Intelligent hydraulic control method and system for flow regulation and medium

Abstract

The invention discloses an intelligent hydraulic control method and system for flow regulation and a medium, and relates to the technical field of intelligent hydraulic control. The intelligent hydraulic control method comprises the steps that real-time sensing is carried out based on a hydraulic system, dynamic flow analysis is carried out according to a multi-source sensing data set, and a flow demand parameter set is obtained; flow pressure analysis is conducted, data superposition is conducted according to a pressure analysis result, and an initial flow adjusting instruction is generated; simulating and executing the flow initial adjustment instruction to drive an electro-hydraulic proportional valve to perform opening adjustment, and drawing a flow fluctuation trend chart; and adjusting and backtracking according to the flow fluctuation trend chart, and determining a flow adjusting instruction to intelligently adjust the flow of the hydraulic system. The technical problems that in the prior art, a hydraulic system is insufficient in flow adjustment accuracy, poor in dynamic adaptability and difficult to optimize in real time according to actual working conditions are solved, and the technical effects that intelligent adjustment of the flow of the hydraulic system is achieved, and the accuracy and the dynamic adaptability of flow control are improved are achieved.

Description

Technical Field

[0001] This invention relates to the field of intelligent hydraulic control technology, specifically to an intelligent hydraulic control method, system, and medium for flow regulation. Background Technology

[0002] With the rapid development of industrial automation and intelligence, hydraulic systems, as a key power source in many fields, are widely used in industries such as machinery manufacturing, aerospace, automotive, and construction. However, traditional hydraulic systems have many shortcomings in flow control. Their control methods are slow to respond and cannot make timely adjustments to rapidly changing working conditions. This results in the system being unable to quickly adapt to load changes and process requirements, and has low control accuracy, making it difficult to meet the needs of scenarios with stringent requirements for flow precision.

[0003] Existing technologies suffer from insufficient precision in flow regulation of hydraulic systems, poor dynamic adaptability, and difficulty in real-time optimization based on actual working conditions. Summary of the Invention

[0004] This application provides an intelligent hydraulic control method, system, and medium for flow regulation, which addresses the technical problems of insufficient accuracy, poor dynamic adaptability, and difficulty in real-time optimization based on actual working conditions in existing hydraulic systems.

[0005] In view of the above problems, this application provides an intelligent hydraulic control method, system and medium for flow regulation.

[0006] A first aspect of this application provides an intelligent hydraulic control method for flow regulation, the method comprising: Based on real-time sensing of the hydraulic system, dynamic flow analysis is performed using a multi-source sensor dataset to obtain a set of flow demand parameters. Flow and pressure analysis is then performed on the hydraulic system according to these parameters. Data is superimposed based on the pressure analysis results to generate an initial flow adjustment command. The initial flow adjustment command is simulated to drive an electro-hydraulic proportional valve to adjust its opening. Feedback compensation is performed based on the opening adjustment results, and a flow fluctuation trend graph is plotted. Adjustment backtracking is performed according to the flow fluctuation trend graph. Data closed-loop updates and optimizations of the flow demand parameters are performed based on the backtracking data to generate optimized flow demand parameters to correct the initial flow adjustment command. Finally, the flow adjustment command is determined to intelligently regulate the flow of the hydraulic system.

[0007] A second aspect of this application provides an intelligent hydraulic control system for flow regulation, the system comprising: The system comprises the following modules: a dynamic flow analysis module for real-time sensing of the hydraulic system, dynamic flow analysis based on multi-source sensor datasets to obtain a set of flow demand parameters; a regulation command generation module for flow and pressure analysis of the hydraulic system according to the flow demand parameters, data superposition based on the pressure analysis results to generate an initial flow regulation command; a feedback compensation module for simulating the execution of the initial flow regulation command to drive the electro-hydraulic proportional valve to adjust its opening, performing feedback compensation based on the opening adjustment results, and plotting a flow fluctuation trend graph; and an intelligent flow regulation module for performing regulation backtracking based on the flow fluctuation trend graph, updating and optimizing the flow demand parameters in a closed loop based on the backtracking data, generating optimized flow demand parameters to correct the initial flow regulation command, and determining the flow regulation command to perform intelligent flow regulation of the hydraulic system.

[0008] In a third aspect of this application, a computer-readable storage medium is provided storing a computer program for executing the intelligent hydraulic control method for flow regulation provided in this application.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: Based on real-time sensing of the hydraulic system, dynamic flow analysis is performed using multi-source sensor datasets to obtain a set of flow demand parameters. Flow and pressure analysis of the hydraulic system is then conducted, and data is superimposed based on the pressure analysis results to generate an initial flow adjustment command. The initial flow adjustment command is simulated to drive the electro-hydraulic proportional valve to adjust its opening, and a flow fluctuation trend graph is plotted. Adjustment backtracking is performed according to the flow fluctuation trend graph, and the flow demand parameters are updated and optimized using backtracking data to determine the flow adjustment command for intelligent flow regulation of the hydraulic system. This achieves intelligent flow regulation of the hydraulic system, improving the accuracy and dynamic adaptability of flow control. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a schematic flowchart of the intelligent hydraulic control method for flow regulation provided in an embodiment of this application.

[0012] Figure 2 A schematic diagram of the intelligent hydraulic control system for flow regulation provided in the embodiments of this application.

[0013] Figure labeling: Dynamic flow analysis module 10, adjustment command generation module 20, feedback compensation module 30, intelligent flow adjustment module 40. Detailed Implementation

[0014] This application provides an intelligent hydraulic control method, system, and medium for flow regulation, which addresses the technical problems of insufficient accuracy, poor dynamic adaptability, and difficulty in real-time optimization based on actual working conditions in existing hydraulic systems.

[0015] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0016] Example 1, as Figure 1 As shown, this application provides an intelligent hydraulic control method for flow regulation, the method comprising: Step S100: Real-time sensing is performed based on the hydraulic system, and dynamic flow analysis is conducted based on the multi-source sensor dataset to obtain the flow demand parameter set.

[0017] Specifically, a multi-source sensor array deployed within the hydraulic system performs multi-dimensional sensing to collect pressure data, flow data, and load status data. The pressure data is frequency-adjusted to obtain pressure pulsation data, the flow data undergoes multi-band noise reduction to obtain instantaneous flow data, and the load status data is filtered to obtain hydraulic actuation displacement data. Next, based on the load change gradient of the hydraulic actuation displacement data, a coupling analysis is performed on the pressure pulsation data and instantaneous flow data to determine the coupling coefficient between the load change gradient and the pressure-flow rate. Finally, based on this coupling coefficient, the flow demand of the hydraulic system is predicted, thereby determining the flow demand parameter set.

[0018] Step S200: Perform flow and pressure analysis on the hydraulic system according to the flow demand parameters, and superimpose the data based on the pressure analysis results to generate an initial flow adjustment command.

[0019] Specifically, the acquired flow demand parameter set and pressure data are dynamically coupled and analyzed. First, based on the flow demand parameters, the basic flow value, compensation flow value, and flow increment value are parsed out. Based on the pressure pulsation data, the pump outlet pressure value, actuator inlet pressure value, and return oil back pressure value are parsed out. Then, the steady-state pressure margin data is calculated by correlating the basic flow value and the pump outlet pressure value. The pressure-flow compensation mapping relationship is determined by matching the compensation flow value and the actuator inlet pressure value. The back pressure influence factor is established by aligning the flow increment value and the return oil back pressure value, and then a pressure-flow feature matrix is ​​constructed. The matrix is ​​traversed to perform pressure fluctuation anomaly analysis to extract the pressure fluctuation suppression coefficient. Flow change anomaly analysis is performed to determine the flow compensation gradient coefficient. Based on these two coefficients, the data are superimposed to obtain the anti-disturbance flow baseline value and the dynamic compensation amount. Finally, these two data are merged to generate the initial flow regulation command.

[0020] Step S300: Simulate the execution of the initial flow adjustment command to drive the electro-hydraulic proportional valve to adjust the opening, perform feedback compensation based on the opening adjustment result, and draw a flow fluctuation trend graph.

[0021] Specifically, a three-dimensional mapping table of current-opening degree-flow rate for the electro-hydraulic proportional valve is first established. An initial flow rate adjustment command is loaded and decomposed into a current time sequence. The electro-hydraulic proportional valve is then simulated and driven according to this current time sequence, and the valve core movement trajectory is recorded to generate a virtual opening curve. Simultaneously, the actual valve core displacement feedback signal of the electro-hydraulic proportional valve is acquired, and the actual valve core displacement feedback signal is compared with the virtual opening curve in real time to calculate the opening following error. Based on this opening following error, dynamic compensation is performed to generate feedback compensation data. Then, the flow rate changes are traced based on the feedback compensation data, and a flow rate fluctuation trend chart is drawn.

[0022] Step S400: Adjust and trace back according to the flow fluctuation trend chart, perform data closed-loop update and optimization of the flow demand parameters based on the trace back data, generate flow demand optimization parameters to correct the initial flow adjustment command, and determine the flow adjustment command to perform intelligent flow adjustment of the hydraulic system.

[0023] Specifically, the flow fluctuation range is analyzed based on the flow fluctuation trend chart to extract fluctuation feature patterns. A timing backtracking command is triggered based on these patterns, and the original operation data is located through analysis of the associated operations of the hydraulic system. The flow demand is then deduced backward from the original operation data to generate a flow demand correction factor set. This set is dynamically weighted and fused with the flow demand parameters to obtain optimized flow demand parameters. The initial flow adjustment command is reconstructed based on these optimized parameters to obtain a regeneration command. Subsequently, fluctuation analysis is performed based on the regeneration command executed through a virtual channel to obtain a first flow fluctuation trend, and fluctuation analysis is performed based on the regeneration command executed through an actual channel to obtain a second flow fluctuation trend. Phase cross-validation is then performed based on the first and second flow fluctuation trends to finally determine the flow adjustment command for intelligent flow regulation of the hydraulic system.

[0024] In one possible implementation, step S100 further includes: Step S110: Perform multi-dimensional sensing based on the multi-source sensor array deployed within the hydraulic system to obtain pressure data, flow data, and load status data.

[0025] Step S120: Adjust the frequency based on the pressure data to obtain pressure pulsation data.

[0026] Step S130: Perform multi-band noise reduction based on the traffic data to obtain instantaneous traffic data.

[0027] Step S140: Filter the load state data to obtain hydraulic actuation displacement data.

[0028] Step S150: Perform coupling analysis on the pressure pulsation data and the instantaneous flow rate data according to the load change gradient of the hydraulic displacement data to determine the coupling coefficient between the load change gradient and the pressure-flow rate.

[0029] Step S160: Based on the coupling coefficient, predict the flow demand of the hydraulic system and determine the flow demand parameter set.

[0030] Specifically, a multi-source sensor array is pre-deployed inside the hydraulic system. This array can monitor the system's operating status in real time from different dimensions. Through the collaborative work of the sensors, it collects and acquires pressure data (reflecting the pressure magnitude and changes in various parts of the hydraulic system), flow data (reflecting the flow rate and total amount of the medium in the system), and load status data (characterizing the external load on the hydraulic system), providing basic data support for subsequent dynamic flow analysis.

[0031] The collected pressure data is subjected to Fourier transform to convert it from a time domain signal to a frequency domain signal. Characteristic frequency bands related to the inherent vibration frequency of the hydraulic system and the operating frequency of the pump and valve are selected by using a preset frequency threshold. The signal within the characteristic frequency band is subjected to spectrum analysis to extract the amplitude and phase information corresponding to each frequency component. Then, the frequency domain features are restored to the time domain signal by inverse Fourier transform to obtain pressure pulsation data after removing non-pulsation interference. This accurately reflects the periodic or transient pulsation characteristics in the pressure data caused by the dynamic operation of the system.

[0032] The collected flow data is decomposed into wavelet coefficients of different frequency bands by performing wavelet transform. Based on the inherent frequency characteristics of the hydraulic system flow signal, noise thresholds are set for each frequency band. The decomposed wavelet coefficients are then processed to filter out coefficients corresponding to high-frequency noise. Low-frequency and specific frequency band coefficients related to the effective flow signal are retained. The processed coefficients are then reconstructed into a time-domain signal by inverse wavelet transform to obtain instantaneous flow data after removing multi-frequency noise interference, so as to accurately reflect the real-time dynamic changes of flow.

[0033] The load status data collected from the hydraulic system is processed using a filtering algorithm. By filtering out noise interference (such as sensor noise and electromagnetic interference during system operation), effective information that accurately reflects the motion of the hydraulic actuator is extracted, ultimately obtaining hydraulic actuator displacement data. This data can accurately characterize the real-time displacement change of the hydraulic actuator under load, providing a reliable basis for subsequent pressure and flow coupling analysis based on load change gradient.

[0034] First, the actuator displacement data is processed by time differentiation using a differential algorithm to calculate the piston acceleration. Then, combined with the effective working area parameter of the piston, the real-time load force is derived using the dynamic formula (force = mass × acceleration, converted using piston area), thus determining the load change gradient. Next, the pressure pulsation data is processed using a spectrum analysis tool (such as Fourier transform) to extract the dominant fluctuation amplitude and its corresponding frequency. Finally, a phase difference calculation algorithm (such as cross-correlation analysis) is used to compare the time difference between the pressure fluctuation and the flow fluctuation in the instantaneous flow data to obtain the phase difference. Finally, this phase difference is multiplied by the aforementioned fluctuation amplitude to obtain the coupling coefficient characterizing the load change gradient and the strength of the pressure-flow interaction.

[0035] Using a defined coupling coefficient as the core input, a multiple linear regression prediction model is constructed by combining pressure-flow correlation data from the historical operation of the hydraulic system. The coupling coefficient, historical pressure pulsation data, historical instantaneous flow data, and load change gradient are used as independent variables, and the actual flow demand is used as the dependent variable for training. The regression coefficient is optimized through model iteration, enabling the model to output predicted flow demand values ​​based on the real-time coupling coefficient and current system state parameters (pressure pulsation, instantaneous flow, and load change gradient). Confidence interval analysis is performed on the predicted values, and prediction results falling within the preset confidence range are selected. These predicted results are then decomposed into basic flow value, compensated flow value, and flow increment value, which together form a flow demand parameter set, achieving accurate prediction of the hydraulic system's flow demand.

[0036] In one possible implementation, step S200 further includes: Step S210: Perform dynamic coupling analysis between the flow demand parameter set and the pressure data to generate a pressure-flow characteristic matrix.

[0037] Step S220: Traverse the pressure-flow characteristic matrix to perform pressure fluctuation anomaly analysis and extract the pressure fluctuation suppression coefficient.

[0038] Step S230: Traverse the pressure-flow characteristic matrix to perform flow change anomaly analysis and determine the flow compensation gradient coefficient.

[0039] Step S240: Perform data superposition calculation based on the pressure fluctuation suppression coefficient and the flow compensation gradient coefficient to generate the anti-disturbance flow reference value and dynamic compensation amount.

[0040] Step S250: The anti-disturbance flow reference value and the dynamic compensation amount are fused to generate the initial flow adjustment command.

[0041] Specifically, the hydraulic system is first analyzed based on the flow demand parameter set to determine the basic flow rate, compensated flow rate, and flow increment value. Simultaneously, the hydraulic system is analyzed based on pressure pulsation data to determine the pump outlet pressure, actuator inlet pressure, and return oil back pressure. Then, the basic flow rate is correlated with the pump outlet pressure to calculate steady-state pressure margin data. The compensated flow rate is matched with the actuator inlet pressure to determine the pressure-flow compensation mapping relationship. The flow increment value and return oil back pressure value are time-series aligned to establish a back pressure influence factor. Finally, a three-dimensional coordinate system is constructed. The steady-state pressure margin data is mapped to this three-dimensional coordinate system according to the pressure-flow compensation mapping relationship, and real-time pressure data points are marked. Then, the real-time pressure data points are correlated with the flow demand parameter set according to the back pressure influence factor. Based on the correlation results, the three-dimensional coordinate system is interpolated and filled to generate a pressure-flow feature matrix.

[0042] A comprehensive traversal of the pressure-flow characteristic matrix is ​​performed, examining each pressure data point to identify regions where pressure values ​​exceed a preset safety threshold. These regions are then marked as abnormal pressure fluctuation areas. Next, the total area of ​​all abnormal areas is calculated and compared with the total area of ​​the pressure-flow characteristic matrix to obtain the ratio, which serves as an indicator of the intensity of pressure fluctuations. Finally, based on this fluctuation intensity indicator, a coefficient capable of suppressing corresponding pressure fluctuations is determined, known as the pressure fluctuation suppression coefficient. This coefficient can be used to subsequently mitigate the impact of abnormal pressure fluctuations on the flow regulation of the hydraulic system.

[0043] A matrix traversal algorithm is used to scan the pressure-flow characteristic matrix row by row and column by column. For each set of flow demand parameters in the matrix, a linear fit is performed with the corresponding pressure data to calculate the slope value of their change. A slope threshold value is set (determined based on the historical slope range during stable operation of the hydraulic system). A comparator compares the calculated absolute value of the slope with the threshold value. When the absolute value of the slope exceeds the threshold value, a marking mechanism is triggered to mark the area as a compensation section. For the marked compensation section, the specific value and direction of its slope are extracted. Combined with the maximum allowable flow adjustment rate of the system, a proportional algorithm is used to calculate the compensation gradient that matches the slope change, and then the flow compensation gradient coefficient is determined. This coefficient can quantify the amount of flow compensation required per unit pressure change.

[0044] A weighted summation algorithm is used to superimpose the pressure fluctuation suppression coefficient and the flow compensation gradient coefficient. First, preset weights are assigned to the two coefficients (the weight values ​​are determined based on the sensitivity analysis of the hydraulic system to pressure fluctuations and flow changes). The pressure fluctuation suppression coefficient is multiplied by its corresponding weight and then multiplied by the base flow value to obtain the anti-disturbance flow benchmark value, which can resist the interference caused by pressure fluctuations. At the same time, the flow compensation gradient coefficient is multiplied by its corresponding weight and then multiplied by the real-time flow change rate to obtain the dynamic compensation amount, which is used to adjust the flow in real time to cope with abnormal changes. The above calculations are completed by the calculation module and the results are output, providing data support for the generation of subsequent initial flow adjustment commands.

[0045] Based on the anti-disturbance flow reference value, the dynamic compensation quantity is superimposed and fused with the anti-disturbance flow reference value according to the time series. During the fusion process, the dynamic compensation quantity is time-series calibrated according to the response characteristics of the hydraulic system to ensure the matching of the two in the time dimension. The fused data stream is smoothed by a weighted average algorithm to eliminate the interference caused by data mutation. Finally, an initial flow adjustment command that can take into account the anti-disturbance capability of the system and the real-time adjustment requirements is generated. This command can be directly used to drive the electro-hydraulic proportional valve to adjust the opening.

[0046] In one possible implementation, step S210 further includes: Step S211: Based on the flow demand parameters, analyze the hydraulic system to determine the basic flow value, the compensation flow value, and the flow increment value.

[0047] Step S212: Based on the pressure pulsation data, analyze the hydraulic system to determine the pump outlet pressure value, actuator inlet pressure value, and return oil back pressure value.

[0048] Step S213: Correlate the basic flow rate value with the pump outlet pressure value to calculate the steady-state pressure margin data.

[0049] Step S214: Match the compensated flow rate value with the actuator inlet pressure value to determine the pressure-flow rate compensation mapping relationship.

[0050] Step S215: Align the incremental flow rate value with the back pressure value in time to establish a back pressure influence factor.

[0051] Step S216: Construct the pressure-flow characteristic matrix based on the steady-state pressure margin data, the pressure-flow compensation mapping relationship, and the back pressure influence factor.

[0052] Specifically, based on the set of flow demand parameters, and combined with the design parameters, operating conditions, and load characteristics of the hydraulic system, the basic flow value to ensure the realization of the system's basic functions is determined by analyzing the minimum flow demand of the system under stable operating conditions. Based on the additional flow required by the system under normal load fluctuations, the compensation flow value to offset the impact of fluctuations is calculated. For possible sudden load changes or operating condition switching, based on the maximum increase range of flow demand, the incremental flow value that can quickly respond to changes is determined, thereby comprehensively covering the flow demand of the hydraulic system under different operating conditions.

[0053] Based on pressure pulsation data, and combined with the pipeline layout and component characteristics of the hydraulic system, the pulsation data collected by the pressure sensor at the pump outlet is filtered and peak value extracted to determine the pump outlet pressure value. For the pressure pulsation signal at the actuator inlet, after removing pipeline loss interference, steady-state value calculation is performed to obtain the actuator inlet pressure value. For the pressure pulsation data in the return oil pipeline, by analyzing its fluctuation characteristics under different flow rates and combining the back pressure formation mechanism, the return oil back pressure value that reflects the return oil resistance is extracted, thereby comprehensively obtaining the pressure parameters of key locations in the hydraulic system.

[0054] A data association algorithm is used to bind the base flow rate value with the pump outlet pressure value to establish a correspondence model between the two. By querying the rated pressure parameters of the hydraulic system, the minimum stable pressure threshold required by the system under the base flow rate value is determined. The difference calculation method is used to subtract the minimum stable pressure threshold from the pump outlet pressure value, and the result is the steady-state pressure margin data. This quantifies the degree of pressure surplus of the system when the base flow rate is output, and provides data support for subsequent analysis.

[0055] The compensation flow rate and actuator inlet pressure values ​​are standardized to eliminate dimensional differences. Then, the K-nearest neighbor matching algorithm is used to find the K most similar samples in the compensation flow rate dataset, using the actuator inlet pressure value as the search keyword. The compensation flow rate value of these K samples is calculated by weighted average to obtain the compensation flow rate matching value corresponding to the current inlet pressure value. This process is repeated to cover all pressure ranges, and finally a mapping table is formed with pressure range as the key and compensation flow rate value as the value, i.e., the pressure-flow rate compensation mapping relationship.

[0056] Based on time-series data of flow increment and return oil back pressure, a time synchronization algorithm is used to align the acquisition timestamps of both, ensuring that the corresponding flow increment and return oil back pressure data are matched at the same time node. Correlation analysis is performed on the aligned time-series data to calculate the rate of change of flow increment under different back pressure values, thereby quantifying the degree of influence of return oil back pressure on flow increment. Based on the magnitude of the influence, a back pressure influence factor that reflects the effect of back pressure on flow increment is generated. This factor can be used to construct the pressure-flow characteristic matrix to improve the accuracy of the matrix in representing the dynamic characteristics of the system.

[0057] Using steady-state pressure margin data, pressure-flow compensation mapping relationship, and back pressure influencing factor as core construction elements, a three-dimensional coordinate system is first constructed. The steady-state pressure margin data is used as the basic data and mapped onto the three-dimensional coordinate system according to the pressure-flow compensation mapping relationship, marking the corresponding real-time pressure data points. Then, based on the back pressure influencing factor, these real-time pressure data points are associated with the flow demand parameter set. Based on the association results, the blank areas between data points in the three-dimensional coordinate system are interpolated and filled to make the data distribution within the coordinate system more complete and continuous. Finally, a pressure-flow characteristic matrix that can comprehensively reflect the complex correlation characteristics between pressure and flow is formed.

[0058] In one possible implementation, step S216 further includes: Step S2161: Construct a three-dimensional coordinate system, map the steady-state pressure margin data to the three-dimensional coordinate system according to the pressure-flow compensation mapping relationship, and mark the real-time pressure data points.

[0059] Step S2162: Associate the real-time pressure data points with the flow demand parameter set according to the back pressure influence factor, and interpolate and fill the three-dimensional coordinate system according to the association result to construct the pressure-flow feature matrix.

[0060] Specifically, a 3D coordinate system is constructed using 3D modeling tools, with pressure, flow rate, and associated characteristic values ​​as coordinate axes. The X-axis corresponds to pressure parameters, the Y-axis to flow rate parameters, and the Z-axis to pressure-flow associated characteristic values. The pressure-flow compensation mapping database is called to transform the steady-state pressure margin data according to the pressure-flow correspondence rules in the mapping relationship, and the spatial coordinates of each steady-state pressure margin data in the 3D coordinate system are calculated. The corresponding real-time pressure data is marked at the calculated coordinate positions using a data marking algorithm, forming a discrete data point set with real-time pressure labels, thus completing the mapping and marking of the steady-state pressure margin data in the 3D coordinate system.

[0061] The quantitative parameters of the back pressure influence factor are called, and the real-time pressure data points marked in the three-dimensional coordinate system are matched with the parameters in the flow demand parameter set through the correlation algorithm to establish the correspondence between pressure data points and flow demand under different back pressure influence levels. Based on this correlation, the Kriging interpolation method is used to interpolate the blank areas between discrete data points in the three-dimensional coordinate system to supplement the missing pressure-flow correlation data. The interpolated data is integrated with the original data to form a three-dimensional data grid covering the complete parameter range, and then a pressure-flow feature matrix containing pressure, flow and correlation features is constructed.

[0062] In one possible implementation, step S300 further includes: Step S310: Establish a three-dimensional mapping table of current-opening degree-flow rate for the electro-hydraulic proportional valve, load the initial flow rate adjustment command, and decompose the initial flow rate adjustment command into a current timing sequence.

[0063] Step S320: Simulate the change of valve core movement trajectory by driving the electro-hydraulic proportional valve according to the current timing sequence, and generate a virtual opening curve.

[0064] Step S330: Collect the actual valve core displacement feedback signal of the electro-hydraulic proportional valve, compare the actual valve core displacement feedback signal with the virtual opening curve in real time, and calculate the opening following error.

[0065] Step S340: Perform dynamic compensation based on the opening degree following error, generate feedback compensation data, trace flow changes based on the feedback compensation data, and draw the flow fluctuation trend chart.

[0066] Specifically, firstly, the valve opening data and corresponding output flow data of the electro-hydraulic proportional valve under different current inputs are collected through experiments. Based on these data, a three-dimensional mapping relationship table of current-opening-flow is constructed, which can clearly define the correspondence between current, opening, and flow. Then, the initial flow adjustment command is loaded into the system. According to the established three-dimensional mapping relationship table, the valve opening corresponding to the command is looked up in reverse. Then, the required driving current is determined according to the opening. Finally, the initial flow adjustment command is decomposed into a series of continuous current values ​​in time sequence to form the current timing sequence that drives the electro-hydraulic proportional valve.

[0067] Using the current time sequence as the input signal, the dynamic response model of the electro-hydraulic proportional valve is used to simulate the movement of the valve core. During the simulation, the displacement changes of the valve core at different time points are recorded in real time, including the position parameters of the valve core in the opening, holding, and closing stages. Based on the recorded displacement data and the corresponding time information, the discrete displacement points are connected in time sequence to form a continuous curve that reflects the theoretical movement trajectory of the valve core, namely the virtual opening curve. This curve can intuitively reflect the expected opening change law of the electro-hydraulic proportional valve under the drive of the current time sequence.

[0068] The actual displacement of the valve core is collected in real time by a displacement sensor deployed on the electro-hydraulic proportional valve, obtaining a continuous actual valve core displacement feedback signal. This signal contains the actual position information of the valve core at different times. At the same time, a virtual opening curve is retrieved, which records the theoretical position that the valve core should reach within the same time period. The actual valve core displacement feedback signal and the virtual opening curve are compared point by point in real time on the same time axis. The difference between the actual displacement and the theoretical opening at each time is calculated. This difference is the opening following error, which quantifies the degree of deviation between the actual movement trajectory of the valve core and the expected trajectory.

[0069] Based on the opening degree following error, a dynamic compensation algorithm is used to calculate the compensation amount used to correct the valve core movement trajectory, generating feedback compensation data. This data can adjust the drive signal of the electro-hydraulic proportional valve in real time to reduce the deviation between the actual displacement and the theoretical opening degree. Subsequently, based on the feedback compensation data and combined with the current-opening degree-flow rate three-dimensional mapping relationship table, the flow rate change caused by the opening degree error is traced, and the flow rate deviation value at different times is recorded. Finally, these flow rate deviation values ​​are integrated in chronological order to draw a flow rate fluctuation trend chart that can intuitively show the flow rate fluctuation over time. This chart can clearly reflect the flow rate change pattern before and after compensation and the dynamic response characteristics of the system.

[0070] In one possible implementation, step S400 further includes: Step S410: Analyze the flow fluctuation segments based on the flow fluctuation trend chart and extract the fluctuation feature patterns.

[0071] Step S420: Trigger a timing backtracking command based on the fluctuation characteristic pattern, and perform correlation operation analysis on the hydraulic system through the timing backtracking command to locate the original operation data.

[0072] Step S430: Perform reverse deduction of traffic demand based on the original operation data to generate a set of traffic demand correction factors.

[0073] Step S440: Dynamically weight and fuse the traffic demand parameters using the set of traffic demand correction factors to generate traffic demand optimization parameters.

[0074] Step S450: Reconstruct the initial flow adjustment command based on the flow demand optimization parameters to obtain a regeneration command, execute and verify the regeneration command, and determine the flow adjustment command.

[0075] Specifically, taking the traffic fluctuation trend chart as the analysis object, the sliding window algorithm is used to divide the traffic data in the trend chart into segments, dividing the continuous traffic fluctuations into several segments with similar fluctuation characteristics in chronological order; feature extraction is performed on the traffic data in each segment, and key parameters such as the maximum and minimum values ​​of fluctuation amplitude, the average value of fluctuation frequency, and the duration of fluctuation are calculated; based on the differences in these parameters, different segments are classified into different fluctuation characteristic patterns, such as high-frequency low-amplitude fluctuation pattern, low-frequency high-amplitude fluctuation pattern, periodic fluctuation pattern, etc., thereby completing the accurate identification and extraction of traffic fluctuation characteristics.

[0076] Based on the extracted fluctuation feature pattern, a preset time-series backtracking command is automatically triggered. This command activates the hydraulic system's historical data query mechanism, calling up operation logs, historical pressure data, flow data, and load status data related to the fluctuation feature pattern. Through data association algorithms, this information is analyzed to identify system operation records that correspond to the flow fluctuation segment in time, including electro-hydraulic proportional valve opening adjustment commands and pump operating parameter adjustments. This allows for precise location of the original operation data that caused the fluctuation feature pattern, providing data support for the reverse deduction of subsequent flow demand.

[0077] Using pressure data, flow data, and load status data from the original operational data as input, a flow demand deviation model is constructed based on the least squares inverse deduction algorithm. The residual between the original operational parameters and the theoretical value of flow demand is calculated through this model. Principal component analysis is used to perform feature dimensionality reduction on the residual, extracting three key influencing dimensions: load change, pressure fluctuation, and flow response lag. For each dimension, the gradient descent algorithm is used to iteratively optimize the correction coefficient until the residual converges to a preset threshold. Finally, a set of flow demand correction factors is generated, with load correction factor, pressure correction factor, and flow response correction factor as the core. The values ​​of each factor are normalized and mapped to the interval [-1, 1] to quantify the direction and intensity of correction.

[0078] Based on the set of flow demand correction factors, and combined with the current weights of each parameter in the flow demand parameters, a dynamic weighted algorithm is used to fuse the two. Specifically, according to the numerical value of each factor in the correction factor set (reflecting the urgency and scope of the correction demand), the weight ratio of the corresponding flow demand parameters is adjusted in real time. Parameters with larger deviations are given higher weights to enhance the correction effect, while parameters with smaller deviations are appropriately reduced in weight to maintain system stability. Through this dynamic weighted fusion calculation, the original flow demand parameters are combined with the adjustment effects of the correction factors to generate optimized flow demand parameters that better reflect the actual operating state of the hydraulic system, providing a precise parameter basis for the subsequent reconstruction of adjustment commands.

[0079] Based on the optimized parameters of flow demand, and combined with the pressure-flow characteristic matrix of the hydraulic system and the current-opening-flow mapping relationship of the electro-hydraulic proportional valve, the parameter structure of the initial flow regulation command is reconstructed. Key parameters such as the current timing and pressure regulation threshold of the electro-hydraulic proportional valve are recalculated to generate a regeneration command containing the corrected control logic. Subsequently, the regeneration command is simulated and executed through a virtual channel to obtain the corresponding first flow fluctuation trend. At the same time, the regeneration command is executed in the actual hydraulic system to collect the second flow fluctuation trend. The first flow fluctuation trend and the second flow fluctuation trend are cross-validated in phase. If the fluctuation deviation between the two is within the preset allowable range, the regeneration command is determined as the final flow regulation command for intelligent flow regulation of the hydraulic system.

[0080] In one possible implementation, step S450 further includes: Step S451: Execute the regeneration command based on the virtual channel to perform fluctuation analysis and obtain the first flow fluctuation trend.

[0081] Step S452: Perform fluctuation analysis based on the actual channel execution of the regeneration command to obtain the second flow fluctuation trend.

[0082] Step S453: Perform phase cross-validation based on the first flow fluctuation trend and the second flow fluctuation trend to generate the flow adjustment command.

[0083] Specifically, a regeneration command is loaded into a virtual channel, and the execution process of the regeneration command is simulated through a digital twin model of the hydraulic system. This model accurately reproduces the opening characteristics of the electro-hydraulic proportional valve, the pressure loss of the hydraulic pipeline, and the dynamic response of the system load. During the simulation, virtual flow data is collected at preset time intervals, and the data is processed by multi-band noise reduction to eliminate simulation error interference. Then, the fluctuation amplitude, frequency, and phase changes of the flow data over time are analyzed to draw a continuous flow fluctuation curve, i.e., the first flow fluctuation trend. This trend can reflect the flow regulation effect of the regeneration command in an ideal environment without physical interference.

[0084] A regeneration command is loaded into the physical channel of the actual hydraulic system, controlling the electro-hydraulic proportional valve to adjust its opening according to the command. At the same time, the actual flow data is collected in real time by multi-source flow sensors deployed in the system. The collected flow data is filtered to remove noise caused by factors such as pipeline vibration and electromagnetic interference, retaining the true flow change information. Then, the fluctuation of the processed flow data in different time periods is analyzed, and characteristic parameters such as the peak value, valley value, period and duration of the fluctuation are recorded. Based on these parameters, a flow fluctuation curve that reflects the actual execution effect is plotted, namely the second flow fluctuation trend. This trend intuitively reflects the flow adjustment response of the regeneration command under real working conditions.

[0085] The first and second flow fluctuation trends are compared on the same time axis. The time difference between the peak and trough of the fluctuation is calculated using a phase analysis algorithm to determine the phase deviation value. At the same time, the difference in fluctuation amplitude and frequency consistency of the two are analyzed to evaluate the degree of consistency between the virtual and actual flow fluctuations. If the phase deviation, amplitude deviation, and frequency difference are all within the preset threshold range, the regeneration command is determined to have passed the verification and is directly identified as a flow regulation command. If there is a deviation that exceeds the threshold, a correction coefficient is generated based on the deviation analysis results, and the regeneration command is adjusted accordingly and then verified again until a flow regulation command that meets the accuracy requirements is obtained.

[0086] Example 2, based on the same inventive concept as the intelligent hydraulic control method for flow regulation in the foregoing examples, such as... Figure 2 As shown, this application provides an intelligent hydraulic control system for flow regulation. The system and method embodiments in this application are based on the same inventive concept. The system includes: The dynamic flow analysis module 10 is used to perform real-time sensing based on the hydraulic system, and to perform dynamic flow analysis based on the multi-source sensor dataset to obtain a set of flow demand parameters.

[0087] The adjustment command generation module 20 is used to perform flow and pressure analysis on the hydraulic system according to the flow demand parameters, and to generate an initial flow adjustment command by superimposing the data based on the pressure analysis results.

[0088] The feedback compensation module 30 is used to simulate the execution of the initial flow adjustment command to drive the electro-hydraulic proportional valve to adjust the opening, perform feedback compensation based on the opening adjustment result, and draw a flow fluctuation trend diagram.

[0089] The intelligent flow regulation module 40 is used to perform adjustment backtracking according to the flow fluctuation trend chart, perform data closed-loop update and optimization of the flow demand parameters based on the backtracking data, generate flow demand optimization parameters to correct the initial flow regulation command, and determine the flow regulation command to perform intelligent flow regulation of the hydraulic system.

[0090] Furthermore, the system is also used to implement the following functions: Multi-source sensor arrays deployed within the hydraulic system are used for multi-dimensional sensing to obtain pressure data, flow data, and load status data. Based on the pressure data, frequency adjustment is performed to obtain pressure pulsation data. Based on the flow data, multi-band noise reduction is performed to obtain instantaneous flow data. Based on the load status data, filtering is performed to obtain hydraulic actuation displacement data. The pressure pulsation data and the instantaneous flow data are coupled and analyzed according to the load change gradient of the hydraulic actuation displacement data to determine the coupling coefficient between the load change gradient and the pressure-flow rate. Based on the coupling coefficient, the flow demand of the hydraulic system is predicted to determine the flow demand parameter set.

[0091] Furthermore, the system is also used to implement the following functions: The flow demand parameter set and the pressure data are dynamically coupled and analyzed to generate a pressure-flow feature matrix; the pressure fluctuation anomaly analysis is performed on the pressure-flow feature matrix to extract the pressure fluctuation suppression coefficient; the flow change anomaly analysis is performed on the pressure-flow feature matrix to determine the flow compensation gradient coefficient; the pressure fluctuation suppression coefficient and the flow compensation gradient coefficient are superimposed to generate an anti-disturbance flow benchmark value and a dynamic compensation amount; the anti-disturbance flow benchmark value and the dynamic compensation amount are fused to generate the initial flow adjustment command.

[0092] Furthermore, the system is also used to implement the following functions: Based on the flow demand parameters, the hydraulic system is analyzed to determine the basic flow rate, the compensation flow rate, and the flow increment. Based on the pressure pulsation data, the hydraulic system is analyzed to determine the pump outlet pressure, the actuator inlet pressure, and the return oil back pressure. The basic flow rate and the pump outlet pressure are correlated to calculate the steady-state pressure margin data. The compensation flow rate and the actuator inlet pressure are matched to determine the pressure-flow compensation mapping relationship. The flow increment value and the return oil back pressure value are time-series aligned to establish a back pressure influence factor. Based on the steady-state pressure margin data, the pressure-flow compensation mapping relationship, and the back pressure influence factor, the pressure-flow feature matrix is ​​constructed.

[0093] Furthermore, the system is also used to implement the following functions: A three-dimensional coordinate system is constructed, and the steady-state pressure margin data is mapped to the three-dimensional coordinate system according to the pressure-flow compensation mapping relationship, and the real-time pressure data points are marked; the real-time pressure data points are associated with the flow demand parameter set according to the back pressure influence factor, and the three-dimensional coordinate system is interpolated and filled according to the association result to construct the pressure-flow feature matrix.

[0094] Furthermore, the system is also used to implement the following functions: A three-dimensional mapping table of current-opening-flow rate for the electro-hydraulic proportional valve is established. The initial flow rate adjustment command is loaded and decomposed into a current time sequence. The electro-hydraulic proportional valve is driven according to the current time sequence to simulate and record the changes in the valve core movement trajectory, generating a virtual opening curve. The actual valve core displacement feedback signal of the electro-hydraulic proportional valve is collected, and the actual valve core displacement feedback signal is compared with the virtual opening curve in real time to calculate the opening following error. Dynamic compensation is performed based on the opening following error to generate feedback compensation data. Flow rate change is traced based on the feedback compensation data, and the flow rate fluctuation trend chart is plotted.

[0095] Furthermore, the system is also used to implement the following functions: Based on the flow fluctuation trend chart, flow fluctuation segment analysis is performed to extract fluctuation feature patterns. A time-series backtracking command is triggered according to the fluctuation feature patterns, and the hydraulic system is analyzed for related operations using the time-series backtracking command to locate the original operation data. The flow demand is then reverse-engineered according to the original operation data to generate a flow demand correction factor set. The flow demand correction factor set is dynamically weighted and fused with the flow demand parameters to generate optimized flow demand parameters. Based on the optimized flow demand parameters, the initial flow adjustment command is reconstructed to obtain a regeneration command. The regeneration command is then executed and verified to determine the flow adjustment command.

[0096] Furthermore, the system is also used to implement the following functions: Fluctuation analysis is performed based on the regeneration command executed through the virtual channel to obtain a first flow fluctuation trend; fluctuation analysis is performed based on the regeneration command executed through the actual channel to obtain a second flow fluctuation trend; phase cross-validation is performed based on the first flow fluctuation trend and the second flow fluctuation trend to generate the flow adjustment command.

[0097] Example 3: Based on the same inventive concept as the intelligent hydraulic control method for flow regulation in the foregoing examples, this example provides a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the intelligent hydraulic control method for flow regulation in this application. The processor executes the software programs, instructions, and modules stored in the memory to perform various functional applications and data processing of the computer device, thereby realizing the aforementioned intelligent hydraulic control method for flow regulation.

[0098] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0099] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0100] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A method of flow-regulated intelligent hydraulic control, characterized in that The method comprises: Real-time sensing based on the hydraulic system, dynamic flow analysis based on the multi-source sensing data set, and obtaining the flow demand parameter set; Flow pressure analysis of the hydraulic system according to the flow demand parameter, data superposition according to the pressure analysis result, and generating the flow initial adjustment instruction; Simulating the execution of the flow initial adjustment instruction to drive the electro-hydraulic proportional valve to adjust the opening, feeding back and compensating according to the opening adjustment result, and drawing a flow fluctuation trend chart; According to the flow fluctuation trend chart, backtracking adjustment is performed, the flow demand parameter is updated and optimized through data closed loop according to the backtracking data, the flow demand optimization parameter is generated to modify the flow initial adjustment instruction, and the flow adjustment instruction is determined to intelligently adjust the flow of the hydraulic system.

2. The flow-regulated, smart hydraulic control method of claim 1, wherein, Real-time sensing based on the hydraulic system, dynamic flow analysis based on the multi-source sensing data set, and obtaining the flow demand parameter set, the method comprising: Multi-dimensional sensing based on the multi-source sensor array deployed in the hydraulic system, obtaining pressure data, flow data, and load state data; Frequency adjustment based on the pressure data, obtaining pressure pulsation data; Multi-band denoising based on the flow data, obtaining instantaneous flow data; Filtering based on the load state data, obtaining hydraulic execution displacement data; Coupling analysis of the pressure pulsation data and the instantaneous flow data according to the load change gradient of the hydraulic execution displacement data, determining the coupling coefficient of the load change gradient and the pressure-flow; Flow demand prediction of the hydraulic system according to the coupling coefficient, determining the flow demand parameter set.

3. The flow-regulated, smart hydraulic control method of claim 2, wherein, Flow pressure analysis of the hydraulic system according to the flow demand parameter, data superposition according to the pressure analysis result, and generating the flow initial adjustment instruction, the method comprising: Dynamic coupling analysis of the flow demand parameter set and the pressure data, generating a pressure-flow characteristic matrix; Pressure fluctuation anomaly analysis of the pressure-flow characteristic matrix, extracting a pressure fluctuation suppression coefficient; Flow change anomaly analysis of the pressure-flow characteristic matrix, determining a flow compensation gradient coefficient; Data superposition operation according to the pressure fluctuation suppression coefficient and the flow compensation gradient coefficient, generating an anti-interference flow reference value and a dynamic compensation amount; Data fusion of the anti-interference flow reference value and the dynamic compensation amount, generating the flow initial adjustment instruction.

4. The flow-regulated, smart hydraulic control method of claim 3, wherein, Dynamic coupling analysis of the flow demand parameter set and the pressure data, generating a pressure-flow characteristic matrix, the method comprising: Analyzing the hydraulic system based on the flow demand parameter, determining a basic flow value, a compensation flow value, and a flow increment value; Analyzing the hydraulic system based on the pressure pulsation data, determining a pump outlet pressure value, an actuator inlet pressure value, and a back oil back pressure value; Associating the basic flow value with the pump outlet pressure value, calculating steady-state pressure margin data; Matching the compensation flow value with the actuator inlet pressure value, determining a pressure-flow compensation mapping relationship; Time sequence alignment of the flow increment value and the back oil back pressure value, establishing a back pressure influence factor; constructing the pressure-flow characteristic matrix based on the steady-state pressure margin data, the pressure-flow compensation mapping relationship, and the back pressure influence factor.

5. The flow-regulated, smart hydraulic control method of claim 4, wherein, constructing the pressure-flow characteristic matrix based on the steady-state pressure margin data, the pressure-flow compensation mapping relationship, and the back pressure influence factor, the method comprising: constructing a three-dimensional coordinate system, mapping the steady-state pressure margin data to the three-dimensional coordinate system according to the pressure-flow compensation mapping relationship, and marking real-time pressure data points; associating the real-time pressure data points with the flow demand parameter set according to the back pressure influence factor, interpolating and filling the three-dimensional coordinate system according to the association result, and constructing the pressure-flow characteristic matrix.

6. The flow-regulated, smart hydraulic control method of claim 1, wherein, simulating the execution of the flow initial adjustment instruction to drive the electro-hydraulic proportional valve to adjust the opening, performing feedback compensation according to the opening adjustment result, and drawing a flow fluctuation trend graph, the method comprising: establishing a current-opening-flow three-dimensional mapping relationship table of the electro-hydraulic proportional valve, loading the flow initial adjustment instruction, and decomposing the flow initial adjustment instruction into a current time sequence; simulating driving the electro-hydraulic proportional valve according to the current time sequence to record changes in the spool movement trajectory, and generating a virtual opening curve; collecting actual spool displacement feedback signals of the electro-hydraulic proportional valve, comparing the actual spool displacement feedback signals with the virtual opening curve in real time, and calculating opening following errors; performing dynamic compensation based on the opening following errors, generating feedback compensation data, tracing flow changes according to the feedback compensation data, and drawing the flow fluctuation trend graph.

7. The flow-regulated, smart hydraulic control method of claim 1, wherein, performing adjustment backtracking according to the flow fluctuation trend graph, updating and optimizing the flow demand parameters according to the backtracking data to generate flow demand optimization parameters, correcting the flow initial adjustment instruction with the flow demand optimization parameters, and determining a flow adjustment instruction, the method comprising: performing flow fluctuation section analysis based on the flow fluctuation trend graph, and extracting fluctuation characteristic patterns; triggering a time sequence backtracking instruction according to the fluctuation characteristic patterns, performing associated operation analysis on the hydraulic system through the time sequence backtracking instruction, and locating original operation data; performing reverse deduction of flow demand according to the original operation data, and generating a flow demand correction factor set; dynamically weighting and fusing the flow demand correction factor set to the flow demand parameters to generate flow demand optimization parameters; reconstructing the flow initial adjustment instruction based on the flow demand optimization parameters to obtain a regenerated instruction, performing execution verification on the regenerated instruction, and determining a flow adjustment instruction.

8. The flow-regulated, smart hydraulic control method of claim 7, wherein, performing execution verification on the regenerated instruction to determine a flow adjustment instruction, the method comprising: performing fluctuation analysis on the regenerated instruction based on a virtual channel to obtain a first flow fluctuation trend; performing fluctuation analysis on the regenerated instruction based on an actual channel to obtain a second flow fluctuation trend; performing phase cross verification according to the first flow fluctuation trend and the second flow fluctuation trend to generate the flow adjustment instruction.

9. A flow-regulated smart hydraulic control system, characterized by The system is used to implement the intelligent hydraulic control method for flow adjustment according to any one of claims 1-8, and the system comprises: A dynamic flow analysis module is configured to perform real-time sensing based on the hydraulic system, perform dynamic flow analysis based on a multi-source sensing data set, and obtain a flow demand parameter set; An adjustment instruction generation module is configured to perform flow pressure analysis on the hydraulic system according to the flow demand parameters, perform data superposition according to a pressure analysis result, and generate a flow initial adjustment instruction; A feedback compensation module is configured to simulate execution of the flow initial adjustment instruction to drive an electro-hydraulic proportional valve to perform opening degree adjustment, perform feedback compensation according to an opening degree adjustment result, and draw a flow fluctuation trend graph; A flow intelligent adjustment module is configured to perform adjustment backtracking according to the flow fluctuation trend graph, perform data closed-loop update optimization on the flow demand parameters according to backtracking data, generate flow demand optimization parameters to correct the flow initial adjustment instruction, determine a flow adjustment instruction, and perform flow intelligent adjustment on the hydraulic system.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the intelligent hydraulic control method for flow adjustment according to any one of claims 1-8.

Images