer performs non-linear transformation on the input data through an activation function to learn the complex relationships in the data. The output layer then outputs the value of the material mixing state conformity. For example, the MLP is trained with a large amount of historical mixing data to enable the model to learn the appropriate mixing state conformity corresponding to different combinations of material component proportions and content difference degrees. Then, for new input data, the corresponding conformity evaluation result can be quickly output. Using the MLP can handle non-linear relationships, has good fitting ability for complex data, and for possible overfitting problems, it can be addressed by reasonably setting the number of layers and nodes of the hidden layer and performing regularization processing.

[0044] It should be noted that in order to ensure that the value ranges of the temperature state conformity and the mixing state conformity are the same, the Sigmoid activation function or the Softmax activation function can be used in the output layer of the MLP.

[0045] Exemplarily, the specific output process of the mixing state conformity of the mixing process output by the multi-layer perceptron model is outlined as follows: 1) Collect training data.

[0046] Understandably, the training data should include the proportions, reference proportions, and maximum content difference degrees of each material component at each monitoring position under different conditions, as well as the labels of the mixing state conformity of the corresponding mixing process. This data can be obtained from historical production records or carefully designed experiments.

[0047] 2) Construct a multi-layer perceptron model.

[0048] It should be noted that for the input layer: the number of neurons in the input layer is equal to the number of input features, that is, the proportions of each material component at n monitoring positions, n reference proportions, and a maximum material component content difference degree, for a total of n + 1 input neurons.

[0049] Hidden layer: One or more hidden layers can be set. Each hidden layer contains a certain number of neurons. These neurons perform a non-linear transformation on the input through a non-linear activation function, such as the ReLU function or the Sigmoid function. The number of neurons and the number of layers in the hidden layer can be adjusted according to the complexity of the specific problem and the scale of the training data. For example, two hidden layers can be set, with 128 neurons in the first layer and 64 neurons in the second layer.

[0050] Output layer: The number of neurons and the activation function in the output layer are set according to the type of task. If it is a regression task, aiming to output a continuous mixed state matching degree between 0 and 1, one neuron can be used, and the Sigmoid activation function can be used to limit the output between 0 and 1. If it is a classification task, the number of neurons in the output layer depends on the number of classification categories. If divided into two categories (matched and unmatched), one neuron can be used and the Sigmoid activation function can be used to interpret the output as the probability of belonging to a certain category. If divided into multiple categories, the Softmax activation function can be used to convert the output into a probability distribution. The background of the present invention is a regression task, so the Sigmoid activation function can be selected.

[0051] 3) Forward propagation needs to be performed through the MLP.

[0052] Understandably, in the training and prediction phases, the data needs to go through forward propagation through the MLP, and the calculation process is as follows: The input data enters the input layer, and each input neuron receives the corresponding feature value.

[0053] For each neuron in the hidden layer , its input is the sum of the output of the neurons in the previous layer multiplied by the corresponding weight plus the bias , that is , and then the output of this neuron is obtained through the activation function , represents the hidden layer neuron index, represents the layer index.

[0054] For the neurons in the output layer , the calculation method is similar to that of the hidden layer. The output of the last hidden layer is used as the input for calculation , and then calculate the final output according to the activation function of the output layer , represents the neuron index of the output layer.

[0055] 4) Use the collected data to train the MLP model.

[0056] It should be added that training the MLP model with data includes selecting a loss function. Since this invention belongs to a regression task, the mean squared error can be selected as the loss function. At the same time, optimization algorithms such as stochastic gradient descent, Adam, Adagrad, etc. are used to update the weights and biases of the model to minimize the loss function. The optimization algorithm calculates the gradient of the loss function with respect to each weight and bias and updates the parameters according to the gradient.

[0057] 5) After training the MLP model, use the proportions of each material component, the reference proportion, and the maximum material component content difference at each new monitoring position as inputs, and calculate the output through forward propagation.

[0058] In a specific embodiment, the weights of the temperature state compliance and the mixing state compliance can be set to 0.4 and 0.6 respectively.

[0059] Furthermore, the normalization processing methods in steps A2 and A3 are the same. Taking the temperature deviation as an example for the normalization processing example, subtract the temperature deviation from the set reference temperature deviation, divide the difference by the set reference temperature deviation. If the ratio is greater than or equal to 0, take 0 as the normalization result. If the ratio is less than 0, take the absolute value of the ratio as the normalization result.

[0060] Specifically, the specific analysis process of the process linkage analysis is as follows: B1. Extract the influence coefficients between each process, construct a process transfer matrix in combination with the production state compliance, and perform weighted averaging on the matrix elements to obtain the global production compliance.

[0061] B2. Extract the energy parameters at the inlet and outlet from the production parameters, calculate the energy utilization rate, loss rate, and balance deviation based on the law of conservation of energy. After standardization processing, calculate the energy transfer balance degree through the entropy method and select the minimum value.

[0062] B3. Extract the production identifiers from the production parameters, mark the processes with the production identifier as completed as the analysis processes, count the actual time differences of each analysis process, select the minimum and maximum time differences, and calculate the ratio of the two as the production rhythm matching degree.

[0063] B4. Perform weighted averaging on the global production compliance, the minimum energy transfer balance degree, and the production rhythm matching degree, and output the process linkage compliance degree.

[0064] An example of the specific statistical process for the global production compliance in step B1 is as follows: B11. Denote the influence coefficient of the mixing process on the reaction process as , and denote the influence coefficient of the mixing process on the separation process as . Denote the influence coefficient of the chemical reaction process on the separation and purification process as .

[0065] B12. Denote the transfer matrix between processes as . Denote the production status compliance of the mixing, reaction, and separation processes as , and respectively. .

[0066] B12. Since the influence of mixing on chemical reaction is relatively large and the influence on separation and purification is relatively small, set = 0.6, = 0.4. Since the influence of chemical reaction on separation and purification is relatively large, set = 0.7, that is The specific instantiation is: . The global production compliance is obtained by weighted averaging all elements of the transfer matrix, that is , represents the global production compliance, is the total number of processes, represents the element in the transfer matrix between processes. Further assume that , and take values of 0.85, 0.78, and 0.92 in sequence. The transfer matrix between processes is , .

[0067] Regarding what needs to be supplemented in step B2, the energy parameters of the import and export include but are not limited to temperature, pressure, flow rate, voltage, and current.

[0068] It also needs to be supplemented that, according to the law of conservation of energy, before calculating the energy utilization rate, energy loss rate, and energy balance deviation, first calculate the energy input and energy output of each process, and take the difference between the two as the energy loss. Furthermore, denote the ratio of energy output to energy input as the energy utilization rate, denote the ratio of energy loss to energy input as the energy loss rate, and denote the difference between energy input and output as the energy balance deviation.

[0069] In a specific embodiment, assume that the material flow rate of a certain reaction process is 100 kg / s, the specific heat capacity is 4.18, the inlet temperature is 100 °C, and the outlet temperature is 80 °C, the reference temperature is 25 °C. Heat energy input is: .

[0070] Heat energy output is: .

[0071] Heat energy loss is: .

[0072] Another specifically, please refer to Figure 3 as shown, to determine whether process control change is required, including: C1, determining whether the production status compliance of the mixing process is less than the set reference production status compliance.

[0073] C2, if yes, determining that the mixing process requires process control change, otherwise, proceeding to the next step.

[0074] C3, determining whether the production status compliance of the reaction process is less than the set reference production status compliance, if yes, determining that the reaction process requires process control change, otherwise, proceeding to the next step.

[0075] C4, determining whether the production status compliance of the separation process is less than the set reference production status compliance, if yes, determining that the separation process requires process control change, otherwise, proceeding to the next step.

[0076] C5, determining whether the process linkage compliance is less than the set reference process linkage compliance, if yes, determining that the process connection requires process control change, otherwise, determining that process control change is not required.

[0077] Further, the specific setting process of the above reference production status compliance is as follows: The first step, extract the date, performance indicators, basic parameters and abnormal events of each inspection from the inspection record form, set evaluation indicators, calculate the index compliance of each inspection based on the relative error method, and obtain the comprehensive index compliance through statistical functions.

[0078] The second step, count the number of times the comprehensive index compliance is lower than the preset benchmark, which is recorded as the number of type-I abnormal inspections. Count the highest continuous number of times lower than the benchmark, which is recorded as the number of type-II abnormal inspections.

[0079] The third step, divide the number of type-I and type-II abnormal inspections by the total number of inspections respectively to obtain the type-I inspection abnormal ratio and type-II abnormal ratio, and calculate the comprehensive inspection abnormal ratio through weighted average.

[0080] The fourth step, correct the reference production status compliance based on the comprehensive inspection abnormal ratio to obtain the reference production status compliance.

[0081] In a specific embodiment, the data in the verification record table and the set evaluation indicators are specifically shown in Table 2 below.

[0082] Table 2 Schematic Table of Data in the Verification Record Table and Set Evaluation Indicators

[0083]

[0084] It should be added that the statistical formula of the relative error method is: Index coincidence degree = (1 - min(1, |actual monitoring and analysis value - standard value| / standard value)) × 100%. For indicators within the standard range, the coincidence degree is 100%. For indicators outside the standard range, the coincidence degree is calculated according to the degree of exceeding. Among them, the standard value can be manually input or calculated based on historical production data.

[0085] In another specific embodiment, to obtain the comprehensive index coincidence degree through a statistical function, a linear regression function can be specifically used for statistics. The linear regression function model is simple and intuitive, with clear parameter meanings, facilitating the understanding and interpretation of results. Moreover, it has strong predictability, can predict the dependent variable value based on the known independent variable value to evaluate the coincidence degree, and can handle various variable types. Multiple linear regression can consider the influence of multiple factors. When dealing with big data, it can quickly obtain results and improve the ability to analyze the comprehensive index coincidence degree.

[0086] Regarding what needs to be added in the fourth step, the specific correction formula for correcting based on the pre-set benchmark production status coincidence degree for comprehensive verification anomalies is as follows: Referenced production status coincidence degree = min[pre-set production status coincidence degree threshold, (1 + comprehensive verification anomaly ratio) × pre-set benchmark production status coincidence degree].

[0087] The process adjustment confirmation module is used to, when process control changes are required, judge and output adjustment categories based on pre-set adjustment judgment rules, and confirm the adjusted production control indicators based on the adjustment categories.

[0088] Specifically, the adjustment judgment rules are composed of a combined nested structure of a mixed process adjustment judgment sub-rule and a reaction process adjustment judgment sub-rule. When it is judged that the mixed process requires process control changes, the mixed process adjustment judgment sub-rule is triggered, and the adjustment categories are output, including the mixing temperature, mixing duration, and stirring speed.

[0089] When it is judged that the reaction process requires process control changes, the reaction process adjustment judgment sub-rule is triggered, and the adjustment categories are output, including the reaction temperature and reaction pressure.

[0090] When it is judged that the separation process requires process control changes, the separation environment is used as the adjustment category.

[0091] When it is determined that process control changes are required for process connection, the production rhythm is used as the adjustment category.

[0092] It should be added that the specific judgment process of the mixing process adjustment judgment sub-rule is as follows: If the temperature state compliance is lower than the corresponding set threshold, the mixing temperature is used as the adjustment category.

[0093] If the mixing state compliance is lower than the corresponding set threshold, it is judged whether the current mixing progress ratio exceeds the set reference mixing progress ratio. If it exceeds, the mixing duration is used as the adjustment item; otherwise, the stirring speed is used as the adjustment item.

[0094] It should be added that the specific judgment process of the reaction process adjustment judgment sub-rule is as follows: If the normalized result of the temperature deviation or the normalized result of the reaction rate is 0, the reaction temperature is used as the adjustment category; if the normalized result of the pressure deviation is 0, the reaction pressure is used as the adjustment category; if the normalized result of the product concentration deviation is 0, the reaction temperature and the reaction rate are used as the adjustment category.

[0095] Specifically, the adjusted production control indicators are confirmed, including: D1. When the adjustment category is the mixing temperature, the temperature compliance is used as the input variable, and the mixing temperature adjustment factor is determined through a logical function, which is multiplied by the preset single adjustment temperature value to obtain the increased temperature value, and added to the currently detected temperature to obtain the adjusted target mixing temperature, which is used as the adjusted production control indicator.

[0096] D2. When the adjustment category is the mixing duration or the stirring speed, the mixing state compliance is used as the input variable, and the mixing time adjustment factor and the stirring speed adjustment factor are respectively determined in the same way as the setting method of the mixing temperature adjustment factor, and the adjusted target mixing duration and the adjusted target stirring speed are confirmed as the adjusted production control indicators.

[0097] D3. When the adjustment category is the reaction temperature, the normalized temperature deviation is used as the input variable, the reaction temperature adjustment factor is set, and the adjusted target reaction temperature is confirmed in the same way as the adjustment method of the mixing temperature, and then used as the adjusted production control indicator.

[0098] D4. When the adjustment category is the reaction pressure, the normalized pressure deviation is used as the input variable, the reaction pressure adjustment factor is set, and the adjusted target reaction pressure is confirmed in the same way as the adjustment method of the mixing temperature and used as the adjusted production control indicator.

[0099] D5. When the adjustment category is the separation environment, the separation environment parameter combination is confirmed and used as the adjusted production control indicator.

[0100] D6. When the adjustment category is the production rhythm, the process linkage compliance is used as the input variable, the rhythm adjustment factor is set, and the target production rhythm is confirmed according to the adjustment method of the mixing temperature, which is used as the adjustment production control index.

[0101] In a specific embodiment, the logical function can specifically adopt the Sigmoid function. The logical function determines the setting of adjustment factors such as the mixing temperature. It can not only accurately adjust the mixing temperature according to the input variable, such as fine-tuning when the compliance is high and large adjustment when it is low, but also flexibly adapt to different application scenarios. By changing the function logic and parameters, it can meet the requirements of different working conditions, etc. At the same time, it can enhance the stability and reliability of the system, avoid excessive or unreasonable adjustment, and is convenient for integration and optimization with other systems to form a coordinated control system.

[0102] The embodiment of the present invention solves the problem of difficult to comprehensively evaluate the impact of equipment status on production by judging the adjustment category and confirming the adjustment production control index, realizes specific, data-based and targeted production management, and can dynamically adapt to the changes in the production process.

[0103] Further, confirm the separation environment parameter combination, including: D51. The separation flow rate, separation pressure and separation temperature are used as each separation environment parameter.

[0104] D52. According to the physical and chemical principles of the separation process, establish a mathematical model of the separation process. Use the established mathematical model to predict the product purity and recovery rate at each moment within a set time window.

[0105] D53. Define the constraint conditions, and at the same time use the optimization algorithm to find the separation environment parameter combination that minimizes the cost function, which is used as the separation environment parameter combination.

[0106] Regarding what needs to be supplemented in step D52, according to the physical and chemical principles of the separation process, establish a mathematical model of the separation process, where the mathematical model can be composed of a mass balance equation, an energy balance equation, a phase balance equation and a kinetic equation. Among them, the mass balance equation, energy balance equation, phase balance equation and kinetic equation are existing equations and are not exemplified here.

[0107] Specifically, based on the above mathematical model, the product purity and recovery rate at each moment within a set time window can be predicted through the following steps: U1. Set the initial conditions and operating conditions.

[0108] Among them, the initial conditions are such as the total amount of materials in the tower, the molar fraction of components, temperature, pressure, etc., and the operating conditions are such as the feed flow rate, heating power, cooling power, etc.

[0109] U2. Solve the mass balance equation, energy balance equation, and phase equilibrium equation using numerical methods, and calculate the component mole fractions of the overhead distillate and bottom product at each moment;

[0110] Among them, the numerical methods are specifically such as the Euler method and the Runge-Kutta method.

[0111] U3. Calculate the product purity and recovery rate.

[0112] Among them, the purity of the overhead product: the component mole fraction of the target product in the overhead distillate × 100%, and the purity of the bottom product: the component mole fraction of the target product in the bottom product × 100%.

[0113] Among them, the purity of the overhead product: the component mole fraction of the target product in the overhead distillate × the flow rate of the overhead distillate, and the purity of the bottom product: the component mole fraction of the target product in the bottom product × the flow rate of the bottom product.

[0114] U4. Repeat the above steps within the set time window to calculate the product purity and recovery rate at each moment.

[0115] Regarding step D53, the defined constraint conditions can be set according to the total mass conservation of substances and the set value ranges of parameters, such as the separation temperature must be within the range that the equipment can withstand: , and represent the lowest temperature and the highest temperature that the equipment can withstand.

[0116] Regarding step D53, it should also be noted that the optimization algorithm needs to be selected correspondingly according to the nature of the problem and the complexity of the constraint conditions. If both the cost function and the constraint conditions are linear, the linear programming algorithm can be used. The linear programming algorithm has the characteristics of high efficiency and stability and can find the global optimal solution within polynomial time. Common linear programming solvers include the simplex method, the interior point method, etc. When the cost function or the constraint conditions are non-linear, the non-linear programming algorithm needs to be used. The non-linear programming algorithm can be divided into local optimization algorithms and global optimization algorithms. Local optimization algorithms such as the gradient descent method, the Newton method, etc., and global optimization algorithms such as the genetic algorithm, the simulated annealing algorithm, etc. For optimization problems with constraint conditions, a dedicated constraint optimization algorithm can be used, such as the sequential quadratic programming algorithm. The sequential quadratic programming algorithm gradually approaches the optimal solution by iteratively solving a series of quadratic programming sub-problems and has good performance in dealing with non-linear constraint optimization problems.

[0117] Furthermore, before using the optimization algorithm, it also includes creating a cost function, and its specific expression formula is as follows: , represents the time number, and respectively represent the product purity and recovery rate at the predicted th moment, and respectively represent the target purity and target recovery rate,

[0118] The process control execution terminal is used to perform corresponding control based on the analysis result of the process adjustment confirmation module.

[0119] In a specific embodiment, the process control execution is specifically shown in Table 3.

[0120] Table 3 Schematic Table of Process Control Execution

[0121]

[0122] In the embodiment of the present invention, by setting up a production data monitoring module to collect parameters in real time, an equipment data import module to introduce equipment status data, a process production analysis module to judge whether process control changes are needed, and timely respond to production changes. The process adjustment confirmation module clarifies the change content and triggers the adjustment analysis module to accurately lock the adjustment process and indicators. Each module cooperates closely, significantly improving the flexibility, stability and efficiency of production, ensuring product quality while reducing costs, enhancing the adaptability of the production line to complex working conditions, and greatly improving the refinement level of production management.

[0123] It should be noted that the temperature in each process is obtained by real-time monitoring with a temperature sensor. The temperature sensor accurately measures the temperature and records the test data, providing data support for subsequent data screening.

[0124] The above content is only an example and explanation of the concept of the present invention. Those skilled in the art of the present technology make various modifications or supplements or use similar methods to replace the specific embodiments described, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all belong to the protection scope of the present invention.

Claims

1. A monitoring and control management system for the production process of sodium dibutyryl cyclic adenosine phosphate, characterized in that, Including: A production data monitoring module, which is used to collect the production parameters of the corresponding mixing process, reaction process and separation process of the current production line; An equipment data import module, which is used to import the nuclear inspection record form of production equipment; A process production analysis module, which is used to perform production adaptive analysis and process linkage analysis based on the production parameters and the nuclear inspection record form, output the production status compliance degrees of the mixing, reaction and separation processes and the process linkage compliance degree, and judge whether process control changes are needed accordingly; A process adjustment confirmation module, which is used to judge and output adjustment categories based on pre-set adjustment judgment rules when process control changes are needed, and confirm the adjusted production control indicators based on the adjustment categories; A process control execution terminal, which is used to perform corresponding control based on the analysis result of the process adjustment confirmation module.

2. The monitoring and control management system for the production process of sodium dibutyryl adenosine cyclophosphate according to claim 1, wherein: The performing of the production adaptive analysis includes: Extracting the initial set mixing duration, current mixing duration, real-time monitored temperature, and the content of each material component in each monitoring position from the production parameters of the mixing process, and statistically calculating the production status compliance degree of the mixing process; Extracting the current reaction duration, reaction temperature, reaction pressure, product concentration and corresponding target values from the production parameters of the reaction process, calculating the temperature, pressure, product concentration deviation and reaction rate, and performing weighted summation after normalization to obtain the production status compliance degree of the reaction process; Extracting the current separation duration, product purity, recovery rate and corresponding target values from the production parameters of the separation process, calculating the purity and recovery rate deviation, and performing weighted summation after normalization to obtain the production status compliance degree of the separation process; Taking the production status compliance degrees of the mixing, reaction and separation processes as the production adaptive analysis results.

3. The monitoring and control management system for the production process of sodium dibutyryl cyclic adenosine phosphate according to claim 2, wherein: The statistically calculating the production status compliance degree of the mixing process includes: Screening out the maximum temperature from the real-time monitored temperature, calculating the temperature change rate, and at the same time calculating the proportion of each material component based on the content of each material component; For the same material component, calculating the standard deviation of its content in different monitoring positions, which is denoted as the content difference degree, and screening out the maximum content difference degree; Calculating the ratio of the current mixing duration to the initial set mixing duration, which is denoted as the current mixing progress ratio, and positioning the reference temperature range, reference temperature change rate range and reference proportion of each material component from the pre-set mixing reference data table according to the mixing progress ratio; If the maximum temperature exceeds the reference temperature range or the temperature change rate exceeds the safe temperature change rate range, assigning the temperature status compliance degree to 0, and if both are within the corresponding reference ranges, assigning the temperature status compliance degree to 1; Inputting the proportion of the material components in each monitoring position, the reference proportion and the maximum content difference degree into a multi-layer perceptron model, and outputting the mixing status compliance degree; Integrating the temperature status compliance degree and the mixing status compliance degree through a weighted model to obtain the production status compliance degree of the mixing process.

4. The monitoring and control management system for the production process of sodium dibutyryl cyclic adenosine phosphate according to claim 1, wherein: The specific analysis process of the process linkage analysis is as follows: Extracting the influence coefficients between each process, constructing a process transfer matrix in combination with the production status compliance degree, and performing weighted averaging on the matrix elements to obtain the global production compliance degree; Extract the energy parameters of import and export from the production parameters, calculate the energy utilization rate, loss rate and balance deviation based on the law of conservation of energy, calculate the energy transfer balance degree by the entropy method after standardization, and screen the minimum value; Extract the production identification from the production parameters, record the process with the production identification as completed as the analysis process, count the actual time differences of each analysis process, screen the minimum and maximum time differences, and calculate the ratio of the two as the production rhythm matching degree; Perform a weighted average on the global production compliance degree, the minimum energy transfer balance degree and the production rhythm matching degree, and output the process linkage compliance degree.

5. The monitoring and control management system for the production process of sodium dibutyryl cyclic adenosine phosphate according to claim 3, wherein: The determination of whether process control changes are required includes: Judge whether the production status compliance degree of the mixing process is less than the set reference production status compliance degree; If yes, judge that the mixing process requires process control changes, otherwise, proceed to the next step; Judge whether the production status compliance degree of the reaction process is less than the set reference production status compliance degree. If yes, judge that the reaction process requires process control changes, otherwise, proceed to the next step; Judge whether the production status compliance degree of the separation process is less than the set reference production status compliance degree. If yes, judge that the separation process requires process control changes, otherwise, proceed to the next step; Judge whether the process linkage compliance degree is less than the set reference process linkage compliance degree. If yes, judge that the process connection requires process control changes, otherwise, judge that process control changes are not required.

6. The monitoring and control management system for the production process of sodium dibutyryl cyclic adenosine phosphate according to claim 4, characterized in that: The specific setting process of the reference production status compliance degree is as follows: Extract the date, performance indicators, basic parameters and abnormal events of each nuclear reduction from the nuclear inspection record form, set evaluation indicators, calculate the index compliance degree of each nuclear inspection based on the relative error method, and obtain the comprehensive index compliance degree through statistical functions; Count the number of times the comprehensive index compliance degree is lower than the preset benchmark, which is recorded as the number of first-class abnormal nuclear inspection times; count the highest continuous number of times lower than the benchmark, which is recorded as the number of second-class abnormal nuclear inspection times; Divide the number of first-class and second-class abnormal nuclear inspection times by the total number of nuclear inspections respectively to obtain the first-class nuclear inspection abnormal ratio and the second-class abnormal ratio, and calculate the comprehensive nuclear inspection abnormal ratio through weighted average; Based on the comprehensive nuclear inspection abnormal ratio, correct the benchmark production status compliance degree to obtain the reference production status compliance degree.

7. The monitoring and control management system for the production process of sodium dibutyryl cyclic adenosine phosphate according to claim 4, wherein: The adjustment judgment rule is composed of a combination and nesting of a mixing process adjustment judgment sub-rule and a reaction process adjustment judgment sub-rule; When it is judged that the mixing process requires process control changes, trigger the mixing process adjustment judgment sub-rule and output the adjustment categories, including mixing temperature, mixing duration and stirring speed; When it is judged that the reaction process requires process control changes, trigger the reaction process adjustment judgment sub-rule and output the adjustment categories, including reaction temperature and reaction pressure; When it is judged that the separation process requires process control changes, take the separation environment as the adjustment category; When it is judged that the process connection requires process control changes, take the production beat as the adjustment category.

8. The monitoring and control management system for the production process of sodium dibutyryl cyclic adenosine phosphate according to claim 7, wherein: The confirmation of adjusting the production control indicators includes: When the adjustment category is the mixed temperature, using the temperature matching degree as the input variable, the mixed temperature adjustment factor is determined through a logical function, multiplied by the preset single adjustment temperature value to obtain the increased temperature value, and added to the currently detected temperature to obtain the adjusted target mixed temperature, which is used as the adjusted production control index; When the adjustment category is the mixing duration or the stirring speed, using the mixing state matching degree as the input variable, in the same way as setting the mixed temperature adjustment factor, the mixing time adjustment factor and the stirring speed adjustment factor are respectively determined, and the adjusted target mixing duration and the adjusted target stirring speed are confirmed, which are used as the adjusted production control index; When the adjustment category is the reaction temperature, using the normalized temperature deviation as the input variable, setting the reaction temperature adjustment factor, and confirming the adjusted target reaction temperature in the same way as adjusting the mixed temperature, which is then used as the adjusted production control index; When the adjustment category is the reaction pressure, using the normalized pressure deviation as the input variable, setting the reaction pressure adjustment factor, and confirming the adjusted target reaction pressure in the same way as adjusting the mixed temperature, which is used as the adjusted production control index When the adjustment category is the separation environment, confirming the separation environment parameter combination, which is used as the adjusted production control index; When the adjustment category is the production beat, using the process linkage matching degree as the input variable, setting the beat adjustment factor, and confirming the adjusted target production beat in the same way as adjusting the mixed temperature, which is used as the adjusted production control index.

9. The monitoring and control management system for the production process of sodium dibutyryl cyclic adenosine phosphate according to claim 8, characterized in that: The confirmation of the separation environment parameter combination includes: Regarding the separation flow rate, separation pressure, and separation temperature as the respective separation environment parameters; According to the physical and chemical principles of the separation process, establishing a mathematical model of the separation process, and using the established mathematical model to predict the product purity and recovery rate at each moment within the set time window; Defining the constraint conditions, and at the same time using an optimization algorithm to find the separation environment parameter combination that minimizes the cost function, which is used as the separation environment parameter combination.

10. A monitoring and control management system for the production process of sodium dibutyryl cyclic adenosine phosphate as described in claim 9, characterized in that: Before using the optimization algorithm, it also includes creating a cost function, and its specific representation formula is as follows: , represents the time number,[[]] and respectively represent the product purity and recovery rate at the th predicted time,[[]] and respectively represent the target purity and target recovery rate,[[]] and respectively represent the weight coefficients of purity and recovery rate.[[]]

Images