Electromagnetic valve flow intelligent adaptive control method and system for composite working conditions

Abstract

The application provides a kind of electromagnetic valve flow intelligent adaptive control method and system for composite working condition, it is related to industrial automation control technical field, first, the mutual feedback type working condition flow data containing working condition influence data, flow feedback data and dynamic mutual feedback trace data under composite working condition are collected;Then, the working condition flow mutual feedback evolution model is constructed based on the mutual feedback type working condition flow data, the dynamic correlation evolution of working condition and flow is realized;Then, the evolution type flow adaptation strategy containing the flow regulation path and parameter combination of dynamic adjustment is generated according to the model real-time evolution result;The evolution type flow adaptation strategy is iteratively optimized through dynamic mutual feedback trace data, and the intelligent adaptive control signal is generated;Finally, the intelligent adaptive control signal is transmitted to the actuator, and the model is continuously updated by inputting data reversely.The application can effectively deal with composite working condition, improve the precision and adaptability of electromagnetic valve flow control.

Description

Technical Field

[0001] This invention relates to the field of industrial automation control technology, and more specifically, to a method and system for intelligent adaptive control of solenoid valve flow under complex operating conditions. Background Technology

[0002] In the field of industrial automation control, solenoid valves, as key fluid control components, are crucial for the stable operation of the entire system due to their flow control accuracy and adaptability. In practical applications, solenoid valves often face complex and combined operating conditions, encompassing various environmental factors, equipment operating states, and changes in media properties. For example, in chemical production processes, fluctuations in ambient temperature and pressure, changes in equipment operating frequency, and differences in media density and viscosity can all significantly impact the flow rate of solenoid valves.

[0003] Traditional solenoid valve flow control methods are often based on fixed control strategies, making it difficult to fully consider the dynamic interactions between various factors under complex operating conditions. These methods typically only respond to single or simple changes in operating conditions and cannot accurately capture the complex relationship between operating conditions and flow rate. When complex changes occur in complex operating conditions, traditional methods struggle to achieve precise flow control, leading to problems such as unstable flow and decreased control accuracy, which in turn affects the efficiency and quality of the entire production process. Summary of the Invention

[0004] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, embodiments of the present invention provide a method for intelligent adaptive control of solenoid valve flow under complex operating conditions, the method comprising: Collect feedback-type operating condition flow data of solenoid valve under combined operating conditions. The feedback-type operating condition flow data includes operating condition influence data, flow feedback data and dynamic feedback trace data. Among them, the operating condition influence data covers environmental effect data, equipment operation data and medium property data, the flow feedback data is a record of the flow state of the medium through the solenoid valve, and the dynamic feedback trace data is a record of the interaction process between the operating condition influence data and the flow feedback data. Based on the aforementioned feedback-type operating condition flow data, an operating condition flow feedback evolution model is constructed. The operating condition flow feedback evolution model is composed of the feedback intensity evolution trajectory and the flow response evolution law as its core, and is used to realize the dynamic correlation evolution between operating conditions and flow. Based on the real-time evolution results of the operating condition flow feedback evolution model, an evolutionary flow adaptation strategy is generated. The evolutionary flow adaptation strategy includes a flow adjustment path and parameter combination that are dynamically adjusted with the feedback evolution. The evolutionary flow adaptation strategy is iteratively optimized using the dynamic feedback trace data to generate an intelligent adaptive control signal for the solenoid valve flow. The intelligent adaptive control signal of the solenoid valve flow is transmitted to the solenoid valve actuator, and the feedback-type operating condition flow data is input in reverse into the operating condition flow feedback evolution model to promote the continuous evolution and update of the operating condition flow feedback evolution model.

[0005] Furthermore, embodiments of the present invention also provide an intelligent adaptive control system for electromagnetic valve flow under complex operating conditions, characterized in that it includes: A processor; a machine-readable storage medium for storing machine-executable instructions of the processor; wherein the processor is configured to execute the above-described intelligent adaptive flow control method for solenoid valves under complex operating conditions by executing the machine-executable instructions.

[0006] In another aspect, embodiments of the present invention also provide a computer program product, the computer program product including machine-executable instructions stored in a computer-readable storage medium, a processor of a solenoid valve flow intelligent adaptive control system for complex operating conditions reading the machine-executable instructions from the computer-readable storage medium, the processor executing the machine-executable instructions, causing the solenoid valve flow intelligent adaptive control system for complex operating conditions to execute the above-described solenoid valve flow intelligent adaptive control method for complex operating conditions.

[0007] Based on the above, a feedback-based flow data model for combined operating conditions, including operating condition impact data, flow feedback data, and dynamic feedback trace data, is constructed. This model, with the evolution trajectory of feedback intensity and the evolution law of flow response as its core, achieves dynamic correlation between operating conditions and flow, accurately simulating and predicting flow change trends under different operating conditions. An evolutionary flow adaptation strategy, generated based on the model's real-time evolution results, includes flow regulation paths and parameter combinations dynamically adjusted with feedback evolution. This strategy flexibly adapts to dynamic changes in combined operating conditions, ensuring that flow is always in optimal control. Iterative optimization of the adaptation strategy using dynamic feedback trace data generates intelligent adaptive control signals, further improving control accuracy and stability. By transmitting control signals to the actuator and inputting data in reverse to drive continuous model evolution and updates, the model can stably cope with various complex combined operating conditions over a long period, significantly improving the accuracy, adaptability, and reliability of solenoid valve flow control. Attached Figure Description

[0008] Figure 1 This is a schematic diagram of the execution flow of the intelligent adaptive control method for electromagnetic valve flow under complex operating conditions provided in this embodiment of the invention.

[0009] Figure 2This is a schematic diagram of exemplary hardware and software components of an intelligent adaptive control system for electromagnetic valve flow under complex operating conditions provided in an embodiment of the present invention. Detailed Implementation

[0010] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 This is a flowchart illustrating an embodiment of the intelligent adaptive control method for solenoid valve flow under complex operating conditions provided by the present invention. The following is a detailed description of the intelligent adaptive control method for solenoid valve flow under complex operating conditions.

[0011] Step S110: Collect feedback-type operating condition flow data of the solenoid valve under combined operating conditions. The feedback-type operating condition flow data includes operating condition influence data, flow feedback data, and dynamic feedback trace data. The operating condition influence data covers environmental impact data, equipment operation data, and medium property data. The flow feedback data is a record of the flow state of the medium through the solenoid valve. The dynamic feedback trace data is a record of the interaction between the operating condition influence data and the flow feedback data.

[0012] In this embodiment, a solenoid valve in a hydraulic control system for industrial production is used as an application scenario. This solenoid valve controls the flow rate of hydraulic oil in the hydraulic pipeline to drive hydraulic actuators to complete specific actions. In this scenario, the complex operating conditions may include the simultaneous action of multiple factors such as changes in ambient temperature, fluctuations in system pressure, and changes in hydraulic oil viscosity.

[0013] When collecting feedback-type operating condition flow data, the first step is to determine the data collection scope and frequency. For environmental impact data within the operating condition data, temperature, humidity, and vibration sensors are installed near the solenoid valve's mounting location to acquire data such as ambient temperature, humidity, and vibration amplitude. Equipment operation data is obtained through controllers connected to the solenoid valve and pressure and flow sensors in the hydraulic system, including the solenoid valve's drive voltage, drive current, valve spool position, and system operating pressure. Medium property data is obtained through periodic sampling and analysis of the hydraulic oil, including its viscosity, density, and cleanliness. The aforementioned environmental impact data, equipment operation data, and medium property data collectively constitute the operating condition impact data, which is collected at a frequency of once per millisecond to ensure timely capture of dynamic changes in the operating conditions.

[0014] The flow feedback data is a record of the flow status of the medium through the solenoid valve. It is collected by a high-precision flow sensor installed at the outlet of the solenoid valve. Specifically, it includes parameters such as real-time flow value, flow fluctuation amplitude, and flow change rate. The acquisition frequency is also once every millisecond.

[0015] Dynamic feedback trace data is a record of the interaction between operating condition impact data and flow feedback data. To acquire this data, a temporal correlation needs to be established between the operating condition impact data and the flow feedback data. For example, when an increase in ambient temperature leads to a decrease in hydraulic oil viscosity, it will cause a change in the real-time flow rate value in the flow feedback data. This causal relationship, its time sequence, and the intensity of its effect need to be recorded. Specifically, a timestamp synchronization mechanism is set up in the data acquisition system to ensure that each data point in both the operating condition impact data and the flow feedback data has a precise time stamp. Then, a data association algorithm identifies significant changes in the operating condition impact data (such as a sudden increase in temperature or pressure) and matches these changes with subsequent changes in the flow feedback data, recording the time interval between them, the ratio of the flow rate change to the operating condition impact change, and other information, thus forming dynamic feedback trace data.

[0016] Step S120: Based on the feedback-type operating condition flow data, construct an operating condition flow feedback evolution model. The operating condition flow feedback evolution model is composed of the feedback intensity evolution trajectory and flow response evolution law as its core, and is used to realize the dynamic correlation evolution of operating conditions and flow.

[0017] Step S121: Analyze the constituent dimensions of the feedback-type operating condition flow data, distinguish the environmental effect dimension, equipment operation dimension, and medium attribute dimension in the operating condition influence data, the flow rate dimension and flow stability dimension in the flow feedback data, and the effect trigger dimension, response feedback dimension, and continuous effect dimension in the dynamic feedback trace data, and extract the data representation form of each constituent dimension.

[0018] The data on the impact of operating conditions is further subdivided into environmental effects, equipment operation, and media properties. The environmental effects dimension includes parameters such as ambient temperature, ambient humidity, and ambient vibration amplitude, represented as continuous numerical sequences in degrees Celsius, percentages, and millimeters per second, respectively. The equipment operation dimension includes parameters such as drive voltage, drive current, valve spool position, and system operating pressure, also represented as continuous numerical sequences in volts, amperes, millimeters, and megapascals, respectively. The media properties dimension includes the viscosity, density, and cleanliness of the hydraulic oil. Viscosity is measured in square millimeters per second, density in kilograms per cubic meter, and cleanliness is characterized by particle counts in particles per milliliter.

[0019] Flow feedback data is divided into two dimensions: flow rate and flow stability. The flow rate dimension represents real-time flow values, measured in liters per minute (L / min), and is represented as a continuous numerical sequence. The flow stability dimension includes the amplitude of flow fluctuations and the rate of change of flow. The amplitude of flow fluctuations is represented by the standard deviation of flow values ​​within a statistical time window, measured in L / min; the rate of change of flow is the ratio of the difference between flow values ​​at two adjacent sampling times to the sampling time interval, measured in the square of L / min.

[0020] Dynamic feedback trace data includes three dimensions: triggering, response feedback, and duration. The triggering dimension records significant changes in various parameters within the operational condition impact data, represented as event markers including trigger time, trigger parameter type, and trigger change magnitude. The response feedback dimension corresponds to the flow feedback data's response to the operational condition impact trigger, recording the response time, response parameter type, and response change magnitude. The duration dimension records the duration of the operational condition impact's effect on the flow feedback and the changes in its intensity within that time period. The intensity is characterized by the ratio of the response change magnitude to the trigger change magnitude, with the duration measured in milliseconds.

[0021] Step S122: Extract the feedback event sequence from the dynamic feedback trace data. Each feedback event in the feedback event sequence includes a working condition impact trigger point, a flow response feedback point, the time interval between the working condition impact trigger point and the flow response feedback point, and a record of the intensity of the effect. Connect the feedback events in series to form a continuous feedback event chain.

[0022] Step S1221: Collect the complete record in the dynamic feedback trace data, the complete record covering the interaction record of all operating conditions and flow response during the operation of the solenoid valve under combined operating conditions.

[0023] The complete record of dynamic feedback trace data includes all operating condition trigger points and corresponding flow response feedback points from the start of solenoid valve operation to the current moment, as well as the time correlation and intensity of their effects. For example, at a certain moment, the ambient temperature suddenly rises by a certain amount (operating condition trigger point), and after a period of time, the real-time flow value in the flow feedback data increases accordingly by a certain amount (flow response feedback point). This interaction process is recorded in the dynamic feedback trace data.

[0024] Step S1222: Sort the collected dynamic feedback trace data by time and organize it into time series data according to the order in which the data was generated, so as to ensure the temporal integrity of the time series data.

[0025] Since operational condition impacts and flow responses occur dynamically over time, it is necessary to sort the dynamic feedback trace data by time. Specifically, based on the timestamps in the data records, all feedback events are arranged in chronological order. For example, the operational condition impact trigger point and its corresponding flow response feedback point occurring at time t1 are listed first, while those occurring at time t2 (t2>t1) are listed later, and so on, forming a continuous time series data.

[0026] Step S1223: Identify the trigger points of the operating condition impact from the time series data, mark the time nodes and changes in the operating condition impact data that are significantly changed, and the time nodes in which the operating condition impact data are significantly changed become the starting points of the feedback event.

[0027] Thresholds are set to identify trigger points for operational conditions. For continuously changing parameters such as ambient temperature, ambient humidity, and system operating pressure, a significant change is considered to have occurred when the change in a parameter exceeds a preset threshold within a unit of time. For example, if the threshold for ambient temperature change is set to 5 degrees Celsius per minute, then a 6-degree Celsius increase in ambient temperature within a minute is marked as a trigger point for operational conditions. The change details include the parameter name, the value before the change, the value after the change, and the magnitude of the change.

[0028] Step S1224: After each operating condition trigger point, track the changes in flow feedback data, identify flow response feedback points, and mark the time nodes and change characteristics of the corresponding changes in flow feedback data. The time nodes of the corresponding changes in flow feedback data become the feedback points of the mutual feedback event.

[0029] After identifying the trigger points for operational conditions, it's necessary to track their corresponding responses in subsequent flow feedback data. This is also done by setting thresholds to identify flow response feedback points. For example, when the trigger point is an increase in system operating pressure, the expected real-time flow value in the flow feedback data will increase accordingly. If, at some point after the trigger point, the change in real-time flow value exceeds a preset flow change threshold (e.g., 2 liters per minute), that moment is marked as a flow response feedback point. Change characteristics include the direction of flow change (increase or decrease), the magnitude of the change, and the duration of the change.

[0030] Step S1225: Calculate the time difference between each operating condition's trigger point and the corresponding flow response feedback point. The time difference becomes the time interval of the mutual feedback event, reflecting the transmission time of the operating condition's impact on the flow response.

[0031] The time interval is calculated by subtracting the timestamp of the condition-induced trigger point from the timestamp of the flow response feedback point. For example, if the timestamp of the condition-induced trigger point is t1 and the timestamp of the flow response feedback point is t2, then the time interval is t2 - t1, in milliseconds. This time interval reflects the time required for a condition-induced effect to occur and trigger a flow response; different types of condition-induced factors may have different transmission durations.

[0032] Step S1226: Analyze the change amplitude of the operating condition influence trigger point and the response amplitude of the flow response feedback point. Based on the correlation between the change amplitude of the operating condition influence trigger point and the response amplitude of the flow response feedback point, determine the intensity of the mutual feedback event. The intensity of the event reflects the magnitude of the effect of the operating condition influence on the flow response.

[0033] Determining the intensity of an effect requires considering the proportional relationship between the magnitude of change in the trigger point of the operating condition and the magnitude of the response at the flow response feedback point. For example, if the system operating pressure increases by ΔP (megapascals), resulting in an increase of ΔQ (liters per minute) in the real-time flow rate, then the intensity of the effect can be defined as the ratio of ΔQ to ΔP (liters per minute per megapascal). For different types of operating condition influence parameters, their corresponding intensity calculation methods need to be defined separately to accurately reflect the magnitude of the effect of different operating condition factors on the flow response.

[0034] Step S1227: Integrate each operating condition impact trigger point, the corresponding flow response feedback point, the time interval between the operating condition impact trigger point and the flow response feedback point, and the intensity of the effect to form a single mutual feedback event record.

[0035] Each feedback event log contains the following information: timestamp, parameter type, and change magnitude of the operating condition impact trigger point; timestamp, parameter type, and response magnitude of the flow response feedback point; time interval; and intensity of effect. For example, a feedback event log might be: operating condition impact trigger point (t1, system operating pressure, +2 MPa), flow response feedback point (t2, real-time flow value, +3 L / min), time interval (150 ms), and intensity of effect (1.5 L / min / MPa).

[0036] Step S1228: Record all mutual feedback events in sequence according to the time sequence to form a continuous mutual feedback event chain. Each mutual feedback event in the mutual feedback event chain maintains a temporal and logical association with the mutual feedback events before and after it.

[0037] All individual feedback events are recorded and arranged in chronological order of their trigger points based on their operating conditions, forming a feedback event chain. In this chain, the flow response feedback point of a previous feedback event may become part of the trigger point for the operating conditions of a subsequent feedback event, because changes in flow can have a reciprocal effect on equipment operating status or media properties. For example, an increase in flow may lead to further changes in system operating pressure, thereby triggering a new feedback event.

[0038] Step S1229: Supplement the missing mutual feedback event records in the mutual feedback event chain, and correct the recording deviations in the time interval and intensity of the mutual feedback events.

[0039] Due to various interference factors, missing or inaccurate records may occur in the feedback event chain. Data interpolation and filtering algorithms are used to supplement missing feedback event records. For example, when there is a long time interval between two adjacent feedback events, and historical data patterns indicate that other feedback events should exist within that time period, interpolation methods are used to generate missing records. For discrepancies in time intervals and intensity, the records are compared with the average of similar historical feedback events, and values ​​with large deviations are corrected to better reflect the overall trend.

[0040] Step S12210: Mark the mutual feedback event chain, indicating the operating condition impact dimension and flow response dimension corresponding to each mutual feedback event.

[0041] To facilitate subsequent analysis and processing, each feedback event needs to be labeled with dimensions. For example, if a feedback event is caused by a change in ambient temperature in the environmental impact dimension, and its corresponding flow response dimension is the flow rate dimension, then the corresponding dimension label should be added to the feedback event record, such as "Environmental impact dimension - temperature, flow rate dimension - real-time flow".

[0042] Step S123: Analyze the correlation between adjacent mutual feedback events in the mutual feedback event chain, track the process of changes in operating condition impact data triggering adjustments in flow feedback data, and the path of how adjustments in flow feedback data react to subsequent changes in operating condition impact data, forming the transmission trajectory of mutual feedback effects.

[0043] Complex relationships exist between adjacent feedback events in the feedback event chain, reflecting the dynamic feedback process between operating conditions and flow. These relationships are analyzed by constructing a directed graph, where each feedback event is a node, and directed edges between nodes represent causal relationships between them.

[0044] For example, the first feedback event is caused by an increase in system operating pressure (change in operating condition data), leading to an increase in real-time flow rate (adjustment of flow feedback data). This increase in flow rate may cause pressure changes in other components of the hydraulic system, resulting in a second feedback event, i.e., a further change in system operating pressure (subsequent change in operating condition data). By tracing the direction and connection of the directed edges mentioned above, the path of how changes in operating condition data trigger adjustments in flow feedback data, and how these adjustments in flow feedback data react to subsequent changes in operating condition data, can be clearly depicted, thus forming the transmission trajectory of the feedback effect. During the analysis, the time delay factor needs to be considered. The time intervals between adjacent feedback events may differ; some feedback events may have direct, immediate effects, while others may have a certain lag. By calculating the product of the time interval between adjacent feedback events and the intensity of the effect, the transmission efficiency and cumulative effect of the feedback effect can be evaluated.

[0045] Step S124: Define the core evolution parameters of the working condition flow mutual feedback evolution model. The core evolution parameters include mutual feedback intensity parameters, evolution rate parameters, response hysteresis parameters, and fitness parameters. The core evolution parameters together describe the dynamic characteristics of mutual feedback evolution.

[0046] The feedback strength parameter describes the intensity of the interaction between the operating condition and the flow response. Its value comprehensively considers the intensity of the interaction and the frequency of the interaction events. The evolution rate parameter reflects the speed of change in the transmission trajectory of the feedback effect, calculated as the rate of change of the number of interaction events in the chain per unit time. The response hysteresis parameter characterizes the average time interval between the trigger point of the operating condition and the feedback point of the flow response, obtained by averaging the time intervals of multiple interaction events. The fit parameter measures the degree of matching between the current operating condition and the flow rate. Its value is determined based on the flow stability dimension parameters (such as flow fluctuation amplitude) in the flow feedback data and the deviation between the actual and expected flow values. The smaller the flow fluctuation amplitude and the smaller the deviation, the higher the value of the fit parameter.

[0047] Step S125: Establish the correspondence between the mutual feedback event sequence and the core evolution parameters, and convert the feature data of each mutual feedback event into the corresponding core evolution parameter values ​​to form a parameter evolution trajectory.

[0048] For the feedback intensity parameter, the effect intensity of each feedback event is multiplied by a weighting coefficient, which is positively correlated with the occurrence frequency of the feedback event. Then, the weighted effect intensity of all feedback events is summed to obtain the current value of the feedback intensity parameter. As new feedback events are added, the value of the feedback intensity parameter is continuously updated, forming its evolution trajectory.

[0049] The evolution rate parameter is calculated by statistically analyzing the change in the number of feedback events per unit time. For example, if 5 feedback events occurred in the past 10 seconds, while 3 feedback events occurred in the previous 10 seconds, then the evolution rate parameter is (5-3) / 10 = 0.2 events per second. This parameter reflects the changing trend of the frequency of feedback events.

[0050] The response hysteresis parameter is obtained by averaging the time intervals of all feedback events within a time window. For example, the arithmetic mean of the time intervals of the past 100 feedback events is calculated as the current response hysteresis parameter value. As time progresses, the time window is continuously slid to update the value of the response hysteresis parameter.

[0051] The adaptation parameter is calculated by first predicting an expected flow rate based on current operating condition data, and then calculating the deviation between the actual and expected flow rates. Simultaneously, considering the flow rate fluctuation amplitude, the deviation and fluctuation amplitude are normalized before being substituted into a preset formula to calculate the adaptation parameter. For example, the adaptation parameter equals 1 minus the weighted sum of the normalized deviation and the normalized flow rate fluctuation amplitude; the weights are set according to the importance placed on flow accuracy and stability in the actual application scenario.

[0052] Step S126: Build the evolution architecture of the working condition flow mutual feedback evolution model, and set up a data input module, a mutual feedback analysis module, a parameter update module and a result output module. The data input module receives the mutual feedback working condition flow data, the mutual feedback analysis module processes the correlation of mutual feedback events, the parameter update module dynamically adjusts the core evolution parameters, and the result output module outputs the evolution results.

[0053] The data input module receives externally collected feedback-type operating condition flow data, including operating condition impact data, flow feedback data, and dynamic feedback trace data. This module has an internal data buffer for temporarily storing the received data and performing preliminary format verification and timestamp synchronization to ensure data integrity and consistency. The feedback analysis module's main function is to handle the correlation of feedback events. It includes a feedback event identification submodule, a correlation analysis submodule, and a transmission trajectory construction submodule. The feedback event identification submodule identifies operating condition impact trigger points and flow response feedback points from the dynamic feedback trace data, generating feedback event records. The correlation analysis submodule analyzes the temporal and logical correlations between adjacent feedback events. The transmission trajectory construction submodule constructs the transmission trajectory of the feedback effect based on the correlations. The parameter update module dynamically adjusts the core evolution parameters based on the feedback event sequence and transmission trajectory output by the feedback analysis module. This module includes a parameter calculation submodule and a parameter correction submodule. The parameter calculation submodule calculates the current values ​​of the core evolution parameters based on a preset algorithm and the characteristic data of the feedback events. The parameter correction submodule then corrects the calculated core evolution parameters by combining historical evolution data and actual flow regulation effects to improve the accuracy of the model. The result output module formats and outputs the evolution results obtained from the parameter update module, including the core evolution parameter values, evolution stage identifiers, and the trajectory of the feedback effect.

[0054] Step S127: Input the historical feedback-type operating condition flow data into the evolution architecture, run the feedback analysis module and parameter update module to obtain the simulated evolution results; compare the simulated evolution results with the corresponding historical flow feedback data, and adjust the transformation logic and correlation of the core evolution parameters based on the comparison results.

[0055] Historical feedback-based operating condition flow data over a period of time (e.g., one month) is collected and input into the data input module of the evolutionary architecture in batches according to chronological order. The data input module performs the same preprocessing operations on the historical data as on the real-time data before passing it to the feedback analysis module. The feedback analysis module processes the historical feedback-based operating condition flow data, identifies historical feedback event sequences, analyzes correlations, and constructs transmission trajectories. The parameter update module then calculates simulated values ​​of core evolutionary parameters based on this historical feedback event data, obtaining the simulated evolution results, including time-series curves of the core evolutionary parameters and changes in evolutionary stage identifiers.

[0056] The core evolution parameters in the simulated evolution results are compared and analyzed with the corresponding historical flow feedback data. For example, the correlation between the simulated value of the feedback intensity parameter and the historical flow change amplitude is compared, and the consistency between the simulated value of the evolution rate parameter and the frequency changes of historical feedback events is analyzed. If a large deviation is found between the simulation results and historical data, such as the simulated value of the feedback intensity parameter being too high or too low, leading to inaccurate predictions of flow changes, the transformation logic of the core evolution parameters needs to be adjusted. For example, the weighting coefficients in the calculation process of the feedback intensity parameter may be modified, or the time window size of the response lag parameter may be adjusted. Simultaneously, regarding the correlation between feedback events, if the logical correlation between certain types of feedback events is found to be incorrectly identified, the judgment conditions and thresholds in the correlation analysis algorithm need to be corrected.

[0057] Step S128: Integrate real-time feedback-type operating condition flow data into the data input module; adjust the processing order and computing resource allocation ratio of the feedback analysis module and the parameter update module according to the generation frequency of real-time feedback events; based on the adjusted processing order and computing resource allocation ratio, drive the feedback analysis module and the parameter update module to process the real-time feedback-type operating condition flow data, and update the values ​​of the core evolution parameters and the evolution stage identifier.

[0058] Step S1281: Establish a real-time data access interface and transmit the real-time feedback-type operating condition flow data to the evolution architecture through the interface.

[0059] A dedicated real-time data access interface is designed, employing an industrial Ethernet protocol (such as PROFINET) to ensure the real-time performance and reliability of data transmission. This interface supports full-duplex communication, with a data transmission rate set to 100Mbps. Internally, the interface includes a data receive buffer and a data verification unit. The data receive buffer temporarily stores the received real-time data, while the data verification unit performs CRC checks on the data to ensure that no errors occur during transmission.

[0060] Step S1282: Prioritize the real-time incoming feedback-type operating condition flow data, mark the latest feedback event record in the dynamic feedback trace data as the highest priority, and mark the operating condition impact data and flow feedback data as the second highest priority.

[0061] Data is prioritized based on its importance to model evolution and timeliness requirements. The latest feedback event records in the dynamic feedback trace data directly reflect the latest feedback relationship between the current operating conditions and flow, and are most critical for updating core evolution parameters; therefore, they are marked as the highest priority. Operating condition impact data and flow feedback data are the basis for generating feedback events. Although important, their timeliness requirements are slightly lower than the latest feedback event records; therefore, they are marked as the second highest priority. During data processing, high-priority data will be processed first.

[0062] Step S1283: Analyze the functional division of each module in the evolutionary architecture, and analyze the processing flow and interdependencies of the data input module, mutual feedback analysis module, parameter update module and result output module.

[0063] The data input module's processing flow is as follows: receive real-time data → data verification → timestamp synchronization → data caching → data distribution to the feedback analysis module. The feedback analysis module's processing flow is as follows: receive data distributed by the data input module → feedback event identification → correlation analysis → transmission trajectory construction → pass the results to the parameter update module. The parameter update module's processing flow is as follows: receive the output results from the feedback analysis module → calculate core evolution parameters → parameter correction → evolution stage judgment → pass the core evolution parameter values ​​and evolution stage identifiers to the result output module. The result output module's processing flow is as follows: receive the output from the parameter update module → result formatting → output to the external control system.

[0064] The dependencies between the modules are as follows: the feedback analysis module depends on the data provided by the data input module; the parameter update module depends on the analysis results of the feedback analysis module; and the result output module depends on the calculation results of the parameter update module.

[0065] Step S1284: Based on the priority classification results of the feedback-type operating condition flow data, adjust the processing resource allocation of each module in the evolution architecture, allocate more computing resources to the module that processes the highest priority data, so as to improve the processing speed of the module.

[0066] During the evolutionary architecture's operation, the operating system's process scheduling mechanism adjusts the allocation of processing resources across modules. Higher CPU utilization and larger memory are allocated to submodules within the feedback analysis module responsible for processing the highest-priority dynamic feedback trace data (such as the feedback event recognition submodule). For example, the CPU priority of this submodule is set to the highest, and its memory allocation is increased to 40% of the total available memory, while other submodules and modules processing the next highest priority data are allocated relatively fewer computing resources. This ensures that the highest-priority data is processed quickly, thereby updating core evolution parameters in a timely manner.

[0067] Step S1285: In the mutual feedback analysis module, a parallel computing unit is configured to simultaneously perform the correlation analysis on multiple latest mutual feedback event records.

[0068] Leveraging the advantages of multi-core processors, parallel computing units are configured within the correlation analysis submodule of the feedback analysis module. Multiple recent feedback event records (e.g., five simultaneously arriving feedback event records) are assigned to different computing cores for parallel processing. Each computing core independently analyzes the correlation between a feedback event and its preceding and following feedback events. The processing results from each computing core are then aggregated to form a complete feedback action propagation trajectory. The number of parallel computing units is determined based on the number of processor cores, typically set to half the number of processor cores to avoid resource contention.

[0069] Step S1286: Adjust the update frequency of the parameter update module and set an update cycle consistent with the generation frequency of real-time mutual feedback event records so that the core evolution parameters can reflect the latest mutual feedback status in a timely manner.

[0070] By statistically analyzing the generation frequency of real-time feedback event records, for example, an average of 3 feedback event records per second, the update cycle of the parameter update module is set to 1 / 3 second, meaning the core evolution parameters are updated approximately every 333 milliseconds. Within each update cycle, the parameter update module receives all feedback event analysis results output by the feedback analysis module within that cycle and calculates and updates the values ​​of the core evolution parameters accordingly. If the generation frequency of feedback event records changes, such as increasing to 5 per second, the update cycle is adjusted accordingly to 200 milliseconds to ensure that the core evolution parameters can keep pace with the changing speed of the feedback state.

[0071] Step S1287: Configure a real-time data access interface in the data input module of the evolution architecture; receive real-time feedback-type operating condition flow data through the real-time data access interface, and forward the data to the data buffer of the data input module.

[0072] After establishing the real-time data access interface as described in step S1281, the interface is configured in the data input module, including setting the IP address, port number, and data transmission protocol parameters. Upon receiving real-time feedback-type operating condition traffic data, the interface first performs data verification to check the data's integrity and format correctness. After successful verification, a precise timestamp (accurate to the microsecond level) is added to the data, and then the data is forwarded to the data buffer inside the data input module. The data buffer uses a first-in, first-out (FIFO) storage method, with a capacity set to store real-time data within 10 seconds to handle sudden data transmissions.

[0073] Step S1288: Set real-time response trigger rules and set a threshold for the effect intensity record; in the data input module, compare the effect intensity of the incoming feedback event record with the threshold; when the effect intensity exceeds the threshold, send a priority processing instruction to the data scheduling unit of the evolution architecture; after receiving the priority processing instruction, the data scheduling unit prioritizes the processing of the feedback event record that exceeds the threshold and related operating condition impact data and traffic feedback data to the feedback analysis module.

[0074] Based on historical data and practical application experience, a threshold is set for the intensity of feedback events, for example, 2.0 liters per minute per megapascal. In the data input module, when a feedback event record is received, its intensity parameter is immediately extracted and compared with this threshold. If the intensity exceeds the threshold, it indicates that the feedback event has a significant impact on traffic and requires priority processing. At this point, the data input module sends a priority processing instruction to the data scheduling unit in the evolutionary architecture. This instruction includes the identifier of the feedback event record and the storage location of related data. Upon receiving the instruction, the data scheduling unit pauses the currently processing low-priority data and retrieves the high-intensity feedback event record, along with its related operational impact data and traffic feedback data, from the data buffer, sending them preferentially to the feedback analysis module for processing. After processing is complete, processing of low-priority data resumes.

[0075] Step S1289: Periodically evaluate the response effect of the working condition flow feedback evolution model after the processing priority of each module in the evolution architecture is adjusted, and fine-tune the processing resource allocation ratio based on the processing time of real-time feedback events and the accuracy of evolution results.

[0076] The responsiveness of the evolutionary architecture is evaluated periodically (e.g., hourly). The processing time for real-time feedback events refers to the time elapsed from when the feedback event is recorded in the data input module to when the parameter update module outputs the updated core evolution parameters. The average processing time for each feedback event is calculated by setting timestamps at key nodes in each module. The accuracy of the evolution results is measured by comparing the deviation between the predicted values ​​of the core evolution parameters and the actual traffic feedback data. If the average processing time is found to be too long (e.g., exceeding 500 milliseconds), it indicates that the allocation of computing resources may be unreasonable, requiring further improvement in the resource allocation ratio between the feedback analysis module and the parameter update module. If the accuracy of the evolution results decreases (e.g., the deviation increases), it may be due to sacrificing analytical accuracy for excessive processing speed. This requires appropriately adjusting the number of parallel computing units or the complexity of the correlation analysis algorithm, while fine-tuning the resource allocation ratio to achieve a balance between processing speed and accuracy.

[0077] Step S12810: Record the correspondence between the processing priority adjustment of each module in the evolution architecture and the response effect of the working condition flow feedback evolution model each time, and form an adjustment log.

[0078] During the evolutionary architecture's operation, each adjustment to the processing priority or computational resource allocation ratio of each module must be meticulously recorded, including the adjustment time, details (e.g., which module's CPU priority was increased, how the memory allocation ratio changed), and performance metrics before and after the adjustment (e.g., average processing time, evolutionary result deviation). This information is stored in an adjustment log, which is in binary format and a new log file is generated daily to facilitate subsequent analysis and optimization. By analyzing the adjustment log, the optimal processing resource allocation strategy under different operating conditions can be identified.

[0079] Step S129: Divide the evolution stages of the operating condition flow feedback evolution model. Based on the value range and change trend of the core evolution parameters, divide the evolution process into an initial evolution stage, a stable evolution stage, and a dynamic adjustment evolution stage. Each stage corresponds to a specific evolution logic.

[0080] When the initial operation condition flow feedback evolution model is started, the core evolution parameters are unstable due to the limited amount of feedback event data, placing the model in the initial evolution phase. During this phase, the feedback strength parameter is typically low and highly volatile, the evolution rate parameter may be high (due to the increasing number of feedback events initially), the response lag parameter may have significant deviations, and the fit parameter is low. The specific evolution logic for this initial phase involves using a large parameter update step size to quickly learn the correlations between feedback events. The calculation of core evolution parameters primarily relies on recent feedback event data to stabilize the model as quickly as possible.

[0081] When the core evolutionary parameters gradually stabilize, the fluctuation range of the feedback strength parameter is less than a preset threshold (e.g., 5%), the evolution rate parameter decreases to a low level (e.g., less than 0.1 per second), the response lag parameter tends to stabilize, and the fitness parameter reaches a high value (e.g., greater than 0.8), the model enters the stable evolutionary stage. The evolutionary logic in this stage is to use a small parameter update step size to slowly adjust the core evolutionary parameters to maintain model stability. Emphasis is placed on the long-term correlations between feedback events, and the calculation of the core evolutionary parameters comprehensively considers both historical and recent data, with a relatively balanced weight distribution.

[0082] When the trends of core evolutionary parameters change significantly, such as a sudden increase in the evolution rate parameter (e.g., greater than 0.5 per second), a large fluctuation in the value of the feedback strength parameter, or a sharp decrease in the fitness parameter (e.g., less than 0.6), it indicates a drastic change in the operating conditions, and the model enters a dynamic adjustment evolutionary phase. The evolutionary logic in this phase involves re-activating larger parameter update steps to quickly respond to changes in operating conditions. This includes strengthening the analysis weight of newly emerging feedback events and promptly adjusting the feedback action transmission trajectory and the transformation logic of core evolutionary parameters to adapt to the new operating conditions.

[0083] Step S1210: Integrate the optimized evolution architecture, core evolution parameters, transformation logic of core evolution parameters, and evolution stage division to form the operating condition flow mutual feedback evolution model. The operating condition flow mutual feedback evolution model simulates the dynamic mutual feedback evolution process of operating conditions and flow through real-time updates of core evolution parameters and dynamic adaptation of evolution stages.

[0084] The evolutionary architecture (including the functional configuration of each module and the setting of parallel computing units), validated and adjusted using historical data, is organically integrated with the defined core evolutionary parameters (feedback strength parameters, evolution rate parameters, response hysteresis parameters, and fitness parameters), the transformation logic of the core evolutionary parameters (such as the calculation formulas and weighting coefficients of each parameter), and the evolutionary stage division criteria (the value range and trend conditions of the core evolutionary parameters for each stage). During model runtime, the data input module continuously receives real-time feedback-type operating condition flow data. The feedback analysis module and parameter update module work collaboratively based on real-time data and the adjusted processing resource allocation method to continuously update the values ​​of the core evolutionary parameters. Simultaneously, based on the current values ​​and trends of the core evolutionary parameters, the model dynamically determines its current evolutionary stage and activates the corresponding stage's dedicated evolutionary logic. Through this approach, the operating condition flow feedback evolutionary model can simulate the dynamic feedback evolution process between operating conditions and flow in real time.

[0085] Step S130: Based on the real-time evolution results of the operating condition flow feedback evolution model, generate an evolutionary flow adaptation strategy, which includes a flow adjustment path and parameter combination that are dynamically adjusted with the feedback evolution.

[0086] Step S131: Analyze the real-time evolution results output by the operating condition flow feedback evolution model, extract the current value, change trend and evolution stage identifier of the core evolution parameters, so as to obtain the current operating condition and flow feedback status.

[0087] The output module of the working condition flow mutual feedback evolution model outputs real-time evolution results at a fixed frequency (e.g., every 100 milliseconds). The results include the current values ​​of the core evolution parameters (e.g., mutual feedback intensity parameter is 1.8 liters per minute per megapascal, evolution rate parameter is 0.3 units per second, response lag parameter is 200 milliseconds, and fitness parameter is 0.75), the changing trends of each core evolution parameter (e.g., mutual feedback intensity parameter is increasing, evolution rate parameter remains stable, response lag parameter is decreasing, and fitness parameter is decreasing), and the evolution stage indicator (e.g., currently in the dynamic adjustment evolution stage).

[0088] By analyzing these outputs, the feedback status between the current operating condition and the flow rate can be obtained. For example, a high and increasing feedback strength parameter indicates that the operating condition's impact on the flow rate is increasing; a stable evolution rate parameter indicates that the frequency of feedback events has not changed significantly; a decreasing response hysteresis parameter means that the time it takes for the operating condition to affect the flow response is shortening; a decreasing fit parameter indicates that the matching degree between the current operating condition and the flow rate is decreasing, requiring adjustment. An evolution stage marked as a dynamic adjustment evolution stage suggests the need to adopt a flow regulation strategy that can quickly respond to changes in the operating condition.

[0089] Step S132: Based on the current value of the core evolution parameter, determine the core objective of flow regulation. The core objective includes the flow rate regulation objective and the flow stability regulation objective. The core objective directly corresponds to the feedback state.

[0090] The flow rate adjustment target refers to the desired real-time flow rate value, which is determined based on the feedback strength parameter and the fit parameter. When the feedback strength parameter is high and the fit parameter is low, it indicates that the current flow rate value does not match the operating conditions. A new flow rate target needs to be set based on the operating condition impact data (such as system operating pressure, hydraulic oil viscosity, etc.) and the magnitude of the feedback strength parameter. For example, if an increase in system operating pressure leads to an increase in flow rate, but the fit parameter is low, it may be necessary to set the flow rate adjustment target to a lower value to restore the match between the operating conditions and the flow rate.

[0091] Flow stability adjustment targets focus on flow fluctuations and are related to response hysteresis and evolution rate parameters. A smaller response hysteresis parameter indicates a faster flow response; in this case, flow stability requirements can be appropriately increased, and the target for flow fluctuation amplitude can be set to a smaller value (e.g., less than 0.5 liters per minute). When the evolution rate parameter is larger, feedback events occur frequently, and operating conditions change rapidly. Flow stability adjustment targets should then focus on suppressing sudden flow fluctuations, and the target for the rate of flow change should be set to a smaller value (e.g., less than the square of 1 liter per minute).

[0092] Step S133: Define the adjustment path type of the evolutionary traffic adaptation strategy. The adjustment path type includes progressive adjustment path, responsive adjustment path and predictive adjustment path. Different adjustment paths correspond to different evolution stages and the changing trends of core evolution parameters.

[0093] A gradual adjustment path is a slow and steady adjustment method suitable for the stable evolution phase. In this phase, the core evolution parameters change relatively smoothly, the evolution rate parameter is low, and the fitness parameter is high. The gradual adjustment path uses small steps and multiple adjustments to gradually adjust the flow to the target value, thus avoiding significant shocks to the system. For example, the flow change in each adjustment does not exceed 5% of the current flow value, and the adjustment interval is relatively long (e.g., 500 milliseconds).

[0094] Response-based control paths are a fast and direct control method suitable for the initial evolution phase. In this phase, core evolution parameters are unstable, the evolution rate parameter may be high, and the fit parameter may be low. Response-based control paths can react quickly to immediate changes in operating conditions, with large control steps and short control intervals (e.g., 100 milliseconds) to bring the flow to an initial stable state as quickly as possible.

[0095] Predictive regulation is a forecast-based regulation method suitable for the dynamic evolution phase. In this phase, core evolution parameters exhibit drastic changes, with high evolution rate parameters and large fluctuations in feedback intensity parameters. Predictive regulation analyzes the changing trends of these core evolution parameters to predict the direction of future operating conditions and flow response, allowing for proactive regulation. For example, based on the upward trend of the feedback intensity parameter, it predicts a further increase in future flow, thus enabling timely flow suppression regulation.

[0096] Step S134: For the initial evolution stage, select a responsive adjustment path and set a preset adjustment frequency and response time threshold for the responsive adjustment path.

[0097] In the initial evolution phase, because the model has just started or has re-entered the adjustment period after experiencing significant changes in operating conditions, the core evolution parameters are unstable and require rapid response. After selecting the responsive adjustment path, the adjustment frequency is set to once every 100 milliseconds, meaning that the flow is detected and adjusted every 100 milliseconds. The response time threshold is set to 200 milliseconds, meaning that the time interval from detecting a change in operating conditions to completing an adjustment action cannot exceed 200 milliseconds. If adjustment is not completed within 200 milliseconds, an alarm signal needs to be issued to indicate a possible system anomaly.

[0098] Step S135: For the stable evolution stage, a gradual adjustment path is adopted, and an adjustment frequency matching the stable feedback state is set to maintain the stability of the adjustment parameters and maintain the continuous stability of the flow.

[0099] During the stable evolution phase, the operating conditions are relatively stable, and the core evolution parameters change slowly. A gradual adjustment path is adopted, with an adjustment frequency set to once every 500 milliseconds. Compared with the responsive adjustment path, this reduces the adjustment frequency to minimize the interference of adjustment actions on system stability. At the same time, the adjustment step size is set to a small value, such as 2% of the current flow rate. After each adjustment, the change in flow rate is observed, and the direction and magnitude of the next adjustment are determined based on the change in the fitness parameter, ensuring that the flow rate can slowly and smoothly reach the target value and remain stable.

[0100] Step S136: For the dynamic adjustment evolution stage, a predictive adjustment path is enabled. The adjustment direction and parameters are set in advance based on the changing trend of the core evolution parameters to achieve advance adaptation to the upcoming mutual feedback state changes.

[0101] The dynamic adjustment evolution stage involves drastic changes in operating conditions, with clear trends in core evolution parameters. When employing a predictive adjustment path, a predictive model is first established by analyzing historical data and current trends of core evolution parameters. For example, a linear regression algorithm can be used to predict the trend of the mutual feedback intensity parameter over the next 500 milliseconds. Based on the prediction results, the adjustment direction (e.g., if the predicted flow rate increases, the adjustment direction is to decrease the flow rate) and adjustment parameters (e.g., the adjustment magnitude is 1.2 times the predicted increase, to allow for a certain adjustment margin) are set in advance. The adjustment frequency is set to once every 200 milliseconds, falling between responsive and gradual adjustment, ensuring rapid response to predicted changes without excessively frequent adjustments.

[0102] Step S137: Define the core adjustment parameter combination corresponding to each adjustment path. The core adjustment parameter combination includes valve core motion parameters, drive signal parameters and adjustment timing parameters. The value of the core adjustment parameter combination and the value range of the core evolution parameter form a corresponding matching relationship.

[0103] Valve spool motion parameters include valve spool opening degree, valve spool speed, and valve spool acceleration. For responsive control paths, due to the need for rapid response, the valve spool speed and acceleration are set to relatively large values ​​(e.g., valve spool speed of 5 mm / s and acceleration of 10 mm / s²), and the valve spool opening degree is calculated based on the deviation between the current flow rate and the target value. For progressive control paths, the valve spool speed and acceleration are relatively small (e.g., speed of 2 mm / s and acceleration of 3 mm / s²), and the adjustment of the valve spool opening degree is more precise. For predictive control paths, the valve spool motion parameters need to consider the predicted flow rate change trend. If a significant increase in flow rate is predicted, the valve spool speed and acceleration are set to moderately large values ​​(e.g., speed of 4 mm / s and acceleration of 7 mm / s²) to suppress excessive flow rate changes in advance.

[0104] The drive signal parameters include the drive voltage amplitude, drive current amplitude, and drive pulse width. The responsive control path requires the drive signal to quickly move the valve core; therefore, the drive voltage and current amplitudes are set to 90%-100% of their rated values, and the drive pulse width is narrower (e.g., 10 microseconds) to improve response speed. In the progressive control path, the drive voltage and current amplitudes are 60%-80% of their rated values, and the drive pulse width is wider (e.g., 50 microseconds) to ensure smooth valve core movement. The drive signal parameters for the predictive control path are set based on the predicted control amplitude. When the predicted control amplitude is large, the drive signal parameters are closer to those of the responsive path; when the predicted control amplitude is small, the parameters are closer to those of the progressive path.

[0105] The timing parameters for regulation include the regulation start time, regulation duration, and regulation interval. For responsive regulation paths, the regulation start time is set to execute immediately upon detecting a change in operating conditions, the regulation duration is short (e.g., 50 milliseconds), and the regulation interval is the preset regulation frequency (100 milliseconds). For progressive regulation paths, the regulation start time can be appropriately delayed (e.g., execution begins 50 milliseconds after detecting a change in operating conditions), the regulation duration is longer (e.g., 200 milliseconds), and the regulation interval is 500 milliseconds. For predictive regulation paths, the regulation start time is set in advance based on the results of the prediction model (e.g., if the flow rate is predicted to change in 50 milliseconds, regulation begins 30 milliseconds in advance), and the regulation duration and interval are determined based on the predicted duration and severity of the change.

[0106] The values ​​of the core regulation parameter combinations correspond to the value ranges of the core evolution parameters. For example, when the mutual feedback intensity parameter is in the range of 1.5-2.0 liters per minute per megapascal, the valve core opening degree adjustment range under the responsive regulation path is 10%-15% of the current opening degree; when the mutual feedback intensity parameter is in the range of 1.0-1.5 liters per minute per megapascal, the adjustment range is 5%-10%. The above correspondence is established through a large amount of experimental data and simulation results and stored in the parameter mapping table for querying and calling when generating the regulation strategy.

[0107] Step S138: Establish dynamic association rules between adjustment paths and parameter combinations, and set the switching conditions of adjustment paths and the adjustment methods of core adjustment parameter combinations when the core evolution parameters change.

[0108] Step S1381: Collect the core evolution parameter values, corresponding regulation paths and core regulation parameter combinations under different feedback states, as well as regulation effect records, and establish a correlation analysis dataset.

[0109] Through long-term experiments and field operation, a large amount of data under different feedback states was collected. For example, the solenoid valve system was run in the initial evolution stage, stable evolution stage, and dynamic adjustment evolution stage, recording the continuous values ​​of core evolution parameters (e.g., every 10 milliseconds), the adjustment path adopted (responsive, gradual, or predictive), the corresponding core adjustment parameter combinations (specific values ​​of valve core motion parameters, drive signal parameters, and adjustment timing parameters), and the adjustment effect records (e.g., adjusted flow rate, flow fluctuation amplitude, and fit parameters). This data was then categorized and organized according to the feedback state, outliers and noisy data were removed, and a correlation analysis dataset was formed. This dataset should be large enough to ensure the accuracy and reliability of subsequent analysis, typically containing at least several thousand sets of data records under different states.

[0110] Step S1382: Extract the range and rate of change of the core evolutionary parameters from the association analysis dataset. The range and rate of change of the core evolutionary parameters become the key basis for determining the conditions for switching the regulation path.

[0111] For each core evolutionary parameter (feedback strength parameter, evolution rate parameter, response hysteresis parameter, and fitness parameter), its variation range at different evolutionary stages is determined in the association analysis dataset. For example, the variation range of the feedback strength parameter in the initial evolutionary stage may be 0.5–2.5 L / min / MPa, in the stable evolutionary stage it may be 1.0–2.0 L / min / MPa, and in the dynamic adjustment evolutionary stage it may be 1.5–3.0 L / min / MPa. The rate of change of the core evolutionary parameters is obtained by calculating the ratio of the difference between the parameter values ​​at two adjacent recording times to the time interval. For example, the rate of change of the evolution rate parameter may reach 0.5 units per second in the dynamic adjustment evolutionary stage, while it may be less than 0.1 units per second in the stable evolutionary stage.

[0112] Step S1383: For the switching between the responsive regulation path and the gradual regulation path, set an initial switching threshold for the core evolution parameter. When the rate of change of the core evolution parameter is lower than the initial switching threshold, perform the switching from the responsive regulation path to the gradual regulation path.

[0113] By analyzing the correlation analysis dataset, the initial switching thresholds for core evolutionary parameters are determined when switching from a responsive control path to a gradual control path. The evolution rate parameter and fitness parameter are typically chosen as the primary criteria. For example, the initial switching threshold is set as follows: the evolution rate parameter changes at a rate less than 0.2 changes per second, and the fitness parameter changes at a rate greater than 0.7. When real-time monitoring shows that the change rate of the evolution rate parameter remains below 0.2 changes per second for 5 seconds, and the fitness parameter remains greater than 0.7 for 5 seconds, the switching conditions are met, and the switch from the responsive control path to the gradual control path is executed. During the switchover, the core control parameter combination needs to be adjusted according to preset transition rules to avoid flow fluctuations.

[0114] Step S1384: For the switching between the gradual adjustment path and the predictive adjustment path in the dynamic adjustment evolution stage, a dynamic switching threshold for the core evolution parameters is set. When the rate of change of the core evolution parameters is higher than the dynamic switching threshold, the switching from the gradual adjustment path to the predictive adjustment path is executed.

[0115] For the switch from a gradual to a predictive regulation path, the main focus is on the rate of change of the evolution rate parameter and the mutual feedback strength parameter. A dynamic switching threshold is set at a change rate of the evolution rate parameter greater than 0.4 units per second, or a change rate of the mutual feedback strength parameter greater than 0.8 liters per minute per megapascal per second. When either of these conditions is met in real-time monitoring and the duration reaches 3 seconds, the switch is executed. For example, if the system operating pressure suddenly increases, causing the mutual feedback strength parameter to increase from 1.5 liters per minute per megapascal to 3.0 liters per minute per megapascal within 3 seconds (a change rate of 0.5 liters per minute per megapascal per second), exceeding the dynamic switching threshold, then the system switches from a gradual to a predictive regulation path.

[0116] Step S1385: For the switching between predictive and responsive adjustment paths, a smooth switching threshold for core evolution parameters is set. When the change trend of core evolution parameters tends to be stable and the rate of change is lower than the smooth switching threshold, the switching from predictive to responsive adjustment paths is executed.

[0117] The switch from a predictive to a responsive control path typically occurs during the transition period after the dynamic adjustment evolution phase ends and before the system enters the initial or stable evolution phase. A smooth transition threshold is set as follows: the evolution rate parameter changes at a rate less than 0.15 units per second, the feedback strength parameter changes at a rate less than 0.3 liters per minute per megapascal per second, and the fitness parameter is below 0.65. The switch is executed when these conditions are met simultaneously and last for 4 seconds. For example, after experiencing drastic changes in operating conditions, the system gradually stabilizes, the rates of change of the evolution rate and feedback strength parameters decrease, and the fitness parameter remains low because the operating conditions are not yet fully stable. At this point, the system switches from a predictive to a responsive control path to quickly adjust the flow rate to a stable state.

[0118] Step S1386: Analyze the correspondence between the values ​​of the core regulation parameter combinations and the values ​​of the core evolution parameters under each regulation path, establish the basic adjustment logic of the core regulation parameter combinations, and set the basic rules for the changes of the values ​​of the core regulation parameter combinations with the core evolution parameters.

[0119] In the association analysis dataset, for each regulation path (responsive, gradual, predictive), the relationship between each parameter in the core regulation parameter combination (such as valve opening degree, driving voltage amplitude, regulation start time, etc.) and the core evolution parameter values ​​is analyzed. For example, under the responsive regulation path, the valve opening degree and the mutual feedback strength parameter may be positively correlated, that is, the larger the mutual feedback strength parameter, the greater the reduction in valve opening degree needs to be; the driving voltage amplitude and the evolution rate parameter may be positively correlated, the higher the evolution rate parameter, the larger the driving voltage amplitude. These correspondences are established by drawing scatter plots and calculating correlation coefficients, and then the basic adjustment logic of the core regulation parameter combination is set based on these relationships. For example, the basic adjustment logic can be expressed as: valve opening degree adjustment amount = K1 × mutual feedback strength parameter change amount + K2 × fit parameter, where K1 and K2 are coefficients obtained from the data through methods such as linear regression.

[0120] Step S1387: Based on the adjustment effect record, calculate the deviation between the actual adjusted flow feedback data and the expected target; based on the deviation, generate a mutual feedback adaptation correction coefficient to correct the output result of the basic adjustment logic; in subsequent adjustments, calculate the values ​​of the core adjustment parameter combination obtained based on the basic adjustment logic with the mutual feedback adaptation correction coefficient to obtain the optimized values ​​of the core adjustment parameter combination.

[0121] The deviation between the actual flow feedback data after adjustment and the expected target in the adjustment effect record is an important indicator for measuring the adjustment quality. The deviation is calculated by subtracting the expected flow target value from the actual flow value. When the deviation is positive, it indicates that the actual flow is greater than the target flow; when it is negative, the actual flow is less than the target flow. Based on the magnitude and direction of the deviation, a mutual feedback adaptation correction coefficient is generated. For example, when the absolute value of the deviation is large, the absolute value of the correction coefficient is also correspondingly large, so as to make a larger correction to the output result of the basic adjustment logic; when the deviation is positive, the correction coefficient is negative, so as to reduce the value of the core adjustment parameter combination (such as reducing the valve core opening degree), thereby reducing the actual flow.

[0122] In subsequent adjustments, the initial values ​​of the core adjustment parameter combination are first calculated based on the basic adjustment logic. Then, these initial values ​​are multiplied by the mutual feedback adaptation correction coefficient to obtain the optimized core adjustment parameter combination. For example, if the valve opening degree calculated by the basic adjustment logic is 50% and the mutual feedback adaptation correction coefficient is 0.9, then the optimized valve opening degree is 50% × 0.9 = 45%. The generation of the mutual feedback adaptation correction coefficient is a dynamic process, updated after each adjustment based on new deviations to continuously optimize the adjustment effect.

[0123] Step S1388: Define the adjustment step size of the core adjustment parameter combination. Set the size of the adjustment step size of the core adjustment parameter combination according to the change range of the core evolution parameter. The change range of the core evolution parameter and the size of the adjustment step size of the core adjustment parameter combination are positively correlated.

[0124] The magnitude of change in the core evolution parameters is obtained by calculating the difference between the maximum and minimum values ​​of the core evolution parameters within a certain time window (e.g., 100 milliseconds). For example, if the mutual feedback intensity parameter changes from 1.2 L / min / MPa to 1.8 L / min / MPa within 100 milliseconds, the magnitude of the change is 0.6 L / min / MPa. The adjustment step size of the core regulation parameter combination is positively correlated with this magnitude of change; that is, the larger the magnitude of the change, the larger the adjustment step size. For example, the adjustment step size can be set as K3 × the magnitude of change in the core evolution parameters, where K3 is a proportionality coefficient. In this way, when the operating conditions change drastically and the magnitude of the core evolution parameters changes significantly, the core regulation parameter combination can adjust with a larger step size to respond quickly to changes; while when the operating conditions change gradually and the magnitude of the change in the core evolution parameters is small, the adjustment step size is smaller to maintain the stability of the system.

[0125] Step S1389: Establish transition rules for the core adjustment parameter combination when switching adjustment paths, and set the adjustment order and transition duration of the core adjustment parameter combination during the switching process to achieve a smooth transition of changes in the core adjustment parameter combination.

[0126] When switching control paths, the core control parameter combination needs to smoothly transition from the current path's values ​​to the target path's values ​​to avoid drastic flow fluctuations. The transition rules include the adjustment order and transition duration. The adjustment order is set based on the sensitivity of the core control parameters to flow; typically, parameters with less impact on flow are adjusted first, followed by those with greater impact. For example, the adjustment interval in the timing parameters is adjusted first, then the drive pulse width in the drive signal parameters, and finally the valve opening degree in the valve core motion parameters. The transition duration is set based on the degree of difference in the core control parameter combination before and after the switch; the greater the difference, the longer the transition duration. For example, when switching from a responsive control path to a progressive control path, the difference in the core control parameter combination is large, so the transition duration is set to 500 milliseconds; while when switching from progressive to predictive, the difference is relatively small, so the transition duration is set to 300 milliseconds. Within the transition duration, the core control parameter combination gradually changes from the current value to the target value in a linear or non-linear manner, such as using an exponential curve to make the change smoother.

[0127] Step S13810: Integrate the adjustment path switching conditions, the basic adjustment logic of the core adjustment parameter combination, the adjustment step size of the core adjustment parameter combination, and the transition rules of the core adjustment parameter combination to form a dynamic association rule between the adjustment path and the parameter combination. The dynamic association rule between the adjustment path and the parameter combination guides the adjustment path and the core adjustment parameter combination to dynamically adjust with the core evolution parameters.

[0128] The aforementioned determined adjustment path switching conditions (initial switching threshold, dynamic switching threshold, and smooth switching threshold), the basic adjustment logic of the core adjustment parameter combination (such as the calculation formula for valve core opening adjustment), the adjustment step size (correlation with the change amplitude of core evolution parameters), and the transition rules (adjustment sequence and transition duration) are integrated to form a complete dynamic correlation rule system. This rule system is implemented in the form of a software program and stored in the control system's memory. When the core evolution parameters change, the system automatically determines whether to switch the adjustment path based on the dynamic correlation rules, and calculates and adjusts the values ​​of the core adjustment parameter combination according to the rules, achieving dynamic adaptation of the adjustment path and parameter combination.

[0129] Step S139: Analyze the connection method of the core adjustment parameter combination when switching between different adjustment paths, and construct the transition parameter combination to avoid the flow fluctuation caused by path switching and achieve continuous connection of the adjustment process.

[0130] For example, step S1391: collect historical adjustment data under different adjustment path switching scenarios. The historical adjustment data covers the changes in the core adjustment parameter combinations and flow change records of the switching scenarios from responsive to progressive, progressive to predictive, and predictive to responsive.

[0131] Historical data was specifically collected during the switching process of the control path through experiments and field operation. For example, in a laboratory environment, operating conditions were artificially set to cause the solenoid valve system to switch from responsive to progressive, progressive to predictive, and predictive to responsive modes. The detailed changes of the core control parameter combination (valve core motion parameters, drive signal parameters, and control timing parameters) in each switching scenario were recorded (e.g., parameter values ​​were recorded every 5 milliseconds) as well as the corresponding flow change records (real-time flow values, flow fluctuation amplitude, etc.). At least hundreds of switching process data were collected for each switching scenario to ensure data diversity and representativeness. At the same time, the core evolution parameter values ​​and evolution stage identifiers at different switching moments were recorded to facilitate subsequent analysis of the relationship between the switching process and the feedback state.

[0132] Step S1392: Extract the values ​​of the core adjustment parameter combinations for each switching scenario from the historical adjustment data, and analyze the degree of difference and trend of change among the values ​​of the core adjustment parameter combinations.

[0133] For each switching scenario, such as the transition from responsive to gradual switching, the core control parameter combination values ​​at the last moment of the responsive control path before the switch (e.g., valve opening 40%, drive voltage 12 volts, adjustment interval 100 ms) and the core control parameter combination values ​​at the initial moment of the gradual control path after the switch (e.g., valve opening 35%, drive voltage 9 volts, adjustment interval 500 ms) are extracted from historical control data. The degree of difference between the two sets of values ​​is calculated. For each parameter, the degree of difference is the ratio of the absolute value of the value after the switch minus the value before the switch to the value before the switch. For example, the degree of difference for valve opening is |35%-40%| / 40%=12.5%. Then, a weighted average of the degree of difference for all parameters is calculated to obtain the overall degree of difference for the core control parameter combination. Simultaneously, the changing trends of each parameter value are analyzed, such as whether the valve opening increases or decreases, and whether the drive voltage increases or decreases.

[0134] Step S1393: Evaluate the degree of difference of each parameter in the core adjustment parameter combination of the before and after adjustment paths, and comprehensively evaluate the degree of difference based on preset rules to obtain an overall difference evaluation result; set a first preset threshold and a second preset threshold for the overall difference evaluation result, wherein the first preset threshold is less than the second preset threshold; compare the overall difference evaluation result with the first preset threshold and the second preset threshold: when the overall difference evaluation result is less than the first preset threshold, it is determined to be a first type of switching scenario; when the overall difference evaluation result is greater than or equal to the first preset threshold and less than or equal to the second preset threshold, it is determined to be a second type of switching scenario; when the overall difference evaluation result is greater than the second preset threshold, it is determined to be a third type of switching scenario.

[0135] The preset rule can be to weight and sum the differences of individual parameters based on their weights in relation to flow rate, thus obtaining the overall difference assessment result. For example, the valve opening degree has the greatest impact on flow rate, with a weight of 0.5; the drive voltage is second, with a weight of 0.3; and the adjustment timing parameter has a weight of 0.2. Therefore, the overall difference assessment result = 0.5 × valve opening degree difference + 0.3 × drive voltage difference + 0.2 × adjustment timing parameter difference.

[0136] The first preset threshold is set to 10%, and the second preset threshold is set to 25%. When the overall difference assessment result is 8%, which is less than the first preset threshold of 10%, it is determined to be a first type of handover scenario; when the overall difference assessment result is 15%, which is between 10% and 25%, it is determined to be a second type of handover scenario; when the overall difference assessment result is 30%, which is greater than the second preset threshold of 25%, it is determined to be a third type of handover scenario.

[0137] Step S1394: For the first type of switching scenario, construct a linear transition parameter combination, and gradually adjust the value of the core adjustment parameter combination of the previous path to the value of the core adjustment parameter combination of the next path according to a fixed ratio.

[0138] In the first type of switching scenario, the overall difference in the core adjustment parameter combination is relatively small, so a linear transition method is adopted. The transition parameter combination is constructed as follows: the transition process is divided into N equal time intervals (e.g., N=10, the transition duration is 500 milliseconds, then each time interval is 50 milliseconds). Within each time interval, the value of the core adjustment parameter combination is adjusted from the value of the previous path to the value of the next path according to a fixed ratio. The adjustment ratio is calculated as: (parameter value of the next path - parameter value of the previous path) / N. For example, if the valve opening degree of the previous path is 40%, and the next path is 38%, and N=10, then the adjustment ratio of each time interval is (38%-40%) / 10=-0.2%. That is, after the first time interval, the valve opening degree is adjusted to 39.8%, after the second time interval it is 39.6%, and so on, reaching 38% after 10 time intervals. Linear transition can ensure smooth changes in the parameter combination and is suitable for scenarios with small differences.

[0139] Step S1395: For the second type of switching scenario, a segmented transition parameter combination is adopted, dividing the transition process into a start-up stage, an adjustment stage, and a stabilization stage. Each stage sets an adjustment ratio for a dedicated core adjustment parameter combination, gradually approaching the value of the target core adjustment parameter combination.

[0140] The second type of switching scenario has a moderate degree of difference, and segmented transitions allow for better control of the transition process. In the initial stage (e.g., the first 20% of the transition time), the adjustment percentage is small, such as 10% of the target adjustment, to slowly initiate the transition and avoid impacting traffic. In the adjustment stage (the middle 60% of the transition time), the adjustment percentage increases, such as 70% of the target adjustment, to quickly move towards the target parameter combination. In the stabilization stage (the last 20% of the transition time), the adjustment percentage decreases again, such as 20% of the target adjustment, to finely adjust the parameters and ensure a smooth transition to the target value. For example, if the valve opening degree in the previous path is 40%, and in the next path it is 30%, the target adjustment is -10%, and the transition time is 500 milliseconds. During the initial phase (100 milliseconds), the adjustment is -10% × 10% / (100 milliseconds / time interval) for each time interval; during the adjustment phase (300 milliseconds), the adjustment is -10% × 70% / (300 milliseconds / time interval) for each time interval; during the stable phase (100 milliseconds), the adjustment is -10% × 20% / (100 milliseconds / time interval) for each time interval.

[0141] Step S1396: For the third type of switching scenario, construct a buffer transition parameter combination, set a buffer parameter range between the values ​​of the core adjustment parameter combination of the preceding and following paths, first adjust the value of the core adjustment parameter combination to the buffer parameter range, and then adjust it from the buffer parameter range to the value of the target core adjustment parameter combination.

[0142] The third type of switching scenario has significant differences, and a direct transition can easily lead to large fluctuations in traffic. Therefore, a buffer parameter range is set. The upper and lower limits of the buffer parameter range are determined based on the parameter values ​​of the preceding and following paths. For example, if the parameter value of the preceding path is A and the parameter value of the following path is B (A>B), then the buffer range can be set to [(A+B) / 2, A-(AB)×0.2]. First, in the first stage of the transition (e.g., 40% of the total transition time), the value of the core adjustment parameter combination is adjusted from A in the preceding path to the midpoint of the buffer range. Then, in the second stage (60% of the total transition time), the value is adjusted from the midpoint of the buffer range to B in the following path. For example, if A=50% and B=20%, the buffer range is [35%, 44%], with a midpoint of 39.5%. The first stage adjusts 50% to 39.5%, and the second stage adjusts it from 39.5% to 20%. By setting the buffer range, a large adjustment is divided into two smaller adjustments, reducing the impact of each adjustment on traffic.

[0143] Step S1397: Determine the transition duration for each combination of transition parameters. Based on the time required for flow stabilization in historical adjustment data and in conjunction with the overall difference assessment results, set the transition duration.

[0144] This analysis examines the time required for traffic stabilization after handover under different overall difference assessment results in historical adjustment data. For example, when the overall difference assessment result is 10%, traffic stabilization takes an average of 300 milliseconds; at 20%, it takes 500 milliseconds; and at 30%, it takes 800 milliseconds. A functional relationship is established between the overall difference assessment result and the traffic stabilization time, such as transition duration = a × overall difference assessment result + b, where a and b are coefficients obtained from data fitting. Then, based on the overall difference assessment result of the current handover scenario, the initial transition duration is calculated by substituting it into this function. Fine-tuning is then performed based on practical experience; for example, for critical applications, the transition duration can be appropriately increased to ensure stability. The final determined transition duration may be 300-500 milliseconds for the first type of handover scenario, 500-800 milliseconds for the second type, and 800-1200 milliseconds for the third type.

[0145] Step S1398: Analyze the flow changes after the implementation of the transition parameter combination, evaluate the transition effect, and control the flow fluctuation within the preset range.

[0146] During the implementation of the transition parameter combination, traffic feedback data is monitored in real time, and the amplitude and duration of traffic fluctuations are recorded. Evaluation indicators for the transition effect include the maximum traffic fluctuation amplitude, the duration of fluctuation, and the time it takes for the traffic to reach a stable state after the transition. A preset traffic fluctuation range is established, for example, the maximum fluctuation amplitude should not exceed ±5% of the target traffic, and the fluctuation duration should not exceed 50% of the transition duration. If the traffic fluctuation exceeds the preset range after the transition, it indicates that the transition parameter combination is unreasonable, and the transition method or transition duration needs to be readjusted. For example, for the third type of handover scenario, if the traffic fluctuation is still large after using a buffer transition, the length of the buffer zone needs to be increased or the transition duration extended.

[0147] Step S1399: Establish dynamic adjustment rules for the transition parameter combination, and fine-tune the values ​​and transition duration of the transition parameter combination based on the flow feedback in the real-time feedback-type operating condition flow data.

[0148] The flow feedback data from real-time feedback-based operating condition flow data (such as real-time flow fluctuation amplitude and changes in adaptability parameters) serves as the basis for dynamically adjusting the transition parameter combination. When the flow fluctuation amplitude is detected to be close to the preset upper limit during the transition process, the values ​​of the transition parameter combination are automatically fine-tuned, such as reducing the adjustment ratio of the current stage or increasing the intermediate value between buffer zones. Simultaneously, if the flow stabilization speed is faster than expected, the duration of subsequent transition stages can be appropriately shortened; if the stabilization speed is slower than expected, the transition duration is extended. For example, in the adjustment stage of a segmented transition, if the flow fluctuation is found to be very small, the duration of the stabilization stage can be shortened, completing the transition ahead of schedule. The dynamic adjustment rules are embedded in the adjustment strategy generation module in the form of an algorithm to achieve real-time adaptive adjustment.

[0149] Step S13910: Integrate different switching scenarios, corresponding transition parameter combinations, transition durations, and dynamic adjustment rules for transition parameter combinations to form a parameter connection scheme.

[0150] The linear transition parameter combinations, segmented transition parameter combinations, and buffered transition parameter combinations corresponding to the first, second, and third types of switching scenarios, along with their respective transition durations and dynamic adjustment rules, are integrated to form a complete parameter connection scheme. This scheme clearly specifies which transition method should be used in which switching scenario, how the transition duration is determined, and how to dynamically adjust it based on real-time traffic feedback. As a crucial component of the evolutionary traffic adaptation strategy, the parameter connection scheme is stored in the control system's database and is invoked and executed during adjustment path switching to ensure a smooth transition of core adjustment parameter combinations and stable traffic.

[0151] Step S1310: Integrate the adjustment path type, core adjustment parameter combination, dynamic association rules of adjustment path and parameter combination, and transition parameter combination to form the evolutionary flow adaptation strategy. The evolutionary flow adaptation strategy dynamically adapts to the real-time evolution results of the working condition flow feedback evolution model by dynamically switching the adjustment path and adjusting the core adjustment parameter combination in real time.

[0152] The system organically integrates the aforementioned determined adjustment path types (responsive, progressive, and predictive), the core adjustment parameter combinations corresponding to each path, the dynamic association rules between the adjustment path and parameter combinations (switching conditions, parameter adjustment methods), and transition parameter combinations (transition methods, durations, and dynamic adjustment rules under different switching scenarios). By developing software programs, these elements are combined to form a complete evolutionary flow adaptation strategy system. This system can automatically select appropriate adjustment paths and determine corresponding core adjustment parameter combinations based on the real-time evolution results (core evolution parameter values, trends, and evolution stage identifiers) output by the operating condition flow feedback evolution model. It also applies transition parameter combinations when switching adjustment paths, achieving dynamic adaptation and adjustment of the solenoid valve flow. The system also possesses self-learning capabilities, continuously optimizing dynamic association rules and transition parameter combinations through long-term data accumulation, thereby improving the adaptability and effectiveness of the adjustment strategy.

[0153] Step S140: Iteratively optimize the evolutionary flow adaptation strategy using the dynamic feedback trace data to generate an intelligent adaptive control signal for the solenoid valve flow.

[0154] Step S141: Extract the feedback effect records from the dynamic feedback trace data, and analyze the degree of feedback matching between the operating condition impact data and the flow feedback data after the implementation of the evolutionary flow adaptation strategy.

[0155] The feedback effect records in the dynamic feedback trace data contain detailed changes in operating condition impact data and flow feedback data after the implementation of the evolutionary flow adaptation strategy, as well as the interaction results between the two. For example, it records how operating condition impact data such as changes in ambient temperature and system pressure affect flow feedback data after adopting a certain adjustment path and parameter combination, and how changes in flow feedback data in turn affect operating condition impact data (such as flow changes leading to further adjustments in system pressure).

[0156] When analyzing the degree of feedback matching, the following aspects are mainly examined: First, whether the flow feedback data has achieved the preset core objectives (flow rate adjustment target and flow stability adjustment target); second, whether changes in operating condition impact data can be adapted to changes in flow feedback data, that is, whether the flow can be quickly and accurately adjusted to the new target value when operating conditions change; and third, whether changes in flow feedback data will have adverse effects on operating conditions, such as excessive flow adjustment leading to drastic fluctuations in system pressure. The degree of feedback matching is comprehensively evaluated by calculating indicators such as the deviation rate between the actual flow value and the target flow value, the normalized value of the flow fluctuation amplitude, and the fluctuation amplitude of operating condition parameters. The smaller the deviation rate, the smaller the flow fluctuation amplitude, and the more stable the fluctuation of operating condition parameters, the higher the degree of feedback matching.

[0157] Step S142: Based on the mutual feedback matching degree, identify the rationality of the adjustment path selection and the adaptability of the core adjustment parameter combination in the evolutionary traffic adaptation strategy, and locate the links of the evolutionary traffic adaptation strategy with optimization space.

[0158] Step S1421: Define the evaluation dimensions of the mutual feedback matching degree. The evaluation dimensions include the time sequence matching dimension, the intensity matching dimension, and the stability matching dimension. The evaluation dimensions evaluate the mutual feedback adaptation status of the working conditions and the flow from different perspectives.

[0159] The timing matching dimension focuses on the time synchronization between changes in operating condition impact data and the response of flow feedback data. Ideally, after a change in operating condition, the flow should respond immediately, and the response time delay should be within an acceptable range (e.g., the value of the response hysteresis parameter). The timing matching dimension is evaluated by calculating the deviation between the average time interval from the point of triggering the operating condition impact to the point of flow response feedback and the set ideal time interval.

[0160] The intensity matching dimension measures the matching relationship between the strength of the operating condition's impact and the strength of the flow regulation's execution. That is, the greater the impact of the operating condition, the greater the magnitude of the flow regulation should be to offset the impact and maintain a stable flow. The intensity matching dimension is evaluated by comparing whether the ratio of the change magnitude of the operating condition's impact parameter to the change magnitude of the flow regulation parameter is within a preset reasonable range.

[0161] The stability matching dimension assesses the stability of flow feedback data after adjustment and its contribution to operational stability. Adjusted flow fluctuations should be as small as possible, and flow stability should not come at the expense of increased fluctuations in operational parameters. The stability matching dimension comprehensively evaluates the stability by considering the magnitude of flow fluctuations, the magnitude of operational parameter fluctuations, and their covariance.

[0162] Step S1422: For the timing matching dimension, analyze the time synchronization between the trigger point of the operating condition and the flow adjustment action, and determine the matching status between the response speed of the adjustment path and the mutual feedback transmission time.

[0163] Extract the timestamps of multiple operating condition impact trigger points and their corresponding flow regulation actions from the dynamic feedback trace data. Calculate the time difference between each operating condition impact trigger point and the start of the flow regulation action, i.e., the regulation response time. Compare the above regulation response time with the feedback transmission duration (the value of the response lag parameter). If the regulation response time is much longer than the feedback transmission duration, it indicates that the response speed of the regulation path is too slow and cannot match the changes in operating conditions in a timely manner; if the regulation response time is much shorter than the feedback transmission duration, it may lead to the regulation action being too advanced and out of sync with the actual flow response. By statistically analyzing the deviation distribution between the regulation response time and the feedback transmission duration, the timing matching status is determined.

[0164] Step S1423: For the intensity matching dimension, compare the intensity of the effect of the operating condition with the execution intensity of the flow regulation, and evaluate the fit between the values ​​of the core regulation parameter combination and the effect of the operating condition.

[0165] The intensity of the impact of operating conditions is characterized by the value of the feedback strength parameter, while the execution intensity of flow regulation is measured by the adjustment range of the core regulation parameter combination (such as the change in valve opening degree, the change in drive voltage, etc.). The change in the feedback strength parameter is compared with the adjustment range of the core regulation parameter combination to calculate their proportional relationship. If this proportional relationship is not within a preset reasonable range (e.g., the preset range is 0.8-1.2), it indicates that the value of the core regulation parameter combination does not match the effect of the operating conditions. For example, if the feedback strength parameter increases significantly, but the adjustment range of the core regulation parameter combination is small, the flow cannot effectively offset the impact of the operating conditions, resulting in a low evaluation of the intensity matching dimension.

[0166] Step S1424: For the stability matching dimension, observe the fluctuation of the traffic feedback data after adjustment, and determine the ability of the adjustment path and the combination of core adjustment parameters to maintain traffic stability.

[0167] Collect adjusted flow feedback data and calculate the flow fluctuation amplitude (e.g., the standard deviation of flow values ​​within 5 minutes) and fluctuation frequency (the number of flow fluctuations per unit time). Compare these indicators with preset stability targets (e.g., flow fluctuation amplitude less than 0.5 liters per minute, fluctuation frequency less than 5 times per minute). If the flow fluctuation amplitude exceeds the target value or the fluctuation frequency is too high, it indicates that the current adjustment path and core adjustment parameter combination are insufficient to maintain flow stability. Simultaneously, analyze the relationship between flow fluctuation and operating parameter fluctuation. If there is a strong positive correlation between flow fluctuation and operating parameter fluctuation, it indicates that flow adjustment may have exacerbated operating instability, and the stability matching dimension evaluation is also low.

[0168] Step S1425: Set matching criteria for each evaluation dimension, determine the ideal matching range for each dimension based on historical best feedback state data, and identify the evolutionary traffic adaptation strategy for dimensions that exceed the ideal matching range and have room for optimization.

[0169] Historically optimal feedback state data refers to data from a period during past operations where the feedback matching degree was highest and the adjustment effect was best. Statistical analysis of this data determines the ideal matching range for each evaluation dimension. For example, the ideal matching range for the time-series matching dimension is a deviation of ±20% between the adjustment response time and the feedback transmission duration; the ideal matching range for the intensity matching dimension is a ratio between 0.9 and 1.1 for the change in the feedback intensity parameter and the adjustment amplitude of the core adjustment parameter combination; the ideal matching range for the stability matching dimension is a flow fluctuation amplitude of less than 0.3 liters per minute, and an absolute value of the correlation coefficient with the fluctuation of operating parameters of less than 0.3. When the actual evaluation result of a certain evaluation dimension exceeds its ideal matching range, it indicates that there is room for optimization in the corresponding evolutionary flow adaptation strategy. For example, if the time-series matching dimension exceeds the range, the response speed of the corresponding adjustment path needs optimization; if the intensity matching dimension exceeds the range, the value selection of the corresponding core adjustment parameter combination needs optimization.

[0170] Step S1426: Compare the evaluation results of each dimension of the current mutual feedback matching degree with the corresponding ideal matching range, and mark the evaluation dimensions that have not reached the ideal range.

[0171] The evaluation results for the time-series matching dimension, intensity matching dimension, and stability matching dimension of the current mutual feedback matching degree are calculated in real time, and then compared with the ideal matching range of each dimension. For example, if the deviation of the current time-series matching dimension is 30%, exceeding the ideal range of ±20%; the ratio of the intensity matching dimension is 0.7, which is lower than the range of 0.9-1.1; and the flow fluctuation of the stability matching dimension is 0.4 liters per minute, which is within the ideal range, then the time-series matching dimension and the intensity matching dimension are marked as evaluation dimensions that have not reached the ideal range.

[0172] Step S1427: For timing matching dimensions that do not reach the ideal range, analyze the switching threshold setting status of the adjustment path to locate the problem of response delay or premature response.

[0173] For cases where the timing matching dimension fails to meet the requirements, the focus is on analyzing the switching threshold setting of the control path. If the control path fails to switch from gradual to predictive control when the rate of change in operating conditions is already high, resulting in a delayed control response, it indicates that the dynamic switching threshold is set too high. Conversely, if the control path switches to a responsive control path prematurely when the rate of change in operating conditions is low, leading to excessively frequent and premature control actions, it indicates that the initial switching threshold is set too low. By analyzing the relationship between the switching threshold and the control response time in historical switching data, the problem of response delay or premature response caused by an unreasonable switching threshold setting can be identified.

[0174] Step S1428: For intensity matching dimensions that do not reach the ideal range, analyze the rationality of the value range of the core adjustment parameter combination, and check the adaptation status between the execution intensity of the flow regulation and the effect intensity of the operating condition.

[0175] Inadequate strength matching is usually related to the value range of the core adjustment parameter combination. If the maximum adjustment range of the core adjustment parameter combination is set too small, it cannot provide sufficient adjustment strength when encountering significant operating conditions; if the minimum adjustment range is set too large, it can easily lead to over-adjustment when the operating conditions are relatively small. The reasonableness of the value range can be determined by analyzing the relationship between the actual value distribution of the core adjustment parameter combination and the preset value range, as well as the degree of fit between the execution strength of the flow adjustment and the intensity of the operating condition influence (such as the magnitude of the flow deviation after adjustment). For example, if the flow deviation remains large after adjustment multiple times, and the core adjustment parameter combination has reached its maximum value limit, it indicates that the value range setting is unreasonable and needs to be expanded.

[0176] Step S1429: For stability matching dimensions that do not reach the ideal range, check the switching frequency of the adjustment path and the rationality of the adjustment step size of the core adjustment parameter combination to locate the cause of frequent traffic fluctuations.

[0177] Excessive switching frequency of the adjustment path leads to frequent changes in the core adjustment parameter combination, causing traffic fluctuations. If the adjustment step size of the core adjustment parameter combination is too large, each adjustment will have a significant impact on traffic; if the adjustment step size is too small, multiple adjustments may be needed to achieve the target, prolonging the instability period. The cause can be identified by statistically analyzing the correlation between the number of adjustment path switching times, the adjustment step size of the core adjustment parameter combination, and the magnitude of traffic fluctuations. For example, a positive correlation between switching frequency and traffic fluctuation magnitude indicates that excessively high switching frequency is the cause of stability problems; a positive correlation between adjustment step size and traffic fluctuation magnitude indicates that the adjustment step size is too large.

[0178] Step S14210: Integrate the analysis results from various dimensions, identify the specific optimization problems in the adjustment path selection and core adjustment parameter combination in the evolutionary traffic adaptation strategy, and pinpoint the links in the evolutionary traffic adaptation strategy that need to be optimized.

[0179] The analysis results for the time-series matching, intensity matching, and stability matching dimensions are summarized to clarify the specific problems pointed to by each non-compliant dimension. For example, the time-series matching dimension problem indicates that the adjustment path switching threshold is set too high; the intensity matching dimension problem indicates that the value range of the core adjustment parameter combination is too small; and the stability matching dimension problem indicates that the adjustment path switching frequency is too high. These specific problems are then mapped to the corresponding aspects of the evolutionary traffic adaptation strategy (such as adjustment path switching conditions, core adjustment parameter combination settings, dynamic association rules, etc.) to identify the aspects that need optimization.

[0180] Step S143: For scenarios where the adjustment path and the mutual feedback state do not match, a suitable adjustment path is reselected based on the changing trend of the core evolution parameters in the dynamic mutual feedback trace data, and the switching conditions of the adjustment path are adjusted.

[0181] When a mismatch is identified between the adjustment path and the feedback state (e.g., using a gradual adjustment path during the dynamic adjustment evolution phase), the adjustment path needs to be reselected based on the changing trends of core evolution parameters in the dynamic feedback trace data. For example, if the evolution rate parameter in the core evolution parameters continues to rise and exceeds the dynamic switching threshold, it indicates that the operating conditions are changing more rapidly, and the current gradual adjustment path should be switched to a predictive adjustment path. Simultaneously, the switching conditions of the adjustment path should be adjusted, such as lowering the dynamic switching threshold, so that the adjustment path can switch from gradual to predictive earlier to adapt to the changing trends of the operating conditions. The adjusted switching conditions need to be verified through small-scale experiments to ensure their rationality before being updated in the dynamic association rules.

[0182] Step S144: For scenarios where the core adjustment parameter combination does not match the feedback requirements, adjust the value range of the core adjustment parameter combination based on the feedback intensity record and flow response record in the dynamic feedback trace data.

[0183] The feedback intensity records in the dynamic feedback trace data reflect the magnitude of the effect of the operating conditions on the flow rate, while the flow response records reflect the actual response of the flow rate to regulation. When the core regulation parameter combination does not match the feedback requirements, such as a large feedback intensity but insufficient flow response after regulation, it indicates that the value range of the core regulation parameter combination may be too small. By analyzing the frequency and amplitude of large feedback intensity values ​​in the feedback intensity records, and the degree of insufficient flow change in the corresponding flow response records, it is determined that the value range of the core regulation parameter combination needs to be expanded (e.g., increasing the maximum adjustment range of the valve core opening, increasing the upper limit of the drive voltage, etc.). Conversely, if the feedback intensity is small but the flow fluctuation is too large after regulation, it is necessary to narrow the value range of the core regulation parameter combination and reduce the adjustment amplitude. The adjusted value range also needs to be verified and updated in the parameter mapping table.

[0184] Step S145: Establish a periodic rule for strategy iterative optimization, and set the time length of the optimization period to be an integer multiple of the update period of the dynamic feedback trace data.

[0185] The update cycle of dynamic feedback trace data is the frequency of data acquisition, such as updating once every millisecond. The optimization cycle rule sets the optimization cycle length to an integer multiple of the dynamic feedback trace data update cycle, for example, 1000 times, meaning the optimization cycle is 1 second. This ensures that a sufficient amount of dynamic feedback trace data can be collected within one optimization cycle to reflect the current feedback status. Simultaneously, setting it to an integer multiple facilitates data alignment and processing, avoiding time discrepancies. The specific multiple of the optimization cycle is determined based on the system's response speed and the drastic nature of data changes. Systems with rapidly changing operating conditions can choose a smaller multiple (e.g., 500 times, optimization cycle 0.5 seconds), while systems with stable operating conditions can choose a larger multiple (e.g., 2000 times, optimization cycle 2 seconds).

[0186] Step S146: In each optimization cycle, collect dynamic feedback trace data within that optimization cycle, and compare the degree of feedback matching and the flow adjustment effect before and after the optimization of the evolutionary flow adaptation strategy.

[0187] At the beginning of each optimization cycle, record the current version of the evolutionary traffic adaptation strategy (including adjustment path switching conditions, core adjustment parameter combination value ranges, etc.). During the optimization cycle, continuously collect dynamic feedback trace data and apply the current evolutionary traffic adaptation strategy for traffic adjustment. At the end of the cycle, calculate the feedback matching degree (scores for each evaluation dimension) and traffic adjustment effect indicators (such as average traffic deviation, traffic fluctuation energy, etc.) for that cycle. Then, apply the preliminarily optimized evolutionary traffic adaptation strategy (such as adjusted switching conditions or parameter ranges) to simulate and adjust the dynamic feedback trace data from the same time period, calculating the simulated feedback matching degree and traffic adjustment effect indicators. Compare the results of actual application and simulated adjustment to evaluate the optimization effect.

[0188] Step S147: Based on the comparison results, further fine-tune the switching threshold of the adjustment path and the accuracy of the core adjustment parameter combination to improve the adaptation degree of the evolutionary traffic adaptation strategy and the feedback state.

[0189] If the simulated regulation's feedback matching degree and flow regulation effect are better than the actual application results, it indicates that the initial optimization direction is correct. It is necessary to fine-tune the switching threshold of the regulation path and the accuracy of the core regulation parameter combination according to the initial optimization scheme. For example, fine-tune the dynamic switching threshold from 0.5 times per second to 0.45 times per second to make the regulation path switching more sensitive; increase the accuracy of the valve core opening degree in the core regulation parameter combination from 1% to 0.5% to make the regulation more precise. If the simulation results do not improve significantly or even worsen, it is necessary to re-analyze the reasons and adjust the optimization direction, such as increasing the switching threshold or changing the adjustment logic of the parameter combination. The fine-tuning process is a gradual iterative process; the magnitude of each fine-tuning should not be too large to ensure the stability of the system.

[0190] Step S148: The optimized adjustment path and core adjustment parameter combination are matched again with the real-time evolution results of the operating condition flow feedback evolution model to verify the continuous adaptability of the optimization effect of the evolutionary flow adaptation strategy.

[0191] After fine-tuning the adjustment path and core adjustment parameter combination, the optimized evolutionary flow adaptation strategy is applied to the actual solenoid valve system and continuously matched with the real-time evolution results of the operating condition flow feedback evolution model. Specifically, based on the core evolution parameter values, trends, and evolution stage indicators output by the model, the optimized adjustment path selection and core adjustment parameter combination are continuously tested to ensure they can accurately and promptly respond to changes in operating conditions. The degree of feedback matching and flow regulation effect indicators are continuously monitored to observe the stability of the optimization effect under different feedback states. If the optimization effect remains good over a relatively long period (e.g., several hours), it indicates that the optimized evolutionary flow adaptation strategy has continuous adaptability; if the adaptability decreases, the iterative optimization process needs to be restarted.

[0192] Step S149: Integrate the adjustment paths, core adjustment parameter combinations, and adjustment path switching rules after multiple iterations of optimization to form the final optimized evolutionary traffic adaptation strategy.

[0193] After multiple optimization cycles, data such as the switching conditions of the adjustment path, the value range of the core adjustment parameter combination, dynamic correlation rules, and transition parameter combinations are collected after each optimization. Statistical analysis is performed on this data to select the adjustment path, core adjustment parameter combination, and switching rules that perform optimally in most feedback states, integrating them to form the final optimized evolutionary flow adaptation strategy. This final strategy requires comprehensive testing and verification, including simulation tests and field trials under various typical operating conditions, to ensure its stable and effective intelligent adaptive flow control. After successful testing, the final optimized evolutionary flow adaptation strategy is embedded into the solenoid valve control system program.

[0194] Step S1410: The final optimized evolutionary flow adaptation strategy is converted into a signal form that can be recognized by the solenoid valve actuator, generating a solenoid valve flow intelligent adaptive control signal that includes the adjustment path identifier, core parameter values ​​of the core adjustment parameter combination, and execution timing.

[0195] Solenoid valve actuators typically receive electrical signals (such as analog signals of 4-20mA, digital pulse signals, etc.) to drive the valve spool movement. The optimized evolutionary flow adaptation strategy needs to convert the adjustment path identifier (e.g., using different numerical codes to represent responsive, progressive, and predictive modes), the core parameter values ​​of the core adjustment parameter combination (e.g., converting valve spool opening degree to the corresponding current value, driving voltage to PWM duty cycle, etc.), and the execution timing (adjustment start time, duration, and interval time converted to time pulse signals) into signal forms recognizable by the actuator. For example, the adjustment path identifier "predictive" is encoded as the number "3" and sent to the actuator via serial communication; a valve spool opening degree of 35% corresponds to a 10mA analog current signal; the adjustment start time in the execution timing is set to 100 milliseconds after receiving the control signal, and a corresponding trigger pulse is generated by setting a timer. These signals are then packaged according to the actuator's communication protocol format to generate the solenoid valve flow intelligent adaptive control signal.

[0196] Step S150: The intelligent adaptive control signal of the solenoid valve flow rate is transmitted to the solenoid valve actuator, and the feedback-type operating condition flow rate data is input in reverse into the operating condition flow rate feedback evolution model to promote the continuous evolution and update of the operating condition flow rate feedback evolution model.

[0197] For example, step S151: Analyze the final optimized evolutionary flow adaptation strategy, extract the adjustment path identifier, the specific values ​​of the core adjustment parameter combination, the adjustment order of the core adjustment parameter combination and the execution time node, so as to extract the key information that the solenoid valve flow intelligent adaptive control signal needs to carry.

[0198] The final optimized evolutionary flow adaptation strategy is stored in structured data format, such as XML or JSON. When parsing this strategy, the adjustment path identifier field is first located, and the current adjustment path code (e.g., "2" represents progressive) is extracted. Then, in the core adjustment parameter combination section, the specific values ​​of the valve core motion parameters (valve core opening degree 30%, valve core motion speed 2 mm / s, valve core motion acceleration 3 mm / s²), drive signal parameters (drive voltage 10 volts, drive current 1.5 amps, drive pulse width 30 microseconds), and adjustment timing parameters (adjustment start time 50 ms, adjustment duration 200 ms, adjustment interval 500 ms) are extracted. The adjustment order of the core adjustment parameter combination is determined according to the priority of its impact on flow, such as adjusting the valve core motion parameters first, then the drive signal parameters, and finally the adjustment timing parameters. The execution time nodes include the start and end times of each parameter adjustment; this information collectively constitutes the key content that the control signal needs to carry.

[0199] Step S152: Obtain the signal receiving specifications of the solenoid valve actuator, and extract the signal transmission form, amplitude range, frequency range and encoding requirements.

[0200] The signal reception specifications for solenoid valve actuators are typically provided by the manufacturer, including the signal transmission format (e.g., analog, digital, serial communication), amplitude range (e.g., analog current signal 4-20mA, analog voltage signal 0-10V), frequency range (e.g., PWM drive signal frequency range 1-10kHz), and encoding requirements (e.g., communication protocol, data bits, and parity bit settings for digital signals). For example, a certain model of solenoid valve actuator receives a 4-20mA analog current signal to control the valve spool position, where 4mA corresponds to the valve spool being fully closed and 20mA corresponds to the valve spool being fully open; simultaneously, it receives the adjustment path identifier and timing parameters via RS485 serial communication, using the Modbus RTU protocol, a baud rate of 9600bps, 8 data bits, 1 stop bit, and no parity.

[0201] Step S153: Establish the correspondence between adjustment path identifiers and signal codes, assign a unique code identifier to each adjustment path, and convert the adjustment path identifier into the corresponding signal code.

[0202] According to the coding requirements of the solenoid valve actuator, a unique digital code is assigned to each of the three control paths. For example, the responsive control path is coded as "01", the progressive path as "02", and the predictive path as "03". This correspondence is stored in a coding mapping table. When a progressive control path is identified, it is converted into the signal code "02" by querying the mapping table. If the actuator uses serial communication, this code is embedded as a data byte in the communication data packet; if digital input is used, different codes are represented by combinations of high and low levels on multiple pins.

[0203] Step S154: Quantize the specific values ​​of the core adjustment parameter combination according to the requirements of the signal receiving specification of the solenoid valve actuator, and convert them into signal parameters that conform to the amplitude range and frequency range.

[0204] For analog parameters, such as valve spool opening degree, linear quantization is required. For example, if the valve spool opening degree ranges from 0% to 100%, corresponding to an analog current signal of 4-20mA for the actuator, the quantization formula is: Current signal value = 4mA + (valve spool opening degree / 100%) × (20mA - 4mA). When the valve spool opening degree is 30%, the current signal value = 4 + 0.3 × 16 = 8.8mA. For digital pulse signal parameters, such as drive pulse width, the microsecond-level pulse width value is converted into the corresponding duty cycle according to the frequency range requirements of the actuator. For example, if the drive pulse width is 30 microseconds and the PWM signal period is 100 microseconds, the duty cycle is 30%. For digital parameters, such as the adjustment sequence, the adjustment sequence "valve spool motion parameters → drive signal parameters → adjustment timing parameters" is encoded as binary "1010".

[0205] Step S155: Based on the adjustment sequence and execution time nodes of the core adjustment parameter combination, construct the timing structure of the intelligent adaptive control signal for the solenoid valve flow, and set the sending sequence, sending time and duration of each signal code and signal parameter.

[0206] The transmission order of each signal is arranged according to the adjustment sequence of the core control parameter combination (e.g., valve core motion parameters first, then drive signal parameters, and finally adjustment timing parameters). The adjustment start time in the execution time node determines the start time of the entire control signal, the adjustment duration determines the duration of each parameter adjustment signal, and the adjustment interval determines the time interval between different parameter adjustment signals. For example, if the adjustment start time is 50 milliseconds, the system starts sending control signals 50 milliseconds after receiving the evolutionary flow adaptation strategy. First, the valve core motion parameter signal is sent, lasting for 200 milliseconds (adjustment duration); after a 500-millisecond interval (adjustment interval), the drive signal parameter signal is sent, also lasting for 200 milliseconds; after another 500-millisecond interval, the adjustment timing parameter signal is sent. The adjustment path identification signal is sent at the very beginning of the entire control signal sequence as a marker for the actuator to identify the adjustment mode.

[0207] Step S156: According to the timing structure of the solenoid valve flow intelligent adaptive control signal, integrate the signal encoding and signal parameters into the original signal data sequence, so that each data unit in the original signal data sequence corresponds one-to-one with the adjustment logic in the final optimized evolutionary flow adaptation strategy.

[0208] Based on the timing structure, the adjustment path identifier code, valve core motion parameter signal, drive signal parameter signal, and adjustment timing parameter signal are arranged into a raw signal data sequence according to the transmission order and time interval. Each data unit contains a signal type identifier (e.g., "P" represents valve core motion parameter, "D" represents drive signal parameter), specific signal value, and duration information. For example, the raw signal data sequence might be: [path identifier "02", duration 10 ms], [interval 40 ms], [valve core opening degree signal 8.8mA, duration 200 ms], [interval 500 ms], [drive voltage signal 10V, duration 200 ms], [interval 500 ms], [adjustment start time 50 ms, duration 10 ms]... This ensures that the content and timing of each data unit accurately correspond to the adjustment logic in the evolutionary flow adaptation strategy. For example, the 8.8mA valve core opening degree signal corresponds to a 30% valve core opening degree value, and the duration of 200 ms corresponds to the adjustment duration.

[0209] Step S157: Using a predetermined modulation method, perform signal modulation processing on the original signal data sequence to obtain a modulated signal data sequence.

[0210] The modulation method is selected according to the signal reception specifications of the solenoid valve actuator. For analog signals, such as the current signal corresponding to the valve core opening degree, a digital-to-analog converter (DAC) is used to convert the original digital signal data into a continuous analog current signal. For digital pulse signals, such as drive pulse width, pulse width modulation (PWM) is used to generate the corresponding pulse sequence according to the duty cycle. For serial communication signals, such as adjustment path identifiers and timing parameters, the appropriate communication protocol is used for frame encapsulation and modulation. For example, data is formatted according to the Modbus RTU protocol, with start bits, address code, function code, data check bits, and stop bits added to form a modulated serial data frame.

[0211] Step S158: Encapsulate the modulated signal data sequence according to the signal format requirements of the solenoid valve actuator to form a standard control signal frame structure.

[0212] Solenoid valve actuators typically require control signals with a specific frame structure, including a frame header, data segment, frame trailer, and check bit. The modulated signal data sequence is encapsulated according to this frame structure. For example, for serial communication signals, the frame header is a specific synchronization byte "0xAA", the data segment is the modulated signal data (such as path identifier encoding and timing parameters), the frame trailer is "0x55", and the check bit is calculated using the CRC16 checksum algorithm. For analog signals, although usually continuous, they may need to be transmitted synchronously with digital frame signals. In this case, the amplitude information of the analog signal is embedded as part of the data segment into the frame structure. The encapsulated control signal frame structure must strictly conform to the actuator's format requirements to ensure correct parsing.

[0213] Step S159: Integrate all control signal frames to form a solenoid valve flow intelligent adaptive control signal stream, which contains all the information required for the final optimized evolutionary flow adaptation strategy to be executed.

[0214] The encapsulated control signal frames are integrated according to the transmission order and time intervals set in the timing structure to form a continuous intelligent adaptive control signal stream for the solenoid valve flow. This signal stream begins with the adjustment path identification signal and sequentially includes all control information such as valve core motion parameter signals, drive signal parameter signals, and adjustment timing parameter signals. The duration of the signal stream is determined based on the adjustment duration and interval time, ensuring that the actuator has sufficient time to receive and process each signal frame. The control signal stream may also include synchronization signals and handshake signals to ensure communication synchronization and data integrity with the actuator.

[0215] Step S1510: Perform a transmission simulation test on the intelligent adaptive control signal flow of the solenoid valve to simulate the transmission process of the signal in the actual transmission environment and verify the restoration effect of the solenoid valve actuator on the adjustment path and core adjustment parameter combination after receiving the signal.

[0216] Before sending the control signal stream to the actual solenoid valve actuator, a transmission simulation test is performed. A simulated transmission environment is built, including simulations of actual communication line losses, electromagnetic interference, and delays. The control signal stream is sent through this simulation environment to the simulation model or physical prototype of the solenoid valve actuator. The status information returned by the actuator is then received, such as the received regulation path identifier and the parsed core regulation parameter combinations. This returned information is compared with the key information in the original evolutionary flow adaptation strategy to verify whether the actuator can accurately reproduce the regulation path and core regulation parameter combinations. If the reproduction effect is poor (e.g., parameter value deviation exceeds 5%), problems in the signal modulation, encapsulation, or transmission process need to be checked, corrected, and retested until verification is successful.

[0217] After the above steps, the intelligent adaptive control signal for the solenoid valve flow is generated and tested through transmission simulation. Subsequently, this control signal is transmitted to the solenoid valve actuator, which adjusts the flow rate according to the instructions in the signal. Simultaneously, the latest collected feedback-type operating condition flow data is input back into the operating condition flow feedback evolution model. The model uses this new data to update its core evolution parameters and adjust the evolution stage markers, achieving continuous evolution and updating, thus forming a closed-loop intelligent adaptive control process.

[0218] After the intelligent adaptive flow control signal of the solenoid valve is transmitted to the solenoid valve actuator in step S150, the solenoid valve actuator performs the corresponding flow regulation action according to the control signal. In order to monitor the actual execution effect of the actuator and its own health status, it is necessary to collect real-time execution feedback data after execution.

[0219] Appropriate sensors are installed on the solenoid valve actuator to collect real-time execution feedback data. Specifically, a high-precision displacement sensor is installed on the valve core to collect the actual displacement trajectory data of the valve core; a voltage probe and a current probe are connected in parallel in the drive circuit to collect the drive signal response waveform data; and a power analyzer is used to collect the solenoid valve's power consumption data from the power input terminal of the drive circuit.

[0220] The collected real-time execution feedback data is processed. Trajectory deviation analysis is performed on the actual displacement trajectory data of the valve core and the valve core motion parameters in the intelligent adaptive flow control signal of the solenoid valve. The actual displacement trajectory is compared point-by-point with the theoretically expected trajectory, and the displacement overshoot parameter, displacement steady-state error parameter, and displacement response time parameter are calculated. These parameters together constitute the trajectory execution deviation characteristics. Waveform consistency comparison is performed on the drive signal response waveform data and the drive signal parameters in the intelligent adaptive flow control signal of the solenoid valve. The actual waveform is aligned and compared with the theoretically expected waveform, and the rise edge delay parameter, fall edge delay parameter, and waveform distortion rate parameter are calculated, constituting the drive signal response deviation characteristics. The power consumption data of the solenoid valve action is compared with the preset standard operating condition power consumption baseline curve. The peak power consumption deviation parameter and average power consumption deviation parameter are calculated through point-by-point difference, constituting the power consumption execution deviation characteristics.

[0221] Trajectory execution deviation characteristics, drive signal response deviation characteristics, and power consumption execution deviation characteristics are fused into a comprehensive execution deviation vector. This vector is then input into a pre-constructed actuator degradation state assessment model, and a nonlinear transformation is performed through the model's feature mapping layer to generate a degradation state assessment index characterizing the degree of health degradation of the solenoid valve actuator.

[0222] Based on the comparison between the degradation status assessment index and the preset degradation threshold range, actuator maintenance early warning information is generated. This early warning information is then appended to the operating condition flow feedback evolution model as a new input dimension. During subsequent evolution, the model uses this information to adjust the update weights of core evolution parameters to compensate for flow control deviations caused by actuator degradation.

[0223] After the intelligent adaptive control signal for the flow of the solenoid valve is transmitted to the solenoid valve actuator in step S150, the operating status of the upstream and downstream related equipment in the production process where the solenoid valve is located will have a coupled effect on its flow control. Therefore, it is necessary to collect the operating data of the related equipment.

[0224] A pressure sensor is installed at the output end of the upstream equipment to collect data on pressure fluctuations at the upstream equipment output; a flow meter is installed at the inlet of the downstream equipment to collect data on changes in inlet flow demand at the downstream equipment; and a level gauge is installed on the intermediate buffer container to collect data on the liquid level status of the intermediate buffer container.

[0225] Feature extraction is performed on the collected data. Pressure fluctuation features are extracted from the pressure fluctuation data output by upstream equipment, resulting in a pressure fluctuation feature set including pressure fluctuation amplitude sequences, pressure fluctuation frequency distributions, and pressure fluctuation propagation speeds. Flow demand pattern recognition is performed on the inlet flow demand change data of downstream equipment, resulting in a flow demand pattern feature set including parameters such as the rate of demand change, the time of peak demand occurrence, and the demand cycle regularity. Liquid level dynamic change analysis is performed on the liquid level status data of the intermediate buffer container, resulting in a liquid level status feature set including parameters such as the rate of liquid level change, the degree of liquid level deviation from the safe threshold, and liquid level fluctuation energy.

[0226] The pressure fluctuation feature set, flow demand pattern feature set, and liquid level status feature set are fused into a process coupled state vector. Through correlation analysis and causal inference algorithms, coupling influencing factors that significantly affect the solenoid valve flow control in the process coupled state vector are identified, including the upstream pressure shock influence coefficient, the downstream demand traction influence coefficient, and the buffer capacity adjustment influence coefficient.

[0227] Based on the coupling influence factor, the core evolution parameters currently output by the working condition flow feedback evolution model are coupled and compensated to obtain the compensated core evolution parameters. These compensated core evolution parameters are then input into the parameter update module of the working condition flow feedback evolution model, replacing the original core evolution parameters in the subsequent evolutionary flow adaptation strategy generation process. This enables the solenoid valve flow control to adapt to the coupling influence of upstream and downstream equipment, achieving optimized adaptation from a global perspective of the production process. In an exemplary embodiment, a solenoid valve flow intelligent adaptive control system for complex working conditions is provided. This system can be a terminal, server, etc., and its internal structure diagram can be as follows: Figure 2 As shown, this intelligent adaptive control system for solenoid valve flow under complex operating conditions includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, near-field communication, or other technologies. When the computer program is executed by the processor, it implements an intelligent adaptive control method for solenoid valve flow under complex operating conditions. The display unit is used to generate a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device can be a touch layer covering the display screen, or a button, trackball, or touchpad set on the housing of the intelligent adaptive control system for flow of solenoid valves for complex working conditions, or an external keyboard, touchpad, or mouse, etc.

[0228] It should be noted that, in order to simplify the description of the present invention and thus help to understand one or more embodiments of the invention, multiple features may sometimes be grouped into one embodiment, drawing or description thereof in the foregoing description of the embodiments of the present invention.

Claims

1. A method for intelligent adaptive flow control of a solenoid valve under complex operating conditions, characterized in that, The method includes: The system collects feedback-type operating flow data of the solenoid valve under combined operating conditions. The feedback-type operating flow data includes operating condition impact data, flow feedback data, and dynamic feedback trace data. The operating condition impact data covers environmental impact data, equipment operation data, and medium property data. The flow feedback data is a record of the flow state of the medium through the solenoid valve. The dynamic feedback trace data is a record of the interaction between the operating condition impact data and the flow feedback data. The dynamic feedback trace data is obtained by analyzing the time correlation between the operating condition impact data and the flow feedback data, specifically including the action trigger dimension, response feedback dimension, and continuous action dimension. Based on the aforementioned feedback-type operating condition flow data, an operating condition flow feedback evolution model is constructed. This model is based on the feedback intensity evolution trajectory and flow response evolution law, and is used to realize the dynamic correlation evolution between operating conditions and flow. Specifically, the operating condition flow feedback evolution model is based on the feedback event sequence obtained from the dynamic feedback trace data, the core evolution parameters of the operating condition flow feedback evolution model, and the correspondence between the two to obtain the core evolution parameter values ​​for each feedback event, forming a parameter evolution trajectory. The core evolution parameters are then integrated and the evolution stages are divided to form the operating condition flow feedback evolution model. The core evolution parameters include feedback intensity parameters, evolution rate parameters, response lag parameters, and fitness parameters. These core evolution parameters collectively describe the dynamic characteristics of the feedback evolution. Based on the real-time evolution results of the operating condition flow feedback evolution model, an evolutionary flow adaptation strategy is generated. The evolutionary flow adaptation strategy includes a flow regulation path and a combination of core regulation parameters that are dynamically adjusted with the feedback evolution. The evolutionary flow adaptation strategy is iteratively optimized using the dynamic feedback trace data to generate an intelligent adaptive control signal for the solenoid valve flow. The intelligent adaptive control signal of the solenoid valve flow is transmitted to the solenoid valve actuator, and the feedback-type operating condition flow data is input in reverse into the operating condition flow feedback evolution model to promote the continuous evolution and update of the operating condition flow feedback evolution model.

2. The intelligent adaptive flow control method for solenoid valves under complex operating conditions according to claim 1, characterized in that, The construction of the operating condition flow feedback evolution model based on the feedback-type operating condition flow data includes: The constituent dimensions of the feedback-type operating condition flow data are analyzed, and the environmental effect dimension, equipment operation dimension, and medium attribute dimension in the operating condition impact data, the flow rate dimension and flow stability dimension in the flow feedback data, and the effect trigger dimension, response feedback dimension, and continuous effect dimension in the dynamic feedback trace data are distinguished, and the data representation form of each constituent dimension is extracted. Extract the feedback event sequence from the dynamic feedback trace data. Each feedback event in the feedback event sequence includes a working condition impact trigger point, a flow response feedback point, the time interval between the working condition impact trigger point and the flow response feedback point, and a record of the intensity of the effect. Connect the feedback events in series to form a continuous feedback event chain. Analyze the correlation between adjacent mutual feedback events in the mutual feedback event chain, track the process of changes in operating condition impact data triggering adjustments in flow feedback data, and the path of how adjustments in flow feedback data react to subsequent changes in operating condition impact data, thus forming the transmission trajectory of mutual feedback effects. Define the core evolution parameters of the operating condition flow feedback evolution model; Establish the correspondence between the mutual feedback event sequence and the core evolution parameters, and transform the feature data of each mutual feedback event into the corresponding core evolution parameter values ​​to form a parameter evolution trajectory; An evolutionary architecture for the aforementioned working condition flow feedback evolution model is constructed, comprising a data input module, a feedback analysis module, a parameter update module, and a result output module. The data input module receives feedback-type working condition flow data, the feedback analysis module processes the correlation of feedback events, the parameter update module dynamically adjusts the core evolution parameters, and the result output module outputs the evolution results. Historical feedback-type operating condition flow data is input into the evolution architecture, and the feedback analysis module and parameter update module are run to obtain the simulated evolution results. The simulated evolution results are compared with the corresponding historical flow feedback data, and the transformation logic and correlation of the core evolution parameters are adjusted based on the comparison results. Real-time feedback-type operating condition flow data is input into the data input module; the processing order and computing resource allocation ratio of the feedback analysis module and the parameter update module are adjusted according to the generation frequency of real-time feedback events; based on the adjusted processing order and computing resource allocation ratio, the feedback analysis module and the parameter update module are driven to process the real-time feedback-type operating condition flow data and update the values ​​of the core evolution parameters and the evolution stage identifier. The evolution stages of the operating condition flow feedback evolution model are divided. Based on the value range and change trend of the core evolution parameters, the evolution process is divided into an initial evolution stage, a stable evolution stage, and a dynamic adjustment evolution stage, with each stage corresponding to a specific evolution logic. The optimized evolutionary architecture, core evolutionary parameters, transformation logic of core evolutionary parameters, and evolutionary stage division are integrated to form the operating condition flow mutual feedback evolutionary model. The operating condition flow mutual feedback evolutionary model simulates the dynamic mutual feedback evolution process of operating conditions and flow through real-time updates of core evolutionary parameters and dynamic adaptation of evolutionary stages.

3. The intelligent adaptive flow control method for solenoid valves under complex operating conditions according to claim 2, characterized in that, The step of generating an evolutionary traffic adaptation strategy based on the real-time evolution results of the operating condition traffic feedback evolution model includes: The real-time evolution results output by the operating condition flow feedback evolution model are analyzed, and the current values, trends and evolution stage identifiers of the core evolution parameters are extracted to obtain the current operating condition and flow feedback status. Based on the current values ​​of the core evolution parameters, the core objectives of flow regulation are determined. These core objectives include flow rate regulation objectives and flow stability regulation objectives, and they directly correspond to the feedback state. Define the adjustment path types of the evolutionary traffic adaptation strategy. The adjustment path types include progressive adjustment path, responsive adjustment path and predictive adjustment path. Different adjustment paths correspond to different evolutionary stages and the changing trends of core evolutionary parameters. For the initial evolution stage, a responsive adjustment path is selected, and a preset adjustment frequency and response time threshold are set for the responsive adjustment path; For the stable evolution stage, a gradual adjustment path is adopted, and an adjustment frequency that matches the stable feedback state is set to maintain the stability of the adjustment parameters and maintain the continuous stability of the flow. For the dynamic adjustment and evolution stage, a predictive adjustment path is activated, and the adjustment direction and parameters are set in advance based on the changing trend of the core evolution parameters, so as to adapt to the upcoming mutual feedback state changes in advance. Define a core adjustment parameter combination for each adjustment path. The core adjustment parameter combination includes valve core motion parameters, drive signal parameters, and adjustment timing parameters. The values ​​of the core adjustment parameter combination and the value range of the core evolution parameters form a corresponding matching relationship. Establish dynamic association rules between adjustment paths and parameter combinations, and set the switching conditions of adjustment paths and the adjustment methods of core adjustment parameter combinations when the core evolution parameters change; The connection method of core control parameter combinations during the switching of different control paths is analyzed, and transition parameter combinations are constructed to avoid flow fluctuations caused by path switching and achieve continuous connection of the control process. The evolutionary flow adaptation strategy is formed by integrating the adjustment path type, core adjustment parameter combination, dynamic association rules between adjustment path and parameter combination, and transition parameter combination. The evolutionary flow adaptation strategy dynamically adapts to the real-time evolution results of the operating condition flow feedback evolution model by dynamically switching the adjustment path and adjusting the core adjustment parameter combination in real time.

4. The intelligent adaptive flow control method for solenoid valves under complex operating conditions according to claim 1, characterized in that, The step of iteratively optimizing the evolutionary flow adaptation strategy using the dynamic feedback trace data to generate an intelligent adaptive control signal for the solenoid valve flow includes: Extract the feedback effect records from the dynamic feedback trace data, and analyze the degree of feedback matching between the operating condition impact data and the traffic feedback data after the implementation of the evolutionary traffic adaptation strategy; Based on the degree of mutual feedback matching, the rationality of the adjustment path selection and the adaptability of the core adjustment parameter combination in the evolutionary traffic adaptation strategy are identified, and the links of the evolutionary traffic adaptation strategy with optimization space are located. For scenarios where the adjustment path and the mutual feedback state do not match, a suitable adjustment path is reselected based on the changing trend of the core evolution parameters in the dynamic mutual feedback trace data, and the switching conditions of the adjustment path are adjusted. For scenarios where the core adjustment parameter combination does not match the feedback requirements, the value range of the core adjustment parameter combination is adjusted based on the feedback intensity record and flow response record in the dynamic feedback trace data. Establish a periodic rule for strategy iteration optimization, and set the time length of the optimization period to be an integer multiple of the update period of the dynamic feedback trace data; Within each optimization cycle, dynamic feedback trace data is collected, and the degree of feedback matching and traffic adjustment effect before and after the optimization of the evolutionary traffic adaptation strategy are compared. Based on the comparison results, the switching threshold of the adjustment path and the accuracy of the core adjustment parameter combination are further fine-tuned to improve the adaptability of the evolutionary traffic adaptation strategy to the feedback state. The optimized adjustment path and core adjustment parameter combination are then matched again with the real-time evolution results of the operating condition flow feedback evolution model to verify the continuous adaptability of the optimization effect of the evolutionary flow adaptation strategy. By integrating the adjustment paths, core adjustment parameter combinations, and adjustment path switching rules after multiple iterations of optimization, a final optimized evolutionary traffic adaptation strategy is formed. The final optimized evolutionary flow adaptation strategy is transformed into a signal form that can be recognized by the solenoid valve actuator, generating a solenoid valve flow intelligent adaptive control signal that includes adjustment path identifier, core parameter values ​​of core adjustment parameter combination and execution timing.

5. The intelligent adaptive flow control method for solenoid valves under complex operating conditions according to claim 2, characterized in that, The step of extracting the feedback event sequence from the dynamic feedback trace data, wherein each feedback event in the sequence includes a condition impact trigger point, a flow response feedback point, the time interval between the condition impact trigger point and the flow response feedback point, and a record of the intensity of the effect, and connecting the feedback events in series to form a continuous feedback event chain, includes: Collect complete records from the dynamic feedback trace data, which cover the interaction records of all operating conditions and flow response during the operation of the solenoid valve under combined operating conditions; The collected dynamic feedback trace data is sorted by time and organized into time series data according to the order in which the data was generated, so as to ensure the temporal integrity of the time series data. Identify the trigger points of the operating condition impact from the time series data, mark the time nodes and changes in the operating condition impact data that are significantly different, and the time nodes in which the operating condition impact data are significantly different become the starting points of the feedback event; After each working condition trigger point, the changes in flow feedback data are tracked, flow response feedback points are identified, and the time nodes and change characteristics of the corresponding changes in flow feedback data are marked. The time nodes of the corresponding changes in flow feedback data become the feedback points of the mutual feedback event. Calculate the time difference between each operating condition's trigger point and the corresponding flow response feedback point. This time difference becomes the time interval of the mutual feedback event, reflecting the transmission time of the operating condition's impact on the flow response. The magnitude of the change in the trigger point affected by the operating condition and the magnitude of the response at the flow response feedback point are analyzed. Based on the correlation between the magnitude of the change in the trigger point affected by the operating condition and the magnitude of the response at the flow response feedback point, the intensity of the mutual feedback event is determined. The intensity of the event reflects the magnitude of the effect of the operating condition on the flow response. Each operating condition impact trigger point, the corresponding flow response feedback point, the time interval between the operating condition impact trigger point and the flow response feedback point, and the intensity of the effect are integrated to form a single mutual feedback event record; All feedback events are recorded and linked together in chronological order to form a continuous feedback event chain. Each feedback event in the feedback event chain is temporally and logically related to the feedback events before and after it. Supplement the missing feedback event records in the aforementioned feedback event chain, and correct the recording deviations in the time interval and intensity of the feedback events; The feedback event chain is marked, and the operating condition impact dimension and traffic response dimension corresponding to each feedback event are noted.

6. The intelligent adaptive flow control method for solenoid valves under complex operating conditions according to claim 3, characterized in that, The establishment of dynamic association rules between adjustment paths and parameter combinations, and the setting of switching conditions for adjustment paths and adjustment methods for core adjustment parameter combinations when the core evolution parameters change, include: Collect the core evolution parameter values, corresponding regulation paths and core regulation parameter combinations under different feedback states, as well as regulation effect records, and establish a correlation analysis dataset; The range and rate of change of the core evolutionary parameters are extracted from the association analysis dataset. The range and rate of change of the core evolutionary parameters become the key basis for determining the switching conditions of the regulation path. For the switching between responsive regulation path and gradual regulation path, an initial switching threshold for core evolution parameters is set. When the rate of change of core evolution parameters is lower than the initial switching threshold, the switching from responsive regulation path to gradual regulation path is executed. To facilitate the switching between a gradual adjustment path and a predictive adjustment path during the dynamic adjustment evolution stage, a dynamic switching threshold for the core evolution parameters is set. When the rate of change of the core evolution parameters exceeds the dynamic switching threshold, a switch from the gradual adjustment path to the predictive adjustment path is executed. To facilitate the switching between predictive and responsive control paths, a smooth switching threshold for core evolution parameters is set. When the trend of change of core evolution parameters tends to be stable and the rate of change is lower than the smooth switching threshold, the switching from predictive to responsive control paths is executed. Analyze the correspondence between the values ​​of the core regulation parameter combinations and the values ​​of the core evolution parameters under each regulation path, establish the basic adjustment logic of the core regulation parameter combinations, and set the basic rules for the changes of the values ​​of the core regulation parameter combinations with the core evolution parameters. Based on the recorded adjustment effect, the deviation between the actual adjusted flow feedback data and the expected target is calculated; according to the deviation, a mutual feedback adaptation correction coefficient is generated to correct the output result of the basic adjustment logic; in subsequent adjustments, the values ​​of the core adjustment parameter combination obtained according to the basic adjustment logic are calculated with the mutual feedback adaptation correction coefficient to obtain the optimized values ​​of the core adjustment parameter combination. Define the adjustment step size of the core adjustment parameter combination, and set the size of the adjustment step size of the core adjustment parameter combination according to the change range of the core evolution parameter. The change range of the core evolution parameter and the size of the adjustment step size of the core adjustment parameter combination are positively correlated. Establish transition rules for the core control parameter combination when switching control paths, and set the adjustment order and transition duration of the core control parameter combination during the switching process to achieve a smooth transition of changes in the core control parameter combination; By integrating the switching conditions of the adjustment path, the basic adjustment logic of the core adjustment parameter combination, the adjustment step size of the core adjustment parameter combination, and the transition rules of the core adjustment parameter combination, a dynamic association rule between the adjustment path and the parameter combination is formed. This dynamic association rule guides the adjustment path and the core adjustment parameter combination to dynamically adjust with the core evolution parameters.

7. The intelligent adaptive flow control method for solenoid valves under complex operating conditions according to claim 4, characterized in that, The step of identifying the rationality of the adjustment path selection and the adaptability of the core adjustment parameter combination in the evolutionary traffic adaptation strategy based on the mutual feedback matching degree, and locating the part of the evolutionary traffic adaptation strategy with optimization space, includes: The evaluation dimensions for the degree of mutual feedback matching are defined, including time-series matching dimension, intensity matching dimension and stability matching dimension. The evaluation dimensions evaluate the mutual feedback adaptation status of operating conditions and flow from different perspectives. For the timing matching dimension, analyze the time synchronization between the trigger point of the operating condition and the flow adjustment action, and determine the matching status between the response speed of the adjustment path and the mutual feedback transmission time. For the intensity matching dimension, compare the intensity of the effect of the operating condition with the intensity of the flow regulation, and evaluate the fit between the values ​​of the core regulation parameter combination and the effect of the operating condition. Regarding the stability matching dimension, observe the fluctuation of traffic feedback data after adjustment to determine the ability of the adjustment path and core adjustment parameter combination to maintain traffic stability; Set matching criteria for each evaluation dimension, determine the ideal matching range for each dimension based on historical best feedback state data, and identify the evolutionary traffic adaptation strategy for dimensions that exceed the ideal matching range and have room for optimization. Compare the evaluation results of each dimension of the current mutual feedback matching degree with the corresponding ideal matching range, and mark the evaluation dimensions that have not reached the ideal range; For timing matching dimensions that do not reach the ideal range, analyze the switching threshold setting status of the adjustment path to locate the problem of response delay or premature response; For intensity matching dimensions that do not reach the ideal range, analyze the rationality of the value range of the core adjustment parameter combination, and verify the adaptation status between the execution intensity of the flow regulation and the effect intensity of the operating condition. For stability matching dimensions that do not reach the ideal range, check the switching frequency of the adjustment path and the rationality of the adjustment step size of the core adjustment parameter combination to locate the cause of frequent traffic fluctuations; By integrating the analysis results from various dimensions, specific optimization problems in the adjustment path selection and core adjustment parameter combination in the evolutionary traffic adaptation strategy are identified, and the links in the evolutionary traffic adaptation strategy that need to be optimized are pinpointed.

8. The intelligent adaptive flow control method for solenoid valves under complex operating conditions according to claim 2, characterized in that, The real-time feedback-type operating condition flow data is input into the data input module; the processing order and computing resource allocation ratio of the feedback analysis module and the parameter update module are adjusted according to the generation frequency of real-time feedback events. Based on the adjusted processing order and computing resource allocation ratio, the mutual feedback analysis module and parameter update module are driven to process the real-time mutual feedback type operating condition flow data, update the values ​​of the core evolution parameters and the evolution stage identifier, including: Establish a real-time data access interface to transmit the real-time feedback-type operating condition flow data to the evolution architecture through the interface; The real-time feed-in operating condition flow data is prioritized and classified. The latest feed-in event record in the dynamic feed-in trace data is marked as the highest priority, and the operating condition impact data and flow feedback data are marked as the second highest priority. The functional division of each module in the evolutionary architecture is analyzed, and the processing flow and interdependencies of the data input module, mutual feedback analysis module, parameter update module and result output module are analyzed. Based on the priority classification results of the feed-through operating condition flow data, the processing resource allocation of each module in the evolution architecture is adjusted. In the mutual feedback analysis module, a parallel computing unit is configured to simultaneously perform the correlation analysis on multiple latest mutual feedback event records; Adjust the update frequency of the parameter update module and set an update cycle consistent with the generation frequency of real-time mutual feedback event records so that the core evolution parameters can reflect the latest mutual feedback status in a timely manner. A real-time data access interface is configured in the data input module of the evolutionary architecture; real-time feedback-type operating condition flow data is received through the real-time data access interface, and the data is forwarded to the data buffer of the data input module; Set real-time response trigger rules and set a threshold for the effect intensity record; in the data input module, compare the effect intensity of the incoming feedback event record with the threshold; when the effect intensity exceeds the threshold, send a priority processing instruction to the data scheduling unit of the evolution architecture; after receiving the priority processing instruction, the data scheduling unit prioritizes the feedback event record that exceeds the threshold and related operating condition impact data and traffic feedback data to the feedback analysis module for processing. Periodically evaluate the response effect of the working condition flow feedback evolution model after adjusting the processing priority of each module in the evolution architecture, and fine-tune the processing resource allocation ratio based on the processing time of real-time feedback events and the accuracy of evolution results. Record the correspondence between the processing priority adjustment of each module in the aforementioned evolutionary architecture and the response effect of the working condition flow feedback evolution model, and form an adjustment log.

9. The intelligent adaptive flow control method for solenoid valves under complex operating conditions according to claim 1, characterized in that, After transmitting the intelligent adaptive flow control signal of the solenoid valve to the solenoid valve actuator, the process further includes: Collect real-time execution feedback data after the solenoid valve actuator performs flow regulation action. The real-time execution feedback data includes actual valve core displacement trajectory data, drive signal response waveform data, and solenoid valve action power consumption data. The actual displacement trajectory data of the valve core and the valve core motion parameters in the intelligent adaptive flow control signal of the solenoid valve are subjected to trajectory deviation analysis processing to obtain trajectory execution deviation characteristics including displacement overshoot parameters, displacement steady-state error parameters and displacement response time parameters; The waveform consistency of the drive signal response waveform data and the drive signal parameters in the intelligent adaptive control signal of the solenoid valve flow are compared to obtain the drive signal response deviation characteristics including the rising edge delay parameter, the falling edge delay parameter and the waveform distortion rate parameter. The solenoid valve's power consumption data is compared with a preset standard operating condition power consumption baseline curve to obtain power consumption execution deviation characteristics including peak power consumption deviation parameters and average power consumption deviation parameters. The trajectory execution deviation feature, the drive signal response deviation feature, and the power consumption execution deviation feature are fused into a comprehensive execution deviation vector. The comprehensive execution deviation vector is then input into a pre-constructed actuator degradation state assessment model to generate a degradation state assessment index that characterizes the degree of health degradation of the solenoid valve actuator. Based on the comparison results between the degradation state assessment index and the preset degradation threshold range, an actuator maintenance early warning information is generated. The actuator maintenance early warning information is then attached to the operating condition flow feedback evolution model to correct the update weights of core evolution parameters in the subsequent evolution process.

10. The intelligent adaptive flow control method for solenoid valves under complex operating conditions according to claim 1, characterized in that, After transmitting the intelligent adaptive flow control signal of the solenoid valve to the solenoid valve actuator, the process further includes: Collect the operating data of the upstream and downstream related equipment in the production process where the solenoid valve actuator is located. The operating data of the related equipment includes the output pressure fluctuation data of the upstream equipment, the inlet flow demand change data of the downstream equipment, and the liquid level status data of the intermediate buffer container. The pressure fluctuation data output by the upstream equipment is processed by pressure fluctuation feature extraction to obtain a pressure fluctuation feature set including pressure fluctuation amplitude sequence, pressure fluctuation frequency distribution and pressure fluctuation propagation speed. The downstream equipment inlet traffic demand change data is processed by traffic demand pattern recognition to obtain a traffic demand pattern feature set including demand change rate parameter, demand peak occurrence time parameter and demand cycle regularity parameter; The liquid level status data of the intermediate buffer container is subjected to dynamic change analysis to obtain a set of liquid level status features including the rate of change of liquid level, the degree of deviation of liquid level from the safety threshold, and the energy parameters of liquid level fluctuation. The pressure fluctuation feature set, the flow demand pattern feature set, and the liquid level state feature set are fused into a process coupling state vector, and coupling influence factors that have a significant impact on the flow control of the solenoid valve are identified in the process coupling state vector. Based on the coupling influence factor, the core evolution parameters currently output by the operating condition flow feedback evolution model are coupled and compensated to obtain the compensated core evolution parameters. The compensated core evolution parameters are then input into the operating condition flow feedback evolution model to replace the original core evolution parameters in the subsequent evolutionary flow adaptation strategy generation process.

11. A solenoid valve flow intelligent adaptive control system for complex operating conditions, characterized in that, include: processor; A machine-readable storage medium for storing machine-executable instructions of the processor; The processor is configured to execute the intelligent adaptive flow control method for solenoid valves under complex operating conditions as described in any one of claims 1 to 10 by executing the machine-executable instructions.

12. A computer program product, characterized in that, The computer program product includes machine-executable instructions stored in a computer-readable storage medium. The processor of the intelligent adaptive control system for solenoid valve flow under complex operating conditions reads the machine-executable instructions from the computer-readable storage medium and executes the machine-executable instructions, causing the intelligent adaptive control system for solenoid valve flow under complex operating conditions to perform the intelligent adaptive control method for solenoid valve flow under complex operating conditions as described in any one of claims 1 to 10.

Images