Hydraulic pump power self-adaptive control method and system based on load dynamic perception

Abstract

The application discloses a hydraulic pump power self-adaptive control method and system based on load dynamic perception, relates to the related technical field of hydraulic pumps, and comprises the following steps: arranging pressure sensors, flow sensors and displacement sensors in a hydraulic pump system and performing long-time sequence monitoring; performing interactive fusion analysis on the physical behavior characteristics of the hydraulic pump; performing load scene identification on the hydraulic pump; performing interactive guided prediction and matching a hydraulic pump power self-adaptive control template; acquiring real-time pressure monitoring data sequences, real-time flow monitoring sequences and real-time load monitoring data sequences; performing self-adaptive correction on the hydraulic pump power self-adaptive control template, determining a real-time hydraulic pump power self-adaptive control scheme and performing power self-adaptive control. The technical problems of insufficient multi-source information fusion, low load scene identification accuracy and poor real-time adaptability of the prior art are solved, and the technical effects of accurately matching the hydraulic pump power, dynamically optimizing energy efficiency and improving the control response speed are achieved.

Description

Technical Field

[0001] This application relates to the technical field of hydraulic pumps, specifically to a hydraulic pump power adaptive control method and system based on load dynamic sensing. Background Technology

[0002] As the core power unit of irrigation systems, the power control of hydraulic pumps directly affects water resource utilization efficiency, system energy efficiency, stability, and reliability. Traditional hydraulic pump power control often adopts fixed displacement or pressure-flow regulation strategies based on fixed thresholds, which are difficult to cope with the complex and variable load conditions in irrigation operations, such as differences in water requirements among different crop types, changes in pipeline resistance, and terrain undulations. This leads to energy waste, unbalanced system power matching, or lag in response. In large-scale irrigation systems, hydraulic pumps often face dynamically changing load scenarios. For example, the required output pressure and flow rate of hydraulic pumps vary significantly under different modes such as sprinkler irrigation, drip irrigation, or canal water conveyance. At the same time, soil moisture, climate conditions, and crop growth stages further exacerbate the time-varying and uncertain nature of the load. Existing control methods lack the ability to perceive and dynamically analyze the load status in real time, and rely solely on feedback control based on local parameters. This makes it difficult to achieve precise power adaptation, resulting in excessive energy consumption at low loads and insufficient response at high loads. Furthermore, the methods fail to fully explore the interaction characteristics between multi-source data and the coupling relationship with load scenarios, limiting the adaptability and robustness of the control strategy.

[0003] Therefore, current technologies suffer from technical problems such as insufficient fusion of multi-source information, low accuracy in identifying load scenarios, and poor real-time performance of adaptive control. Summary of the Invention

[0004] This application provides a hydraulic pump power adaptive control method and system based on load dynamic perception, which solves the technical problems of insufficient multi-source information fusion, low load scenario identification accuracy and poor real-time performance of adaptive control in the prior art, and achieves the technical effects of accurately matching hydraulic pump power, dynamically optimizing energy efficiency and improving control response speed.

[0005] This application provides a hydraulic pump power adaptive control method based on load dynamic perception. The method includes: deploying pressure sensors, flow sensors, and displacement sensors in a hydraulic pump system, and using the pressure sensors, flow sensors, and displacement sensors to perform long-term time-series monitoring of the hydraulic pump system to determine pressure monitoring data sequences, flow monitoring data sequences, and load monitoring data sequences; performing interactive fusion analysis of hydraulic pump physical behavior characteristics based on the pressure monitoring data sequences and the flow monitoring data sequences to determine hydraulic pump physical behavior fusion characteristics; identifying hydraulic pump load scenarios based on the load monitoring data sequences to determine hydraulic pump load scenario characteristics; interactively guiding prediction of the hydraulic pump physical behavior fusion characteristics based on the hydraulic pump load scenario characteristics, and matching a hydraulic pump power adaptive control template according to the prediction results; using the pressure sensors, flow sensors, and displacement sensors to acquire real-time pressure monitoring data sequences, real-time flow monitoring data sequences, and real-time load monitoring data sequences of the hydraulic pump system; adaptively correcting the hydraulic pump power adaptive control template according to the real-time pressure monitoring data sequences, real-time flow monitoring data sequences, and real-time load monitoring data sequences to determine a real-time hydraulic pump power adaptive control scheme, and performing power adaptive control of the hydraulic pump system according to the real-time hydraulic pump power adaptive control scheme.

[0006] In a possible implementation, the hydraulic pump power adaptive control method based on load dynamic perception further performs the following processing: pre-constructing a physical behavior feature analyzer; calling the physical behavior feature analyzer to perform feature analysis on the pressure monitoring data sequence and the flow monitoring data sequence respectively to determine the pressure monitoring trend features and the flow monitoring trend features; performing feature interaction fusion analysis on the pressure monitoring trend features and the flow monitoring trend features to determine the hydraulic pump physical behavior fusion features.

[0007] In a possible implementation, the hydraulic pump power adaptive control method based on load dynamic perception also performs the following processing: the physical behavior feature analyzer is obtained by supervised training of the framework built on the feedforward neural network using training data, and the physical behavior feature analyzer includes an input layer, a convolutional layer and an output layer.

[0008] In a possible implementation, the hydraulic pump power adaptive control method based on load dynamic perception further performs the following processing: calling an interaction probability analyzer to perform interaction probability analysis on the pressure monitoring trend features and the flow monitoring trend features to obtain an interaction probability set; constructing a feature interaction fusion matrix based on the interaction probability set, and using the feature interaction fusion matrix to perform feature interaction fusion on the pressure monitoring trend features and the flow monitoring trend features respectively to obtain pressure monitoring fusion trend features and flow monitoring fusion trend features; and using the pressure monitoring fusion trend features and flow monitoring fusion trend features as the hydraulic pump physical behavior fusion features.

[0009] In a possible implementation, the hydraulic pump power adaptive control method based on load dynamic perception further performs the following processing: constructing a load scenario library, wherein the load scenario library includes multiple historical load scenario features and multiple historical load monitoring data record templates; matching the load monitoring data sequence with the multiple historical load monitoring data record templates to obtain a matching historical load monitoring data record template, and using the corresponding historical load scenario features as the hydraulic pump load scenario features.

[0010] In a possible implementation, the hydraulic pump power adaptive control method based on load dynamic perception further performs the following processing: acquiring a set of historical load monitoring data records of the hydraulic pump system; dividing the historical load monitoring data record set into similar categories to obtain multiple historical load monitoring data record sets; extracting scene features from the multiple historical load monitoring data record sets to obtain multiple historical load scene features; calculating the mean of the multiple historical load monitoring data record sets to construct multiple historical load monitoring data record templates; and mapping and associating the multiple historical load scene features with the multiple historical load monitoring data record templates to construct a load scene library.

[0011] In a possible implementation, the hydraulic pump power adaptive control method based on load dynamic perception further performs the following processing: using the hydraulic pump load scenario characteristics as constraints, an interactive guided prediction is performed on the fusion characteristics of the hydraulic pump physical behavior using a physical behavior predictor to obtain prediction results; based on the prediction results, hydraulic power adaptive control scheme matching is performed to obtain a set of matching hydraulic power adaptive control schemes; the set of matching hydraulic power adaptive control schemes is filtered to determine the hydraulic power adaptive control template.

[0012] In a possible implementation, the hydraulic pump power adaptive control method based on load dynamic perception further performs the following processing: calculating the mean of the set of matched hydraulic power adaptive control schemes, using it as a screening center, and iteratively screening the set of matched hydraulic power adaptive control schemes based on the screening center to determine the hydraulic power adaptive control template.

[0013] In a possible implementation, the hydraulic pump power adaptive control method based on load dynamic perception also performs the following processing: obtaining a preset feedback window; identifying power fluctuations in the hydraulic pump system within the preset feedback window; and obtaining an early warning command if the power fluctuation identification result exceeds a preset threshold.

[0014] This application also provides a hydraulic pump power adaptive control system based on load dynamic perception. The system includes: a monitoring data sequence determination module, used to deploy pressure sensors, flow sensors, and displacement sensors in the hydraulic pump system, and use these sensors to perform long-term time-series monitoring of the hydraulic pump system to determine pressure monitoring data sequences, flow monitoring data sequences, and load monitoring data sequences; a physical feature fusion analysis module, used to perform interactive fusion analysis of hydraulic pump physical behavior features based on the pressure monitoring data sequences and the flow monitoring data sequences to determine the fused physical behavior features of the hydraulic pump; a load scene identification module, used to identify hydraulic pump load scenes based on the load monitoring data sequences to determine the hydraulic pump load scene characteristics; and interactive guided prediction. The system includes a module for interactively guiding and predicting the physical behavior fusion features of the hydraulic pump based on the load scenario characteristics of the hydraulic pump, and matching the hydraulic pump power adaptive control template according to the prediction results; a real-time monitoring data sequence acquisition module for acquiring real-time pressure monitoring data sequences, real-time flow monitoring data sequences, and real-time load monitoring data sequences of the hydraulic pump system using the pressure sensor, flow sensor, and displacement sensor; and a power adaptive control module for adaptively correcting the hydraulic pump power adaptive control template according to the real-time pressure monitoring data sequences, real-time flow monitoring data sequences, and real-time load monitoring data sequences, determining a real-time hydraulic pump power adaptive control scheme, and performing power adaptive control of the hydraulic pump system according to the real-time hydraulic pump power adaptive control scheme.

[0015] This application proposes a hydraulic pump power adaptive control method and system based on load dynamic perception. The method involves deploying pressure sensors, flow sensors, and displacement sensors in the hydraulic pump system for long-term monitoring; performing interactive fusion analysis of the hydraulic pump's physical behavior characteristics; identifying hydraulic pump load scenarios; performing interactive guided prediction and matching a hydraulic pump power adaptive control template; acquiring real-time pressure monitoring data sequences, real-time flow monitoring data sequences, and real-time load monitoring data sequences; adaptively correcting the hydraulic pump power adaptive control template; determining the real-time hydraulic pump power adaptive control scheme; and performing power adaptive control. This addresses the technical problems of insufficient multi-source information fusion, low load scenario identification accuracy, and poor real-time performance of adaptive control in existing technologies, achieving the technical effects of accurately matching hydraulic pump power, dynamically optimizing energy efficiency, and improving control response speed. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 A schematic flowchart of the hydraulic pump power adaptive control method based on load dynamic sensing provided in the embodiments of this application.

[0018] Figure 2 A schematic diagram of the hydraulic pump power adaptive control system based on load dynamic sensing provided in this application embodiment.

[0019] Explanation of reference numerals in the attached figures: 10 for monitoring data sequence determination module, 20 for physical feature fusion analysis module, 30 for load scenario identification module, 40 for interactive guidance prediction module, 50 for real-time monitoring data sequence acquisition module, and 60 for power adaptive control module. Detailed Implementation

[0020] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below.

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0023] This application provides a hydraulic pump power adaptive control method based on load dynamic sensing, such as... Figure 1 As shown, the method includes:

[0024] Step S100: Install pressure sensors, flow sensors, and displacement sensors in the hydraulic pump system, and use the pressure sensors, flow sensors, and displacement sensors to perform long-term time-series monitoring of the hydraulic pump system to determine the pressure monitoring data sequence, flow monitoring data sequence, and load monitoring data sequence.

[0025] Preferably, by deploying pressure sensors, flow sensors, and displacement sensors in the hydraulic pump system and performing long-term time-series monitoring of the hydraulic pump's operating status, pressure monitoring data sequences, flow monitoring data sequences, and load monitoring data sequences are obtained. Specifically, the pressure sensor is used to monitor the liquid pressure at the hydraulic pump's output end, such as the water pressure in the pipeline, reflecting the system load size; high pressure indicates a large load, and low pressure indicates a small load. The flow sensor is used to measure the liquid flow rate and liquid volume per unit time output by the hydraulic pump, reflecting system requirements such as nozzle opening and closing and pipeline leakage. The displacement sensor is used to monitor the displacement or motion state of the hydraulic actuator, indirectly reflecting the mechanical characteristics of the load, such as the spray arm movement speed and valve opening. Long-term time-series monitoring refers to the sensors continuously collecting data at a fixed sampling frequency to form a continuous data sequence, including pressure monitoring data sequences, flow monitoring data sequences, and load monitoring data sequences. The load monitoring data sequence is the load state calculated by the displacement sensor and other load-related parameters, such as light load, light load, and heavy load.

[0026] Step S200: Based on the pressure monitoring data sequence and the flow monitoring data sequence, perform interactive fusion analysis of the physical behavior characteristics of the hydraulic pump to determine the fusion characteristics of the physical behavior of the hydraulic pump.

[0027] Step S200 further includes step S210, pre-constructing a physical behavior feature analyzer; step S220, calling the physical behavior feature analyzer to perform feature analysis on the pressure monitoring data sequence and the flow monitoring data sequence respectively, and determining pressure monitoring trend features and flow monitoring trend features; step S230, performing feature interaction fusion analysis on the pressure monitoring trend features and flow monitoring trend features, and determining the physical behavior fusion features of the hydraulic pump.

[0028] Preferably, a physical behavior feature analyzer is pre-built based on a feedforward neural network to extract key features of hydraulic pump operation from sensor data. This involves analyzing the temporal variation patterns of pressure and flow data to identify the physical state of the hydraulic pump, such as normal operation, decreased efficiency, or potential faults. The physical behavior feature analyzer is then invoked to perform feature analysis on the pressure monitoring data sequence, extracting pressure monitoring trend features such as pressure fluctuation amplitude, rise / fall slope, and steady-state value. For example, a continuous rise in pressure may indicate nozzle blockage. Similarly, the physical behavior feature analyzer is invoked to perform feature analysis on the flow monitoring data sequence, extracting flow monitoring trend features such as flow stability, instantaneous rate of change, and phase difference with pressure. For instance, a sudden drop in flow accompanied by a rise in pressure may indicate a pipeline leak. Finally, a feature interaction fusion analysis is performed on the pressure and flow monitoring trend features. This involves calculating the correlation strength between pressure and flow features, such as covariance and mutual information, determining the interaction probability, and converting it into a weight matrix. The pressure and flow monitoring trend features are then weighted and fused to obtain the fused physical behavior features of the hydraulic pump.

[0029] Furthermore, step S210 also includes the physical behavior feature analyzer being obtained by supervised training of the framework built on the feedforward neural network using training data. The physical behavior feature analyzer includes an input layer, a convolutional layer, and an output layer.

[0030] Preferably, the physical behavior feature analyzer is based on a framework built on a feedforward neural network and trained through supervised learning. It is used to extract high-order features from the sensor data of the hydraulic pump. Specifically, it is trained using a historical dataset containing pressure and flow sequences and corresponding expert-annotated features. The training process includes forward propagation, where the input data is processed by the network to obtain predicted features, and backpropagation, which adjusts the weights through gradient descent to minimize the error between the predicted and true features. After training, it can automatically extract pressure / flow trend features from new data. The core structure includes an input layer, a convolutional layer, and an output layer. The input layer receives and preprocesses long-term pressure and flow monitoring data sequences, including normalization and sliding window segmentation, dividing the long sequences into fixed-length subsequences. The convolutional layer extracts local spatiotemporal features from the sensor data, such as sudden pressure increases and periodic flow fluctuations. The convolutional kernel slides along the time axis to capture short-term patterns, generating multiple features to represent different behavior patterns. The output layer integrates the local features extracted by the convolutional layer into global trend features, including feature dimensionality compression, generating pressure monitoring trend features and flow monitoring trend features.

[0031] Furthermore, step S210 also includes step S211, calling the interaction probability analyzer to perform interaction probability analysis on the pressure monitoring trend features and the flow monitoring trend features to obtain an interaction probability set; step S212, constructing a feature interaction fusion matrix based on the interaction probability set, and using the feature interaction fusion matrix to perform feature interaction fusion on the pressure monitoring trend features and the flow monitoring trend features respectively to obtain pressure monitoring fusion trend features and flow monitoring fusion trend features; step S213, using the pressure monitoring fusion trend features and flow monitoring fusion trend features as the fusion features of the hydraulic pump's physical behavior.

[0032] Preferably, an interaction probability analyzer is invoked to perform interaction probability analysis on the pressure monitoring trend features and the flow monitoring trend features. The interaction probability analyzer is essentially a similarity calculator, embedding a cosine similarity function to calculate the cosine similarity between the pressure monitoring trend features and the flow monitoring trend features. This cosine similarity represents the directional consistency of the two feature vectors, with a value range of [-1, 1]. The closer the similarity is to 1, the higher the similarity, meaning a higher correlation between the two features and a higher corresponding interaction probability. This yields an interaction probability set containing multiple similarity scores. The interaction probability set is then normalized, and an M×N empty matrix is ​​constructed, where N is the pressure feature dimension and M is the flow feature dimension. The normalized pressure features are then compared with the flow features... The similarity of features is used as matrix elements to fill an empty matrix to obtain a feature interaction fusion matrix. Finally, the feature interaction fusion matrix is ​​used to perform feature interaction fusion on the pressure monitoring trend features and the flow monitoring trend features respectively. That is, the implicit information in the original features is enhanced based on the convolutional neural network, including weighted summation of the pressure feature vector and the row vector of the matrix, and similarly weighted summation of the flow features using the column vector of the matrix, to output the pressure monitoring fusion trend features and the flow monitoring fusion trend features. Finally, the pressure monitoring fusion trend features and the flow monitoring fusion trend features are concatenated and fused to obtain the hydraulic pump physical behavior fusion features, which characterize the comprehensive state of the hydraulic pump, and thus quantify the dynamic relationship between hydraulic pump pressure and flow, thereby ensuring the reliability and energy efficiency of the hydraulic system.

[0033] Step S300: Based on the load monitoring data sequence, identify the hydraulic pump load scenario and determine the characteristics of the hydraulic pump load scenario.

[0034] Step S300 further includes step S310, constructing a load scenario library, wherein the load scenario library includes multiple historical load scenario features and multiple historical load monitoring data record templates; step S320, matching the load monitoring data sequence with the multiple historical load monitoring data record templates to obtain a matching historical load monitoring data record template, and using the corresponding historical load scenario features as the hydraulic pump load scenario features.

[0035] Preferably, a load scenario library is constructed using multiple historical load scenario features and multiple historical load monitoring data record templates. The historical load scenario features refer to typical working condition feature vectors extracted from the historical operating data of the hydraulic pump, such as "light load constant speed" and "heavy load impact". The historical load monitoring data record templates are standardized data patterns corresponding to the scenario features, such as the time sequence patterns of pressure, flow rate, and displacement. Then, the load monitoring data sequence is matched with multiple historical load monitoring data record templates. For example, dynamic time warping or Euclidean distance is used to calculate the similarity between the load monitoring data sequence and each historical load monitoring data record template. The historical load monitoring data record templates with high similarity are output as the matching historical load monitoring data record templates, and their corresponding historical load scenario features are used as the hydraulic pump load scenario features under the current operating conditions.

[0036] Furthermore, step S310 also includes step S311, obtaining a set of historical load monitoring data records for the hydraulic pump system; step S312, dividing the set of historical load monitoring data records into similar categories to obtain multiple sets of historical load monitoring data records; step S313, extracting scene features from the multiple sets of historical load monitoring data records to obtain multiple historical load scene features; step S314, calculating the mean of the multiple sets of historical load monitoring data records to construct multiple historical load monitoring data record templates; and step S315, mapping and associating the multiple historical load scene features with the multiple historical load monitoring data record templates to construct a load scene library.

[0037] Preferably, a historical load monitoring data record set of the hydraulic pump system is obtained, which is the long-term accumulated sensor data of the hydraulic pump under different operating conditions, including pressure sensor data, flow sensor data, displacement sensor data, as well as timestamps, environmental parameters, etc. Then, K-means clustering is used to classify the historical load monitoring data record set into similar categories, such as light load, heavy load, transient impact, etc., to obtain multiple historical load monitoring data record sets. Then, scene features are extracted from multiple historical load monitoring data record sets, including extracting statistical features such as mean and variance of various types of data, pressure wave, etc. Behavioral characteristics such as dynamic range, average flow rate, displacement change rate, load change rate, and flow-pressure coupling coefficient are used to obtain multiple historical load scenario characteristics. Then, the average value of multiple historical load monitoring data record sets is calculated to construct multiple historical load monitoring data record templates. Finally, the multiple historical load scenario characteristics are mapped and associated with the multiple historical load monitoring data record templates to form a structured query library, namely the load scenario library. When new data is input, the template can be quickly matched and the associated scenario characteristics can be called to realize the working condition identification. For example, if a heavy load template is matched, the high power mode is automatically switched, thereby improving the power control response speed and energy efficiency of the hydraulic system.

[0038] Step S400: Based on the hydraulic pump load scenario characteristics, perform interactive guided prediction on the physical behavior fusion characteristics of the hydraulic pump, and match the hydraulic pump power adaptive control template according to the prediction results.

[0039] Step S400 further includes step S410, using the hydraulic pump load scenario characteristics as constraints, and using a physical behavior predictor to interactively guide the prediction of the fusion characteristics of the hydraulic pump physical behavior to obtain a prediction result; step S420, performing hydraulic power adaptive control scheme matching based on the prediction result to obtain a set of matching hydraulic power adaptive control schemes; step S430, filtering the set of matching hydraulic power adaptive control schemes to determine the hydraulic power adaptive control template.

[0040] Preferably, the characteristics of the hydraulic pump load scenario are used as constraints to limit the prediction range, ensuring that the prediction results conform to the physical laws of the current operating conditions. A physical behavior predictor is used to interactively guide the prediction of the fused physical behavior characteristics of the hydraulic pump. This physical behavior predictor is a prediction model built based on a neural network model or an LSTM time series model, used to analyze the evolution trend of the fused physical behavior characteristics under the current load scenario, and can obtain short-term state predictions and key indicator predictions. These are used as prediction results, which may represent the possible states of pressure and flow under the current load scenario. Based on the prediction results, a hydraulic power adaptive control scheme matching is performed. This involves selecting control strategies that meet the conditions from a pre-set scheme library to obtain multiple matching hydraulic power adaptive control schemes, forming a set of matching hydraulic power adaptive control schemes. Finally, based on the priority of safety > energy efficiency > response speed, the set of matching hydraulic power adaptive control schemes is further filtered, and the optimal solution in the set is calculated, ultimately determining the hydraulic power adaptive control template.

[0041] Furthermore, step S430 also includes calculating the mean of the set of matching hydraulic power adaptive control schemes, using it as a screening center, and iteratively screening the set of matching hydraulic power adaptive control schemes based on the screening center to determine the hydraulic power adaptive control template.

[0042] Preferably, the set of matching hydraulic power adaptive control schemes is screened using a mean-shift algorithm. The mean-shift algorithm is a clustering algorithm that iteratively calculates the density gradient of data points, shifting towards local density maxima until it converges to the center of the data distribution. The set of control schemes is considered as points in a multi-dimensional space, with dimensions including power adjustment range and pressure limit values. The mean-shift algorithm finds the densest region, representing the optimal solution agreed upon by most schemes. Specifically, the mean of the set of matching hydraulic power adaptive control schemes is calculated and used as the iteration starting point (i.e., the screening center). Based on the screening center, the set of matching hydraulic power adaptive control schemes is iteratively screened, including defining the neighboring schemes with the current center point as the center and setting a radius (e.g., an Euclidean distance threshold); calculating the mean of all schemes in the neighboring region as the new center point; repeating the shift process until the change in the center point is less than the threshold, at which point the iteration stops, and the convergence point is finally output as the hydraulic power adaptive control template.

[0043] Step S500: Using the pressure sensor, flow sensor, and displacement sensor, acquire the real-time pressure monitoring data sequence, real-time flow monitoring data sequence, and real-time load monitoring data sequence of the hydraulic pump system.

[0044] Preferably, a pressure sensor is used to detect the liquid pressure at the outlet of the hydraulic pump in real time, reflecting the load intensity of the hydraulic pump system. A continuous rise in pressure may indicate a blockage. A flow sensor is used to monitor the volumetric flow rate of the liquid in the hydraulic circuit, characterizing the functional requirements of the hydraulic pump system. A decrease in flow rate may indicate a leak. A displacement sensor is used to track the displacement of the actuator (such as the piston of a hydraulic cylinder), indirectly reflecting changes in mechanical load. An acceleration in displacement may indicate a reduction in load. Data from the three types of sensors are collected synchronously at the same sampling frequency to form a time-aligned monitoring data sequence, including a real-time pressure monitoring data sequence, a real-time flow monitoring data sequence, and a real-time load monitoring data sequence.

[0045] Step S600: Adaptively modify the hydraulic pump power adaptive control template according to the real-time pressure monitoring data sequence, real-time flow monitoring data sequence and real-time load monitoring data sequence, determine the real-time hydraulic pump power adaptive control scheme, and perform power adaptive control on the hydraulic pump system according to the real-time hydraulic pump power adaptive control scheme.

[0046] Preferably, the pre-generated hydraulic pump power adaptive control template is dynamically fine-tuned using real-time sensor data streams to ensure that the hydraulic pump output power always precisely matches the current load demand. Specifically, the real-time pressure monitoring data sequence, real-time flow monitoring data sequence, and real-time load monitoring data sequence are compared with the expected values ​​of the hydraulic pump power adaptive control template to detect deviations in the hydraulic pump system load parameters. Then, the hydraulic pump power adaptive control template is adaptively corrected, i.e., the parameters of the hydraulic pump power adaptive control template are dynamically corrected using PID algorithms or fuzzy logic, such as adjusting the power increase from 8% to 10%, thereby determining the real-time hydraulic pump power adaptive control scheme. Finally, the hydraulic pump system is subjected to power adaptive control based on the real-time hydraulic pump power adaptive control scheme. This may include a PLC or embedded controller receiving the real-time hydraulic pump power adaptive control scheme and adjusting the frequency converter (motor speed) and proportional valve (flow rate) of the hydraulic pump system to achieve power adaptive control of the hydraulic pump system.

[0047] Furthermore, step S600 also includes step S610, obtaining a preset feedback window; step S620, performing power fluctuation identification on the hydraulic pump system in the preset feedback window, and obtaining a warning command if the power fluctuation identification result exceeds a preset threshold.

[0048] Preferably, a fixed-duration time window is set as a preset feedback window for periodically evaluating the power stability of the hydraulic pump. Then, power fluctuations in the hydraulic pump system are identified within the preset feedback window, i.e., the standard deviation of the power sequence within the window is calculated to obtain the power fluctuation amplitude within the window. The preset threshold is the power fluctuation range set based on historical operating data or equipment safety limits. If the power fluctuation identification result exceeds the preset threshold, it is judged as an abnormal power fluctuation and an early warning command is triggered. The early warning type may include a level one early warning, where the power fluctuation exceeds the threshold but is not dangerous, the log is recorded, and the operator is prompted to check; a level two early warning, where the power fluctuation continues to worsen, the power is automatically reduced or the machine is shut down; for example, if the power fluctuation of the hydraulic pump system exceeds the limit within 10 seconds, it automatically switches to a safe mode and alarms.

[0049] In the above text, refer to Figure 1 The adaptive control method for hydraulic pump power based on dynamic load sensing according to embodiments of the present invention is described in detail. Next, reference will be made to... Figure 2 A hydraulic pump power adaptive control system based on load dynamic sensing according to an embodiment of the present invention is described.

[0050] The hydraulic pump power adaptive control system based on load dynamic perception according to embodiments of the present invention is used to solve the technical problems of insufficient multi-source information fusion, low load scene identification accuracy, and poor real-time performance of adaptive control in the prior art, achieving the technical effects of accurately matching hydraulic pump power, dynamically optimizing energy efficiency, and improving control response speed. Figure 2 As shown, the hydraulic pump power adaptive control system based on load dynamic perception includes: a monitoring data sequence determination module 10, a physical feature fusion analysis module 20, a load scene recognition module 30, an interactive guidance prediction module 40, a real-time monitoring data sequence acquisition module 50, and a power adaptive control module 60.

[0051] The monitoring data sequence determination module 10 is used to deploy pressure sensors, flow sensors, and displacement sensors in the hydraulic pump system, and use these sensors to perform long-term time-series monitoring of the hydraulic pump system to determine pressure monitoring data sequences, flow monitoring data sequences, and load monitoring data sequences. The physical feature fusion analysis module 20 is used to perform interactive fusion analysis of the hydraulic pump's physical behavior characteristics based on the pressure monitoring data sequences and the flow monitoring data sequences to determine the fused physical behavior characteristics of the hydraulic pump. The load scene identification module 30 is used to identify hydraulic pump load scenes based on the load monitoring data sequences to determine the hydraulic pump load scene characteristics. The interactive guidance prediction module 40 is used to predict the hydraulic pump load scenes based on the load scenes. The system uses features to interactively guide and predict the physical behavior of the hydraulic pump, and matches the hydraulic pump power adaptive control template based on the prediction results. A real-time monitoring data sequence acquisition module 50 is used to acquire real-time pressure monitoring data sequences, real-time flow monitoring data sequences, and real-time load monitoring data sequences of the hydraulic pump system using the pressure sensor, flow sensor, and displacement sensor. A power adaptive control module 60 is used to adaptively correct the hydraulic pump power adaptive control template based on the real-time pressure monitoring data sequences, real-time flow monitoring data sequences, and real-time load monitoring data sequences, determine a real-time hydraulic pump power adaptive control scheme, and perform power adaptive control of the hydraulic pump system based on the real-time hydraulic pump power adaptive control scheme.

[0052] The specific configuration of the physical feature fusion analysis module 20 will be described in detail below. The physical feature fusion analysis module 20 further includes: pre-constructing a physical behavior feature analyzer; calling the physical behavior feature analyzer to perform feature analysis on the pressure monitoring data sequence and the flow monitoring data sequence respectively, to determine pressure monitoring trend features and flow monitoring trend features; and performing feature interaction fusion analysis on the pressure monitoring trend features and flow monitoring trend features to determine the physical behavior fusion features of the hydraulic pump.

[0053] The specific configuration of the physical feature fusion analysis module 20 will be described in detail below. The physical feature fusion analysis module 20 further includes: the physical behavior feature analyzer is obtained by supervised training of a framework built on a feedforward neural network using training data; the physical behavior feature analyzer includes an input layer, a convolutional layer, and an output layer.

[0054] The specific configuration of the physical feature fusion analysis module 20 will be described in detail below. The physical feature fusion analysis module 20 further includes: calling an interaction probability analyzer to perform interaction probability analysis on the pressure monitoring trend features and the flow monitoring trend features to obtain an interaction probability set; constructing a feature interaction fusion matrix based on the interaction probability set, and using the feature interaction fusion matrix to perform feature interaction fusion on the pressure monitoring trend features and the flow monitoring trend features respectively to obtain pressure monitoring fusion trend features and flow monitoring fusion trend features; and using the pressure monitoring fusion trend features and flow monitoring fusion trend features as the physical behavior fusion features of the hydraulic pump.

[0055] The specific configuration of the load scene identification module 30 will be described in detail below. The load scene identification module 30 further includes: constructing a load scene library, wherein the load scene library includes multiple historical load scene features and multiple historical load monitoring data record templates; matching the load monitoring data sequence with the multiple historical load monitoring data record templates to obtain a matching historical load monitoring data record template, and using the corresponding historical load scene features as the hydraulic pump load scene features.

[0056] The specific configuration of the load scene identification module 30 will be described in detail below. The load scene identification module 30 further includes: acquiring a set of historical load monitoring data records of the hydraulic pump system; dividing the historical load monitoring data record set into similar categories to obtain multiple historical load monitoring data record sets; extracting scene features from the multiple historical load monitoring data record sets to obtain multiple historical load scene features; calculating the mean of the multiple historical load monitoring data record sets to construct multiple historical load monitoring data record templates; and mapping and associating the multiple historical load scene features with the multiple historical load monitoring data record templates to construct a load scene library.

[0057] The specific configuration of the interactive guidance prediction module 40 will be described in detail below. The interactive guidance prediction module 40 further includes: using the hydraulic pump load scenario characteristics as constraints, performing interactive guidance prediction on the fusion characteristics of the hydraulic pump's physical behavior using a physical behavior predictor to obtain prediction results; performing hydraulic power adaptive control scheme matching based on the prediction results to obtain a set of matching hydraulic power adaptive control schemes; and filtering the set of matching hydraulic power adaptive control schemes to determine a hydraulic power adaptive control template.

[0058] The specific configuration of the interactive guidance prediction module 40 will be described in detail below. The interactive guidance prediction module 40 further includes: calculating the mean of the set of matched hydraulic power adaptive control schemes, using it as a screening center, and iteratively screening the set of matched hydraulic power adaptive control schemes based on the screening center to determine the hydraulic power adaptive control template.

[0059] The specific configuration of the power adaptive control module 60 will be described in detail below. The power adaptive control module 60 further includes: acquiring a preset feedback window; identifying power fluctuations in the hydraulic pump system within the preset feedback window; and acquiring a warning command if the power fluctuation identification result exceeds a preset threshold.

[0060] The hydraulic pump power adaptive control system based on load dynamic perception provided in the embodiments of the present invention can execute the hydraulic pump power adaptive control method based on load dynamic perception provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0061] Although this application makes various references to certain modules in the system according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0062] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A hydraulic pump power adaptive control method based on load dynamic sensing, characterized in that, The method includes: Pressure sensors, flow sensors, and displacement sensors are installed in the hydraulic pump system, and the hydraulic pump system is monitored over a long period of time using the pressure sensors, flow sensors, and displacement sensors to determine the pressure monitoring data sequence, flow monitoring data sequence, and load monitoring data sequence. Based on the pressure monitoring data sequence and the flow monitoring data sequence, an interactive fusion analysis of the physical behavior characteristics of the hydraulic pump is performed to determine the fusion characteristics of the physical behavior of the hydraulic pump. Based on the load monitoring data sequence, hydraulic pump load scenarios are identified to determine the characteristics of hydraulic pump load scenarios. Based on the characteristics of the hydraulic pump load scenario, the physical behavior fusion characteristics of the hydraulic pump are interactively guided to predict, and the hydraulic pump power adaptive control template is matched according to the prediction results. Using the pressure sensor, flow sensor, and displacement sensor, the real-time pressure monitoring data sequence, real-time flow monitoring data sequence, and real-time load monitoring data sequence of the hydraulic pump system are obtained; The hydraulic pump power adaptive control template is adaptively modified based on the real-time pressure monitoring data sequence, real-time flow monitoring data sequence, and real-time load monitoring data sequence to determine the real-time hydraulic pump power adaptive control scheme, and the hydraulic pump system is subjected to power adaptive control based on the real-time hydraulic pump power adaptive control scheme.

2. The hydraulic pump power adaptive control method based on load dynamic sensing as described in claim 1, characterized in that, Based on the pressure monitoring data sequence and the flow monitoring data sequence, an interactive fusion analysis of the physical behavior characteristics of the hydraulic pump is performed to determine the fused physical behavior characteristics of the hydraulic pump, including: Pre-built physical behavior feature analyzer; The physical behavior feature analyzer is invoked to perform feature analysis on the pressure monitoring data sequence and the flow monitoring data sequence respectively, to determine the pressure monitoring trend features and the flow monitoring trend features; The pressure monitoring trend features and flow monitoring trend features are subjected to feature interaction fusion analysis to determine the fusion features of the physical behavior of the hydraulic pump.

3. The hydraulic pump power adaptive control method based on load dynamic sensing as described in claim 2, characterized in that, The physical behavior feature analyzer is obtained by supervised training of a framework built on a feedforward neural network using training data. The physical behavior feature analyzer includes an input layer, a convolutional layer, and an output layer.

4. The hydraulic pump power adaptive control method based on load dynamic sensing as described in claim 2, characterized in that, The pressure monitoring trend features and flow monitoring trend features are subjected to feature interaction fusion analysis to determine the fusion features of the hydraulic pump's physical behavior, including: The interaction probability analyzer is invoked to perform interaction probability analysis on the pressure monitoring trend features and the flow monitoring trend features to obtain an interaction probability set. Based on the set of interaction probabilities, a feature interaction fusion matrix is ​​constructed, and the feature interaction fusion matrix is ​​used to perform feature interaction fusion on the pressure monitoring trend feature and the traffic monitoring trend feature respectively to obtain the pressure monitoring fusion trend feature and the traffic monitoring fusion trend feature. The pressure monitoring fusion trend features and the flow monitoring fusion trend features are used as the physical behavior fusion features of the hydraulic pump.

5. The hydraulic pump power adaptive control method based on load dynamic sensing as described in claim 1, characterized in that, Based on the load monitoring data sequence, hydraulic pump load scene identification is performed to determine the characteristics of the hydraulic pump load scene, including: Construct a load scenario library, wherein the load scenario library includes multiple historical load scenario features and multiple historical load monitoring data record templates; The load monitoring data sequence is matched with the multiple historical load monitoring data record templates to obtain a matching historical load monitoring data record template, and the corresponding historical load scenario features are used as the hydraulic pump load scenario features.

6. The hydraulic pump power adaptive control method based on load dynamic sensing as described in claim 5, characterized in that, include: Obtain the historical load monitoring data record set of the hydraulic pump system; The historical load monitoring data record set is divided into similar categories to obtain multiple historical load monitoring data record sets; Scene features are extracted from the multiple sets of historical load monitoring data records to obtain multiple historical load scene features; Calculate the mean of the multiple historical load monitoring data record sets, and construct multiple historical load monitoring data record templates; The multiple historical load scenario features are mapped and associated with multiple historical load monitoring data record templates to construct a load scenario library.

7. The hydraulic pump power adaptive control method based on load dynamic sensing as described in claim 1, characterized in that, Based on the hydraulic pump load scenario characteristics, interactive guided prediction is performed on the fused physical behavior characteristics of the hydraulic pump, and a hydraulic pump power adaptive control template is matched according to the prediction results, including: Using the hydraulic pump load scenario characteristics as constraints, a physical behavior predictor is used to interactively guide the prediction of the fused physical behavior characteristics of the hydraulic pump to obtain the prediction results. Based on the prediction results, hydraulic power adaptive control scheme matching is performed to obtain a set of matching hydraulic power adaptive control schemes. The set of matching hydraulic power adaptive control schemes is screened to determine the hydraulic power adaptive control template.

8. The hydraulic pump power adaptive control method based on load dynamic sensing as described in claim 7, characterized in that, Calculate the mean of the set of matched hydraulic power adaptive control schemes, use it as the screening center, and iteratively screen the set of matched hydraulic power adaptive control schemes based on the screening center to determine the hydraulic power adaptive control template.

9. The hydraulic pump power adaptive control method based on load dynamic sensing as described in claim 1, characterized in that, Get the preset feedback window; The hydraulic pump system is subjected to power fluctuation identification in a preset feedback window. If the power fluctuation identification result exceeds a preset threshold, an early warning command is obtained.

10. A hydraulic pump power adaptive control system based on dynamic load sensing, characterized in that, The system is used to implement the hydraulic pump power adaptive control method based on load dynamic sensing as described in any one of claims 1 to 9, the system comprising: The monitoring data sequence determination module is used to deploy pressure sensors, flow sensors and displacement sensors in the hydraulic pump system, and use the pressure sensors, flow sensors and displacement sensors to perform long-term time-series monitoring of the hydraulic pump system to determine the pressure monitoring data sequence, flow monitoring data sequence and load monitoring data sequence. The physical feature fusion analysis module is used to perform interactive fusion analysis of the physical behavior features of the hydraulic pump based on the pressure monitoring data sequence and the flow monitoring data sequence, and to determine the fusion features of the physical behavior of the hydraulic pump. The load scene identification module is used to identify the hydraulic pump load scene based on the load monitoring data sequence and determine the characteristics of the hydraulic pump load scene. The interactive guidance prediction module is used to perform interactive guidance prediction on the physical behavior fusion features of the hydraulic pump based on the load scenario features of the hydraulic pump, and match the hydraulic pump power adaptive control template according to the prediction results. The real-time monitoring data sequence acquisition module is used to acquire the real-time pressure monitoring data sequence, real-time flow monitoring data sequence, and real-time load monitoring data sequence of the hydraulic pump system using the pressure sensor, flow sensor, and displacement sensor. The power adaptive control module is used to adaptively correct the hydraulic pump power adaptive control template based on the real-time pressure monitoring data sequence, real-time flow monitoring data sequence, and real-time load monitoring data sequence, determine the real-time hydraulic pump power adaptive control scheme, and perform power adaptive control of the hydraulic pump system based on the real-time hydraulic pump power adaptive control scheme.

Images