Intelligent control method for parameters of rectifying tower for waste liquid treatment

Abstract

The invention provides a rectifying tower parameter intelligent control method for waste liquid treatment, and relates to the technical field of rectifying tower intelligent control. Comprising the steps of collecting influence data in a waste liquid treatment process in real time; analyzing energy utilization efficiency and mass transfer efficiency in the waste liquid rectification and purification process according to the influence data, calculating a reliability factor of key equipment, and constructing a linear relation; constructing a rectification purification mode according to the linear relation and the reliability factor of the equipment, and optimizing the running parameter ratio of the equipment by using an improved self-adaptive genetic algorithm; the optimal operation parameter ratio is converted into a control instruction, and the control instruction is executed; product quality data and equipment operation state data in the waste liquid treatment process are monitored in real time, the deviation value between actual data and an expected target is analyzed, and the operation parameter ratio of all equipment is adjusted according to the actual situation. According to the invention, a rectification purification mode is constructed, and an improved self-adaptive genetic algorithm is used to optimize the operation parameter ratio of each device, so that the intelligent control of waste liquid rectification is realized.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology for distillation columns, and in particular to an intelligent control method for parameters of a distillation column used for waste liquid treatment. Background Technology

[0002] With increasingly stringent environmental regulations, there are ever-higher restrictions on the discharge of industrial wastewater. Organic solvents such as DMF and DMAC, if discharged directly without proper treatment, can cause serious pollution to water bodies, soil, and other environmental media.

[0003] Industrial treatment of DMF waste liquid often employs conventional distillation processes, separating the solvent and water through heating and distillation. Traditional distillation columns rely on manually setting parameters such as reflux ratio, reboiler temperature, and feed rate, failing to consider dynamic factors such as fluctuations in DMF concentration and changes in ambient temperature. This results in low distillation efficiency. Conventional processes do not optimize the separation process for the differences in the physical properties of DMF and DMAC, easily leading to cross-entrainment of the two solvents during the distillation of mixed waste liquid. The remaining solvent is discharged with the bottom wastewater, wasting resources and increasing the burden on subsequent treatment. Furthermore, the inability to dynamically adjust operating parameters based on measured data of the purity of the top product and the concentration of the bottom residue results in the system operating in a suboptimal state for extended periods. Summary of the Invention

[0004] This invention provides an intelligent control method for the parameters of a distillation column used for waste liquid treatment, which solves the defects of low distillation efficiency, waste of resources, and increased pressure on subsequent treatment in the prior art.

[0005] On one hand, the present invention provides an intelligent control method for parameters of a distillation column for waste liquid treatment, comprising: S1: Real-time collection of impact data during the DMF waste liquid treatment process, including waste liquid characteristic data, equipment operating status data, and environmental parameter data; S2: Based on the impact data, analyze the energy utilization efficiency and mass transfer efficiency in the DMF waste liquid distillation and purification process, calculate the reliability factor of key equipment, and analyze the linear relationship between energy utilization efficiency, mass transfer efficiency and equipment operating parameters. S3: Based on the linear relationship and equipment reliability factor, a high-recovery-rate, high-purity DMF distillation purification mode is constructed, and an improved adaptive genetic algorithm is used to optimize the ratio of operating parameters of each device; S4: Convert the optimal operating parameter ratio of each device into control commands, and control each device in the waste liquid treatment system to perform DMF waste liquid collection, storage, distillation and purification according to the control commands; S5: Real-time monitoring of product quality data and equipment operating status data during DMF waste liquid treatment, analysis of deviations between actual data and expected targets, and adjustment of operating parameters of each device according to actual conditions.

[0006] According to the present invention, a method for intelligent control of distillation column parameters for waste liquid treatment is provided. In step S1, the waste liquid characteristic data includes DMF waste liquid concentration, DMAC waste liquid concentration, mass fraction of each component in the DMF mixed waste liquid, and impurity content in the waste liquid.

[0007] According to the intelligent control method for parameters of a distillation column for waste liquid treatment provided by the present invention, the process of analyzing energy utilization efficiency and mass transfer efficiency in step S2 includes: The total mass of waste liquid entering the feed heater per unit time, the mass of steam after evaporation in the evaporator, the mass of DMF steam separated by the DMF gas-liquid separator, and the mass of target components produced at the top of each level of concentration tower, distillation tower, and deacidification tower are collected.

[0008] The recovery rate of DMF is obtained by the ratio of the total mass of the target component produced per unit time to the initial total mass of the target component in the waste liquid. The energy utilization efficiency is calculated based on the energy consumption data of the reboiler and the feed heater.

[0009] Collect temperature and concentration distribution data for each tray in the four distillation towers (primary, secondary, and tertiary), the four distillation towers, and the deacidification tower. Calculate the concentration and temperature differences of the target components between adjacent trays. Combine this with the gas and liquid flow rates within the towers to obtain the mass transfer efficiency.

[0010] According to the intelligent control method for parameters of a distillation column for waste liquid treatment provided by the present invention, the process of calculating the reliability factor of key equipment in step S2 includes: A reliability assessment model for key equipment is constructed using its design life, service life, number of failures and repairs in the past year, and deviation of current operating parameters as input parameters.

[0011] The weights of each input parameter are determined using the analytic hierarchy process (AHP), namely, design life weight ω1, used life weight ω2, number of failure repairs weight ω3, and current operating parameter deviation weight ω4. The reliability factor of each device is obtained by weighted summation.

[0012] According to the intelligent control method for parameters of a distillation column for waste liquid treatment provided by the present invention, the specific steps in step S2 for establishing a linear relationship between energy utilization efficiency, mass transfer efficiency and equipment operating parameters are as follows: Define the variables required to construct a linear relationship. The independent variables are the feed circulation pump rate, the reboiler temperature of each stage of the concentration tower and the distillation tower, the flow rate of each stage of the reflux pump, and the reboiler temperature of the deacidification tower. The dependent variables are the energy utilization efficiency and the mass transfer efficiency.

[0013] The independent and dependent variables are standardized and transformed, and redundant parameters are removed through correlation analysis to obtain simplified variable data.

[0014] Based on simplified variable data, a multiple linear regression method was used to construct a model relating energy utilization efficiency, mass transfer efficiency, and equipment operating parameters. The intercept term and regression coefficients in the model were solved by the least squares method, and a preliminary model of the linear relationship among the three was established.

[0015] The impact data is divided into training and testing sets. Coefficients are calculated to measure the goodness of fit of the model. If the goodness of fit is greater than a preset threshold, significant parameters are selected by stepwise regression. The energy utilization efficiency predicted by the model is substituted into the energy balance equation. Otherwise, the weights of the regression coefficients are adjusted to obtain a linear relationship between energy utilization efficiency, mass transfer efficiency and equipment operating parameters.

[0016] According to the intelligent control method for distillation column parameters for waste liquid treatment provided by the present invention, the specific steps in step S3 for constructing a DMF distillation purification mode with high recovery rate and high purity are as follows: With the goal of minimizing total energy consumption, and with DMF recovery rate and product purity as constraints, an objective function is constructed, which is expressed as:

[0017] The parameter adjustment range is corrected based on the linear relationship and reliability factor.

[0018] Using linear relationships as a link, a mapping relationship is established between the operating parameters of each device and the recovery rate, purity, and energy consumption. The sensitivity of parameter adjustments is corrected by the device reliability factor.

[0019] Using equipment operating parameters as optimization variables in the algorithm and total energy consumption as the objective function, under the premise of satisfying the boundaries and conservation constraints of recovery rate, purity, reliability, and efficiency, a preliminary parameter ratio that synergizes energy utilization efficiency and mass transfer efficiency is found, thus forming a preliminary distillation and purification mode.

[0020] According to the intelligent control method for parameters of a distillation column for waste liquid treatment provided by the present invention, the optimal solution satisfying the conservation constraints is calculated using the gradient descent method, and the iterative formula is as follows:

[0021] In the formula, α is the learning rate, ▽Etotal is the gradient vector of the total energy consumption, and P k Let P be the vector of device operating parameters at the k-th iteration. k+1 This is the updated device operating parameter vector at the (k+1)th iteration.

[0022] According to the intelligent control method for parameters of a distillation column for waste liquid treatment provided by the present invention, the specific steps in step S3 of optimizing the ratio of operating parameters of each device using an improved adaptive genetic algorithm are as follows: Each parameter combination is encoded as a chromosome. Real number encoding is used to standardize the value of a parameter corresponding to each gene. A certain number of initial populations are randomly generated to cover different combinations within the parameter range, forming the initial solution set for algorithm optimization.

[0023] With minimizing the total energy consumption of the system as the core objective, the energy utilization efficiency and mass transfer efficiency are transformed into energy consumption correction terms by combining linear relationships, and the fitness function of the initial solution set is designed.

[0024] The current population is optimized iteratively based on the fitness function.

[0025] For each iteration of the optimized population, the current optimal chromosome is decoded into actual parameter values ​​and substituted into the energy conservation and mass conservation equations for verification. It is then determined whether the verification deviation exceeds a preset threshold. If so, the penalty weight of the corresponding constraint is increased in the next iteration.

[0026] When the rate of change of the optimal fitness value is less than the set threshold for multiple consecutive generations, the iteration is terminated, and the final optimal chromosome is decoded into the actual operating parameter values ​​of each device to obtain the device operating parameter ratio.

[0027] According to the intelligent control method for parameters of a distillation column for waste liquid treatment provided by the present invention, the specific steps for optimizing and iterating the current population are as follows: When selecting parent individuals from the current population, chromosomes with higher fitness are more likely to be selected.

[0028] Perform a crossover operation by exchanging parent gene segments through arithmetic crossover, preserving optimal parameter combinations.

[0029] When performing mutation operations and randomly perturbing gene values, the perturbation amplitude is limited according to the equipment reliability factor. An elite retention strategy is introduced, in which a portion of the best chromosomes are retained in each generation and directly enter the next generation.

[0030] According to the intelligent control method for parameters of a distillation column for waste liquid treatment provided by the present invention, the specific steps for converting the optimal operating parameter ratio of each device into control commands are as follows: Analyze the equipment operating parameter ratios, clarify the target parameter values ​​for each piece of equipment, and form a parameter-equipment correspondence table as the basis for instruction conversion.

[0031] Based on the parameter-equipment correspondence table, the target parameters are converted into control signal format target parameters according to the equipment type.

[0032] The target parameters of the control signal format are sorted according to time sequence, and timestamps and timeout thresholds are added to determine the priority of executing the sorted instructions.

[0033] It issues classification instructions and receives feedback in real time, monitors the matching degree between actual equipment parameters and instructions, sends fine-tuning instructions when deviations exceed limits, and alarms for shutdown when abnormalities persist, and generates instruction execution reports periodically.

[0034] This invention provides an intelligent control method for the parameters of a distillation column used in waste liquid treatment. By constructing a linear relationship between energy utilization efficiency, mass transfer efficiency, and equipment operating parameters, and based on this linear relationship and equipment reliability factors, a high-recovery-rate, high-purity DMF distillation purification mode is built. An improved adaptive genetic algorithm is used to optimize the ratio of operating parameters for each piece of equipment, thereby achieving intelligent control of waste liquid distillation. The beneficial effects obtained are as follows: By combining sensors with laboratory analysis and various monitoring devices and meteorological sensors, the system comprehensively and in real time collects data on waste liquid characteristics, equipment operating status, and environmental parameters. This enables the entire system to have a detailed and accurate understanding of the treatment process, laying a solid foundation for subsequent precise control and avoiding decision-making errors caused by missing or inaccurate data.

[0035] The analysis of energy utilization efficiency and mass transfer efficiency, as well as the calculation of reliability factors of key equipment and the construction of linear relationships, allow the operation of each link to be quantitatively presented. This enables a precise grasp of the inherent laws in the distillation and purification process, a clear understanding of the impact of different equipment parameters on the overall effect, and provides a scientific and reliable basis for subsequent model construction and parameter optimization.

[0036] By constructing a high-recovery, high-purity distillation purification model and utilizing an improved adaptive genetic algorithm to optimize parameter ratios, the system can achieve the lowest total energy consumption while meeting key indicators such as recovery rate and purity. This effectively reduces operating costs and improves the economic efficiency of resource utilization. Furthermore, it focuses on solving the problem of multi-tower parameter coordination, ensuring efficient and coordinated operation of the entire distillation system from feed to individual tower processing and finally to discharge, avoiding situations where local optima result in overall poor performance.

[0037] By converting the optimal parameter ratio into control commands to control the operation of each device, the entire waste liquid treatment process is ensured to operate stably according to the optimal settings. This ensures that each link is closely connected and orderly, and that the collection, storage, heating, and distillation of waste liquid, as well as the reflux and storage of products, can be completed efficiently, thereby improving the treatment efficiency.

[0038] The mechanism of real-time monitoring and dynamic parameter adjustment based on deviations can promptly address practical issues such as product quality fluctuations and equipment failures. It can ensure that the final product quality meets the standards and achieve efficient recycling of DMF resources, while also maintaining the stability of the treatment process and reducing the adverse effects caused by failures or abnormal parameters. Overall, it improves the level of intelligence in waste liquid treatment and the efficiency of resource recovery. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0040] Figure 1 This is a schematic flowchart of an intelligent control method for parameters of a distillation column for waste liquid treatment provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an intelligent control method for parameters of a distillation column for waste liquid treatment provided in an embodiment of the present invention. Figure 1 ; Figure 3 This is a schematic diagram of the structure of an intelligent control method for parameters of a distillation column for waste liquid treatment provided in an embodiment of the present invention. Figure 2 ; Figure 4 This is a schematic diagram of the structure of an intelligent control method for parameters of a distillation column for waste liquid treatment provided in an embodiment of the present invention. Figure 3 . Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0042] The following is combined with Figures 1-4 This invention describes an intelligent control method for parameters of a distillation column used in waste liquid treatment.

[0043] Figure 1 This is a schematic flowchart of an intelligent control method for parameters of a distillation column for waste liquid treatment provided in an embodiment of the present invention.

[0044] The specific structure of a distillation column includes: a pretreatment unit, a concentration unit, a distillation and refining unit, and a post-treatment and storage unit.

[0045] The pretreatment unit includes a feeder and a vapor-liquid separator: the raw material is heated by the feed heater, transported by the feed circulation pump, and enters the evaporator for preliminary vaporization. The gas phase is separated by the DMF gas-liquid separator and enters the subsequent concentration tower; the liquid phase can be returned or transferred via intermediate tank and intermediate pump to provide suitable materials for distillation.

[0046] The gas-water separator separates the gas and water mixture, separating the gas and liquid phases. The water pump at the outlet of the gas-water separator delivers the liquid phase, and the water circulation pump realizes the circulation of the water system, maintaining the system's water balance and energy utilization.

[0047] The concentration unit includes a primary concentration tower, a secondary concentration tower, and a tertiary concentration tower.

[0048] The system is centered around a primary concentration tower, with a reboiler providing heat and facilitating gas-liquid mass transfer within the tower. A top liquid tank collects the condensate from the top vapor phase, and a reflux pump returns a portion of the condensate back into the tower for reflux, maintaining the distillation environment within the tower. A water pump delivers the bottom material to the secondary concentration tower, and a feed pump is used for external delivery or transfer of bottom material.

[0049] The reboiler in the second-stage concentration tower provides heating, the liquid tank at the top of the second tower collects condensate, the reflux pump in the second tower returns the condensate, the water effluent from the second tower is discharged or reused, and the material from the second tower is pumped to the third-stage concentration tower for further concentration of DMF.

[0050] The three-stage concentration tower relies on the reboiler of the three-stage concentration tower for heating, the top liquid tank of the three towers collects condensate, the three towers reflux pump refluxes, and the three towers water pump and the three towers feed pump work together to send the high-concentration DMF material to the downstream distillation tower. The T203 tail gas condenser treats the tail gas at the top of the tower.

[0051] The distillation and refining unit includes four distillation columns, a deacidification column, and a formic acid decomposition and recovery unit.

[0052] The reboiler in the four distillation columns provides heating to enable deep distillation within the column. The condenser at the top of the distillation column condenses the vapor phase at the top of the column, and the liquid tank at the top of the distillation column collects the condensate. The reflux pump in the four columns maintains the distillation process by refluxing. The water pump and feed pump in the four columns are used for the discharge of light components from the top of the column and the delivery of high-purity DMF from the bottom of the column, respectively.

[0053] The deacidification tower reboiler in the deacidification tower is heated to process acidic DMF materials. The DMF deacidification pump transports the materials and removes acidic components through distillation. The gas phase at the top of the tower is condensed, and the DMF at the bottom of the tower is sent to subsequent purification.

[0054] Formic acid decomposition and recovery: The formic acid decomposition tower is equipped with a reboiler for heating and a condenser for condensation to decompose formic acid and other impurities. The formic acid condensate tank collects the decomposed liquid phase, realizing the removal of impurities and the recovery of resources, and ensuring the purity of DMF.

[0055] The post-processing and storage unit includes: pure DMF processing. The refined DMF is cooled by a pure DMF cooler. The upper and lower reflux pumps of DMF work together to create an internal reflux environment. The DMF condenser and DMF condensate tank ensure the condensation process. The DMF discharge pump sends the pure DMF to external storage or packaging. The defective intermediate tank temporarily stores unqualified products for further processing.

[0056] The entire DMF distillation process is as follows: The feedstock is heated by the feed heater, conveyed by the feed circulation pump, and vaporized in the evaporator. The vapor phase is separated by the DMF gas-liquid separator, and the liquid phase is regulated by an intermediate tank / intermediate pump to prepare feed for the concentration tower. Simultaneously, the vapor-liquid separator separates the vapor and liquid phases, and the outlet pump and water circulation pump maintain the water system circulation. The vapor phase feed enters the primary concentration tower, where the reboiler provides heating. Gas-liquid mass transfer occurs within the tower, and the condensate from the top of the tower is refluxed by the reflux pump. The bottom product is pumped to the secondary concentration tower via the outlet pump. The secondary concentration tower further concentrates the product, and the effluent from the secondary concentration tower discharges light components. The outlet product from the secondary concentration tower is pumped to the tertiary concentration tower. The tertiary concentration tower further concentrates the product, and the reflux pump maintains the reflux. The product is pumped to the distillation tower via the outlet pump. The material enters the fourth column of the distillation column, where the reboiler provides heat. The vapor phase at the top of the column is condensed by the top condenser and then refluxed by the fourth column's reflux pump. High-purity DMF from the bottom of the column is discharged by the fourth column's discharge pump. Acidic materials enter the deacidification column, where the reboiler provides heat and the DMF deacidification pump delivers the material. After deacidification, the material is further refined. If formic acid impurities are present, they are decomposed in the formic acid decomposition column, and the formic acid condensate tank collects the byproducts to ensure DMF purity. After refining, the DMF is cooled by the pure DMF cooler, and the internal reflux is regulated by the DMF upper / lower reflux pump. The reflux is ensured by the DMF condenser and DMF condensate tank, and finally discharged by the DMF discharge pump. Substandard products are sent to the substandard intermediate tank for further processing.

[0057] like Figure 1 As shown in the embodiment of the present invention, an intelligent control method for parameters of a distillation column for waste liquid treatment is provided. The method includes: By collecting and storing DMF (dimethylformamide) and DMAC (dimethylacetamide) waste liquids, and then purifying them through a waste liquid treatment system by distillation, the finished DMF / DMAC products are extracted and recycled as products, thus achieving resource recycling. The above uses DMF waste liquid to replace the DMF / DMAC mixed waste liquid, which will be explained in detail below.

[0058] S1: Real-time collection of impact data during the DMF / DMAC waste liquid treatment process, including waste liquid characteristic data, equipment operating status data, and environmental parameter data.

[0059] Waste liquid characteristic data are acquired through a combination of sensors and laboratory analysis, including DMF waste liquid concentration, DMAC waste liquid concentration, mass fraction of each component in the DMF / DMAC mixed waste liquid, and impurity content in the waste liquid. Monitoring devices installed on each piece of equipment track equipment operating status data in real time. The equipment includes: a gas-liquid separator outlet pump, a water circulation pump, a primary concentration tower, a reboiler for tower 1, a reflux pump for tower 1, an outlet pump for tower 1, a feed pump for tower 1, a secondary concentration tower, a reboiler for tower 2, a reflux pump for tower 2, an outlet pump for tower 2, a feed pump for tower 2, a tertiary concentration tower, a reboiler for the tertiary concentration tower, a reflux pump for tower 3, an outlet pump for tower 3, a feed pump for tower 3, a fourth distillation tower, a distillation tower reboiler, a reflux pump for tower 4, an outlet pump for tower 4, a deacidification tower, and a deacidification... The system includes a reboiler, DMF deacidification pump, pure DMF cooler, DMF upper reflux pump, DMF lower reflux pump, DMF discharge pump, formic acid decomposition tower, formic acid decomposition tower reboiler, formic acid decomposition tower condenser, feed heater, feed circulation pump, evaporator, DMF gas-liquid separator, and recovery pot. The corresponding equipment operating status data includes the flow rate and speed of each pump, the temperature and pressure of each tower, the heating power of each reboiler, the cooling efficiency of each condenser, the liquid level and pressure of the gas-liquid separator, and the liquid level and component concentration of the top liquid tanks of each tower. Environmental parameter data of the waste liquid treatment area, including ambient temperature, humidity, and atmospheric pressure, are collected in real time using meteorological sensors. Auxiliary environmental data such as the heating medium temperature of the feed heater and the steam pressure of the recovery pot are also recorded.

[0060] The specific parameter control requirements for the equipment are as follows:

[0061] S2: Based on the impact data analysis, analyze the energy utilization efficiency and mass transfer efficiency in the DMF / DMAC waste liquid distillation and purification process, calculate the reliability factor of key equipment, and construct the linear relationship between energy utilization efficiency, mass transfer efficiency and equipment operating parameters.

[0062] The process of analyzing energy utilization efficiency and mass transfer efficiency includes: The total mass of waste liquid entering the feed heater per unit time, the mass of steam after evaporation in the evaporator, the mass of DMF steam separated by the DMF gas-liquid separator, and the mass of the target component produced at the top of each stage of the concentration tower, distillation tower, and deacidification tower are collected. Based on the ratio of the total mass of the target component produced per unit time to the initial total mass of the target component in the waste liquid, the DMF / DMAC recovery rate is obtained. Combined with the energy consumption data of each reboiler and feed heater, the energy utilization efficiency is calculated, expressed by the formula:

[0063] In the formula, η e For energy utilization efficiency, m targetq represents the total mass of DMF / DMAC produced per unit time. combustion E represents the calorific value of DMF / DMAC. total This represents the total energy consumption of each reboiler and feed heater per unit time.

[0064] Temperature and concentration distribution data for each tray in the primary, secondary, and tertiary concentration towers, the four distillation towers, and the deacidification tower are collected. The concentration and temperature differences of the target component between adjacent trays are calculated. Combined with the gas and liquid flow rates within the towers, the mass transfer efficiency is obtained, expressed by the formula:

[0065] In the formula, For quality transfer efficiency. This represents the actual target component concentration difference between adjacent trays. This represents the theoretical maximum concentration difference.

[0066] The specific steps for calculating the reliability factor of critical equipment are as follows: A reliability assessment model for each piece of equipment is constructed using its design life, actual service life, number of repairs in the past 12 months, and current operating parameter deviation as input parameters. The design life and actual service life are obtained from the equipment's factory documentation and operating records. The number of repairs is statistically analyzed from the equipment maintenance log. The current operating parameter deviation is the percentage of the difference between the actual operating parameters (flow rate of the steam-water separator outlet pump, temperature of the reboiler in tower 1) and the rated parameters relative to the rated parameters.

[0067] The weights of each input parameter are determined using the Analytic Hierarchy Process (AHP): design life (0.3), spent life (0.25), number of repair failures (0.25), and current operating parameter deviation (0.2). The reliability factor of each device is calculated by weighted summation, expressed by the following formula:

[0068] In the formula, R i Let L be the reliability factor of the i-th device. d For the design life of the i-th device, L u N represents the service life of the i-th device. f D represents the number of malfunctions and repairs for the i-th device in the past 12 months. d Let σ be the deviation value of the current operating parameters of the i-th device. i This represents the standard deviation of the equipment's operating parameters over the past 30 days.

[0069] The process of constructing a linear relationship between energy utilization efficiency, mass transfer efficiency, and equipment operating parameters includes: selecting key equipment operating parameters as independent variables, including feed circulation pump rate, reboiler temperature of column 1, reflux pump flow rate of column 1, reboiler temperature of column 2, reflux pump flow rate of column 2, reboiler temperature of the tertiary concentration column, reflux pump flow rate of column 3, reboiler temperature of the distillation column, reflux pump flow rate of column 4, and reboiler temperature of the deacidification column; using energy utilization efficiency and mass transfer efficiency as dependent variables; and constructing a linear model through multiple linear regression, expressed by the formula:

[0070]

[0071] In the formula, , For the intercept term, - , - For regression coefficients, T1r is the feed circulation pump rate, Q1 is the reboiler temperature of column 1, Q1 is the reflux pump flow rate of column 1, T2r is the reboiler temperature of column 2, Q2r is the reflux pump flow rate of column 2, T3r is the reboiler temperature of the tertiary concentration column, Q3r is the reflux pump flow rate of column 3, T4r is the reboiler temperature of the distillation column, Q4r is the reflux pump flow rate of column 4, and Td is the reboiler temperature of the deacidification column.

[0072] The historical operating data is fitted to the linear model formula, the regression coefficients are obtained by least squares method, and the predictive ability of the model is evaluated by cross-validation method to ensure that the prediction error of the model on the test set is ≤3%.

[0073] S3: Construct a high-recovery, high-purity DMF / DMAC distillation purification mode based on linear relationships and equipment reliability factors, and use an improved adaptive genetic algorithm to optimize the ratio of operating parameters for each piece of equipment.

[0074] The specific steps for constructing a distillation purification model are as follows: With the goal of minimizing total energy consumption, and with DMF / DMAC recovery rate and product purity as constraints, an objective function is constructed as follows:

[0075] In the formula, P represents the total energy consumption of the system. i Let t be the power of the i-th device. i This refers to the equipment's uptime.

[0076] The parameter adjustment range is corrected based on the linear relationship and reliability factor.

[0077] Using linear relationships as a link, a mapping relationship is established between the operating parameters of each device and the recovery rate, purity, and energy consumption. The sensitivity of parameter adjustment is corrected by the device reliability factor, and the problem of multi-tower parameter coordination is addressed to ensure that the optimization of single-tower parameters does not affect the overall system objective.

[0078] Using equipment operating parameters as optimization variables in the algorithm and total energy consumption as the objective function, under the premise of satisfying the boundaries and conservation constraints of recovery rate, purity, reliability, and efficiency, a preliminary parameter ratio that synergizes energy utilization efficiency and mass transfer efficiency is found, thus forming a preliminary distillation and purification mode.

[0079] The gradient descent method is used to find the optimal solution that satisfies the conservation constraints. The iterative formula is as follows:

[0080] In the formula, α is the learning rate, ▽Etotal is the gradient vector of the total energy consumption, and P k For the k-th iteration, P is a vector representation of the device operating parameters, containing the operating parameter values ​​of each device in the current iteration. It represents the current solution in the gradient descent iteration process. k+1 This is the updated device operating parameter vector at the (k+1)th iteration, which is the new solution obtained after the gradient descent update operation.

[0081] The specific steps for optimizing the operating parameter ratios of each device using an improved adaptive genetic algorithm are as follows: Each parameter combination is encoded as a chromosome. Real number encoding is used to standardize the value of a parameter corresponding to each gene. A certain number of initial populations are randomly generated to cover different combinations within the parameter range, forming the initial solution set for algorithm optimization.

[0082] With minimizing the total energy consumption of the system as the core objective, the energy utilization efficiency and mass transfer efficiency are transformed into energy consumption correction terms by combining linear relationships, and the fitness function of the initial solution set is designed.

[0083] The current population is optimized iteratively based on the fitness function.

[0084] When selecting parent individuals from the current population, chromosomes with higher fitness are more likely to be selected. Perform crossover operations by exchanging parent gene segments through arithmetic crossover, preserving optimal parameter combinations; When performing mutation operations and randomly perturbing gene values, the perturbation amplitude is limited according to the equipment reliability factor. An elite retention strategy is introduced, in which a portion of the best chromosomes are retained in each generation and directly enter the next generation.

[0085] For each iteration of the optimized population, the current optimal chromosome is decoded into actual parameter values ​​and substituted into the energy conservation and mass conservation equations for verification. It is then determined whether the verification deviation exceeds a preset threshold. If so, the penalty weight of the corresponding constraint is increased in the next iteration.

[0086] When the rate of change of the optimal fitness value is less than the set threshold for multiple consecutive generations, the iteration is terminated, and the final optimal chromosome is decoded into the actual operating parameter values ​​of each device to obtain the device operating parameter ratio.

[0087] S4: Convert the optimal operating parameters of each device into control commands, controlling each device in the wastewater treatment system to perform DMF / DMAC wastewater collection, storage, and distillation purification operations according to the control commands. The process of converting control commands includes: based on the optimal operating parameters of each device and the device control protocol, converting the parameter values ​​into electrical signal commands that the device can recognize. For example, for the feed circulation pump, if the optimal speed is 2.5m... 3 The frequency conversion ( / h) is used to convert the pump's variable frequency control characteristics into corresponding frequency control commands. For the reboiler in Tower 1, if the optimal temperature is 108℃, this is converted into a heating power control command. The converted control commands are transmitted to the control systems of each device via industrial Ethernet, controlling the outlet pump and water circulation pump of the gas-liquid separator to operate at the optimal flow rate, ensuring that the liquid level in the gas-liquid separator is stable at 1 / 2-2 / 3 of its height. The feed circulation pump is controlled to transport the classified and stored DMF / DMAC waste liquid to the feed heater, where it is heated to the optimal temperature and then sent to the primary concentration tower. The reboiler in Tower 1 is controlled to heat at the optimal temperature, the reflux pump in Tower 1 achieves reflux at the optimal flow rate, the outlet pump in Tower 1 transports the top liquid of the primary concentration tower to the top liquid tank in Tower 1, and the bottom liquid in Tower 1 transports it to the secondary concentration tower. Similarly, the supporting equipment of the secondary concentration tower, tertiary concentration tower, distillation tower, and deacidification tower are controlled to operate at optimal parameters. The effluent from the second secondary concentration tower is treated to meet discharge standards or reused. The tail gas from the top of the tertiary concentration tower is condensed by the T203 tail gas condenser and then enters the top liquid tank of the third tower. The top liquid of the fourth distillation tower is condensed by the distillation tower top condenser and then enters the distillation tower top liquid tank. The pure DMF produced by the deacidification tower is cooled by the pure DMF cooler. Part of it is refluxed through the DMF upper reflux pump and DMF lower reflux pump, and part of it is transported to the DMF condensate tank for storage through the DMF discharge pump. Products that do not meet the purity standards are transported to the defective intermediate tank for temporary storage, to be reprocessed later. Simultaneously, the operation of the formic acid decomposition tower and its supporting formic acid decomposition tower reboiler and formic acid decomposition tower condenser is controlled. After the formic acid produced during the distillation process is decomposed, the condensate is stored in the formic acid condensate tank. The intermediate products are transported to the corresponding processing units through intermediate tanks and intermediate pumps. The waste heat generated by each piece of equipment is collected in the recovery pot and used for auxiliary heating or other process steps.

[0088] S5: Real-time monitoring of product quality data and equipment operating status data during the DMF / DMAC waste liquid treatment process; analysis of deviations between actual data and expected targets; and adjustment of operating parameter ratios for each piece of equipment based on actual conditions. In a specific embodiment, the monitored product quality data includes the concentration of the top liquid in each stage of the concentration tower, the purity of the top liquid in the four distillation towers, the purity of pure DMF / DMAC at the outlet of the deacidification tower, the formic acid concentration at the outlet of the formic acid decomposition tower, and the residual amount of DMF / DMAC in the bottom liquid of each tower. The monitored equipment operating status data includes the actual flow rate and speed of each pump, the actual temperature and pressure of each tower, the actual heating power of each reboiler, the actual cooling efficiency of each condenser, and the actual liquid level and pressure of the gas-liquid separator. The process of analyzing deviations includes: calculating the difference between the actual product purity and the expected purity, the difference between the actual recovery rate and the expected recovery rate, the difference between the actual energy consumption and the expected energy consumption, and the difference between the actual operating parameters and the optimal operating parameters of each piece of equipment. The adjusted parameter ratios are then converted back into control commands and transmitted to the control systems of each piece of equipment to achieve dynamic optimization. Substandard products temporarily stored in the intermediate tank for defective products are transported to a three-stage concentration tower or a four-stage distillation tower for re-distillation and purification after the parameters are adjusted and stabilized. This ensures that the final product meets the recycling standards and achieves efficient recycling of DMF / DMAC resources.

[0089] In summary, this embodiment provides an intelligent control method for the parameters of a distillation column used in waste liquid treatment. By constructing a linear relationship between energy utilization efficiency, mass transfer efficiency, and equipment operating parameters, a high-recovery-rate, high-purity DMF / DMAC distillation purification mode is built based on this linear relationship and equipment reliability factors. An improved adaptive genetic algorithm is used to optimize the ratio of operating parameters for each piece of equipment, thereby achieving intelligent control of waste liquid distillation. The beneficial effects obtained are as follows: By combining sensors with laboratory analysis and various monitoring devices and meteorological sensors, the system comprehensively and in real time collects data on waste liquid characteristics, equipment operating status, and environmental parameters. This enables the entire system to have a detailed and accurate understanding of the treatment process, laying a solid foundation for subsequent precise control and avoiding decision-making errors caused by missing or inaccurate data.

[0090] The analysis of energy utilization efficiency and mass transfer efficiency, as well as the calculation of reliability factors of key equipment and the construction of linear relationships, allow the operation of each link to be quantitatively presented. This enables a precise grasp of the inherent laws in the distillation and purification process, a clear understanding of the impact of different equipment parameters on the overall effect, and provides a scientific and reliable basis for subsequent model construction and parameter optimization.

[0091] By constructing a high-recovery, high-purity distillation purification model and utilizing an improved adaptive genetic algorithm to optimize parameter ratios, the system can achieve the lowest total energy consumption while meeting key indicators such as recovery rate and purity. This effectively reduces operating costs and improves the economic efficiency of resource utilization. Furthermore, it focuses on solving the problem of multi-tower parameter coordination, ensuring efficient and coordinated operation of the entire distillation system from feed to individual tower processing and finally to discharge, avoiding situations where local optima result in overall poor performance.

[0092] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent control of parameters of a distillation column for waste liquid treatment, characterized in that, include: S1: Real-time collection of impact data during the DMF waste liquid treatment process, including waste liquid characteristic data, equipment operating status data, and environmental parameter data; S2: Based on the impact data, analyze the energy utilization efficiency and mass transfer efficiency in the DMF waste liquid distillation and purification process, calculate the reliability factor of key equipment, and analyze the linear relationship between energy utilization efficiency, mass transfer efficiency and equipment operating parameters. S3: Based on the linear relationship and equipment reliability factor, a high-recovery-rate, high-purity DMF distillation purification mode is constructed, and an improved adaptive genetic algorithm is used to optimize the ratio of operating parameters of each device; S4: Convert the optimal operating parameter ratio of each device into control commands, and control each device in the waste liquid treatment system to perform DMF waste liquid collection, storage, distillation and purification according to the control commands; S5: Real-time monitoring of product quality data and equipment operating status data during DMF waste liquid treatment, analysis of deviations between actual data and expected targets, and adjustment of operating parameters of each device according to actual conditions.

2. The intelligent control method for parameters of a distillation column for waste liquid treatment according to claim 1, characterized in that, In step S1, the waste liquid characteristic data includes DMF waste liquid concentration, DMAC waste liquid concentration, mass fraction of each component in the DMF mixed waste liquid, and impurity content in the waste liquid.

3. The intelligent control method for parameters of a distillation column for waste liquid treatment according to claim 1, characterized in that, In step S2, the process of analyzing energy utilization efficiency and mass transfer efficiency includes: The total mass of waste liquid entering the feed heater per unit time, the mass of steam after evaporation in the evaporator, the mass of DMF steam separated by the DMF gas-liquid separator, and the mass of target components produced at the top of each level of concentration tower, distillation tower, and deacidification tower are collected. The recovery rate of DMF is obtained by the ratio of the total mass of the target component produced per unit time to the initial total mass of the target component in the waste liquid. The energy utilization efficiency is calculated based on the energy consumption data of the reboiler and the feed heater. Collect temperature and concentration distribution data for each tray in the four distillation towers (primary, secondary, and tertiary), the four distillation towers, and the deacidification tower. Calculate the concentration and temperature differences of the target components between adjacent trays. Combine this with the gas and liquid flow rates within the towers to obtain the mass transfer efficiency.

4. The intelligent control method for parameters of a distillation column for waste liquid treatment according to claim 1, characterized in that, In step S2, the process of calculating the reliability factor of critical equipment includes: A reliability assessment model for key equipment is constructed using its design life, service life, number of failures and repairs in the past year, and deviation of current operating parameters as input parameters. The weights of each input parameter are determined using the analytic hierarchy process (AHP), namely, design life weight ω1, used life weight ω2, number of failure repairs weight ω3, and current operating parameter deviation weight ω4. The reliability factor of each device is obtained by weighted summation.

5. The intelligent control method for parameters of a distillation column for waste liquid treatment according to claim 1, characterized in that, In step S2, the specific steps for establishing a linear relationship between energy utilization efficiency, mass transfer efficiency, and equipment operating parameters are as follows: The variables required to construct a linear relationship are defined as follows: the independent variables are the feed circulation pump rate, the reboiler temperature of each stage of the concentration tower and the distillation tower, the flow rate of each stage of the reflux pump, and the reboiler temperature of the deacidification tower; the dependent variables are the energy utilization efficiency and the mass transfer efficiency. The independent and dependent variables are standardized and transformed, and redundant parameters are removed through correlation analysis to obtain simplified variable data; Based on the simplified variable data, a multiple linear regression method was used to construct a model relating energy utilization efficiency, mass transfer efficiency, and equipment operating parameters. The intercept term and regression coefficients in the model were solved by the least squares method to establish a preliminary model of the linear relationship among the three. The impact data is divided into training and testing sets. Coefficients are calculated to measure the goodness of fit of the model. It is determined whether the goodness of fit is greater than a preset threshold. If it is, significant parameters are screened by stepwise regression. The energy utilization efficiency predicted by the model is substituted into the energy balance equation. Otherwise, the weights of the regression coefficients are adjusted to obtain a linear relationship between energy utilization efficiency, mass transfer efficiency and equipment operating parameters.

6. The intelligent control method for parameters of a distillation column for waste liquid treatment according to claim 1, characterized in that, In step S3, the specific steps for constructing a high-recovery, high-purity DMF distillation purification mode are as follows: With the goal of minimizing total energy consumption, and with DMF recovery rate and product purity as constraints, an objective function is constructed, which is expressed as: In the formula, P represents the total energy consumption of the system. i Let t be the power of the i-th device. i For equipment uptime; The parameter adjustment range is corrected based on the linear relationship and reliability factor. Using linear relationships as a link, a mapping relationship between the operating parameters of each device and the recovery rate, purity, and energy consumption is established, and the sensitivity of parameter adjustment is corrected by the device reliability factor. Using equipment operating parameters as optimization variables in the algorithm and total energy consumption as the objective function, under the premise of satisfying the boundaries and conservation constraints of recovery rate, purity, reliability, and efficiency, a preliminary parameter ratio that synergizes energy utilization efficiency and mass transfer efficiency is found, thus forming a preliminary distillation and purification mode.

7. The intelligent control method for parameters of a distillation column for waste liquid treatment according to claim 6, characterized in that, The optimal solution satisfying the conservation constraints is calculated using the gradient descent method, with the following iterative formula: In the formula, α is the learning rate, ▽Etotal is the gradient vector of the total energy consumption, and P k Let P be the vector of device operating parameters at the k-th iteration. k+1 This is the updated device operating parameter vector at the (k+1)th iteration.

8. The intelligent control method for parameters of a distillation column for waste liquid treatment according to claim 1, characterized in that, In step S3, the specific steps for optimizing the operating parameter ratios of each device using the improved adaptive genetic algorithm are as follows: Each parameter combination is encoded into a chromosome. Real number encoding is used to standardize the value of a parameter corresponding to each gene. A certain number of initial populations are randomly generated to cover different combinations within the parameter range, forming the initial solution set for algorithm optimization. With minimizing the total energy consumption of the system as the core objective, the energy utilization efficiency and mass transfer efficiency are transformed into energy consumption correction terms by combining linear relationships, and the fitness function of the initial solution set is designed. The current population is optimized iteratively based on the fitness function. For the optimized population, after a certain number of iterations, the current optimal chromosome is decoded into actual parameter values, substituted into the energy conservation and mass conservation equations for verification, and it is determined whether the verification deviation exceeds the preset threshold. If so, the penalty weight of the corresponding constraint is increased in the next iteration. When the rate of change of the optimal fitness value is less than the set threshold for multiple consecutive generations, the iteration is terminated, and the final optimal chromosome is decoded into the actual operating parameter values ​​of each device to obtain the device operating parameter ratio.

9. The intelligent control method for parameters of a distillation column for waste liquid treatment according to claim 8, characterized in that, The specific steps for optimizing and iterating the current population are as follows: When selecting parent individuals from the current population, chromosomes with higher fitness are more likely to be selected. Perform crossover operations by exchanging parent gene segments through arithmetic crossover, preserving optimal parameter combinations; When performing mutation operations and randomly perturbing gene values, the perturbation amplitude is limited according to the equipment reliability factor. An elite retention strategy is introduced, in which a portion of the best chromosomes are retained in each generation and directly enter the next generation.

10. The intelligent control method for parameters of a distillation column for waste liquid treatment according to claim 1, characterized in that, The specific steps to convert the optimal operating parameter ratio of each device into control commands are as follows: The equipment operating parameter ratios are analyzed to determine the target parameter values ​​for each piece of equipment, and a parameter-equipment correspondence table is formed as the basis for instruction conversion. Based on the parameter-device correspondence table, the target parameters are converted into control signal format target parameters according to the device type; The target parameters of the control signal format are sorted according to time sequence, and timestamps and timeout thresholds are added to determine the priority of executing the classification instructions. It issues classification instructions and receives feedback in real time, monitors the matching degree between actual equipment parameters and instructions, sends fine-tuning instructions when deviations exceed limits, and alarms for shutdown when abnormalities persist, and generates instruction execution reports periodically.

Images