Control method, device and equipment for distributed hydraulic system of loading machine and medium

Abstract

The invention discloses a control method, device, equipment and medium for a distributed hydraulic system of a loader, and relates to the technical field of hydraulic systems of loaders. The control method comprises the steps that control signals of the steering oil cylinder, the lifting oil cylinder and the tipping bucket oil cylinder are obtained; and according to the control signal, the stretching speed of each oil cylinder is obtained. According to the stretching speed of each oil cylinder, a first theoretical demand flow is obtained; and the first theoretical demand flow is compensated through model self-adaption, and the first actual demand flow of each oil cylinder is obtained. And according to the first actual demand flow of each oil cylinder, the theoretical valve port demand flow of each flow output valve port of the flow distribution valve group is constructed. And compensation is carried out through deep reinforcement learning, and the actual valve port demand flow of each valve is obtained. And according to the actual valve port demand flow of each valve, the demand flow of the working pump and the steering pump and the rotating speeds of the first motor and the second motor are obtained. And the opening degree of each valve element of the valve element assembly is calculated according to the actual valve port demand flow of each valve.

Description

Technical Field

[0001] The present invention relates to the technical field of loader hydraulic systems, and in particular to a control method for a loader distributed hydraulic system. Background Art

[0002] With the continuous development of industry, loaders play a vital role in various engineering operations, and their electrification has become an inevitable trend in the industry. In many engineering operations, there is an urgent need for energy-saving and efficient operation of loaders to reduce energy consumption and improve the economic efficiency and sustainability of operations.

[0003] At present, the common solution is to directly use an electric motor instead of the engine to drive the original hydraulic transmission system. Although this solution achieves power energy saving to a certain extent, it still has many problems.

[0004] First, the hydraulic transmission system itself is inefficient, resulting in high power consumption of the entire machine. This not only increases the cost of use, but also limits the application scope of the loader in some operating scenarios that require endurance.

[0005] Secondly, due to the limitations of the hydraulic system efficiency, the demand for battery capacity has increased significantly, which not only increases the initial purchase cost of the equipment, but also increases the weight and volume of the equipment, which has a certain negative impact on the maneuverability and flexibility of the equipment, and thus affects the loader's operating efficiency and adaptability in complex and changing working environments.

[0006] In summary, in the process of loader electrification, the application of existing hydraulic transmission systems faces many challenges in energy saving and overall performance improvement, and it is urgent to seek more efficient and energy-saving hydraulic system solutions to meet the needs of engineering operations. Summary of the Invention

[0007] The present invention provides a control method, device, equipment and medium for a distributed hydraulic system of a loader to improve at least one of the above technical problems.

[0008] In a first aspect, the present invention provides a control method for a distributed hydraulic system of a loader, which comprises steps S1 to S6.

[0009] S1. Obtain control signals of the steering cylinder, lifting cylinder, and dump cylinder.

[0010] S2. Obtain the extension speed of each oil cylinder according to the control signal.

[0011] S3. Obtain a first theoretical required flow rate according to the extension speed of each oil cylinder, and compensate the first theoretical required flow rate using model adaptation to obtain a first actual required flow rate of each oil cylinder.

[0012] S4. Based on the first actual required flow rate of each oil cylinder, a theoretical valve port required flow rate of each flow output valve port of the flow distribution valve group is constructed, and compensation is performed through deep reinforcement learning to obtain the actual valve port required flow rate of each valve.

[0013] S5. According to the actual valve port required flow rates of the respective valves, the required flow rates of the working pump and the steering pump, as well as the rotational speeds of the first motor and the second motor are obtained.

[0014] S6. Calculate the opening of each valve core of the valve core assembly according to the actual valve port required flow of each valve.

[0015] As a further solution of the present invention, step S3 specifically includes: According to the extension speed of each oil cylinder, the first theoretical required flow rate of each oil cylinder is obtained. The first theoretical required flow rate model of a single oil cylinder is as follows: .

[0016] Where, The first theoretical required flow rate of the rodless chamber when the piston rod is extended. The first theoretical required flow rate of the rod chamber when the piston rod is retracted. is the effective area of the rodless cavity, is the effective area of the rod cavity, is the volume of the rodless cavity, is the volume of the rod cavity, is the effective bulk elastic modulus of the oil, is the rodless cavity pressure of the cylinder, The rod cavity pressure of the cylinder, Derivative, is the derivative of partial pressure with respect to time, is the cylinder extension speed.

[0017] Adopt model adaptation to compensate the first theoretical demand flow and obtain the first actual demand flow. Specifically including: Define the system parameter error vector. , where is the system parameter error vector, is the area error, Elastic modulus deviation, valve flow coefficient drift .

[0018] A first compensation model of the first theoretical demand flow model is obtained according to the first theoretical demand flow model and the system parameter error vector. Where, is the first compensation demand flow, is the nominal effective area of the cylinder cavity, is a real-time estimate of the area error, is a real-time estimate of the flow coefficient drift, is the valve port pressure difference.

[0019] Constraints are performed according to the first compensation model to obtain a first constraint model. Where, is the first actual demand flow, is the proportional gain coefficient, is the actual output pressure of the pump, To set the pressure threshold.

[0020] Define a flow tracking error and derive a parameter update rate based on the flow tracking error to obtain the first actual demand flow. The flow tracking error is: The parameter update rate is: Where, is the flow tracking error, is the target flow reference value, is the updated area error, is the updated flow coefficient error, is the area gain coefficient, is the flow coefficient gain coefficient.

[0021] As a further solution of the present invention, the theoretical valve port required flow rate of each flow output valve port of the flow distribution valve group is as follows: The theoretical flow rate of valve outlet A1 is: .

[0022] The theoretical flow rate of valve outlet A2 is: .

[0023] The theoretical flow rate of valve outlet A3 is: .

[0024] The theoretical flow rate of valve outlet A11 is: .

[0025] The theoretical flow rate of valve outlet A12 is: .

[0026] The theoretical flow rate of valve outlet A21 is: .

[0027] The theoretical flow rate of valve outlet A22 is: . Where, is the theoretical valve port flow requirement of valve outlet A1, The actual required flow rate of the lifting cylinder, is the pipe volume of the first circuit, is the load pressure of valve outlet A1, The theoretical valve port flow rate required at valve outlet A2, is the actual required flow of the bucket cylinder, is the pipe volume of the second circuit, is the load pressure of valve outlet A2, The theoretical valve port flow rate required at valve outlet A3, is the actual required flow of the steering cylinder, is the pipe volume of the third circuit, is the load pressure of valve outlet A3, The theoretical valve port flow rate required for valve outlet A11, is the volume of the pipe from valve outlet A11 to A1, is the load pressure of valve outlet A11, The theoretical valve port flow rate required for valve outlet A12, is the pipe volume from valve outlet A11 to A2, is the load pressure of valve outlet A12, The theoretical valve port flow rate required for valve outlet A21, is the volume of the pipe from valve outlet A21 to A1, is the load pressure of valve outlet A21, The theoretical valve port flow rate required for valve outlet A22, is the volume of the pipe from valve outlet A22 to A2, is the load pressure of valve outlet A22, is the effective bulk elastic modulus of the oil, Derivative, is the time derivative of pressure, It is the maximum output flow of a single pump.

[0028] As a further solution of the present invention, compensation is performed through deep reinforcement learning to obtain the actual valve port required flow of each valve, specifically including: Define dynamic environmental parameters, collect relevant data, and create data sets. . Where, Dynamic environmental parameters, Input voltage signal to the handle, is the rodless cavity pressure of the cylinder, The rod cavity pressure of the cylinder, The real data collected during training, is the target speed, is the cylinder displacement, is the cylinder speed.

[0029] Define the flow demand function parameters as continuous actions. Where, is the action vector, is the flow-pressure nonlinear friction compensation coefficient, is the flow-pressure nonlinear leakage compensation coefficient, For time.

[0030] Construct the loss function. Where, is the loss function, For the expected value, is the predicted value of flow compensation, is the neural network weight parameter.

[0031] according to 、 and Train a deep reinforcement learning neural network, using the tracking accuracy term of the loss function , training model output compensation parameters , to ensure the accuracy of demand flow.

[0032] The theoretical valve port required flow rate is compensated according to the compensation parameter to obtain the actual valve port required flow rate of each valve.

[0033] As a further solution of the present invention, according to the actual valve port required flow of each valve, the required flow of the working pump and the steering pump, as well as the speed of the first motor and the second motor are obtained, which specifically includes: According to the actual valve port demand flow of each valve, the demand flow of the working pump and the steering pump is obtained. The demand flow of the working pump is: The required flow rate of the steering pump is: Where, is the required flow rate of the working pump, is the required flow of the steering pump, The theoretical valve port flow rate required for valve outlet A11, The theoretical valve port flow rate required for valve outlet A12, The theoretical valve port flow rate required at valve outlet A3, The theoretical valve port flow rate required for valve outlet A21, It is the theoretical valve port required flow rate of valve outlet A22.

[0034] According to the required flow of the working pump and steering pump, based on the motor efficiency MAP diagram and the pump efficiency MAP diagram, the table lookup method is used with the optimal efficiency as the constraint condition to obtain the real-time displacement of the working pump and steering pump, as well as the real-time speed of the first motor and the second motor.

[0035] According to the actual displacement signals of the steering cylinder, the lifting cylinder and the dump cylinder, the real-time displacement and the real-time rotational speed are updated in real time through fuzzy control.

[0036] As a further solution of the present invention, the calculation model of the valve core opening is: .

[0037] Where, is the valve output flow. is the flow coefficient, is the valve core opening, is the valve core area, is the oil density, is the pressure difference across the valve, is the valve inlet pressure. is the valve outlet pressure.

[0038] As a further embodiment of the present invention, the control signal includes a manipulation signal and a status signal. The manipulation signal includes a handle signal, a steering wheel signal, an accelerator pedal signal, and a brake pedal signal. The status signal includes the first motor speed, the working pump outlet pressure, the second motor speed, the steering pump outlet pressure, the lift cylinder large and small chamber pressures, the dump cylinder large and small chamber pressures, and the steering cylinder large and small chamber pressures.

[0039] As a further solution of the present invention, the extension speed model is: Where, Input voltage signal to the handle, is the mapping coefficient, is the cylinder extension speed.

[0040] In a second aspect, the present invention provides a control device for a distributed hydraulic system of a loader, which includes a signal module, a speed module, a cylinder flow module, a valve flow module, a pump flow module and a valve core module.

[0041] The signal module is used to obtain the control signals of the steering cylinder, lifting cylinder and dump cylinder.

[0042] The speed module is used to obtain the extension speed of each cylinder according to the control signal.

[0043] The oil cylinder flow module is used to obtain a first theoretical required flow according to the extension speed of each oil cylinder, and to compensate the first theoretical required flow by using a model adaptive method to obtain a first actual required flow of each oil cylinder.

[0044] The valve flow module is configured to construct a theoretical valve port demand flow rate for each flow output valve port of the distribution valve group based on the first actual demand flow rate of each cylinder. The module also performs compensation through deep reinforcement learning to obtain the actual valve port demand flow rate of each valve.

[0045] The pump flow module is used to obtain the required flow of the working pump and the steering pump, as well as the rotational speed of the first motor and the second motor according to the actual valve port required flow of each valve.

[0046] The valve core module is used to calculate the opening of each valve core of the valve core assembly according to the actual valve port required flow of each valve.

[0047] In a third aspect, the present invention provides a control device for a distributed hydraulic system of a loader, comprising a processor, a memory, and a computer program stored in the memory. The computer program can be executed by the processor to implement the control method of the distributed hydraulic system of a loader as described in any paragraph of the first aspect.

[0048] In a fourth aspect, the present invention provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a control method for a loader distributed hydraulic system as described in any paragraph of the first aspect.

[0049] By adopting the above technical solution, the present invention can achieve the following technical effects: A control method for a distributed hydraulic system of a loader according to an embodiment of the present invention can accurately identify the driver's operating intentions under normal operating conditions, eliminate the bypass throttling loss and pressure coupling loss existing in the centralized hydraulic system through coordinated control of pumps and valves, and reduce the additional oil inlet and return oil throttling losses caused by excessively high return oil back pressure, which is a significant improvement. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the specific implementation methods of the present invention. It should be understood that the following drawings only show certain specific implementation methods of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 It is a flow chart of the control method of the distributed hydraulic system of the loader.

[0052] Figure 2 It is a structural diagram of the loader's distributed hydraulic system.

[0053] Markings in the figure: 1-working pump, 2-first motor, 3-steering pump, 4-second motor, 5-distribution valve group, 6-hydraulic steering gear, 7-steering cylinder, 8-tipping cylinder, 9-tipping oil circuit assembly, 10-lifting cylinder, 11-lifting oil circuit assembly. DETAILED DESCRIPTION

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present invention.

[0055] Example 1, please refer to Figures 1 to 2 A first embodiment of the present invention provides a method for controlling a distributed hydraulic system of a loader, which can be executed by the loader or a control device of the loader (hereinafter referred to as the control device). Specifically, the method is executed by one or more processors in the control device to implement steps S1 to S6.

[0056] S1, obtain the control signals of the steering cylinder 7, the lifting cylinder 10 and the dump cylinder 8. The sampling period of the control signal is Need to be less than the system response time (usually ), to avoid signal delay. In addition, after obtaining the control signal, the collected voltage signal needs to be smoothed, filtered and normalized.

[0057] Preferably, in this embodiment, the loader requires control of two operations during operation: rotation and digging. These operations involve the steering cylinder 7, the lift cylinder 10, and the bucket cylinder 8. The control signal includes a handle signal. The handle signal is a voltage signal output by the handle. The handle output voltage signal (e.g., 0-5V) corresponds to the operator's control intention (corresponding to the push rod displacement or angle).

[0058] Specifically, the control signals include control signals and status signals. The control signals include the handle signal, steering wheel signal, accelerator pedal signal, and brake pedal signal. The status signals include the speed of the first motor 2, the outlet pressure of the working pump 1, the speed of the second motor 4, the outlet pressure of the steering pump 3, the pressures of the lift cylinder 10, the dump cylinder 8, and the steering cylinder 7.

[0059] S2. Obtain the extension speed of each oil cylinder according to the control signal.

[0060] Before using the control signals obtained in step S1 to construct the first required flow rates for the lift cylinder 10, the bucket cylinder 8, and the steering cylinder 7, the embodiment of the present invention first calculates the extension speed of the cylinders. Then, based on the extension speed of the cylinders, the first required flow rates are further calculated.

[0061] The extension velocity model is: .

[0062] Where, Input voltage signal to the handle, is the mapping coefficient, is the cylinder extension speed.

[0063] The mapping coefficient is calculated based on the actual system. Loaders with different structures have different mapping coefficients, which are characteristic coefficients of the loader.

[0064] S3. Obtain a first theoretical required flow rate for each cylinder based on the extension speed of each cylinder. Model adaptation is then used to compensate the first theoretical required flow rate to obtain a first actual required flow rate. Preferably, step S3 includes steps S31 and S32.

[0065] S31. Obtaining a first theoretical required flow rate of each oil cylinder according to the extension speed of each oil cylinder, wherein the oil cylinder is a single-rod oil cylinder.

[0066] The first theoretical demand flow model for a single cylinder is as follows: .

[0067] Where, The first theoretical required flow rate of the rodless chamber when the piston rod is extended. The first theoretical required flow rate of the rod chamber when the piston rod is retracted. is the effective area of the rodless cavity, is the effective area of the rod cavity, is the volume of the rodless cavity, is the volume of the rod cavity, is the effective bulk elastic modulus of the oil, is the rodless cavity pressure of the cylinder, The rod cavity pressure of the cylinder, Derivative, is the derivative of partial pressure with respect to time, is the cylinder extension speed.

[0068] S32, using the model to adapt to compensate the first theoretical demand flow, to obtain the first actual demand flow. Specifically, the inventors have found through a lot of creative work that As the initial model of the dynamic pressure change term, compensation is required to obtain a more accurate value. Preferably, step S32 includes steps S321 to S324.

[0069] S321. Define a system parameter error vector. , where is the system parameter error vector, is the area error (manufacturing tolerance, wear), The elastic modulus deviation (oil temperature change), valve flow coefficient drift (Pollution level impact).

[0070] S322: Acquire a first compensation model of the first theoretical demand flow model according to the first theoretical demand flow model and the system parameter error vector.

[0071] The first compensation model is: .

[0072] Where, is the first compensation demand flow, is the nominal effective area of the cylinder cavity, is a real-time estimate of the area error, is a real-time estimate of the flow coefficient drift, is the valve port pressure difference, is the cylinder extension speed.

[0073] in, Where, is the valve inlet pressure, is the valve outlet pressure.

[0074] S323: Constraining is performed according to the first compensation model to obtain a first constraint model. Specifically, the first constraint model considers pressure feedback compensation flow saturation and adds constraint conditions thereto.

[0075] The first constraint model is: .

[0076] Where, is the first actual demand flow, is the proportional gain coefficient (used for pressure feedback compensation), is the actual output pressure of the pump, To set the pressure threshold (to prevent the pump from overflowing), is the first compensation demand flow.

[0077] S324: Define a flow tracking error and derive a parameter update rate based on the flow tracking error to obtain the first actual required flow.

[0078] The flow tracking error is: .

[0079] Where, is the flow tracking error, is the target flow reference value, is the first compensation demand flow.

[0080] The parameter update rate is: .

[0081] Where, is the flow tracking error, is the target flow reference value, is the updated area error, is the updated flow coefficient error, is the area gain coefficient, is the flow coefficient gain coefficient, is the cylinder extension speed, is the pressure difference at the valve port. and Used to determine the convergence speed.

[0082] In this embodiment, a theoretical model is first used to obtain the theoretical required flow rates for the lift cylinder 10, bucket cylinder 8, and steering cylinder 7 during operation. Compensation is then used to obtain a more accurate actual required flow rate, thereby preventing the excavator from malfunctioning and slowing down due to insufficient pressure, as well as energy loss due to excessive pressure.

[0083] S4. Based on the first actual required flow rates of each oil cylinder, a theoretical valve port required flow rate of each flow output valve port of the flow distribution valve group 5 is constructed, and compensation is performed through deep reinforcement learning to obtain the actual valve port required flow rate.

[0084] In an optional embodiment, the first actual required flow rate when the lifting cylinder 10, the dump cylinder 8, and the steering cylinder 7 are in action is used as input, and the input data needs to be smoothed and filtered, and then the processed data is normalized.

[0085] The theoretical valve port required flow rate of each flow output valve port of the distribution valve group 5 is as follows: The theoretical flow rate of valve outlet A1 is: .

[0086] The theoretical flow rate of valve outlet A2 is: .

[0087] The theoretical flow rate of valve outlet A3 is: .

[0088] The theoretical flow rate of valve outlet A11 is: .

[0089] The theoretical flow rate of valve outlet A12 is: .

[0090] The theoretical flow rate of valve outlet A21 is: .

[0091] The theoretical flow rate of valve outlet A22 is: .

[0092] Where, The theoretical valve port flow rate required at valve outlet A1, is the actual required flow rate of the lifting cylinder (10), is the pipe volume of the first circuit, is the load pressure of valve outlet A1, The theoretical valve port flow rate required at valve outlet A2, is the actual required flow rate of the bucket cylinder (8), is the pipe volume of the second circuit, is the load pressure of valve outlet A2, The theoretical valve port flow rate required at valve outlet A3, is the actual required flow of the steering cylinder (7), is the pipe volume of the third circuit, is the load pressure of valve outlet A3, The theoretical valve port flow rate required for valve outlet A11, is the volume of the pipe from valve outlet A11 to A1, is the load pressure of valve outlet A11, The theoretical valve port flow rate required for valve outlet A12, is the volume of the pipe from valve outlet A11 to A2, is the load pressure of valve outlet A12, The theoretical valve port flow rate required for valve outlet A21, is the volume of the pipe from valve outlet A21 to A1, is the load pressure of valve outlet A21, The theoretical valve port flow rate required for valve outlet A22, is the volume of the pipe from valve outlet A22 to A2, is the load pressure of valve outlet A22, is the effective bulk elastic modulus of the oil, Derivative, is the time derivative of pressure, is the maximum output flow of a single pump. The load pressure is monitored by a pressure sensor.

[0093] Specifically, the valve outlet A1 is connected to the lifting cylinder 10 to supply oil to the lifting cylinder 10. The theoretical valve port required flow rate of the valve outlet A1 is composed of the cylinder required flow rate + the compression amount of the oil, and the same is true for the valve outlets A2 and A3.

[0094] In this embodiment, the three outlets of the flow distribution valve assembly 5 (valve outlet A1, valve outlet A2, and valve outlet A3) are respectively connected to the oil inlet control valve groups of the lift cylinder 10, the bucket cylinder 8, and the steering cylinder 7. The oil inlet control valve groups control whether the hydraulic oil flows to the rod chamber or the rodless chamber of the cylinder, thereby controlling the extension and contraction of the cylinder.

[0095] Preferably, valve outlet A1 is obtained by connecting valve outlet A11 and valve outlet A21 in parallel. Valve outlet A2 is obtained by connecting valve outlet A12 and valve outlet A22 in parallel. When valve outlet A11 cannot meet the flow output demand, the flow of valve outlet A21 is supplemented to port A1 by merging. When A22 cannot meet the flow output demand, the flow of valve outlet A12 is supplemented to port A2 by merging. As the initial model of the dynamic pressure change term, algorithmic compensation is required to obtain a more accurate value. In this embodiment, a deep reinforcement learning algorithm is used to compensate the theoretical valve port demand flow rate to obtain the actual valve port demand flow rate. Preferably, the deep reinforcement learning algorithm is used to compensate and obtain the actual valve port demand flow rate of each valve, including steps S41 to S44.

[0096] S41. Define dynamic environmental parameters, collect relevant data, and create a data set.

[0097] .

[0098] Where, Dynamic environmental parameters, Input voltage signal to the handle, is the rodless cavity pressure of the cylinder, The rod cavity pressure of the cylinder, The real data collected during training, is the target speed, is the cylinder displacement, is the cylinder speed. and Measured by displacement sensor and velocity sensor.

[0099] S42. Define the flow demand function parameters as continuous action.

[0100] .

[0101] Where, is the action vector (which is a compensation coefficient), is the flow-pressure nonlinear friction compensation coefficient, is the flow-pressure nonlinear leakage compensation coefficient, is the time. and For friction / leakage compensation.

[0102] S43. Construct a loss function.

[0103] ; Where, is the loss function, For the expected value, is the predicted value of flow compensation, is the neural network weight parameter, The real data collected during training, is the target speed, Dynamic environmental parameters, It is the actual valve port demand flow.

[0104] S44, according to 、 and Train a deep reinforcement learning neural network, using the tracking accuracy term of the loss function , training model output compensation parameters , to ensure the accuracy of demand flow.

[0105] S45 . Compensate the theoretical valve port required flow rate according to the compensation parameter to obtain the actual valve port required flow rate of each valve.

[0106] Specifically, deep learning neural networks collect empirical data during training Stored in the experience pool D, and then randomly sampled from the experience pool D to obtain a set of historical data ,calculate The value of the target neural network output layer is used as the target value for the next state. The theoretical valve port flow requirement is compensated using the above method, thereby deriving the precise flow function for the flow diversion and confluence requirements of each flow output valve port of the distribution valve group 5, thereby avoiding energy loss.

[0107] S5. Based on the actual valve port demand flow rates of the valves, the demand flow rates of the working pump 1 and the steering pump 3, as well as the rotational speeds of the first motor 2 and the second motor 4, are obtained to control the working pump 1, the steering pump 3, the first motor 2, and the second motor 4. Preferably, step S5 specifically includes steps S51 to S53.

[0108] S51 . Obtain the required flow rates of the working pump 1 and the steering pump 3 according to the actual required flow rates of the valve ports of the respective valves.

[0109] The required flow rate of the working pump (1) is: .

[0110] The required flow rate of the steering pump (3) is: .

[0111] Where, is the required flow rate of the working pump (1), is the required flow of the steering pump (3), The theoretical valve port flow rate required for valve outlet A11, The theoretical valve port flow rate required for valve outlet A12, The theoretical valve port flow rate required at valve outlet A3, The theoretical valve port flow rate required for valve outlet A21, It is the theoretical valve port required flow rate of valve outlet A22.

[0112] S52. According to the required flow of the working pump 1 and the steering pump 3, based on the motor efficiency MAP diagram and the pump efficiency MAP diagram, a table lookup method is used with optimal efficiency as a constraint to obtain the real-time displacement of the working pump 1 and the steering pump 3, and the real-time speed of the first motor 2 and the second motor 4.

[0113] Specifically, the working pump 1 and steering pump 3 are variable displacement pumps, which can be axial piston variable displacement pumps with electric proportional displacement control. The displacement is changed by adjusting the swash plate angle (i.e., valve core opening) through an electrical signal. The motor directly changes the displacement by changing the speed.

[0114] S53: Based on the actual displacement signals of the steering cylinder 7, the lift cylinder 10, and the bucket cylinder 8, the real-time displacement and real-time speed are updated in real time through fuzzy control. The following uses the steering cylinder as an example to describe how to update the real-time displacement and real-time speed through fuzzy control. Specifically, S53 includes steps S531 through S534.

[0115] S531. Define displacement tracking error: .

[0116] Where, is the displacement tracking error, is the cylinder displacement, is the reference displacement of the cylinder.

[0117] S532: Introduce a sliding surface to suppress chattering based on the displacement tracking error: .

[0118] Where, is the sliding surface function, express The derivative of is the proportional sliding mode design parameter, is the integral sliding mode design parameter, is the integral variable, is the tracking error function with respect to the integral variable, is the integral differential, is the displacement tracking error.

[0119] S533, take the derivative of the sliding surface and let , and then substitute it into the dynamic model to obtain the control flow: .

[0120] Where, for The derivative of for The derivative of for The abbreviation of for The abbreviation of To control the flow, is the effective area of the cylinder, is the cylinder reference speed, To control the cavity volume, is the effective bulk elastic modulus of the oil, is the pressure change rate (i.e. the derivative value of the actuating chamber pressure), is the estimated value of leakage coefficient, is the pressure difference between the actuating chamber and the oil return chamber, is the cylinder load mass, is the first sliding mode design parameter, are the design parameters of the second sliding mode, is the reference displacement of the cylinder.

[0121] S534. Based on the motor efficiency MAP diagram and the pump efficiency MAP diagram according to the control flow, a table lookup method is used with the optimal efficiency as a constraint to obtain the real-time displacement of the working pump 1 and the steering pump 3, and the real-time speed of the first motor 2 and the second motor 4.

[0122] S6. Calculate the opening of each valve core of the valve core assembly according to the actual valve port required flow of each valve, so as to control the solenoid valve and output the required flow from each flow output valve port by diverting and merging the flow.

[0123] .

[0124] Where, is the valve output flow. is the flow coefficient, is the valve core opening, is the valve core area, is the oil density, is the pressure difference across the valve, is the valve inlet pressure. is the valve outlet pressure.

[0125] Specifically, according to the above method, a flow function of the diversion and merging requirements of each flow output valve port of the distribution valve group 5 can be constructed, and the flow rate of the valve can be changed by controlling the valve core opening, so as to supply energy to the cylinder more accurately and reduce the energy loss during the cylinder driving process, which is a significant improvement.

[0126] On the basis of the above embodiment, in an optional embodiment of the present invention, the steering cylinder 7 and the valve outlet A3 are connected via a hydraulic steering gear 6. The hydraulic steering gear 6 is used to switch the valve outlet A3 to the rod chamber and the rodless chamber of the steering cylinder 7, thereby controlling the extension and retraction of the steering cylinder 7. The bucket cylinder 8 and the valve outlet A2 are connected via a bucket oil circuit assembly 9. The bucket oil circuit assembly 9 is used to switch the valve outlet A2 to the rod chamber and the rodless chamber of the bucket cylinder 8, thereby controlling the extension and retraction of the bucket cylinder 8. The lifting cylinder 10 and the valve outlet A1 are connected via a lifting oil circuit assembly 11. The lifting oil circuit assembly 11 is used to switch the valve outlet A1 to the rod chamber and the rodless chamber of the lifting cylinder 10, thereby controlling the extension and retraction of the lifting cylinder 10.

[0127] Preferably, a control method for a distributed hydraulic system of a loader further includes step S7.

[0128] S7. Calculate the opening of the valve core of each solenoid valve in the hydraulic steering gear 6, the bucket oil circuit assembly 9 and the lifting oil circuit assembly 11 according to the first actual required flow of each oil cylinder, so as to control the corresponding solenoid valve to perform corresponding actions.

[0129] Specifically, by controlling the flow rate and direction of the hydraulic oil through the hydraulic steering gear 6, the dump bucket oil circuit assembly 9 and the lifting oil circuit assembly 11, the flow rate and pressure of the hydraulic oil can be controlled more accurately, and pressure loss can be better avoided, which is a significant improvement.

[0130] On the basis of the above embodiment, in an optional embodiment of the present invention, as Figure 2As shown, the distribution valve group 5 is provided with a valve outlet A1 connected to the lifting cylinder 10, a valve outlet A2 connected to the dump cylinder 8, a valve outlet A3 connected to the steering cylinder 7, a valve outlet A11 with one end used to be connected to the working pump 1 and the other end connected to the valve outlet A1, a valve outlet A12 with one end used to be connected to the working pump 1 and the other end connected to the valve outlet A2, a valve outlet A21 with one end used to be connected to the steering pump 3 and the other end connected to the valve outlet A1, and a valve outlet A22 with one end used to be connected to the steering pump 3 and the other end connected to the valve outlet A2.

[0131] Specifically, when valve outlet A1 cannot meet the required flow output, the flow distribution valve assembly 5 can combine the flow from valve outlet A21 to supplement the flow at outlet A1. When A2 cannot meet the required flow output, the flow from A12 can be combined to supplement the flow at outlet A2. This more fully leverages the coordination between the steering pump 3 and the working pump 1, ensuring the stability of system operation and representing a significant improvement.

[0132] A control method for a distributed hydraulic system of a loader according to an embodiment of the present invention can accurately identify the driver's operating intentions under normal operating conditions, eliminate the bypass throttling loss and pressure coupling loss existing in the centralized hydraulic system through coordinated control of pumps and valves, and reduce the additional oil inlet and return oil throttling losses caused by excessively high return oil back pressure, which is a significant improvement.

[0133] Embodiment 2: The present invention provides a control device for a distributed hydraulic system of a loader, which includes a signal module, a speed module, a cylinder flow module, a valve flow module, a pump flow module and a valve core module.

[0134] The signal module is used to obtain the control signals of the steering cylinder 7, the lifting cylinder 10 and the dump cylinder 8.

[0135] The speed module is used to obtain the extension speed of each cylinder according to the control signal.

[0136] The oil cylinder flow module is used to obtain a first theoretical required flow according to the extension speed of each oil cylinder, and to compensate the first theoretical required flow by using a model adaptive method to obtain a first actual required flow of each oil cylinder.

[0137] The valve flow module is used to construct the theoretical valve port required flow rate of each flow output valve port of the distribution valve group 5 based on the first actual required flow rate of each cylinder. It also performs compensation through deep reinforcement learning to obtain the actual valve port required flow rate of each valve.

[0138] The pump flow module is used to obtain the required flow of the working pump 1 and the steering pump 3, as well as the rotation speed of the first motor 2 and the second motor 4 according to the actual valve port required flow of each valve.

[0139] The valve core module is used to calculate the opening of each valve core of the valve core assembly according to the actual valve port required flow of each valve.

[0140] Embodiment 3: The present invention provides a control device for a distributed hydraulic system of a loader, comprising a processor, a memory, and a computer program stored in the memory. The computer program can be executed by the processor to implement a control method for a distributed hydraulic system of a loader as described in any paragraph of Embodiment 1.

[0141] Embodiment 4. The present invention provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a control method for a loader distributed hydraulic system as described in any paragraph of Embodiment 1.

[0142] In the several embodiments provided in the embodiments of the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or actions, or can be implemented using a combination of dedicated hardware and computer instructions.

[0143] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0144] If the functions are implemented in the form of software modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, electronic device, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks. It should be noted that, in this document, the terms "comprise," "include," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or device that includes a series of elements includes not only those elements but also other elements not explicitly listed, or also includes elements inherent to such process, method, article, or device. Without further constraints, an element defined by the phrase "comprises a..." does not preclude the existence of additional identical elements in the process, method, article or apparatus that includes the element.

[0145] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "an", "the" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise.

[0146] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0147] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0148] The references to "first" and "second" in the embodiments merely distinguish similar objects and do not represent a specific ordering of the objects. It is understood that the specific order or precedence of "first" and "second" can be interchanged where appropriate. It should be understood that the objects distinguished by "first" and "second" can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein.

[0149] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A control method for a distributed hydraulic system of a loader, characterized in that: Include: Obtaining control signals of the steering cylinder (7), the lifting cylinder (10) and the bucket cylinder (8); According to the control signal, the extension speed of each oil cylinder is obtained; Obtaining a first theoretical required flow rate according to the extension speed of each oil cylinder; and compensating the first theoretical required flow rate by using a model adaptive method to obtain a first actual required flow rate of each oil cylinder; According to the first actual required flow of each oil cylinder, constructing the theoretical valve port required flow of each flow output valve port of the distribution valve group (5); And through deep reinforcement learning, compensation is performed to obtain the actual valve port demand flow of each valve; According to the actual valve port required flow rates of each valve, the required flow rates of the working pump (1) and the steering pump (3), as well as the rotational speeds of the first motor (2) and the second motor (4) are obtained; The opening of each valve core of the valve core assembly is calculated according to the actual valve port required flow of each valve.

2. The control method of a loader distributed hydraulic system according to claim 1, characterized in that: According to the extension speed of each oil cylinder, a first theoretical required flow rate of each oil cylinder is obtained; and the first theoretical required flow rate is compensated by using a model adaptive method to obtain a first actual required flow rate, specifically including: According to the extension speed of each oil cylinder, the first theoretical required flow rate of each oil cylinder is obtained; the first theoretical required flow rate model of a single oil cylinder is as follows: ; Where, The first theoretical required flow rate of the rodless chamber when the piston rod is extended. The first theoretical required flow rate of the rod chamber when the piston rod is retracted. is the effective area of the rodless cavity, is the effective area of the rod cavity, is the volume of the rodless cavity, is the volume of the rod cavity, is the effective bulk elastic modulus of the oil, is the rodless cavity pressure of the cylinder, The rod cavity pressure of the cylinder, Derivative, is the derivative of partial pressure with respect to time, is the cylinder extension speed; The first theoretical demand flow is compensated by using model adaptation to obtain the first actual demand flow; specifically, the method includes: Define the system parameter error vector; , where is the system parameter error vector, is the area error, Elastic modulus deviation, valve flow coefficient drift ; acquiring a first compensation model of the first theoretical demand flow model according to the first theoretical demand flow model and the system parameter error vector; Where, is the first compensation demand flow, is the nominal effective area of the cylinder cavity, is a real-time estimate of the area error, is a real-time estimate of the flow coefficient drift, is the valve port pressure difference; Performing constraints according to the first compensation model to obtain a first constraint model; Where, is the first actual demand flow, is the proportional gain coefficient, is the actual output pressure of the pump, To set the pressure threshold; A flow tracking error is defined and a parameter update rate is derived based on the flow tracking error to obtain the first actual demand flow; the flow tracking error is: ;The parameter update rate is: Where, is the flow tracking error, is the target flow reference value, is the updated area error, is the updated flow coefficient error, is the area gain coefficient, is the flow coefficient gain coefficient.

3. The control method of a distributed hydraulic system for a loader according to claim 1, characterized in that: The theoretical valve port flow requirements of each flow output valve port of the flow distribution valve group (5) are as follows: The theoretical flow rate of valve outlet A1 is: ; The theoretical flow rate of valve outlet A2 is: ; The theoretical flow rate of valve outlet A3 is: ; The theoretical flow rate of valve outlet A11 is: ; The theoretical flow rate of valve outlet A12 is: ; The theoretical flow rate of valve outlet A21 is: ; The theoretical flow rate of valve outlet A22 is: ; Where, The theoretical valve port flow rate required at valve outlet A1, is the actual required flow rate of the lifting cylinder (10), is the pipe volume of the first circuit, is the load pressure of valve outlet A1, The theoretical valve port flow rate required at valve outlet A2, is the actual required flow rate of the bucket cylinder (8), is the pipe volume of the second circuit, is the load pressure of valve outlet A2, The theoretical valve port flow rate required at valve outlet A3, is the actual required flow of the steering cylinder (7), is the pipe volume of the third circuit, is the load pressure of valve outlet A3, The theoretical valve port flow rate required for valve outlet A11, is the volume of the pipe from valve outlet A11 to A1, is the load pressure of valve outlet A11, The theoretical valve port flow rate required for valve outlet A12, is the volume of the pipe from valve outlet A11 to A2, is the load pressure of valve outlet A12, The theoretical valve port flow rate required for valve outlet A21, is the volume of the pipe from valve outlet A21 to A1, is the load pressure of valve outlet A21, The theoretical valve port flow rate required for valve outlet A22, is the volume of the pipe from valve outlet A22 to A2, is the load pressure of valve outlet A22, is the effective bulk elastic modulus of the oil, Derivative, is the time derivative of pressure, It is the maximum output flow of a single pump.

4. The control method of a distributed hydraulic system for a loader according to claim 3, characterized in that: Through deep reinforcement learning, compensation is performed to obtain the actual valve port flow requirements of each valve, including: Define dynamic environmental parameters, collect relevant data, and create data sets; Where, Dynamic environmental parameters, Input voltage signal to the handle, is the rodless cavity pressure of the cylinder, The rod cavity pressure of the cylinder, The real data collected during training, is the target speed, is the cylinder displacement, is the cylinder speed; Define the flow demand function parameters as continuous action; Where, is the action vector, is the flow-pressure nonlinear friction compensation coefficient, is the flow-pressure nonlinear leakage compensation coefficient, For time; Construct loss function; Where, is the loss function, For the expected value, is the predicted value of flow compensation, is the neural network weight parameter; according to 、 and Train a deep reinforcement learning neural network, using the tracking accuracy term of the loss function , training model output compensation parameters , to ensure the accuracy of demand flow; The theoretical valve port required flow rate is compensated according to the compensation parameter to obtain the actual valve port required flow rate of each valve.

5. The control method of a distributed hydraulic system for a loader according to claim 1, characterized in that: According to the actual valve port required flow of each valve, the required flow of the working pump (1) and the steering pump (3), as well as the rotation speed of the first motor (2) and the second motor (4) are obtained, specifically including: According to the actual valve port required flow of each valve, the required flow of the working pump (1) and the steering pump (3) is obtained; the required flow of the working pump (1) is: ; The required flow rate of the steering pump (3) is: Where, is the required flow rate of the working pump (1), is the required flow of the steering pump (3), The theoretical valve port flow rate required for valve outlet A11, The theoretical valve port flow rate required for valve outlet A12, The theoretical valve port flow rate required at valve outlet A3, The theoretical valve port flow rate required for valve outlet A21, The theoretical valve port required flow rate of valve outlet A22; According to the required flow rates of the working pump (1) and the steering pump (3), based on the motor efficiency MAP diagram and the pump efficiency MAP diagram, a table lookup method is used with the optimal efficiency as a constraint condition to obtain the real-time displacement of the working pump (1) and the steering pump (3), as well as the real-time rotational speeds of the first motor (2) and the second motor (4); According to the actual displacement signals of the steering cylinder (7), the lifting cylinder (10) and the bucket cylinder (8), the real-time displacement and the real-time rotation speed are updated in real time through fuzzy control.

6. A control method for a distributed hydraulic system of a loader according to any one of claims 1 to 5, characterized in that: The calculation model of valve core opening is: ； Where, is the valve output flow; is the flow coefficient, is the valve core opening, is the valve core area, is the oil density, is the pressure difference across the valve, is the valve inlet pressure; is the valve outlet pressure.

7. A control method for a distributed hydraulic system of a loader according to any one of claims 1 to 5, characterized in that: The control signal includes a manipulation signal and a status signal; the manipulation signal includes a handle signal, a steering wheel signal, an accelerator pedal signal, and a brake pedal signal; the status signal includes the speed of the first motor (2), the outlet pressure of the working pump (1), the speed of the second motor (4), the outlet pressure of the steering pump (3), the pressure of the large and small chambers of the lifting cylinder (10), the pressure of the large and small chambers of the dump cylinder (8), and the pressure of the large and small chambers of the steering cylinder (7); The extension velocity model is: Where, Input voltage signal to the handle, is the mapping coefficient, is the cylinder extension speed.

8. A control device for a distributed hydraulic system of a loader, used to execute a control method for a distributed hydraulic system of a loader according to any one of claims 1 to 7, characterized in that: Include: A signal module for obtaining control signals of the steering cylinder (7), the lifting cylinder (10) and the dump cylinder (8); A speed module, used to obtain the extension speed of each cylinder according to the control signal; The oil cylinder flow module is used to obtain a first theoretical required flow according to the extension speed of each oil cylinder; and to compensate the first theoretical required flow by using a model adaptive method to obtain a first actual required flow of each oil cylinder; A valve flow module, used for constructing a theoretical valve port required flow rate of each flow output valve port of the distribution valve group (5) according to the first actual required flow rate of each oil cylinder; And through deep reinforcement learning, compensation is performed to obtain the actual valve port demand flow of each valve; A pump flow module is used to obtain the required flow of the working pump (1) and the steering pump (3), as well as the rotational speeds of the first motor (2) and the second motor (4) according to the actual valve port required flow of each valve; The valve core module is used to calculate the opening of each valve core of the valve core assembly according to the actual valve port required flow of each valve.

9. A control device for a distributed hydraulic system of a loader, characterized in that: It comprises a processor, a memory, and a computer program stored in the memory; the computer program can be executed by the processor to implement a control method for a loader distributed hydraulic system as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the control method of a loader distributed hydraulic system according to any one of claims 1 to 7.

Images