5 results about "Residence time distribution" patented technology

The invention discloses a material tracking and real-time release method for double-column continuous flow chromatography, and belongs to the field of chromatographic separation. The method comprises the following steps: carrying out parameter fitting and calibration on a chromatography residence time distribution model through static adsorption experiment and chromatography process data; on the basis of the calibration model, the actual operation parameters and the starting time and the duration time of the to-be-tracked material, a residence time distribution curve of the to-be-tracked material in a single column is predicted, the result is input into a double-column continuous flow model framework constructed based on a Capture SMB mode, and complete residence time distribution of the tracked material in a double-column system is obtained; by repeatedly calculating tracking materials with different time parameters, the distribution condition of the tracking materials in each elution peak is analyzed, and global material tracking is realized; and in combination with a preset product quality acceptance limit value, determining an elution peak needing to be shunted, and forming a real-time release scheme. According to the method, the influence of disturbance at the double-column continuous flow chromatography inlet on the products at the outlet can be predicted, and a product distribution strategy is formulated to meet the requirement of real-time release.

This invention relates to the field of material deodorization control technology, and more particularly to a continuous deodorization adaptive control method and system based on deep learning. It involves simultaneously collecting multi-source sensor data from the silo and heating chamber during continuous deodorization production, constructing a time-series feature sequence based on a sliding time window, and then predicting the current deodorization completion rate and future short-term production capacity range through time series modeling and regression calculation. Furthermore, it calculates a residence time correction coefficient based on the predicted deodorization completion rate and determines the maximum feasible feeding speed by combining it with the predicted production capacity range, forming dynamic control parameters. These parameters are then integrated with real-time weighing data to adjust the feeding frequency, transfer timing, and transfer weight. Additionally, it vectorizes the residence time distribution, filling rate, temperature, vacuum degree, and torque fluctuations within the heating chamber, performs regression assessment on the risk of agglomeration, and adjusts the control parameters according to the risk level to reduce the probability of agglomeration and improve the stability and automation level of the continuous deodorization process.

The application discloses a mechanism-guided cascade reactor dynamic modeling and transfer learning method and device, and belongs to the technical field of chemical engineering and artificial intelligence, and comprises the following steps: residence time and input variables are taken as inputs of a reactor inlet, are processed through a reaction rate learning module, and finally the remaining reactant concentrations of different reaction microelements after corresponding residence time are obtained; flow and residence time are taken as input parameters and are input into a residence time distribution learning module; the module processes the parameters, and outputs the residence time probability distribution under the conditions of corresponding flow and residence time; the remaining reactant concentrations output by the reaction rate learning module and the corresponding probability distribution output by the residence time distribution learning module are subjected to weighted summation through a reactor output module, and finally the reactant concentration at the reactor outlet is obtained.

The invention discloses a material tracking and real-time release method for periodic countercurrent chromatography, and belongs to the field of chromatographic separation. The method comprises the following steps: carrying out parameter fitting and calibration on a chromatography residence time distribution model through static adsorption experiment and chromatography process data; on the basis of the calibration model, the actual operation parameters and the starting time and the duration time of the to-be-tracked material, predicting a residence time distribution curve of the to-be-tracked material in a single column, and inputting the result into a continuous flow chromatography model framework constructed on the basis of a periodic countercurrent chromatography mode to obtain complete residence time distribution of the tracked material in the system; by repeatedly calculating tracking materials with different time parameters, the distribution condition of the tracking materials in each elution peak is analyzed, and global material tracking is realized; and in combination with a preset product quality acceptance limit value, determining an elution peak needing to be shunted, and forming a real-time release scheme. According to the method, the influence of disturbance at the periodic countercurrent chromatography inlet on the outlet product can be predicted, and a product shunting strategy is formulated to meet the requirement of real-time release.

This invention discloses a big data-based method for quality control in the production of supercritical foamed materials, belonging to the field of manufacturing quality control technology. This big data-based method acquires time-series data and secondary mapping data on barrel temperature deviation, melt pressure fluctuation, and screw speed fluctuation during continuous extrusion foaming. Based on these two types of data, it determines the correspondence between the carbon dioxide dissolution rate distribution and the residence time distribution, and generates concentration gradient field characterization data. After fusion, it obtains fused feature data, inputs it into a degradation trend identification model, outputs the degradation trend of dissolution uniformity inside the barrel, and determines the risk of finished product quality defects. This invention simultaneously collects process time-series data and secondary mapping data reflecting the internal state of the melt, generates concentration gradient field characterization data, and fuses and models it to identify the degradation trend and risk status of dissolution uniformity. It locates the data source deviation before defects form, providing a traceable decision-making basis for production quality control.