Hydraulic cylinder intelligent oil supply control system and method applied to hydraulic engineering

Abstract

The invention relates to the hydraulic technical field of hydraulic engineering, and discloses a hydraulic cylinder intelligent oil supply control system and method applied to hydraulic engineering. The system comprises a hydraulic parameter acquisition module, a data fusion processing module, a manifold state modeling module, a dynamic risk prediction module and a self-adaptive oil supply control module. The hydraulic parameter acquisition module is used for acquiring multi-point oil pressure, piston displacement and oil supply flow monitoring signals in real time; the data fusion processing module is used for fusing the multi-source heterogeneous signals; the manifold state modeling module constructs a hydraulic cylinder operation state Riemannian manifold geometric model based on the fusion signal; the dynamic risk prediction module calculates a real-time abnormal aggregation degree index according to the geometric feature vector; and the self-adaptive oil supply control module generates an oil supply control instruction according to the abnormal aggregation degree index. The system can comprehensively sense the operation state of the hydraulic cylinder, accurately model and predict risks, dynamically adjust oil supply parameters, and meet the requirements of modern hydraulic engineering operation.

Description

Technical Field

[0001] This invention relates to the field of hydraulic technology in water conservancy engineering, specifically to an intelligent oil supply control system and method for hydraulic cylinders applied in water conservancy engineering. Background Technology

[0002] In the field of water conservancy engineering, hydraulic cylinders are core actuators for critical operations such as gate opening and closing, dam regulation, and canal water control. The stable operation of their oil supply system directly affects the operational accuracy and safety performance of the entire water conservancy facility. Traditional hydraulic cylinder oil supply control mostly adopts a fixed mode based on preset parameters, that is, manually setting the oil supply pressure and flow threshold, and relying on simple on / off valves or proportional valves for coarse adjustment, which is difficult to adapt to the complex and ever-changing working conditions of water conservancy projects. Hydraulic engineering operations are often accompanied by uncertainties such as water flow impact, water pressure fluctuations, and temperature changes. These factors can cause nonlinear fluctuations in the oil pressure within the hydraulic cylinder's oil supply lines, affecting the accuracy of piston displacement and causing deviations between the oil supply flow and actual requirements. For example, during the opening and closing of a gate, when the water flow velocity suddenly increases, the hydraulic cylinder must withstand a sudden increase in load. If a traditional oil supply control system continues to supply oil according to fixed parameters, insufficient oil pressure can easily lead to gate opening and closing jams, or excessive oil pressure can cause pipeline leaks and seal damage. Traditional control systems often limit their monitoring of hydraulic cylinder operation to single-parameter acquisition, such as monitoring only oil pressure or displacement, lacking the ability to comprehensively analyze multi-source monitoring data. When a parameter becomes abnormal, it is difficult to quickly determine whether the abnormality stems from a fault in the oil supply system itself or from changes in external operating conditions, leading to delayed fault diagnosis and untimely maintenance response, further increasing the safety risks and maintenance costs of hydraulic engineering operations. Traditional hydraulic cylinder supply control methods cannot predict potential risks during hydraulic cylinder operation in advance, and can only respond passively after a fault occurs. For example, when slight wear in the oil supply line causes a slow drop in oil pressure, traditional systems cannot recognize this gradual anomaly until the wear intensifies and causes a significant fault, at which point an alarm may be triggered. By then, the normal operation of the water conservancy project may have already been affected, or even a safety accident may have occurred. As water conservancy projects develop towards larger scale and greater intelligence, the shortcomings of traditional hydraulic cylinder supply control systems in terms of control accuracy, adaptability, and risk prediction capabilities are becoming increasingly apparent, making it difficult to meet the demands of modern water conservancy projects for efficient, safe, and stable operation. Summary of the Invention

[0003] The purpose of this invention is to provide an intelligent oil supply control system for hydraulic cylinders applied in water conservancy projects, so as to solve the problems mentioned in the background art.

[0004] In order to achieve the above object, the application provides a hydraulic cylinder intelligent oil supply control system applied to water conservancy projects. A hydraulic parameter acquisition module is configured to acquire a multi-point oil pressure monitoring signal of a hydraulic cylinder oil supply pipeline, a piston displacement monitoring signal fed back by a displacement sensor, and an oil supply flow monitoring signal collected by a flowmeter in real time. A data fusion processing module is configured to perform multi-source heterogeneous data fusion processing on the oil pressure monitoring signal, the displacement monitoring signal, and the flow monitoring signal output by the hydraulic parameter acquisition module. A manifold state modeling module is configured to construct a Riemann manifold geometric model of the hydraulic cylinder operating state according to the monitoring signal sequence fused by the data fusion processing module. A dynamic risk prediction module is configured to calculate a real-time abnormality aggregation index of the hydraulic cylinder oil supply system based on a geometric feature vector output by the Riemann manifold geometric model. An adaptive oil supply control module is configured to generate an oil supply control instruction of the hydraulic cylinder according to the real-time abnormality aggregation index output by the dynamic risk prediction module.

[0005] Preferably, the hydraulic parameter acquisition module comprises: a first oil pressure sensor distributed at the inlet section of the oil supply pipeline, a second oil pressure sensor distributed at the middle section of the pipeline, and a third oil pressure sensor distributed at the outlet section of the pipeline; a displacement sensor installed on the hydraulic cylinder piston rod; an ultrasonic flowmeter arranged at the outlet of the oil supply pump; The first oil pressure sensor, the second oil pressure sensor, and the third oil pressure sensor output oil pressure monitoring signals respectively, the displacement sensor outputs a displacement monitoring signal, and the ultrasonic flowmeter outputs a flow monitoring signal.

[0006] Preferably, when the data fusion processing module performs multi-source heterogeneous data fusion processing: a wavelet coherence analysis method is used to calculate the propagation time lag between the monitoring signals of the first oil pressure sensor and the second oil pressure sensor; the displacement monitoring signal and the flow monitoring signal are subjected to time domain alignment processing according to the propagation time lag; the oil pressure monitoring signal, the displacement monitoring signal, and the flow monitoring signal subjected to time domain alignment are combined into a multi-dimensional monitoring signal matrix.

[0007] Preferably, when the manifold state modeling module constructs the Riemann manifold geometric model: Hilbert-Huang transformation is performed on the multi-dimensional monitoring signal matrix to extract intrinsic mode function components of each monitoring signal; the instantaneous frequency and the instantaneous amplitude of the intrinsic mode function components are mapped into tangent space coordinates of the Riemann manifold. The geometric feature vector of the hydraulic cylinder operating state is constructed according to the curvature variation of the tangent space coordinates.

[0008] Preferably, when calculating the real-time anomaly aggregation degree index, the dynamic risk prediction module: The topological data analysis algorithm is used to identify the high-dimensional cluster structure of the geometric feature vector on the Riemannian manifold; The aggregation density distribution of the geometric feature vector in the manifold space when the historical fault occurs is calculated; The real-time anomaly aggregation degree index is quantified based on the Hausdorff distance between the current geometric feature vector and the historical aggregation density distribution.

[0009] Preferably, the dynamic risk prediction module further comprises: The causal discovery algorithm is applied to identify the causal correlation strength between the oil pressure fluctuation and the displacement lag from the geometric feature vector; The weight coefficient of the real-time anomaly aggregation degree index is corrected according to the causal correlation strength.

[0010] Preferably, when the adaptive oil supply control module generates the oil supply control instruction: The real-time anomaly aggregation degree index is mapped to the oil supply pressure adjustment amount, the flow compensation amount, and the displacement correction amount by using a three-valued logic system; The opening degree instruction of the proportional overflow valve is adjusted according to the oil supply pressure adjustment amount; The speed control signal of the variable frequency pump is generated according to the flow compensation amount; The piston position calibration instruction is output according to the displacement correction amount.

[0011] Preferably, the adaptive oil supply control module further comprises: The future three operation period oil supply parameter drift trend is predicted by the time series causal reasoning model; When it is detected that the oil supply parameter drift trend exceeds the preset threshold, the parameter self-calibration mechanism of the three-valued logic system is triggered.

[0012] Preferably, the system further comprises: A control instruction execution module for parsing the oil supply control instruction generated by the adaptive oil supply control module; The control instruction execution module drives the proportional overflow valve to perform the opening degree adjustment action; The control instruction execution module controls the variable frequency pump to complete the speed adjustment operation; The control instruction execution module sends the piston position calibration instruction to the hydraulic cylinder servo controller.

[0013] Preferably, the application further includes a hydraulic cylinder intelligent oil supply control method applied to water conservancy projects, comprising all modules and method processes of the hydraulic cylinder intelligent oil supply control system applied to water conservancy projects.

[0014] Compared with the prior art, the application has the beneficial effects that: The hydraulic cylinder intelligent oil supply control system applied to water conservancy projects realizes real-time monitoring of multi-point oil pressure, piston displacement and oil supply flow of the hydraulic cylinder oil supply pipeline through the hydraulic parameter acquisition module. Compared with the single parameter monitoring mode of the traditional control system, the system can comprehensively capture the key state information of the hydraulic cylinder during operation, covers all links from pipeline pressure to actuator displacement to medium flow of the oil supply system, makes the system's perception of the hydraulic cylinder operation state more complete and accurate, can timely find the subtle abnormalities easily ignored in the traditional monitoring mode, and provides comprehensive data support for subsequent control and risk judgment.

[0015] The data fusion processing module fuses and processes the multi-source heterogeneous monitoring signals, effectively solving the problem of independent existence of each monitoring parameter and poor data correlation in the traditional system. Since the oil pressure, displacement and flow signals may produce noise due to environmental interference during the acquisition process, and the dimensions and change laws of different parameters are different, it is difficult to accurately reflect the real operation state of the hydraulic cylinder by directly using a single parameter. Through multi-source data fusion, the data noise interference can be eliminated, the correlation information between different parameters can be integrated, the system operation law hidden behind multiple parameters can be mined, the fused signals are closer to the actual working condition, a high-quality data basis is provided for subsequent state modeling, the judgment of the hydraulic cylinder operation state is more scientific, and control deviation caused by single parameter misjudgment is avoided. The manifold state modeling module constructs a Riemann manifold geometry model based on the fused monitoring signal sequence, breaking through the limitations of the traditional linear modeling method in processing nonlinear and dynamically changing hydraulic cylinder operation states. The operation state of the hydraulic cylinder under complex working conditions of water conservancy projects presents obvious nonlinear characteristics, and the traditional linear model is difficult to accurately describe the complex state change law. The Riemann manifold geometry model can map the change of the hydraulic cylinder operation state to the geometric space by using the characteristics of the geometric space, intuitively reflect the state evolution trend through the geometric feature vector, and is more in line with the operation characteristics of the hydraulic cylinder in actual operation, so that the modeling of the operation state is more accurate and more practical. The dynamic risk prediction module calculates a real-time abnormality aggregation degree index based on the geometric feature vector, and realizes early identification of potential risks of the oil supply system of the hydraulic cylinder. The traditional system can only passively alarm after a fault occurs, but the module can capture the aggregation trend of the abnormal state through analysis of the geometric features of the running state, and can perceive potential risks through changes in the abnormality aggregation degree index before the fault fully appears, thereby changing the "after-treatment" mode of the traditional system, reserving more response time for the staff, helping to take intervention measures in advance, reducing the probability of fault occurrence, and reducing the impact of the fault on the water conservancy engineering operation. The adaptive oil supply control module generates a control instruction according to the real-time abnormality aggregation degree index, so that the oil supply control can be dynamically adjusted according to the change of the running state of the hydraulic cylinder. In the scene where the working condition of the water conservancy project fluctuates greatly, the traditional fixed parameter control mode cannot timely adapt to the change of the working condition, and the problem of mismatch between oil supply and demand is easy to occur, while the adaptive control can judge whether there is a risk in the current running state and the risk degree according to the abnormality aggregation degree index, and then automatically adjust the oil supply pressure, flow and other parameters. For example, when the abnormality aggregation degree index rises, the oil supply parameters are adjusted in time to alleviate the abnormal trend, and when the index is normal, the optimal oil supply state is maintained to ensure that the hydraulic cylinder always operates in the best working condition. The flexibility and adaptability of the oil supply control are improved, the control deviation caused by the change of the working condition is reduced, the probability of faults such as pipeline leakage and damage of sealing elements is reduced, unnecessary energy consumption is also reduced, the economy and stability of the hydraulic cylinder operation are improved, and the related operations of the water conservancy project such as gate opening and closing, dam regulation and the like can be carried out efficiently and stably, thereby reducing the maintenance cost and safety risk. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 a timing diagram of the intelligent oil supply control system of the hydraulic cylinder applied to the water conservancy project described in the application; Figure 2 a working principle flowchart of the hydraulic parameter acquisition module; Figure 3 a working principle flowchart of the manifold state modeling module for constructing a Riemann manifold geometric model; Figure 4 a working principle flowchart of the dynamic risk prediction module for correcting the weight coefficient of the real-time abnormality aggregation degree index. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the application.

[0018] Referring to Figure 1 The application provides a hydraulic cylinder intelligent oil supply control system and method applied to water conservancy projects, and the system comprises: Key parameters in the hydraulic cylinder oil supply process are collected in real time through a multi-source sensor, and accurate modeling and dynamic risk prediction of the operating state are realized based on a manifold geometry theory and a multi-source data fusion technology, so that a self-adaptive oil supply control instruction is finally generated. The system comprises a hydraulic parameter acquisition module, a data fusion processing module, a manifold state modeling module, a dynamic risk prediction module and a self-adaptive oil supply control module. The hydraulic parameter acquisition module acquires, in real time, a multi-point oil pressure monitoring signal of a hydraulic cylinder oil supply pipeline, a piston displacement monitoring signal fed back by a displacement sensor and an oil supply flow monitoring signal collected by a flowmeter. The data fusion processing module performs fusion processing on the above-mentioned multi-source heterogeneous monitoring signals, eliminates time domain inconsistency and forms a unified multi-dimensional data matrix. The manifold state modeling module constructs a Riemann manifold geometry model describing the operating state of the hydraulic cylinder based on the fused signal sequence, and maps the nonlinear characteristics of the monitoring signals to the geometric structure of the manifold space. The dynamic risk prediction module calculates a real-time abnormality aggregation degree index according to the geometric feature vector output by the manifold model, and quantifies the operating risk level. The self-adaptive oil supply control module generates an oil supply control instruction according to the abnormality aggregation degree index, so that closed-loop adjustment of the oil supply pressure, flow and piston position is realized.

[0019] Embodiment 1: Referring to Figure 2 The hydraulic parameter acquisition module comprises a group of oil pressure sensors arranged according to a specific spatial distribution, a high-precision displacement sensor and an ultrasonic flowmeter. The first oil pressure sensor is installed at the pipeline inlet section after the oil supply pump, as close as possible to the outlet flange of the pump, so as to capture the initial value of the oil supply pressure. The second oil pressure sensor is installed at the middle section of the pipeline, usually at the intermediate point after the pipeline direction changes significantly or the length exceeds a certain distance, for monitoring the transmission state of the pressure in the pipeline. The third oil pressure sensor is directly installed near the oil inlet of the hydraulic cylinder, serving as the pressure monitoring point of the pipeline outlet section. The three sensors work in a synchronous sampling mode, and the voltage analog signals output by the sensors are transmitted to a signal conditioning unit through a shielded cable, are amplified and filtered, and are then converted into digital signals. The displacement sensor adopts a magnetostrictive or grating principle, the measurement body of the sensor is fixed to the cylinder barrel of the hydraulic cylinder, and the movable part is mechanically connected with the piston rod, so as to detect the absolute or relative displacement of the piston in real time. The ultrasonic flowmeter adopts a time difference method for measurement, the sensor probe thereof is clamped and installed on the outer wall of the straight pipe section at the outlet of the oil supply pump, and the flow rate and flow are calculated by measuring the time difference of the ultrasonic wave in the fluid in the forward and reverse propagation directions. All these sensors adopt industrial standard, and have the characteristics of moisture-proof, shock-proof and anti-electromagnetic interference, so as to adapt to the complex environmental conditions of the water conservancy project site.

[0020] The data fusion processing module receives the multi-channel digital signals from the above-mentioned sensors. Due to different response characteristics, sampling frequencies and transmission delays of different sensors, there is natural asynchrony in the time domain of these signals. For example, there is a difference between the propagation speed of the pressure signal in the oil and the electrical transmission speed of the displacement signal. The measurement of the flow signal also has a certain pipe flow state response time. In order to eliminate this time domain inconsistency, the module uses wavelet coherence analysis method to process the monitoring signals of the first and second oil pressure sensors. This method determines the propagation time lag of the pressure wave from the pump outlet to the middle of the pipeline by calculating the phase relationship of the two pressure signals at different frequency components. This time lag not only reflects the physical properties of the oil, but also contains the comprehensive effects of pipeline elasticity and fluid inertia.

[0021] After obtaining the propagation time lag, the data fusion processing module performs time domain alignment processing on the displacement monitoring signal and the flow monitoring signal. The displacement signal usually needs to be shifted forward or backward by a certain number of sampling points, and this shift amount is calculated according to the product of the pressure propagation time lag and the sampling frequency. The flow signal is adjusted similarly according to its coupling relationship with the pressure signal. Time domain alignment processing not only considers static time lag, but also pays attention to dynamic changes. For example, when the oil temperature changes, the propagation time lag will change slightly, so the time lag estimation needs to be updated online at this time.

[0022] After completing the time domain alignment, each monitoring signal is combined into a multi-dimensional monitoring signal matrix. Each row of the matrix represents a synchronized time sampling point, and each column represents the measurement value of a sensor. The first column of the matrix is the time-lag-corrected first oil pressure sensor signal, the second column is the second oil pressure sensor signal, the third column is the third oil pressure sensor signal, the fourth column is the displacement sensor signal, and the fifth column is the ultrasonic flowmeter signal. The formation of this matrix makes the originally independent multi-source heterogeneous data highly consistent in the time dimension, providing accurate and consistent data basis for subsequent manifold state modeling. The matrix data is stored in the memory in the form of a ring buffer, which not only retains a long enough history data for trend analysis, but also ensures that new data can be updated in real time.

[0023] During the entire implementation process, the reliability of signal transmission is guaranteed through industrial Ethernet or fieldbus technology. Each sensor channel is provided with self-diagnosis function, which can detect signal abnormalities such as wire breakage, excessive range or noise interference. When a sensor fails, the system can automatically switch to a redundant backup sensor or use an estimation algorithm to compensate for data loss, maintaining the continuous operation of the system. All processing processes are implemented on an embedded industrial computing platform, which has sufficient computing power to process multi-channel high-frequency sampling data and meet the strict real-time requirements of hydraulic engineering hydraulic systems.

[0024] Example 2: see Figure 3The manifold state modeling module receives a multi-dimensional monitoring signal matrix from the data fusion processing module, which contains time-domain aligned oil pressure, displacement, and flow data. The module first performs a Hilbert-Huang transform on each monitoring signal channel in the matrix individually. The transform process includes two main stages: empirical mode decomposition and Hilbert spectrum analysis. For each monitoring signal, empirical mode decomposition decomposes it into a series of intrinsic mode function components, which are generated through an iterative sifting process that satisfies specific conditions about extreme points and zero points, and have a clear physical meaning of instantaneous frequency. Taking the inlet section oil pressure signal as an example, decomposition can generate 5-8 intrinsic mode function components, corresponding to different frequency range fluctuation characteristics, from high-frequency pressure pulsation to low-frequency trend change.

[0025] After completing the empirical mode decomposition, a Hilbert transform is performed on each intrinsic mode function component to calculate its analytic signal, and then the instantaneous frequency and instantaneous amplitude sequences are obtained. The instantaneous frequency reflects the frequency characteristics of the signal component at each time point, while the instantaneous amplitude represents the energy intensity of the frequency component. Taking an intrinsic mode function component of the middle section of the pipeline oil pressure signal as an example, its instantaneous frequency sequence may show a concentrated distribution of frequency values within a certain time interval, and the instantaneous amplitude sequence may show a pattern of gradually decaying or enhancing amplitude.

[0026] When mapping these instantaneous frequency and instantaneous amplitude parameters to the Riemann manifold structure, a differential geometry method is used for processing. The instantaneous frequency and instantaneous amplitude values of all intrinsic mode function components at each time point form a high-dimensional data point, and these data points collectively form a point set on the manifold. By calculating the geodesic distance and tangent space projection between these points, the local geometric structure of the manifold is established. The determination of the tangent space coordinates is realized by constructing a local coordinate system at each point, which takes the tangent plane at the point as the reference and projects the neighborhood points onto the plane.

[0027] After the manifold structure is established, the curvature variation of the tangent space coordinates is calculated, which involves quantifying the degree of curvature of the manifold surface by comparing the difference between the geodesic distance and the Euclidean distance between adjacent points. High curvature regions correspond to rapid changes or transition stages of the system operating state, while low curvature regions represent relatively stable operating states. Taking the reversing stage of the hydraulic cylinder piston movement process as an example, the manifold curvature of this period usually shows significant changes, reflecting the transformation of the system's dynamic characteristics.

[0028] Based on the curvature analysis results, a geometric feature vector is constructed to describe the operating state of the hydraulic cylinder. This vector contains multiple dimensional feature indicators, including geometric features such as average curvature, Gaussian curvature, and curvature rate of change, as well as statistical features extracted from instantaneous frequency and instantaneous amplitude. These features collectively provide a multi-angle description of the system operating state, enabling the capture of subtle changes in system dynamic behavior. For example, when the oil supply pressure experiences slight fluctuations, certain components of the geometric feature vector will exhibit corresponding change patterns, which may be difficult to detect in traditional time or frequency domain analysis.

[0029] The entire manifold state modeling process is implemented on an embedded computing platform, using optimized numerical algorithms to handle large-scale data calculations. During the calculation process, a sliding window mechanism is used to process the latest monitoring data block, ensuring the timeliness of the features and maintaining the computational load within a reasonable range. The generated geometric feature vector is output in the form of a time series, providing input data for the subsequent dynamic risk prediction module. This module has adaptive learning capabilities, allowing it to automatically adjust the manifold parameters based on system operating data, ensuring that the model always matches the actual operating state of the system.

[0030] In Example 3, the geometric feature vector sequence output by the manifold state modeling module is received and processed by the dynamic risk prediction module. This module first uses topological data analysis algorithms to analyze the distribution structure of these high-dimensional vectors on the Riemannian manifold. Topological data analysis identifies topological features in the data by constructing persistent homology. In implementation, the Vietoris-Rips complex construction method is used, and by setting different distance parameters ε, a series of simple complexes are generated. As the value of ε increases, connections between data points gradually form, producing topological features of different dimensions (such as connected components and voids). The birth time and death time of each topological feature are recorded in the persistence diagram. By analyzing the points far from the diagonal line in the persistence diagram, significant clustering structures of the geometric feature vectors in the manifold space can be identified. These clustering structures often correspond to operating modes of the system, including normal operating states and various abnormal states.

[0031] Based on the identification of the phase clustering structure, the module calculates the clustering density distribution of the geometric feature vectors in the manifold space when historical faults occur. This process uses kernel density estimation, with the feature vector points corresponding to each historical fault event as the center to construct a probability density function. The Gaussian kernel function is commonly used for such estimation, and its smoothing parameter is adaptively determined based on the distribution characteristics of the data. Historical fault data comes from system operation logs and manually annotated records, containing multiple fault types such as oil line blockage, internal leakage, and sensor failure. Each fault type forms a density distribution pattern in the manifold space, and these patterns are stored in the knowledge base in the form of probability distributions.

[0032] Based on the relationship between the geometric feature vector at the current time and the historical aggregated density distribution, the module calculates the real-time abnormal aggregation index. This index is quantified by the Hausdorff distance, and its calculation formula is: Wherein: represents the point set formed by the geometric feature vector at the current time in the manifold space, represents the aggregated point set of the kth historical fault mode, represents the geodesic distance between two points in the manifold space. This distance measures the maximum and minimum separation between the current state point set and the historical fault cluster, and the smaller the value, the closer the current state to the historical fault mode.

[0033] The module applies a causal discovery algorithm to identify the causal correlation strength between the oil pressure fluctuation and the displacement lag from the geometric feature vector. The transfer entropy method is used to calculate the causal influence measure between variables, which can capture nonlinear and asymmetric causal relationships. For the oil pressure signal and the displacement signal , the transfer entropy calculation is based on the conditional probability distribution of the two signals, which measures the prediction contribution of the oil pressure historical information to the current displacement value under the condition of knowing the displacement historical information. The strength value of this causal relationship is between 0 and 1, and the larger the value, the stronger the causal influence of oil pressure fluctuation on displacement lag.

[0034] According to the calculated causal correlation strength, the module corrects the weight coefficient of the real-time abnormal aggregation index. The correction process uses a weighted function to introduce the causal strength as a weight factor into the abnormal index calculation. For fault modes with strong causal correlation, their corresponding abnormal aggregation index will be given a higher weight, and vice versa. This correction mechanism enables the system to more accurately reflect the correlation between the current operating state and specific fault modes, improving the accuracy of risk prediction.

[0035] The entire dynamic risk prediction process uses a sliding time window mechanism to perform batch processing analysis on the geometric feature vectors in the recent period. The window length is adjusted according to the dynamic characteristics of the system, usually containing hundreds to thousands of sampling points. The analysis results include the real-time abnormal aggregation index value and the matching probability of each fault mode, which are transmitted to the adaptive fuel supply control module as the basis for control decisions. The module maintains a dynamically updated knowledge base, continuously absorbing new operating data to optimize the historical fault density distribution model, enabling the system to have continuous learning ability. All calculations are implemented on an industrial-grade embedded platform, using numerical optimization algorithms to ensure computational efficiency and meet real-time requirements.

[0036] Example 4: see Figure 4The adaptive oil supply control module receives the real-time abnormality aggregation index value output by the dynamic risk prediction module, which is a continuous value ranging from 0 to 1. The module uses a ternary logic system to discretize the index and divide it into three risk level state intervals: low, medium, and high. The interval boundary values are determined based on historical operation data statistics. For example, set [0, 0.3) as the low-risk state, [0.3, 0.7) as the medium-risk state, and [0.7, 1] as the high-risk state. Each state interval corresponds to a different control rule base, and the abnormality aggregation index is mapped to specific oil supply pressure adjustment, flow compensation, and displacement correction through a lookup table. The following table shows a typical mapping relationship: Abnormality aggregation index and control quantity mapping table

[0037] The specific value of the pressure adjustment is generated by a fuzzy reasoning mechanism. The system establishes a fuzzy rule base containing 49 rules, with the feedforward oil pressure deviation and abnormality aggregation index as input variables. For example, when the inlet pressure deviation is negative and the abnormality index is in the medium-risk interval, the "large amplitude pressure increase" rule is triggered, and the specific pressure adjustment value is output. This value is converted into the opening command of the proportional overflow valve, and the opening change amount ΔK is calculated by the PID controller, with the proportional coefficient dynamically adjusted according to the abnormality aggregation index. The command is transmitted to the electromagnetic driver of the proportional overflow valve through a 4-20 mA analog signal, driving the armature displacement to change the valve core throttling area.

[0038] The generation of the flow compensation value uses a feedforward-feedback composite control strategy. The feedforward part calculates the theoretical flow demand based on the speed signal of the displacement sensor, and the feedback part compensates for the flow deviation based on the abnormality aggregation index. The final generated flow compensation value is converted into the speed control signal of the variable frequency pump, and the pulse width modulation technology is used to generate a three-phase alternating current driving waveform. For example, when an additional 2.5 L / min of flow is required, the control system calculates the corresponding motor speed increment Δn, adjusts the output voltage frequency by changing the IGBT conduction duty cycle, and increases the pump speed by 85 rpm accurately.

[0039] The calculation of the displacement correction value combines the deviation between the actual position of the piston and the target position, as well as the influence factor of the abnormality aggregation index. This correction value is converted into a piston position calibration command and transmitted to the hydraulic cylinder servo controller through the CAN bus using the standard CANopen protocol message. The message contains a 32-bit floating-point target position value and timestamp information. After parsing the command, the servo controller uses a position-speed-current three-closed-loop control strategy to adjust the valve core displacement of the electro-hydraulic servo valve, change the oil flow and direction into the hydraulic cylinder, and move the piston to the calibration position. For example, when a +0.3 mm displacement needs to be compensated, the servo valve opening area increases by 0.8 mm² and maintains for 200 ms.

[0040] The module predicts the oil supply parameter drift trend through a timing causal inference model, which adopts a long short-term memory network architecture, inputs the oil pressure, flow, displacement and abnormal index sequence in the last 120 seconds, and outputs the parameter change prediction value in the next three control periods (about 15 seconds). The network contains 128 memory units, which capture the long-term dependence of time series through the gating mechanism. When the predicted drift of any parameter exceeds the threshold value (such as pressure drift > 0.2 MPa), the parameter self-calibration mechanism of the ternary logic system is triggered. This mechanism automatically adjusts the state interval boundary value and the control quantity mapping relationship, for example, adjusting the lower limit of the medium risk interval from 0.3 to 0.35, or increasing the flow compensation range of the high risk state to ± 6 L / min. The self-calibration parameters are stored in the non-volatile memory, ensuring that the updated control rules are maintained after system restart.

[0041] In embodiment 5, the control instruction execution module receives the digital control instruction set generated by the adaptive oil supply control module, which contains three independent parameters: proportional overflow valve opening adjustment value, variable frequency pump speed set value, and piston position calibration amount. The instruction analysis unit adopts a hierarchical decoding mechanism, first identifies the control object type by the instruction header identifier, and then extracts the 32-bit floating point number data in the parameter area. For the proportional overflow valve control instruction, the signal conversion unit converts the floating point format opening percentage to 0-10V analog voltage signal. The voltage signal is input into the current amplifier circuit, and the voltage-current conversion generates a 4-20mA drive current proportional to the set value. The drive current is applied to the proportional electromagnet coil to generate an electromagnetic force corresponding to the current intensity. The electromagnetic force pushes the valve core to move axially against the spring pre-tightening force, changing the flow area of the throttle. For example, when the opening instruction value is 65%, the system outputs an 8.25V voltage signal, which is converted to generate a 16.5mA drive current, making the valve core displace to the middle position of the designed stroke, at which time the overflow pressure is set to 75% of the system rated pressure.

[0042] The execution of the variable frequency pump speed control command involves power electronics technology. The speed setpoint input digital signal is extracted by the command analysis unit and fed into a digital signal processor, which generates a three-phase pulse width modulation waveform. The waveform generation uses a space vector modulation algorithm to calculate the required output frequency based on the target speed and automatically adjust the voltage amplitude based on the pump's torque-speed characteristic curve. The modulation waveform drives an insulated gate bipolar transistor power module, which converts the DC bus voltage into variable frequency and variable voltage three-phase AC power. For example, when the target speed is set to 1450 rpm, the system outputs 48 Hz three-phase AC power with a voltage amplitude adjusted to 380 V line voltage. This power is transmitted to the pump's three-phase asynchronous motor through a shielded power cable, driving the pump shaft to rotate. The speed closed-loop control is achieved through an encoder installed on the motor shaft end, with the encoder pulse signal fed back to the digital signal processor, which dynamically adjusts the pulse width modulation waveform duty cycle after comparing the setpoint, so that the actual speed is stabilized within the setpoint ± 5 rpm range.

[0043] The execution of the piston position calibration command relies on the hydraulic cylinder servo control system. The displacement correction amount is packaged by the command analysis unit into a standard CANopen protocol message, which contains a 16-bit node address, a 32-bit floating-point position value, and an 8-bit control mode identifier. The message is transmitted to the hydraulic cylinder servo controller through the controller area network bus at a transmission rate of 500 kbps. The communication interface of the servo controller uses optical isolation technology to prevent electromagnetic interference from affecting signal integrity. After message analysis, the position control module inputs the target position value into the position-speed-current three-loop control algorithm. The position loop generates a speed feedforward command, the speed loop outputs a current setpoint, and the current loop controls the servo valve coil current through the proportional valve drive circuit. For example, when receiving a +0.8 mm displacement correction command, the servo controller pushes the electro-hydraulic servo valve spool to the corresponding opening position within 50 ms, causing the pressure oil to enter the hydraulic cylinder rodless chamber. The piston rod displacement is detected in real time by a magnetostrictive displacement sensor, and its feedback signal is compared with the target position to form a closed-loop control. When the actual position and target position difference is less than 0.02 mm, the controller enters the position holding mode, compensating for the drift caused by internal leakage through slight adjustment of the valve opening.

[0044] System-level cooperative control is realized through precise time synchronization mechanism. The control instruction execution module is built-in with high-precision clock source, and all execution actions are scheduled with 1ms time resolution. The three control processes of proportional relief valve regulation, variable frequency pump speed regulation and piston position calibration adopt time-sharing triggering strategy to avoid power fluctuation caused by instantaneous power superposition. The execution state monitoring unit collects feedback signals of each execution mechanism in real time: proportional valve core displacement sensor signal, variable frequency pump motor current waveform, servo controller following error value. These signals are sampled through independent analog input channels and converted to digital quantities at a sampling frequency of 500Hz. When the execution mechanism response delay exceeds the set threshold (such as valve core action delay > 100ms) or the following error continues to exceed the standard (such as position error > 0.1mm for more than 2 seconds), the system automatically triggers the execution abnormality diagnosis process. The process first switches to the backup control channel, while analyzing the fault characteristics to distinguish different fault types such as sensor failure, actuator jamming or mechanical wear, and uploads the diagnosis results to the central monitoring system.

[0045] The environmental adaptability design takes into account the special working conditions of water conservancy projects. All electrical connections use IP67 protection level connectors, and signal cables are equipped with double shielding structure. The execution mechanism installation base is provided with shock absorbing rubber pads to effectively attenuate mechanical vibration from gate opening and closing operation. In low temperature environment, heating tape is wound around the hydraulic valve block to maintain oil viscosity; in high temperature working condition, heat dissipation fins are used to reduce the temperature of electronic components. Modular design allows quick replacement of faulty units. Proportional valve drive board, variable frequency power module and other key components support hot plug operation. Historical execution data is saved in ferroelectric memory in a circular storage mode, recording the control instruction and execution response curve for the last 200 hours, providing a data basis for running state analysis.

[0046] It should be noted that, in the present text, relational terms such as first and second are used only to distinguish one entity or action from another, and do not necessarily require or imply that there is any such actual relationship or order between these entities or actions. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or equipment including a series of elements includes not only those elements, but also other elements not explicitly listed or inherent to such a process, method, article or equipment.

[0047] Although embodiments of the present application have been shown and described, it will be understood by those having ordinary skill in the art that various changes, modifications, alternatives and variations can be made thereto without departing from the principles and spirit of the application, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A hydraulic cylinder intelligent oil supply control system applied to hydraulic engineering, characterized in that, The hydraulic parameter acquisition module is configured to acquire a multi-point oil pressure monitoring signal of a hydraulic cylinder oil supply pipeline, a piston displacement monitoring signal fed back by a displacement sensor, and an oil supply flow monitoring signal collected by a flowmeter in real time. The data fusion processing module is configured to perform multi-source heterogeneous data fusion processing on the oil pressure monitoring signal, the displacement monitoring signal, and the flow monitoring signal output by the hydraulic parameter acquisition module. The manifold state modeling module is configured to construct a Riemann manifold geometric model of a hydraulic cylinder operating state according to the monitoring signal sequence fused by the data fusion processing module. The dynamic risk prediction module is configured to calculate a real-time abnormal aggregation degree index of the hydraulic cylinder oil supply system based on a geometric feature vector output by the Riemann manifold geometric model. The adaptive oil supply control module is configured to generate an oil supply control instruction of the hydraulic cylinder according to the real-time abnormal aggregation degree index output by the dynamic risk prediction module. The hydraulic parameter acquisition module comprises:

2. The intelligent oil supply control system for hydraulic cylinders applied to hydraulic engineering according to claim 1, characterized in that, a first oil pressure sensor distributed at an inlet section of the oil supply pipeline, a second oil pressure sensor distributed at a middle section of the oil supply pipeline, and a third oil pressure sensor distributed at an outlet section of the oil supply pipeline; a displacement sensor installed on a piston rod of the hydraulic cylinder; an ultrasonic flowmeter arranged at an outlet of an oil supply pump; wherein the first oil pressure sensor, the second oil pressure sensor, and the third oil pressure sensor output oil pressure monitoring signals respectively, the displacement sensor outputs a displacement monitoring signal, and the ultrasonic flowmeter outputs a flow monitoring signal. When the data fusion processing module performs multi-source heterogeneous data fusion processing:

3. The intelligent oil supply control system for hydraulic cylinders applied to hydraulic engineering according to claim 1, characterized in that, a wavelet coherence analysis method is used to calculate a propagation time lag between the monitoring signals of the first oil pressure sensor and the second oil pressure sensor; time domain alignment processing is performed on the displacement monitoring signal and the flow monitoring signal according to the propagation time lag; the oil pressure monitoring signal, the displacement monitoring signal, and the flow monitoring signal after time domain alignment are combined into a multi-dimensional monitoring signal matrix. When the manifold state modeling module constructs the Riemann manifold geometric model:

4. The intelligent oil supply control system for hydraulic cylinders applied to hydraulic engineering according to claim 3, characterized in that, Hilbert-Huang transformation is performed on the multi-dimensional monitoring signal matrix to extract intrinsic mode function components of each monitoring signal; instantaneous frequencies and instantaneous amplitudes of the intrinsic mode function components are mapped into tangent space coordinates of the Riemann manifold; a geometric feature vector of the hydraulic cylinder operating state is constructed according to curvature changes of the tangent space coordinates. When the dynamic risk prediction module calculates the real-time abnormal aggregation degree index:

5. The intelligent oil supply control system for hydraulic cylinders applied to hydraulic engineering according to claim 4, characterized in that, a topological data analysis algorithm is used to identify a high-dimensional clustering structure of the geometric feature vector on the Riemann manifold; a clustering density distribution of the geometric feature vector in the manifold space when a historical fault occurs is calculated; a Hausdorff distance between the current geometric feature vector and the historical clustering density distribution is used to quantify the real-time abnormal aggregation degree index. The dynamic risk prediction module further comprises:

6. The intelligent oil supply control system for hydraulic cylinders applied to hydraulic engineering according to claim 5, characterized in that, a causal discovery algorithm is used to identify a causal correlation strength between oil pressure fluctuations and displacement lag from the geometric feature vector; a weight coefficient of the real-time abnormal aggregation degree index is corrected according to the causal correlation strength. When the adaptive oil supply control module generates the oil supply control instruction:

7. The intelligent oil supply control system for hydraulic cylinders applied to hydraulic engineering according to claim 1, characterized in that, a ternary logic system is used to map the real-time abnormal aggregation degree index into an oil supply pressure adjustment amount, a flow compensation amount, and a displacement correction amount. ​ adjusting an opening degree instruction of the proportional overflow valve according to the oil supply pressure adjustment amount; generating a rotating speed control signal of the variable frequency pump according to the flow compensation amount; outputting a piston position calibration instruction according to the displacement correction amount.

8. The intelligent oil supply control system for hydraulic cylinders applied to hydraulic engineering according to claim 7, characterized in that, The adaptive oil supply control module further comprises: predicting a future three operation period oil supply parameter drift trend through a timing causal inference model; when detecting that the oil supply parameter drift trend exceeds a preset threshold, triggering a parameter self-calibration mechanism of the ternary logic system.

9. The intelligent oil supply control system for hydraulic cylinders applied to hydraulic engineering according to claim 1, characterized in that, Further comprising: a control instruction execution module for parsing the oil supply control instruction generated by the adaptive oil supply control module; the control instruction execution module drives the proportional overflow valve to perform opening degree adjustment action; the control instruction execution module controls the variable frequency pump to complete rotating speed adjustment operation; the control instruction execution module sends a piston position calibration instruction to a hydraulic cylinder servo controller.

10. A hydraulic cylinder intelligent oil supply control method applied to hydraulic engineering, characterized in that, all modules and method processes of the hydraulic cylinder intelligent oil supply control system for water conservancy projects according to any one of claims 1 to 9.

Images