Real-time Detection and Optimal Control Method for Liquid Chromatography Flow Rate Based on Multi-point Sensing

Abstract

The present invention discloses a method for real-time detection and optimization control of liquid chromatography flow rate based on multi-point sensing, comprising the following steps: S1, constructing a distributed acquisition network; S2, constructing a fluid transmission topology map and generating a multi-point flow rate time series; S3, inputting the fluid transmission topology map and the multi-point flow rate time series into a FlowFormer model to generate a flow rate evolution prediction map; S4, performing local gradient scanning to generate an optimization control objective function; S5, calling an adaptive fox swarm algorithm controller, inputting the flow rate evolution prediction map and the optimization control objective function to generate an optimal adjustment strategy; S6, adjusting the control parameters of the liquid chromatography system in real time and feeding them back to the FlowFormer model; S7, when an abnormal flow rate change is detected, triggering the adaptive fox swarm algorithm controller to execute a local escape strategy. The present invention integrates multi-point sensing and intelligent optimization algorithms to achieve real-time detection and optimization control of the liquid chromatography flow rate.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence automated control, and particularly to a real-time detection and optimization control method for liquid chromatography flow rate based on multi-point sensing. Background Art

[0002] Liquid chromatography, as a very important separation and quantitative analysis technique in modern analytical chemistry, is widely used in fields such as biomedicine, environmental monitoring, food safety, and chemical processes. In practical applications, the flow rate, as a key operating parameter of the liquid chromatography system, directly affects the separation efficiency of chromatographic peaks, the stability of retention time, and the stable reproducibility of detection sensitivity. Therefore, how to achieve high-precision real-time monitoring and dynamic regulation of the flow rate has become one of the core technologies to ensure the performance of the liquid chromatography system.

[0003] In the prior art, liquid chromatography systems usually use single-point flow sensors in combination with fixed control logic to complete the monitoring and adjustment of the system flow rate. These single-point sensors are usually deployed at the inlet of the system or the front end of the chromatographic column, and mainly rely on the traditional pressure-flow rate conversion relationship to indirectly infer the liquid flow situation in the pipeline. At the same time, the control part relies on a controller based on the proportional-integral-derivative (PID) algorithm or a preset adjustment curve to adjust the high-pressure pump speed or mixing ratio to maintain a relatively stable flow rate output. However, with the wide application of complex sample components and non-linear solvent gradient conditions, this control mode based on single-point sensing and rule-based control gradually shows obvious deficiencies in terms of flow rate response speed, abnormal state handling ability, and overall system stability.

[0004] First of all, during the actual operation process, due to the influence of various factors such as the mixing chamber, chromatographic column packing, and pipe resistance of the connecting pipe section on the flow state of the liquid in the pipeline, the spatial distribution of the flow rate shows obvious non-uniform characteristics. The single-point measurement method cannot comprehensively reflect the fluid dynamic behavior inside the system, and it is easy to have the problem that the flow rate fluctuations at the rear end of the chromatographic column or the front end of the detector are not detected in time, which may then lead to peak shape distortion or a decrease in detection sensitivity. In addition, single-point measurement does not have topological perception ability and is difficult to be used to analyze the true distribution of the fluid among multiple branch paths, and it is particularly weak in judging the multi-section flow states under complex structures (such as switching valves, bypass channels, etc.) in the chromatographic system.

[0005] Secondly, existing control methods often model the liquid phase system as a single-input single-output (SISO) system. The control logic lacks the global awareness of the system state, and the control strategy relies on preset rules and lacks intelligent prediction functions. This results in a lag in the adjustment process response, a decrease in control accuracy, and problems such as under-adjustment or over-adjustment when the controller faces external disturbances such as variable sample loads, temperature fluctuations, and pressure disturbances, affecting the detection repeatability and stability. Especially under high-throughput experiments or continuous analysis conditions, this traditional regulation mechanism has difficulty meeting the requirements of high-frequency stable operation of the system.

[0006] Thirdly, the response ability to abnormal flow rate events is also an important shortcoming of the existing technology. In practical applications, due to reasons such as chromatographic column blockage, turbulent flow in the mixing chamber, pipeline loosening, or sudden change in sample viscosity, sudden changes in flow rate or pressure imbalance may occur in local areas. Traditional systems often trigger alarms or shutdown processing only after the abnormality has caused obvious results (such as over-limit column pressure or detector signal drift), lacking an early prediction mechanism and local adjustment strategy, which not only fails to achieve dynamic risk mitigation but also increases the overall operation risk and maintenance cost of the system.

[0007] In addition, although some high-end liquid phase systems have begun to introduce multi-sensor collaborative control, data-driven modeling, and AI-based adjustment frameworks, these systems mostly exist in the form of commercial closed solutions, making it difficult to deeply customize and optimize algorithms. Moreover, there are engineering adaptability problems such as poor model generalization ability, opaque control strategies, and too strong software-hardware coupling during the actual implementation process, and they still cannot meet the needs of scientific research and high-precision analysis for open, controllable, and evolvable systems.

[0008] Therefore, how to provide a real-time detection and optimization control method for liquid chromatography flow rate based on multi-point sensing is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0009] An object of the present invention is to propose a real-time detection and optimization control method for liquid chromatography flow rate based on multi-point sensing. The present invention integrates multi-point sensing technology, the structure-aware deep prediction model FlowFormer, and the adaptive fox swarm optimization algorithm to construct a closed-loop mechanism of flow rate prediction-control-feedback, realizing high-precision real-time detection and intelligent adjustment of the flow rate of the liquid chromatography system, with the advantages of high regulation accuracy, fast response speed, intelligent abnormal handling, and strong self-learning ability, significantly improving the operation stability and data reliability of the liquid chromatography system under complex working conditions, and being applicable to high-throughput, high-precision, and high-complexity sample analysis scenarios.

[0010] The real-time detection and optimization control method for liquid chromatography flow rate based on multi-point sensing according to the embodiments of the present invention includes the following steps:

[0011] S1. Deploy flow rate sensors at key nodes of the liquid chromatography system to form a distributed acquisition network;

[0012] S2. Construct a fluid transmission topology map based on the distributed acquisition network and synchronously generate a structured multi-point flow rate time series;

[0013] S3. Input the fluid transmission topology map and the multi-point flow rate time series into the FlowFormer model, use the position embedding encoding mechanism to encode the flow resistance relationship between topological nodes, calculate the dependency relationship between topological nodes, and generate a flow rate evolution prediction map;

[0014] S4. Perform local gradient scanning based on the flow rate evolution prediction map, identify potential mutation regions or abnormal fluctuation nodes through curvature detection and high-order difference operations, and generate an optimized control objective function according to the minimum flow rate deviation tolerance and response time constraint set by the chromatography operating parameters;

[0015] S5. Invoke the adaptive fox swarm algorithm controller, input the flow rate evolution prediction map and the optimized control objective function, guide the virtual fox swarm to search in the control parameter space, and generate an optimal adjustment strategy;

[0016] S6. Adjust the control parameters of the liquid chromatography system in real time according to the optimal adjustment strategy, and at the same time feedback to the FlowFormer model for closed-loop iterative optimization;

[0017] S7. When the liquid chromatography system detects an abnormal flow rate change, trigger the adaptive fox swarm algorithm controller to execute a local escape strategy to achieve emergency control under abnormal conditions.

[0018] Optionally, the key nodes of the liquid chromatography system include the injection port, before and after the mixing chamber, the front end of the chromatographic column, the rear end of the chromatographic column, the front end and the end of the detector.

[0019] Optionally, the S2 specifically includes:

[0020] S21. Collect the deployment positions and physical connection relationships of the flow rate sensors in the liquid chromatography system, and establish a node set , where represents the -th node, represents the total number of nodes, and each node represents a flow rate sensor;

[0021] S22. Based on the connection structure and liquid flow direction of the liquid chromatography system, construct an edge set , where each edge represents that there is an effective flow relationship between the -th node and the -th node, forming a fluid transmission topology map , and label each edge with the pipe segment length, inner diameter, friction coefficient, and initial flow resistance estimate;

[0022] S23. Send a unified synchronization trigger signal to all flow velocity sensor nodes, and use the global time synchronization protocol to achieve clock calibration, so that each node starts sampling at the synchronization moment, and set the unified sampling frequency to ;

[0023] S24. Each node collects the current flow velocity value at each sampling moment, forms an initial raw sampling data sequence, and binds a local timestamp and a flow velocity sensor number to each sampling value;

[0024] S25. Perform data alignment processing on all initial raw sampling data sequences, use the time window alignment algorithm to unify the sampling time sequence and correct the sampling error caused by hardware delay or communication difference, and generate a structured multi-point flow velocity time series;

[0025] S26. Store the fluid transmission topology map and the multi-point flow velocity time series in the cloud, and label the acquisition batch number, sampling start and end times, and device status code.

[0026] Optionally, the specific steps of S3 include:

[0027] S31. Based on the structure and physical properties of the fluid transmission topology map, construct an embedding vector for structure modeling, and calculate the local structure perception position tensor for each node:

[0028] ;

[0029] Among them, represents the perception position tensor of the th node, , and represent the three-dimensional space coordinates of the th node in the liquid chromatography system, represents the set of direct adjacent nodes of the th node, represents the perceptron embedding function, represents the initial flow resistance coefficient of the edge , represents the th node and the th node

[0030] S32. Collect the historical flow velocity values of each node at the nearest time step, and splice them with the perception position tensor to form a joint input tensor:

[0031] ;

[0032] Among them, represents the combined input tensor of the -th node, represents the concatenation operation, represents the current time step, represents the time window length, represents the -th node's observed flow velocity value at time ;

[0033] S33. Input the combined input tensors of all nodes into the FlowFormer model. The FlowFormer model includes a structure encoding module and a temporal prediction module. The structure encoding module models topological dependencies in the form of graph attention and introduces a structure consistency scoring function:

[0034] ;

[0035] Among them, represents the structure consistency score between the -th node and the -th node, represents the historical flow velocity change difference sequence between the -th node and the -th node, represents the flow resistance difference vector between the -th node and the -th node, represents the numerical stability term, represents the vector inner product, represents the L2 norm;

[0036] S34. In the temporal prediction module of the FlowFormer model, use a one-dimensional convolutional network to perform step-by-step prediction on the node feature sequence after structure encoding, capture the dynamic trends of each node, and output a hidden state sequence. Then, use a linear transformation layer to map the hidden state sequence to the flow velocity prediction values at future time points;

[0037] S35. Combine the flow velocity prediction values of all nodes at future time points into a flow velocity evolution prediction map during the prediction period.

[0038] Optionally, the specific steps of S4 include:

[0039] S41. Receive the flow velocity evolution prediction map, which includes the flow velocity prediction values of all nodes at future time points, and record the evolution trend of the flow velocity over time;

[0040] S42. Perform local window sliding processing on the time series of each node, and use a sliding window with a fixed width to extract the local flow velocity change curve for gradient change scanning analysis;

[0041] S43. Introduce a curvature sensitivity function to perform curvature change identification on the local flow velocity change curve of each node within the time window:

[0042] ;

[0043] where, represents the curvature index of the -th node at time , represents the predicted flow velocity value of the -th node at time , represents the first-order time derivative, represents the second-order time derivative, represents the adjustment parameter of the -th node, represents the smoothing factor;

[0044] S44. In each node time series, locate the set of time points of the local maximum curvature index as the mutation candidate point set, and perform high-order difference residual filtering on the mutation candidate point set:

[0045] ;

[0046] where, represents the fourth-order central difference mutation index of the -th node at time , represents the predicted flow velocity value of the -th node at time , represents the predicted flow velocity value of the -th node at time , represents the predicted flow velocity value of the -th node at time , represents the predicted flow velocity value of the -th node at time , represents the absolute value operation;

[0047] S45. Combine the curvature index and the fourth-order central difference mutation index and adopt a threshold double-threshold strategy to mark the mutation region or the abnormal fluctuation node set ;

[0048] S46. Construct an optimized control objective function based on the recognition result and the current operating state:

[0049] ;

[0050] Among them, represents the optimized control objective function, represents the set of control variables, 、 and represent the weighting coefficients, represents the target reference flow velocity of the -th node, represents the predicted flow velocity value of the -th node at time , represents the predicted time step, represents the time window length, represents the predicted flow velocity value of the -th node at time , represents the response time required for the -th node to reach the target state, represents a stability term to prevent the denominator from being zero.

[0051] Optionally, the threshold double-threshold strategy specifically includes setting a curvature index threshold and a fourth-order central difference variation index threshold. The curvature index threshold is used to judge the bending degree of the local flow velocity change curve, and the fourth-order central difference variation index threshold is used to judge the fluctuation intensity of the local flow velocity change curve;

[0052] In the flow velocity evolution prediction map, screen out the time points where the curvature index exceeds the curvature index threshold as suspected mutation points, and further judge whether the fourth-order central difference variation index of the suspected mutation points exceeds the fourth-order central difference variation index threshold. Only retain the nodes that meet both threshold conditions to generate a mutation region or an abnormal fluctuation node set .

[0053] Optionally, the S5 specifically includes:

[0054] S51. Obtain the flow velocity evolution prediction map and the optimized control objective function, and establish a control parameter space, where the control parameter space includes the high-pressure pump speed, the solvent ratio, and the valve opening;

[0055] S52. Initialize the population using an adaptive fox swarm algorithm controller, and define the population as a set of fox swarm individuals , where represents the -th fox individual, Represents the total number of fox individuals. Each fox individual represents a set of candidate solutions in the control parameter space. The initial fox population individuals are generated by a uniform random distribution, and the maximum number of evolutionary generations and the convergence threshold are set.

[0056] S53. According to the optimized control objective function, substitute the flow velocity evolution prediction map into the evaluation of control performance, and record the current optimal individual.

[0057] S54. According to the distance difference between each fox population individual and the optimal individual, adaptively and dynamically update the position vector of the fox individual:

[0058] ;

[0059] Among them, represents the position vector of the th fox individual after update, represents the position vector of the th fox individual before update, represents the dynamic step size adjustment factor, represents the position vector of the optimal individual, represents the random perturbation coefficient, represents a random vector of Gaussian distribution with a mean of 0, represents the L2 norm;

[0060] S55. Record the optimal individuals generated during the evolutionary process of the fox population in each generation and add them to the memory bank for assisting in the generation of the next generation of fox population individuals.

[0061] S56. Repeat steps S53 - S55 until the set number of evolutionary generations is reached or the convergence threshold of the optimized control objective function is satisfied, and generate the optimal adjustment strategy.

[0062] Optionally, the specific steps of S6 include:

[0063] S61. According to the optimal adjustment strategy, the central control unit sends control commands to each actuator of the liquid chromatography system in real time, including the high-pressure pump speed adjustment command, the proportion adjustment command of the solvent ratio electric control valve, and the valve opening control command.

[0064] S62. After each actuator receives the control command, it immediately implements the adjustment action. The high-pressure pump adjusts the operating frequency to reach the target flow velocity setting, the proportion valve dynamically adjusts the proportion of different solvents and stabilizes the mixing ratio, and the valve adjusts the pipeline pressure and flow according to the opening.

[0065] S63. During the adjustment execution process, the distributed acquisition network is used to collect the response flow velocity data of each node of the liquid chromatography system in real time, and synchronously record the adjusted response state to obtain the feedback data under the actual operating state.

[0066] S64. Compare the feedback data with the flow rate prediction value of the FlowFormer model, calculate the deviation between the flow rate prediction value and the feedback data, and adaptively update the parameters of the FlowFormer model based on the deviation:

[0067] ;

[0068] Among them, represents the updated parameters of the FlowFormer model, represents the parameters of the FlowFormer model before update, represents the adaptive learning rate, represents the gradient of the parameters of the FlowFormer model, represents the deviation between the flow rate prediction value and the feedback data, represents the L2 norm;

[0069] S65. Use the updated FlowFormer model to regenerate the flow rate evolution prediction map for the next cycle, and further adjust and optimize the adjustment strategy for the next cycle to form a feedback loop.

[0070] Optionally, the local escape strategy includes that when the liquid chromatography system detects an abnormal flow rate change, the adaptive fox swarm algorithm controller limits the search range to the abnormal area where the abnormal node and its directly associated upstream and downstream nodes are located. By compressing the control parameter space and introducing a fast iteration factor, it preferentially generates a local optimal adjustment solution aiming at decompression and bypass flow, including dynamically adjusting the valve opening of the abnormal path segment, temporarily reducing the output frequency of the high-pressure pump or switching to the pre-equipped solvent channel to achieve flow rate unloading and pressure relief of the abnormal node. At the same time, the liquid chromatography system continuously collects the response data of the abnormal area, and records the input parameters and feedback results during the escape process into the offline learning pool.

[0071] The beneficial effects of the present invention are:

[0072] First of all, the present invention constructs a distributed acquisition network with comprehensive spatial coverage by deploying multiple high-frequency micro flow rate sensors at the key nodes of the liquid chromatography system, breaking through the technical bottleneck of single-point sampling and local observation in the prior art. This network not only covers multiple key positions such as the injection port, before and after the mixing chamber, before and after the chromatographic column, the front end and the end of the detector, but also realizes high-precision alignment of multi-point data through a unified time synchronization mechanism. Combining with the system topology structure, a fluid transmission directed graph is further constructed, so that a corresponding mapping relationship is established between the physical structure inside the system, the pipeline connection relationship and the sensing data, significantly enhancing the visualization of the system operation state and the structural computability.

[0073] Secondly, the present invention introduces a structure-aware depth prediction model, FlowFormer, which fuses the fluid topology map with the multi-point flow velocity time series, encodes and models the flow resistance relationship between topological nodes through a position embedding mechanism, and mines the non-linear dynamic dependencies between nodes using a structure consistency scoring mechanism. Compared with traditional methods that only use sequence data for sliding prediction, this model has a stronger global state modeling ability and dynamic evolution trend capturing ability, and can generate high-resolution system flow velocity evolution prediction maps, providing accurate decision-making basis for subsequent regulation strategy generation. At the same time, by introducing a convolutional temporal prediction structure, the generalization ability and robustness of the model on the continuous time axis are improved.

[0074] Thirdly, in terms of generating regulation strategies, the present invention adopts an adaptive fox swarm algorithm controller to break through traditional control algorithms. Based on the swarm intelligence behavior simulation mechanism, this controller takes the flow velocity prediction map and the optimal control objective function as inputs, guides the virtual fox swarm to search and iteratively optimize in the high-dimensional control parameter space, and dynamically generates the system-level optimal regulation strategy. This strategy covers key control variables such as the rotation speed of the high-pressure pump, the solvent ratio, and the opening degree of the micro-valve, with high regulation accuracy, fast convergence speed, and can balance optimization in multiple dimensions such as target deviation, system response time, and flow velocity disturbance suppression, significantly improving the regulation effect of the liquid chromatography system under complex working conditions.

[0075] In addition, the present invention also constructs an integrated closed-loop optimization mechanism of prediction-execution-feedback-update. During the execution of the regulation strategy, the system continuously collects feedback flow velocity data and compares the error with the predicted value of the FlowFormer model. Based on the prediction deviation, the model parameters can be adaptively updated, enabling the prediction performance to continuously improve during continuous use, thus having the learning ability and model evolution ability. This self-closed-loop mechanism effectively solves the problems of static models and fixed regulations in existing liquid phase systems, making the entire system highly adaptable and operationally robust.

[0076] Finally, the present invention proposes a local escape strategy to deal with abnormal states during system operation. When the system detects a flow velocity mutation exceeding the safety threshold at any node, the controller can automatically identify the abnormal area, limit the search space within a local range, and quickly generate a local optimal regulation strategy targeting pressure reduction, flow around, or bypass switching, achieving rapid unloading of the abnormal area and maintaining the stability of the overall system operation. At the same time, the data and strategy results during this process are stored in an offline learning pool for training future models and enhancing the response ability of the escape mechanism, further improving the safety and intelligence of the system. Description of the Drawings

[0077] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the accompanying drawings:

[0078] Figure 1 is the overall flowchart of the real-time detection and optimization control method for liquid chromatography flow rate based on multi-point sensing proposed by the present invention;

[0079] Figure 2 is the architecture diagram of the FlowFormer model of the real-time detection and optimization control method for liquid chromatography flow rate based on multi-point sensing proposed by the present invention;

[0080] Figure 3 is the flowchart for generating the adjustment strategy of the adaptive fox swarm algorithm controller of the real-time detection and optimization control method for liquid chromatography flow rate based on multi-point sensing proposed by the present invention. Detailed implementation manners

[0081] Now, the present invention will be further described in detail with reference to the accompanying drawings. These drawings are all simplified schematic diagrams, only illustrating the basic structure of the present invention in a schematic manner, so they only show the components related to the present invention.

[0082] Refer to Figures 1-3 , the real-time detection and optimization control method for liquid chromatography flow rate based on multi-point sensing includes the following steps:

[0083] S1. Deploy flow rate sensors at key nodes of the liquid chromatography system to form a distributed acquisition network;

[0084] S2. Construct a fluid transmission topology map according to the distributed acquisition network, and synchronously generate a structured multi-point flow rate time series;

[0085] S3. Input the fluid transmission topology map and the multi-point flow rate time series into the FlowFormer model, use the position embedding encoding mechanism to encode the flow resistance relationship between topological nodes, calculate the dependency relationship between topological nodes, and generate a flow rate evolution prediction map;

[0086] S4. Perform local gradient scanning based on the flow rate evolution prediction map, identify potential mutation regions or abnormal fluctuation nodes through curvature detection and high-order difference operations, and generate an optimization control objective function according to the minimum flow rate deviation tolerance and response time constraint set by the chromatographic operation parameters;

[0087] S5. Call the adaptive fox swarm algorithm controller, input the flow rate evolution prediction map and the optimization control objective function, guide the virtual fox swarm to search in the control parameter space, and generate an optimal adjustment strategy;

[0088] S6. According to the optimal adjustment strategy, the control parameters of the liquid chromatography system are adjusted in real time, and at the same time, it is fed back to the FlowFormer model for closed-loop iterative optimization;

[0089] S7. When the liquid chromatography system detects an abnormal flow rate change, it triggers the adaptive fox swarm algorithm controller to execute the local escape strategy to achieve emergency control under abnormal conditions.

[0090] In the present invention, by constructing a multi-point distributed sensing network in the liquid chromatography system, combining structured modeling, deep prediction models and intelligent optimization algorithms, a comprehensive perception, accurate prediction and efficient regulation of the flow rate state inside the system are realized. Compared with the traditional single-point detection and static adjustment methods, the present invention can capture the spatial distribution of the flow rate and its change trend in real time, and improve the response ability of the control system to the dynamic operating state. At the same time, the introduction of the FlowFormer model realizes the global flow rate prediction with structure perception, and cooperates with the adaptive fox swarm algorithm controller to quickly search for the optimal adjustment strategy in the control parameter space, constructing a prediction-control-feedback closed-loop mechanism, enabling the system to have the ability of intelligent optimization and abnormal response while ensuring stable operation, significantly improving the repeatability, accuracy and operation safety of chromatographic separation, and having broad practical application prospects and industrialization value.

[0091] In this embodiment, the key nodes of the liquid chromatography system include the inlet, before and after the mixing chamber, the front end of the chromatographic column, the rear end of the chromatographic column, the front end and the end of the detector.

[0092] By clarifying the position deployment strategy of the key nodes of the liquid chromatography system, such as the inlet, before and after the mixing chamber, before and after the chromatographic column, and both ends of the detector, it ensures that the deployed sensor network is representative and covering, thus providing a basic guarantee for constructing a high-resolution and multi-angle flow rate monitoring system. This layout scheme not only improves the observability of the internal flow state of the system, but also helps to identify the abnormal flow rate fluctuation areas caused by local structural characteristics, providing data support for subsequent modeling and optimization. The implementation of this strategy can effectively enhance the integrity and practicality of data collection, enable the system to have the ability to respond to multiple points under complex flow conditions, and contribute to the construction of a more refined and stable chromatographic control system.

[0093] In this embodiment, the specific content of S2 includes:

[0094] S21. Collect the deployment positions and physical connection relationships of the flow rate sensors in the liquid chromatography system, and establish a node set , where represents the th node, represents the total number of nodes, and each node represents a flow rate sensor;

[0095] S22. Construct an edge set based on the connection structure and liquid flow direction of the liquid chromatography system , where each edge represents that there is an effective flow relationship between the -th node and the -th node, forming a fluid transmission topology graph , and label each edge with the pipe segment length, inner diameter, friction coefficient, and initial flow resistance estimate;

[0096] S23. Send a unified synchronous trigger signal to all flow velocity sensor nodes, and use the global time synchronization protocol to achieve clock calibration, so that each node starts sampling at the synchronous moment, and set the unified sampling frequency to ;

[0097] S24. Each node collects the current flow velocity value at each sampling moment, forms an initial raw sampling data sequence, and binds a local timestamp and a flow velocity sensor number to each sampling value;

[0098] S25. Perform data alignment processing on all initial raw sampling data sequences, use the time window alignment algorithm to unify the sampling time sequence and correct the sampling error caused by hardware delay or communication difference, and generate a structured multi-point flow velocity time series;

[0099] S26. Store the fluid transmission topology graph and the multi-point flow velocity time series in the cloud, and label the acquisition batch number, sampling start and end times, and device status code.

[0100] By introducing a structured modeling method, the construction process of the topology graph, the synchronous sampling mechanism, and the standardized processing method of time series data are described in detail, effectively improving the acquisition efficiency and timing consistency of multi-point flow velocity information. This process ensures the integrity and accuracy of sensor data in both the time and structure dimensions through operations such as unified synchronous triggering, high-frequency sampling, timestamp alignment, and interpolation compensation. The collected structured data not only has high availability but also has the ability to map the graph structure, providing high-quality raw data for the input of subsequent deep learning models, fundamentally improving the perception ability and generalization effect of the prediction model on the flow state of the liquid phase system, and laying a solid foundation for achieving high-precision prediction and stable control.

[0101] In this embodiment, the specific steps of S3 are as follows:

[0102] S31. Based on the topology graph structure and physical properties of the fluid transmission, construct an embedding vector for structure modeling, and calculate the local structure perception position tensor for each node:

[0103] ;

[0104] Among them, represents the The perceived position tensor of the nodes, , and represent the three-dimensional spatial coordinates of the -th node in the liquid chromatography system, represent the set of direct adjacent nodes of the -th node, represents the perceptron embedding function, represents the edge 's initial flow resistance coefficient, represent the -th node and the -th node's spatial distance;

[0105] S32. Collect the historical flow rate values of each node at the most recent time step and concatenate them with the perceived position tensor to form a joint input tensor:

[0106] ;

[0107] Among them, represents the joint input tensor of the -th node, represents the concatenation operation, represents the current moment, represents the time window length, represents the -th node's observed flow rate value at time ;

[0108] S33. Input the joint input tensors of all nodes into the FlowFormer model. The FlowFormer model includes a structure encoding module and a temporal prediction module. The structure encoding module models the topological dependencies in the form of graph attention and introduces a structure consistency scoring function:

[0109] ;

[0110] Among them, represents the structure consistency score between the -th node and the -th node, represents the historical flow rate change difference sequence between the -th node and the -th node, represents the flow resistance difference vector between the -th node and the -th node, represents the numerical stability term, represents the vector inner product, Denotes the L2 norm;

[0111] S34. In the temporal prediction module of the FlowFormer model, a one-dimensional convolutional network is used to perform step-by-step prediction on the node feature sequence after structure encoding, capture the dynamic trends of each node, and output a hidden state sequence. Then, a linear transformation layer maps the hidden state sequence to the flow velocity prediction values at future time points;

[0112] S35. Combine the flow velocity prediction values of all nodes at future time points into a flow velocity evolution prediction map during the prediction period.

[0113] Through the detailed definition of the FlowFormer structure-aware model and the improved design of the node encoding method, the physical structure characteristics, flow resistance distribution, and flow velocity change trends inside the liquid chromatography system are effectively mapped into a unified high-dimensional vector space. A structure consistency scoring function is specifically introduced as the basis for attention allocation, enabling the model to consider both historical dynamic data and integrate topological structure and physical resistance factors when modeling the dependencies between nodes, thereby significantly improving the accuracy and robustness of the flow velocity prediction results. This modeling method is more interpretable and adaptable than traditional temporal prediction models and is suitable for chromatographic analysis environments with complex flow structures and frequent perturbations, providing core support for realizing intelligent perception and precise control.

[0114] In this embodiment, the specific steps of S4 are as follows:

[0115] S41. Receive the flow velocity evolution prediction map, which includes the flow velocity prediction values of all nodes at future time points, and record the evolution trend of the flow velocity over time;

[0116] S42. Perform local window sliding processing on the time series of each node, and use a sliding window with a fixed width to extract the local flow velocity change curve for gradient change scanning analysis;

[0117] S43. Introduce a curvature sensitivity function to perform curvature change identification on the local flow velocity change curve of each node within the time window:

[0118] ;

[0119] where denotes the curvature index of the th node at time , denotes the flow velocity prediction value of the th node at time , denotes the first-order time derivative, denotes the second-order time derivative, denotes the Adjustment parameters of each node, represents the smoothing factor;

[0120] S44. In each node time series, locate the set of time points of the local maximum curvature index as the mutation candidate point set, and perform high-order difference residual filtering on the mutation candidate point set:

[0121] ;

[0122] Among them, represents the fourth-order central difference mutation index of the th node at time , represents the predicted flow velocity value of the th node at time , represents the predicted flow velocity value of the th node at time , represents the predicted flow velocity value of the th node at time , represents the predicted flow velocity value of the th node at time , represents the absolute value operation;

[0123] S45. Combine the curvature index and the fourth-order central difference mutation index and adopt a threshold double-threshold strategy to mark the mutation region or the abnormal fluctuation node set ;

[0124] S46. Based on the recognition result and the current operating state, construct an optimal control objective function:

[0125] ;

[0126] Among them, represents the optimal control objective function, represents the set of control variables, , and represent the weighting coefficients, represents the target reference flow velocity of the th node, represents the predicted flow velocity value of the th node at time , represents the predicted time step, represents the time window length, represents the predicted flow velocity value of the th node at time , Indicates the response time required for the th node to reach the target state,

[0127] By introducing gradient scanning, curvature recognition, and high-order difference residual detection mechanisms, the sensitivity and positioning accuracy of the system to sudden changes or abnormal fluctuations in flow rate are effectively improved. This strategy captures the changing trend of minute perturbations in the flow rate curve in the time domain through a mathematical model. Combining with a dual-threshold decision-making strategy, it can achieve effective early warning at the initial stage of abnormal states, providing the controller with more timely and accurate abnormal recognition results. Furthermore, by constructing an optimized control objective function based on target deviation, fluctuation suppression, and response time constraints, the transformation of the control system from rule-driven to target-aware is realized, significantly enhancing the control effect on non-linear dynamics in complex operating scenarios.

[0128] In this embodiment, the threshold dual-threshold strategy specifically includes setting a curvature index threshold and a fourth-order central difference variation index threshold. The curvature index threshold is used to judge the degree of bending of the local flow rate change curve, and the fourth-order central difference variation index threshold is used to judge the fluctuation intensity of the local flow rate change curve;

[0129] In the flow rate evolution prediction map, screen out the time points where the curvature index exceeds the curvature index threshold as suspected mutation points, and further judge whether the fourth-order central difference variation index of the suspected mutation points exceeds the fourth-order central difference variation index threshold. Only retain the nodes that meet both threshold conditions to generate a mutation region or an abnormal fluctuation node set .

[0130] By introducing a dual-threshold judgment mechanism in the mutation point recognition process and conducting joint analysis on the curvature of the flow rate change and the fourth-order central difference fluctuation intensity respectively, the problem of false alarms or missed alarms easily caused by single-index recognition is effectively solved. This dual-threshold strategy ensures that only when the prediction results simultaneously meet the mutation characteristics in both the changing trend and the fluctuation degree dimensions are marked as valid abnormal nodes, significantly improving the accuracy and discrimination efficiency of abnormal recognition. The use of this strategy provides a more reliable input basis for subsequent control logic for mutation events, effectively avoiding the risks of misregulation and response lag, and ensuring the continuity and stability of the liquid chromatography system.

[0131] In this embodiment, the S5 specifically includes:

[0132] S51. Obtain the flow rate evolution prediction map and the optimized control objective function, and establish a control parameter space, where the control parameter space includes the high-pressure pump speed, solvent ratio, and valve opening;

[0133] S52. Initialize the population using an adaptive fox swarm algorithm controller, and define the population as a set of fox swarm individuals , where represents the th fox individual, represents the total number of fox individuals. Each fox individual represents a set of candidate solutions in the control parameter space. The initial fox population individuals are generated by a uniform random distribution, and the maximum number of evolutionary generations and the convergence threshold are set;

[0134] S53. According to the optimized control objective function, substitute the flow velocity evolution prediction map into the evaluation of control performance, and record the current optimal individual;

[0135] S54. According to the distance difference between each fox population individual and the optimal individual, adaptively and dynamically update the position vector of the fox individual:

[0136] ;

[0137] where represents the position vector of the th fox individual after update, represents the position vector of the th fox individual before update, represents the dynamic step size adjustment factor, represents the position vector of the optimal individual, represents the random perturbation coefficient, represents a random vector of Gaussian distribution with a mean of 0, represents the L2 norm;

[0138] S55. Record the optimal individuals generated during the evolution process of each generation of fox population and add them to the memory bank to assist in the generation of the next generation of fox population individuals;

[0139] S56. Repeat steps S53 - S55 until the set number of evolutionary generations is reached or the convergence threshold of the optimized control objective function is satisfied, and generate the optimal adjustment strategy.

[0140] By designing an adaptive fox swarm algorithm search mechanism based on virtual agents and introducing historical optimal individual memory and multi - generation evolution strategies, an efficient solution to complex non - linear control objectives is achieved. This algorithm can dynamically adjust the search path in the control parameter space, and can find the global or approximate optimal solution in control problems with multiple local optima without relying on gradient information, and has strong adaptability. Especially in the face of high - dynamic system environments such as sudden changes in flow velocity, the adaptive fox swarm algorithm controller FoxOpt has an adaptive jumping ability and a path repair mechanism, can effectively avoid falling into local optima, ensure the effectiveness of the adjustment strategy and the overall control effect of the system, and has obvious intelligent optimization advantages.

[0141] In this embodiment, the specific content of S6 includes:

[0142] S61. According to the optimal adjustment strategy, the central control unit sends regulation instructions to each actuator of the liquid chromatography system in real time, including the high-pressure pump speed adjustment instruction, the proportion adjustment instruction of the solvent ratio electric control valve, and the valve opening control instruction;

[0143] S62. After receiving the regulation instructions, each actuator immediately implements the adjustment action. The high-pressure pump adjusts the operating frequency to reach the target flow rate setting, the proportion valve dynamically adjusts the proportion of different solvents and stabilizes the mixing ratio, and the valve adjusts the pipeline pressure and flow rate according to the opening degree;

[0144] S63. During the adjustment execution process, the distributed acquisition network is used to collect the response flow rate data of each node of the liquid chromatography system in real time, and the adjusted response state is synchronously recorded to obtain the feedback data under the actual operating state;

[0145] S64. Compare the feedback data with the flow rate prediction value of the FlowFormer model, calculate the deviation between the flow rate prediction value and the feedback data, and adaptively update the parameters of the FlowFormer model according to the deviation:

[0146] ;

[0147] where, represents the updated parameters of the FlowFormer model, represents the parameters of the FlowFormer model before update, represents the adaptive learning rate, represents the gradient of the parameters of the FlowFormer model, represents the deviation between the flow rate prediction value and the feedback data, represents the L2 norm;

[0148] S65. Use the updated FlowFormer model to regenerate the flow rate evolution prediction map of the next cycle, and further adjust and optimize the adjustment strategy of the next cycle to form a feedback closed loop.

[0149] This step constructs a closed-loop self-learning control process of optimal strategy execution - real-time feedback - model update, which not only realizes the accurate and real-time execution of control actions, but also enables the system to have the ability to continuously improve the adjustment performance based on historical feedback data. By introducing the adaptive update mechanism of model parameters, the weights of the FlowFormer model can be dynamically adjusted according to the prediction error, so that the prediction model maintains long-term effectiveness and high accuracy. This closed-loop structure improves the operation robustness and adjustment intelligence of the liquid chromatography system in a dynamic environment, and realizes an essential leap from static control to dynamic perception and self-evolution regulation.

[0150] In this embodiment, the local escape strategy includes that when the liquid chromatography system detects an abnormal flow rate change, the adaptive fox swarm algorithm controller limits the search range to the abnormal area where the abnormal node and its directly associated upstream and downstream nodes are located. By compressing the control parameter space and introducing a fast iteration factor, it preferentially generates local optimal adjustment solutions aiming at pressure reduction and flow around, including dynamically adjusting the valve opening of the abnormal path segment, temporarily reducing the output frequency of the high-pressure pump, or switching to the pre-equipped spare solvent channel to achieve flow rate unloading and pressure relief of the abnormal node. At the same time, the liquid chromatography system continuously collects the response data of the abnormal area, and records the input parameters and feedback results during the escape process into the offline learning pool.

[0151] By introducing the local escape strategy, when abnormal states such as sudden flow rate changes are detected, it no longer relies on full-system readjustment or forced shutdown, but limits the abnormal area for local optimal control, effectively reducing the overall system interference. This strategy quickly generates emergency solutions such as flow around, pressure reduction, or bypass switching within the abnormal area to achieve rapid unloading of abnormal pressure and restoration of normal flow, significantly shortening the system self-recovery time. At the same time, by recording data during the escape strategy process and introducing an offline learning mechanism, it enhances the system's empirical response ability to similar abnormalities, provides continuous support for subsequent iterative optimization of the model, and improves the system's adaptability and fault recovery level.

[0152] Example 1:

[0153] To verify the feasibility of the present invention in implementation, the present invention is applied to the liquid chromatography experimental platform of an analysis and testing center in a certain university, which has long been used for the separation and analysis of complex traditional Chinese medicine extracts and multi-component protein solutions. In practical applications, the sample sources are complex, the solution viscosity, particle content, and gradient elution conditions change frequently. The traditional chromatography system often faces technical bottlenecks such as severe flow rate fluctuations, peak shape distortion, and detection signal drift, resulting in poor repeatability and insufficient stability of the analysis results, seriously affecting the reliability of experimental data and the sample processing efficiency.

[0154] The present invention adopts a multi-point flow rate sensing scheme, and a total of 6 high-precision micro flow rate sensors are deployed at the inlet, the outlet of the mixing chamber, the front and rear ends of the chromatographic column, and both ends of the detector to form a distributed acquisition network. The system performs automatic calibration before daily operation to ensure that the sensor sampling frequency is uniformly set to 500 Hz, and the whole system is time synchronized through a high-precision clock module. The flow rate data is uploaded to the central processing module in real time to construct a liquid path topology map and generate a structured flow rate time series. The test sample used in the experiment is a high-concentration flavonoid extract, which is run under the condition of acetonitrile-water gradient. The system operation pressure is relatively high, and strong requirements are placed on the flow rate stability.

[0155] During the first experiment, the FlowFormer model learned the topological structure and historical flow rate sequences and successfully generated a predicted map of the flow rate evolution within the next 15 seconds. The control objective function was set to minimize the flow rate fluctuations across the entire path, taking into account the trade-off between the target flow rate and the response time. The adaptive fox swarm algorithm controller initialized 30 virtual fox swarm individuals in the control parameter space (high-pressure pump speed, solvent ratio, valve opening), set the maximum number of iterations to 50, and the convergence threshold to 0.001. Convergence was achieved in the 12th generation, and the generated optimal adjustment strategy was sent to the high-pressure pump and proportional valve in real time to achieve precise control of the system.

[0156] During the continuous operation for 8 hours, the system identified and actively intervened in 9 abnormal flow rate fluctuation events. Among them, 3 were short-term turbulences in the mixing chamber, 2 were mild blockages at the front end of the chromatographic column, and the remaining 4 were pulse disturbances caused by the instability of the high-pressure pump. Through the local escape strategy, the system switched to the standby solvent channel or temporarily reduced the pump speed in real time, avoiding peak shape distortion and system shutdown. The controller recorded all the adjustment process data, system response status, and flow rate errors in the learning pool to provide training samples for the subsequent adaptive update of the model.

[0157] Under traditional control conditions (using single-point detection + PID regulation), the average time required for the platform to run a batch of complex sample tasks was 3 hours, the effective sample detection rate was 83.6%, and the repeatability deviation (RSD) was about 7.8%. In the continuous three-day operation experiment after applying the present invention, the average task completion time was shortened to 2.1 hours, the effective detection rate increased to 96.4%, the RSD decreased to 3.1%, and the number of system alarms decreased by 82.5%. In addition, the prediction model accuracy increased from the initial 78.5% to 93.2% in the later stage of operation, indicating that the model has good learning ability and real-time adaptation performance.

[0158] Through the actual deployment and operation verification in the liquid chromatography platform of the university analysis and testing center, the present invention significantly improved the system's perception ability of flow rate dynamics, prediction accuracy, and intelligent control level. Based on the deployment of multi-point sensors, a structured fluid topology map was successfully constructed and integrated with the flow rate time series. Combining the structure-aware model FlowFormer and the adaptive fox swarm algorithm controller FoxOpt, the full-process intelligent flow rate optimization control from real-time perception, prediction and early warning to closed-loop regulation was realized.

[0159] During the implementation process, the present invention effectively identified and processed various abnormal flow rate events, such as turbulences in the mixing chamber, blockages in the chromatographic column, and pump fluctuations, etc., avoiding experimental interference caused by peak shape distortion or system shutdown. The system prediction accuracy increased from the initial 78.5% to 93.2%, and the average abnormal response time was shortened to within 3.5 seconds, far superior to the traditional PID control strategy.

[0160] This embodiment fully demonstrates that the present invention has extremely strong adaptability and control effects in the actual complex environment of liquid chromatography. Through the integration of distributed sensing, structural modeling, and intelligent control, the present invention solves the problems that the traditional technology cannot achieve multi-point monitoring, global prediction, and rapid response, and has significant technical advantages in improving the sample detection efficiency, control accuracy, and system stability.

[0161] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent replacements or changes, should be covered by the protection scope of the present invention.

Claims

1. A method for real-time detection and optimization control of liquid chromatography flow rate based on multi-point sensing, characterized in that: The steps include: S1. Deploy flow rate sensors at key nodes of the liquid chromatography system to form a distributed acquisition network; S2, constructing a fluid transmission topology map based on the distributed acquisition network, and synchronously generating a structured multi-point flow velocity time series; S3, input the fluid transmission topology map and multi-point flow velocity time series into the FlowFormer model, use the position embedding coding mechanism to encode the flow resistance relationship between topological nodes, and calculate the dependency relationship between topological nodes to generate a flow velocity evolution prediction map; The FlowFormer model includes a structural encoding module and a time series prediction module. The structural encoding module models topological dependencies in the form of graph attention and introduces a structural consistency scoring function: ； in, Indicates The node and The structural consistency score between nodes, Indicates The node and The historical flow rate change difference sequence of nodes, Indicates The node and The flow resistance difference vector between nodes is represents the numerical stability term, represents the vector inner product, represents the L2 norm; In the time series prediction module of the FlowFormer model, a one-dimensional convolutional network is used to predict the node feature sequence after structural encoding step by step, capture the dynamic trend of each node, and output the hidden state sequence, which is then mapped to the flow velocity prediction value at the future time point by the linear transformation layer; S4. Perform local gradient scanning based on the velocity evolution prediction map, identify potential mutation areas or abnormal fluctuation nodes through curvature detection and high-order differential operations, and generate an optimization control objective function based on the minimum velocity deviation tolerance and response time constraints set by the chromatographic operation parameters; S5, calling the adaptive fox swarm algorithm controller, inputting the velocity evolution prediction map and the optimization control objective function, guiding the virtual fox swarm to search in the control parameter space, and generating the optimal regulation strategy; S6. Adjust the control parameters of the liquid chromatography system in real time according to the optimal adjustment strategy, and feed back to the FlowFormer model for closed-loop iterative optimization; S7. When the liquid chromatography system detects an abnormal flow rate change, the adaptive fox swarm algorithm controller is triggered to execute a local escape strategy to achieve emergency control under abnormal conditions.

2. The method for real-time detection and optimization control of liquid chromatography flow rate based on multi-point sensing according to claim 1, characterized in that: The key nodes of the liquid chromatography system include the injection port, the front and rear of the mixing chamber, the front end of the chromatographic column, the rear end of the chromatographic column, and the front end and the end of the detector.

3. The method for real-time detection and optimization control of liquid chromatography flow rate based on multi-point sensing according to claim 1, characterized in that: The S2 specifically includes: S21. Collect the deployment positions and physical connection relationships of each flow velocity sensor in the liquid chromatography system and establish a node set ,in Indicates nodes, Represents the total number of nodes, each node represents a flow rate sensor; S22. Construct edge sets based on the connection structure and liquid flow direction of the liquid chromatography system , where each edge Indicates The node and There is an effective flow relationship between the nodes, forming a fluid transmission topology diagram , and annotate each edge with the length, inner diameter, friction coefficient and initial flow resistance estimate; S23, send a unified synchronization trigger signal to all flow velocity sensor nodes, use the global time synchronization protocol to implement clock calibration, so that each node starts sampling at the synchronization time, and sets a unified sampling frequency of ; S24, each node collects the current flow velocity value at each sampling time to form an initial original sampling data sequence, and binds a local timestamp and a flow velocity sensor number to each sampling value; S25, performing data alignment processing on all initial raw sampling data sequences, using a time window alignment algorithm, unifying the sampling timing and correcting the sampling error caused by hardware delay or communication difference, and generating a structured multi-point flow velocity time series; S26. Store the fluid transmission topology and multi-point flow velocity time series in the cloud, and mark the collection batch number, sampling start and end time, and device status code.

4. The method for real-time detection and optimization control of liquid chromatography flow rate based on multi-point sensing according to claim 1, characterized in that: The S3 specifically includes: S31. Based on the fluid transport topology structure and physical properties, an embedding vector for structural modeling is constructed, and the local structure-aware position tensor is calculated for each node: ； in, Indicates The perceived position tensor of nodes, , and Indicates The three-dimensional spatial coordinates of the nodes in the liquid chromatography system, Indicates The set of direct neighboring nodes of a node, represents the perceptron embedding function, Represents edge The initial flow resistance coefficient, Indicates The node and The spatial distance between nodes; S32, collect the historical flow velocity value of each node in the most recent time step, and compare it with the perceived position tensor Concatenate to form a joint input tensor: ； in, Indicates The joint input tensor of nodes, Represents a splicing operation, Indicates the current moment, represents the time window length, Indicates Nodes at time Observed flow velocity value; S33, input the joint input tensor of all nodes into the FlowFormer model; S34. Combining the velocity prediction values ​​of all nodes at future time points into a velocity evolution prediction map within the prediction time period.

5. The method for real-time detection and optimization control of liquid chromatography flow rate based on multi-point sensing according to claim 1, characterized in that: The S4 specifically includes: S41, receiving a velocity evolution prediction map, wherein the velocity evolution prediction map includes velocity prediction values ​​of all nodes at future time points, and records the evolution trend of the velocity over time; S42, performing local window sliding processing on the time series of each node, using a sliding window with a fixed width to extract a local flow velocity change curve for gradient change scanning analysis; S43, introducing a curvature sensitivity function to perform curvature change identification on the local flow velocity change curve of each node within the time window: ； in, Indicates Nodes at time The curvature index when Indicates Nodes at time The predicted flow velocity at represents the first-order time derivative, represents the second-order time derivative, Indicates The tuning parameters of each node, represents the smoothing factor; S44. In each node time series, locate the time point set of the local maximum curvature index as a mutation candidate point set, and perform high-order difference residual filtering on the mutation candidate point set: ； in, Indicates Nodes at time The fourth-order central difference variation index when , Indicates Nodes at time The predicted flow velocity at Indicates Nodes at time The predicted flow velocity at Indicates Nodes at time The predicted flow velocity at Indicates Nodes at time The predicted flow velocity at Represents absolute value operation; S45, combining the curvature index and the fourth-order central difference variation index to adopt a double threshold strategy to mark mutation areas or abnormal fluctuation node sets ; S46. Based on the identification results and the current operating status, an optimization control objective function is constructed: ； in, represents the optimization control objective function, represents the set of control variables, , and represents the weighting coefficient, Indicates The target reference flow rate of each node is Indicates Nodes at time The predicted flow velocity at represents the prediction time step, represents the time window length, Indicates Nodes at time The predicted flow velocity at Indicates The response time required for a node to reach the target state, represents a stabilizing term that prevents the denominator from reaching zero.

6. The method for real-time detection and optimization control of liquid chromatography flow rate based on multi-point sensing according to claim 5, characterized in that: The threshold double threshold strategy specifically includes setting a curvature index threshold and a fourth-order central difference variation index threshold, wherein the curvature index threshold is used to determine the curvature degree of the local flow velocity change curve, and the fourth-order central difference variation index threshold is used to determine the fluctuation intensity of the local flow velocity change curve; In the velocity evolution prediction map, the time points where the curvature index exceeds the curvature index threshold are selected as suspected mutation points, and the suspected mutation points are further judged whether the fourth-order central difference variation index exceeds the fourth-order central difference variation index threshold. Only nodes that meet both threshold conditions are retained to generate mutation areas or abnormal fluctuation node sets. .

7. The method for real-time detection and optimization control of liquid chromatography flow rate based on multi-point sensing according to claim 1, characterized in that: The S5 specifically includes: S51, obtaining a flow rate evolution prediction map and an optimization control objective function, and establishing a control parameter space, wherein the control parameter space includes a high-pressure pump speed, a solvent ratio, and a valve opening; S52, using the adaptive fox group algorithm controller to initialize the population, defining the population as a collection of fox group individuals ,in Indicates Individual foxes, represents the total number of fox individuals, each fox individual represents a set of candidate solutions in the control parameter space, the initial fox population individuals are generated by uniform random distribution, and the maximum evolutionary generation and convergence threshold are set; S53, according to the optimization control objective function, the velocity evolution prediction map is substituted into the evaluation control performance, and the current optimal individual is recorded; S54, according to the distance difference between each fox group individual and the optimal individual, adaptively and dynamically update the fox individual position vector: ； in, Indicates the updated The position vector of each fox, Indicates the number before the update The position vector of each fox, represents the dynamic step size adjustment factor, represents the position vector of the optimal individual, represents the random perturbation coefficient, represents a Gaussian distributed random vector with mean 0, represents the L2 norm; S55, record the best individuals produced in the evolution process of fox groups of all generations and add them to the memory bank to assist in the generation of individuals in the next generation of fox groups; S56, repeating steps S53-S55 until the set evolutionary generation is reached or the convergence threshold of the optimization control objective function is met, and generating the optimal adjustment strategy.

8. The method for real-time detection and optimization control of liquid chromatography flow rate based on multi-point sensing according to claim 1, characterized in that: The S6 specifically includes: S61, according to the optimal adjustment strategy, the central control unit sends control instructions to each actuator of the liquid chromatography system in real time, including a high-pressure pump speed adjustment instruction, a solvent ratio electronic control valve ratio adjustment instruction, and a valve opening control instruction; S62. After receiving the control command, each actuator immediately implements the control action. The high-pressure pump adjusts the operating frequency to achieve the target flow rate setting. The proportional valve dynamically adjusts the ratio of different solvents and stabilizes the mixing ratio. The valve adjusts the pipeline pressure and flow according to the opening; S63, during the adjustment execution process, the response flow rate data of each node of the liquid chromatography system is collected in real time through the distributed acquisition network, and the response state after adjustment is synchronously recorded to obtain feedback data under the actual operation state; S64, comparing the feedback data with the flow velocity prediction value of the FlowFormer model, calculating the deviation between the flow velocity prediction value and the feedback data, and adaptively updating the FlowFormer model parameters according to the deviation: ； in, represents the updated FlowFormer model parameters, Indicates the FlowFormer model parameters before updating, represents the adaptive learning rate, represents the gradient of the FlowFormer model parameters, Indicates the deviation between the flow rate prediction value and the feedback data, represents the L2 norm; S65. Use the updated FlowFormer model to regenerate the flow velocity evolution prediction map for the next cycle, and further adjust and optimize the regulation strategy for the next cycle to form a feedback loop.

9. The method for real-time detection and optimization control of liquid chromatography flow rate based on multi-point sensing according to claim 1, characterized in that: The local escape strategy includes that when the liquid chromatography system detects abnormal flow rate changes, the adaptive fox swarm algorithm controller limits the search range to the abnormal node and the abnormal area where the directly related upstream and downstream nodes are located, and by compressing the control parameter space and introducing a fast iteration factor, a local optimal adjustment solution with pressure reduction and bypass as the goal is preferentially generated, which includes dynamically adjusting the valve opening of the abnormal path segment, temporarily reducing the output frequency of the high-pressure pump or switching to a preset backup solvent channel to achieve flow rate unloading and pressure release of the abnormal node. At the same time, the liquid chromatography system continuously collects response data of the abnormal area, and records the input parameters and feedback results in the escape process to an offline learning pool.

Images