Method and system for calculating coupling flow of hydraulic system

Abstract

The invention provides a hydraulic system coupling flow calculation method and system, and the method comprises the steps: firstly building a pump-valve-load coupling dynamic model, and obtaining a flow-pressure-temperature coupling equation; pressure, flow and temperature signals are collected in real time and preprocessed; then carrying out dynamic estimation on the flow based on an extended Kalman filter; and finally, compensating an estimation error through a residual feature fusion inversion network, and outputting a high-precision coupling flow value. Experiments show that the maximum relative error is reduced from + / -7.8% to + / -1.3% under the working condition of the step of 0-25 MPa, the fluctuation quantity is reduced by 62% when the oil temperature drifts at 40-80 DEG C, the time consumed by single calculation is less than 0.8 ms, and the method can be widely applied to high-dynamic complex working conditions of engineering machinery, aviation hydraulic pressure and the like.

Description

Technical Field

[0001] This invention relates to the field of hydraulic control technology, specifically to a method and system for calculating the coupled flow rate of a hydraulic system. Background Technology

[0002] In highly dynamic hydraulic systems such as those used in engineering machinery and aerospace, the coupling between pumps, valves, and loads is severe. Traditional flow calculation methods based on single-component modeling struggle to reflect the true system flow in real time, leading to decreased control accuracy and increased energy consumption. Existing technologies often employ simplified models or offline calibration, which cannot adapt to sudden changes in operating conditions and parameter drift. Therefore, a high-precision and robust online coupled flow calculation method is urgently needed. Summary of the Invention

[0003] This invention proposes a method and system for calculating the coupled flow rate of a hydraulic system to solve the problems mentioned in the background section. The technical solution provided by this invention is as follows:

[0004] Firstly, a method for calculating the coupled flow rate of a hydraulic system includes the following steps:

[0005] Step 1: Construct a pump-valve-load coupled dynamic model, including the flow continuity equation of the hydraulic pump, the flow equation of the throttle valve orifice, and the force balance equation of the load cylinder. The flow-pressure-temperature coupled equation is obtained by coupling the three types of equations under the energy conservation framework.

[0006] Step 2: Real-time acquisition of pressure, flow rate, and temperature signals from the hydraulic system, followed by preprocessing;

[0007] Step 3: Perform dynamic flow estimation on the preprocessed signal based on the extended Kalman filter;

[0008] Step 4: Use the residual feature fusion inversion network to perform closed-loop compensation for the estimation error and output a high-precision coupled flow value.

[0009] Preferably, the flow continuity equation of the hydraulic pump is in the form of:

[0010]

[0011] in, This is the theoretical flow rate at the pump outlet, in cubic meters per second (m³). 3 ·s -1 ; This refers to the pump's geometric displacement (displacement per revolution), in meters (m). 3 ·rad -1 ; The pump shaft angular velocity is expressed in rad·s. -1 , This is the laminar flow coefficient for internal leakage in the pump, in meters. 3 ·s-1 ·Pa -1 ; Pump outlet pressure (high-pressure side of the system), unit: Pa; This is the tank pressure (low-pressure reference), in Pa. This is the laminar flow coefficient for external leakage of the pump, in meters. 3 ·s -1 ·Pa -1 ; This is the effective bulk modulus of the oil, in Pa. This refers to the high-voltage side control volume, measured in cubic meters (m³). 3 ; This is the rate of change of pressure with respect to time, expressed in Pa·s. -1 .

[0012] Preferably, the flow equation at the throttle valve orifice is in the form of:

[0013]

[0014] in, The volumetric flow rate through the valve orifice, in cubic meters per second (m³). 3 ·s -1 ; The valve orifice flow coefficient is dimensionless (0 < 0). ≤1); The instantaneous flow area at the valve orifice is expressed in m². 2 ; This refers to the density of the oil, expressed in kg·m³. -3 ; This refers to the valve inlet pressure, expressed in Pa. This represents the valve outlet pressure, in Pa. (·) is a symbolic function that ensures the correct flow direction.

[0015] Preferably, the force balance equation of the load cylinder is in the form of:

[0016]

[0017] in, This refers to the external load force, expressed in N (N). The pressure in the rodless chamber is expressed in Pa. The effective working area of ​​the rodless cavity is expressed in m². 2 ; The pressure in the rod chamber is expressed in Pa. The effective working area of ​​the rod cavity is expressed in m². 2 ; Mass of piston and load converted to weight, in kg; Piston acceleration, in m·s -2 ; This is the viscous damping coefficient of the hydraulic cylinder, with units of N·s·m. -1 ; Piston speed, in m·s -1 ; This represents the combined frictional force, expressed in N (N).

[0018] Preferably, the flow-pressure-temperature coupling equation is as follows:

[0019]

[0020]

[0021] in: Reference temperature The elastic modulus at 100°, expressed in Pa; This is the temperature sensitivity coefficient of the elastic modulus, in Kelvin. -1 ; Reference temperature Density of the sample, in kg·m -3 ; Density is the coefficient of thermal expansion, in Kelvin. -1 .

[0022] Preferably, a nonlinear state space is established using a pump-valve-load coupled dynamic model as the state equation:

[0023]

[0024]

[0025] in, Let k be the system state vector at time k, containing physical quantities such as flow rate, pressure, and temperature; (·) is the nonlinear state transition function obtained by discretization of the pump-valve-load coupled dynamics model; Let k be the control input vector at time k; The process noise vector follows a zero-mean Gaussian distribution; The observation vector at time k is the pressure obtained by the sensor. ,flow and temperature ; (·) is the observation function, which maps the state vector to the observation vector; To observe the noise vector, which follows a zero-mean Gaussian distribution, an extended Kalman filter is used for iterative prediction and correction to estimate the actual flow rate in real time. .

[0026] Preferably, step 4 includes calculating the estimated residuals. Construct a residual feature fusion and inversion network, with the input being the residual sequence. Temperature gradient and pressure pulsation characteristics; network output compensation amount After PI limiting, it is superimposed on The final coupled flow rate is obtained. .

[0027] Secondly, a hydraulic system coupled flow calculation system is provided, characterized in that the system includes a sensor module for acquiring pressure, flow, and temperature signals; a model building module for establishing a pump-valve-load coupled dynamic model; an extended Kalman filter module for dynamic flow estimation; and a residual feature fusion inversion module for error compensation and high-precision flow output.

[0028] Compared with existing technologies, the beneficial effects achieved by this invention are: the system dynamics are fully described by the pump-valve-load coupled dynamic model, improving the model accuracy; the extended Kalman filter achieves real-time optimal estimation of flow state with strong noise resistance; the residual feature fusion inversion network uses deep learning to mine the nonlinear error law in the residuals, realizes closed-loop compensation, and significantly improves the calculation accuracy; the modular design facilitates embedded deployment and is suitable for various complex scenarios such as engineering machinery, aviation hydraulics, and deep-sea equipment. Attached Figure Description

[0029] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0030] Figure 1 This is a flow change graph calculated by the coupled flow algorithm of this invention. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] To make the above-mentioned objectives, features and effects of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0033] Example 1: A method for calculating the coupled flow rate of a hydraulic system, comprising the following steps:

[0034] Step 1: Construct a pump-valve-load coupled dynamic model to obtain the flow-pressure-temperature coupled equation;

[0035] Step 2: Real-time acquisition of pressure, flow rate, and temperature signals from the hydraulic system, followed by preprocessing;

[0036] Step 3: Perform dynamic flow estimation on the preprocessed signal based on the extended Kalman filter;

[0037] Step 4: Use the residual feature fusion inversion network to perform closed-loop compensation for the estimation error and output a high-precision coupled flow value.

[0038] The pump-valve-load coupled dynamics model includes the flow continuity equation of the hydraulic pump, the flow equation at the throttle valve orifice, and the force balance equation of the load cylinder. The flow continuity equation of the hydraulic pump is in the form of:

[0039]

[0040] in, This is the theoretical flow rate at the pump outlet, in cubic meters per second (m³). 3 ·s -1 ; This refers to the pump's geometric displacement (displacement per revolution), in meters (m). 3 ·rad -1 ; The pump shaft angular velocity is expressed in rad·s. -1 , This is the laminar flow coefficient for internal leakage in the pump, in meters. 3 ·s -1 ·Pa -1 ; Pump outlet pressure (high-pressure side of the system), unit: Pa; This is the tank pressure (low-pressure reference), in Pa. This is the laminar flow coefficient for external leakage of the pump, in meters. 3 ·s -1 ·Pa -1 ; This is the effective bulk modulus of the oil, in Pa. This refers to the high-voltage side control volume, measured in cubic meters (m³). 3 ; This is the rate of change of pressure with respect to time, expressed in Pa·s. -1 .

[0041] The flow equation for the throttle valve orifice is in the form of:

[0042]

[0043] in, The volumetric flow rate through the valve orifice, in cubic meters per second (m³). 3 ·s -1 ; The valve orifice flow coefficient is dimensionless (0 < 0). ≤1); The instantaneous flow area at the valve orifice is expressed in m². 2 ; This refers to the density of the oil, expressed in kg·m³. -3 ; This refers to the valve inlet pressure, expressed in Pa. This represents the valve outlet pressure, in Pa. (·) is a symbolic function that ensures the correct flow direction.

[0044] The force balance equation for the load cylinder is in the form of:

[0045]

[0046] in, This refers to the external load force, expressed in N (N). The pressure in the rodless chamber is expressed in Pa. The effective working area of ​​the rodless cavity is expressed in m². 2 ; The pressure in the rod chamber is expressed in Pa. The effective working area of ​​the rod cavity is expressed in m². 2 ; Mass of piston and load converted to weight, in kg; Piston acceleration, in m·s -2 ; This is the viscous damping coefficient of the hydraulic cylinder, with units of N·s·m. -1 ; Piston speed, in m·s -1 ; This represents the combined frictional force of Coulomb and Stribeck, expressed in N.

[0047] By introducing the oil temperature T to the elastic modulus ,density and leakage laminar flow coefficient , The function mapping couples the above three types of equations within the framework of energy conservation, forming a flow-pressure-temperature coupled equation:

[0048]

[0049]

[0050] in: Reference temperature The elastic modulus at 100°, expressed in Pa; This is the temperature sensitivity coefficient of the elastic modulus, in Kelvin. -1 ; Reference temperature Density of the sample, in kg·m -3 ; Density is the coefficient of thermal expansion, in Kelvin. -1 .

[0051] Step 2 involves synchronously collecting pressure data using a pressure sensor, a turbine flow meter, and a temperature sensor. ,flow and temperature The acquired signals are filtered using a moving average to remove high-frequency noise. The filtered data are then aligned by timestamps to form an observation vector. .

[0052] Step 3 establishes a nonlinear state space using the coupled model as the state equation:

[0053]

[0054]

[0055] in, Let k be the system state vector at time k, containing physical quantities such as flow rate, pressure, and temperature; (·) is the nonlinear state transition function obtained by discretization of the pump-valve-load coupled dynamics model; This is the control input vector at time k, such as pump speed, valve opening, etc. The process noise vector follows a zero-mean Gaussian distribution with a covariance of ; The observation vector at time k is obtained from pressure, flow, and temperature sensors; (·) is the observation function, which maps the state vector to the observation vector; The observed noise vector follows a zero-mean Gaussian distribution with a covariance of An extended Kalman filter is used for iterative prediction-correction to estimate the actual flow rate in real time. .

[0056] Step 4 includes calculating the estimated residual. Construct a residual feature fusion and inversion network, with the input being the residual sequence. Temperature gradient and pressure pulsation characteristics; network output compensation amount After PI limiting, it is superimposed on The final coupled flow rate is obtained. .

[0057] Existing technologies typically , , and Treating it as a constant leads to a calculation error of >10% when the oil temperature changes from 40℃ to 80℃. This application explicitly introduces a temperature-sensitive function into the pump-valve-load coupled dynamic model. , , and And through calibration experiments, it is given and Specific numerical range ( , This reduces the flow error caused by temperature drift.

[0058] Taking the hydraulic system of a certain type of excavator boom as an example, the system parameters are as follows: pump displacement Rotation speed Maximum opening area of ​​valve port Flow coefficient Piston area of ​​hydraulic cylinder , Load quality Sampling frequency 1kHz, sensor accuracy ±0.25%FS.

[0059] The process involves four steps: Step 1, establishing a coupled model; Step 2, synchronously acquiring data; Step 3, estimating the flow rate using an extended Kalman filter; and Step 4, residual network compensation. Traditional extended Kalman filters rely solely on the white noise assumption for linear compensation, failing to handle non-Gaussian nonlinear errors such as cavitation at the throttle valve orifice and sudden load changes. This application constructs a residual feature fusion inversion network. Experimental results show that…

[0060] Compared with the turbine flow meter reference, the method of this invention reduces the maximum relative error from ±7.8% to ±1.3% under the step condition of 0→25MPa; the flow calculation fluctuation is reduced by 62% during the oil temperature drift process of 40→80℃; and the single calculation time is <0.8ms, which meets the real-time control requirements.

[0061] Example 2: A hydraulic system coupled flow calculation system, the system includes a sensor module for acquiring pressure, flow, and temperature signals; a model building module for establishing a pump-valve-load coupled dynamic model; an extended Kalman filter (EKF) module for dynamic flow estimation; and a residual feature fusion inversion module for error compensation and high-precision flow output.

[0062] This application deploys the coupled model, EKF, and residual network after quantization on a single MCU (128kB ROM, 64kB RAM), enabling the three modules of "model-filter-network" to run on the same chip with a power consumption of <0.8W.

[0063] Example 3: The computer-readable storage medium of this example stores a computer program that, when executed by a processor, implements the steps in the method for calculating the coupled flow of a hydraulic system in Example 1.

[0064] The computer-readable storage medium in this embodiment can be an internal storage unit of the terminal, such as the terminal's hard disk or memory; the computer-readable storage medium in this embodiment can also be an external storage device of the terminal, such as a plug-in hard disk, smart memory card, secure digital card, flash memory card, etc. equipped on the terminal; furthermore, the computer-readable storage medium can include both the terminal's internal storage unit and external storage devices.

[0065] The computer-readable storage medium of this embodiment is used to store computer programs and other programs and data required by the terminal. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0066] Example 4: The computer device of this example includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the method for calculating the coupling flow of a hydraulic system in Example 1.

[0067] In this embodiment, the processor can be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The memory can include read-only memory and random access memory, and provides instructions and data to the processor. A portion of the memory can also include non-volatile random access memory. For example, the memory can also store device type information.

[0068] Those skilled in the art will clearly understand that each implementation can be achieved using software plus the necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0069] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for calculating the coupled flow rate of a hydraulic system, characterized in that, Includes the following steps: Step 1: Construct a pump-valve-load coupled dynamic model, including the flow continuity equation of the hydraulic pump, the flow equation of the throttle valve orifice, and the force balance equation of the load cylinder. The flow-pressure-temperature coupled equation is obtained by coupling the three types of equations under the energy conservation framework. Step 2: Real-time acquisition of pressure, flow rate, and temperature signals from the hydraulic system, followed by preprocessing; Step 3: Perform dynamic flow estimation on the preprocessed signal based on the extended Kalman filter; Step 4: Use the residual feature fusion inversion network to perform closed-loop compensation for the estimation error and output a high-precision coupled flow value.

2. The method for calculating the coupled flow rate of a hydraulic system according to claim 1, characterized in that, The flow continuity equation of the hydraulic pump is in the form of: ； in, This is the theoretical flow rate at the pump outlet, in cubic meters per second (m³). 3 ·s -1 ; This refers to the pump's geometric displacement (displacement per revolution), in meters (m). 3 ·rad -1 ; The pump shaft angular velocity is expressed in rad·s. -1 , This is the laminar flow coefficient for internal leakage in the pump, in meters. 3 ·s -1 ·Pa -1 ; Pump outlet pressure (high-pressure side of the system), unit: Pa; This is the tank pressure (low-pressure reference), in Pa. This is the laminar flow coefficient for external leakage of the pump, in meters. 3 ·s -1 ·Pa -1 ; This is the effective bulk modulus of the oil, in Pa. This refers to the high-voltage side control volume, measured in cubic meters (m³). 3 ; This is the rate of change of pressure with respect to time, expressed in Pa·s. -1 .

3. The method for calculating the coupled flow rate of a hydraulic system according to claim 2, characterized in that, The flow equation at the throttle valve orifice is in the form of: ； in, The volumetric flow rate through the valve orifice, in cubic meters per second (m³). 3 ·s -1 ; The valve orifice flow coefficient is dimensionless (0 < 0). ≤1); The instantaneous flow area at the valve orifice is expressed in m². 2 ; This refers to the density of the oil, expressed in kg·m³. -3 ; This refers to the valve inlet pressure, expressed in Pa. This refers to the valve outlet pressure, expressed in Pa. (·) is a symbolic function that ensures the correct flow direction.

4. The method for calculating the coupled flow rate of a hydraulic system according to claim 3, characterized in that, The force balance equation for the load cylinder is in the form of: ； in, This refers to the external load force, expressed in N (N). The pressure in the rodless chamber is expressed in Pa. The effective working area of ​​the rodless cavity is expressed in m². 2 ; The pressure in the rod chamber is expressed in Pa. The effective working area of ​​the rod cavity is expressed in m². 2 ; Mass of piston and load converted to weight, in kg; Piston acceleration, in m·s -2 ; This is the viscous damping coefficient of the hydraulic cylinder, with units of N·s·m. -1 ; Piston speed, in m·s -1 ; This represents the combined frictional force, expressed in N (N).

5. The method for calculating the coupled flow rate of a hydraulic system according to claim 4, characterized in that, The flow-pressure-temperature coupling equation: ； ； in: Reference temperature The elastic modulus at 100°, expressed in Pa; This is the temperature sensitivity coefficient of the elastic modulus, in Kelvin. -1 ; Reference temperature Density of the sample, in kg·m -3 ; Density is the coefficient of thermal expansion, in Kelvin. -1 .

6. The method for calculating the coupling flow rate of a hydraulic system according to claim 1, characterized in that, Using the pump-valve-load coupled dynamic model as the state equation, a nonlinear state space is established: ； ； in, Let k be the system state vector at time k, containing physical quantities such as flow rate, pressure, and temperature; (·) is the nonlinear state transition function obtained by discretization of the pump-valve-load coupled dynamics model; Let k be the control input vector at time k; The process noise vector follows a zero-mean Gaussian distribution; The observation vector at time k is the pressure obtained by the sensor. ,flow and temperature ; (·) is the observation function, which maps the state vector to the observation vector; To observe the noise vector, which follows a zero-mean Gaussian distribution, an extended Kalman filter is used for iterative prediction and correction to estimate the actual flow rate in real time. .

7. The method for calculating the coupled flow rate of a hydraulic system according to claim 6, characterized in that, Step 4 includes calculating the estimated residuals. Construct a residual feature fusion and inversion network, with the input being the residual sequence. Temperature gradient and pressure pulsation characteristics; network output compensation amount After PI limiting, it is superimposed on The final coupled flow rate is obtained. .

8. A system for calculating the coupled flow rate of a hydraulic system, characterized in that, The system includes a sensor module for acquiring pressure, flow, and temperature signals; a model building module for establishing a pump-valve-load coupled dynamic model; an extended Kalman filter module for dynamic flow estimation; and a residual feature fusion and inversion module for error compensation and high-precision flow output.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the method for calculating the coupled flow of a hydraulic system as described in any one of claims 1-7.

10. A computer device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the method for calculating the coupled flow rate of a hydraulic system as described in any one of claims 1-7.

Images