A power coordination control method for a multi-pump multi-motor system

Abstract

The application relates to a power collaborative control method for a multi-pump multi-motor system, which comprises the following steps: a power flow dynamic coupling model based on a fluid continuity equation and a power conservation principle is established, and pump-motor cross coupling and pipeline dynamic effects are introduced; system operation parameters are collected in real time, an adaptive fuzzy reasoning system is used for online identification of working conditions and prediction of control mode switching trends; based on the power flow dynamic coupling model, a model predictive control algorithm is used to solve target displacements of each hydraulic pump and hydraulic motor; each execution unit is modeled as an independent agent, and a distributed negotiation mechanism is used for collaborative optimization and output of final control instructions; the health states of each unit are evaluated in real time, and a fault-tolerant control strategy is triggered under abnormal conditions, so that power reconstruction and load reduction operation are realized. The application can improve the power distribution accuracy and dynamic response capability of the multi-pump multi-motor system, reduce energy loss, and improve the stability and fault tolerance capability of the system.

Description

Technical Field

[0001] This invention relates to the field of hydraulic transmission, and in particular to a power coordination control method for multi-pump and multi-motor systems. Background Technology

[0002] Multi-pump, multi-motor hydraulic drive systems are widely used in construction machinery, mining transportation equipment, ship propulsion systems, and large industrial equipment. These systems typically power multiple hydraulic motors via multiple hydraulic pumps to meet the power output demands of high loads, multiple actuators, and complex operating conditions. Due to their high power density, strong load adaptability, and flexible layout, they have significant application value in heavy-duty equipment.

[0003] Most existing multi-pump, multi-motor hydraulic systems employ fixed power distribution strategies or centralized control strategies, which allocate power to each hydraulic pump and motor according to a preset ratio. While this type of control is relatively simple in structure, it struggles to accurately reflect the real-time coupling relationships between hydraulic units under complex dynamic conditions. When the system is under heavy load startup, frequent load changes, or impact load conditions, problems such as uneven local power distribution, large hydraulic shocks, and system response lag can easily occur, leading to increased system energy consumption, decreased control stability, and overload operation of the actuators.

[0004] Meanwhile, multi-pump, multi-motor systems exhibit significant dynamic coupling characteristics, with complex power flow transfer relationships formed between different hydraulic pumps and motors through hydraulic pipelines. Traditional control methods typically do not adequately consider the dynamic effects of hydraulic pipelines, pump-motor cross-coupling effects, and the impact of system operating state changes on overall power distribution. Therefore, it is difficult to achieve real-time optimization and coordination of system power under complex operating conditions.

[0005] In addition, existing control systems typically lack the ability to identify operating conditions online. During rapid switching of operating conditions, the controller cannot predict the trend of system load changes in advance, which can easily lead to unsmooth switching of control modes, resulting in large fluctuations in displacement regulation and pressure, and affecting the stability of system operation. Summary of the Invention

[0006] The present invention provides a power coordinated control method for multi-pump and multi-motor systems, which is used to solve related technical problems in the background art.

[0007] The technical solution provided by this invention is as follows: A power coordinated control method for multi-pump and multi-motor systems, comprising the following steps: Step S1: Establish a dynamic coupling model of power flow for a multi-pump, multi-motor system. The dynamic coupling model of power flow is established based on the real-time operating parameters of each hydraulic pump and each hydraulic motor. Step S2: Collect system sensor signals in real time, use an adaptive fuzzy inference system to identify the current working condition online, and predict the control mode switching trend based on the identification results; Step S3: Using the power flow dynamic coupling model as the prediction model, the model predictive control algorithm is used to solve the target displacement of each pump and each motor online; Step S4: Model each pump drive unit and each motor drive unit as an independent intelligent agent. Each intelligent agent adjusts the target displacement obtained in step S3 based on a distributed negotiation mechanism and generates the final displacement command. Step S5: Calculate the health index of each unit in real time. When the health index of a certain unit is detected to be lower than the preset threshold, the fault-tolerant control strategy is automatically triggered and the power allocation of the corresponding unit is dynamically adjusted.

[0008] In one implementation, the power flow dynamic coupling model in step S1 is established based on the fluid continuity equation and the power conservation principle, and a pump-motor cross-coupling term and the dynamic effect of hydraulic pipelines are introduced.

[0009] In one implementation, the power flow dynamic coupling model in step S1 includes unknown parameters used to characterize the dynamic response characteristics of the hydraulic system. These unknown parameters are identified using system calibration test data.

[0010] In one implementation, in step S2, the adaptive fuzzy inference system uses the rate of change of outlet pressure of each pump, the rate of change of speed of each motor, and the system power demand parameters as input features to classify and identify the system operating conditions.

[0011] In one implementation, step S2 determines the switching trend of the control mode between steady-state power distribution mode and transient power compensation mode based on the identified operating condition category.

[0012] In one implementation, the model predictive control algorithm in step S3 aims to reduce power tracking error, reduce system power loss, and reduce displacement adjustment fluctuations, and dynamically adjusts the prediction time domain and weight coefficients according to the operating condition category.

[0013] In one implementation, in step S4, each agent uses a distributed communication method to exchange information, and the information exchange content includes at least efficiency parameters, temperature parameters, and operating status parameters.

[0014] In one implementation, in step S4, each agent negotiates based on a non-cooperative game mechanism to achieve dynamic allocation of system power load among multiple units.

[0015] In one implementation, the health index in step S5 is calculated based on pressure data, temperature data, vibration data, and runtime data, and is comprehensively evaluated in combination with physical degradation model and abnormal detection results.

[0016] In one implementation, when the health index is lower than a first threshold, a power reduction operation strategy is triggered; when the health index is lower than a second threshold, a maintenance warning signal is issued, wherein the second threshold is lower than the first threshold.

[0017] Compared with the prior art, the beneficial effects of the present invention are: (1) The power coordination control method of the present invention adopts the method of establishing a dynamic coupling model of power flow and combining it with the model predictive control algorithm. By dynamically predicting and optimizing the power flow relationship between each hydraulic pump and each hydraulic motor, the power of the system is coordinated and allocated in real time. This achieves the technical effects of reducing system power loss, improving dynamic response speed and reducing hydraulic shock, and solves the technical problems of power allocation lag, insufficient dynamic matching capability and high system energy consumption in traditional multi-pump and multi-motor systems.

[0018] (2) The power coordinated control method of the present invention adopts an adaptive fuzzy inference system for online identification of operating conditions. By analyzing the pressure change rate, speed change rate and system power demand parameters in real time, it achieves the purpose of early identification of complex operating conditions and prediction of control mode trends, thereby realizing the technical effects of smooth switching of control mode and improved system dynamic stability. In turn, it solves the technical problems of traditional control methods that are prone to response lag, large output fluctuation and insufficient control stability during the switching of complex operating conditions.

[0019] (3) The power coordination control method of the present invention adopts a multi-agent distributed negotiation control mechanism. Through real-time interaction and negotiation between each pump drive unit and each motor drive unit on efficiency parameters, temperature parameters and operating status parameters, the system load is dynamically balanced among multiple execution units. This achieves the technical effect of reducing the risk of local overload and improving the system's coordinated operation capability, thereby solving the technical problems of easy overload of local execution units, poor system scalability and low coordination efficiency in traditional centralized control structures.

[0020] (4) The power coordination control method of the present invention adopts a combination of health index assessment and fault-tolerant control. By comprehensively analyzing pressure data, temperature data, vibration data and running time data, it achieves the purpose of real-time monitoring and fault warning of the operating health status of the hydraulic unit, thereby realizing the technical effects of dynamic power reduction operation and load reconstruction under fault conditions. In turn, it solves the technical problem that traditional hydraulic systems are prone to system shutdown and fault propagation when the performance of a single actuator degrades or fails. Attached Figure Description

[0021] Figure 1This is a flowchart illustrating the power collaborative control method of the present invention; Figure 2 This is a schematic diagram of the structural layout of the power collaborative control method of the present invention. Detailed Implementation

[0022] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0023] Example 1 This embodiment provides a power coordination control method for multi-pump and multi-motor systems, which can be applied to hydraulic drive systems for engineering machinery, hydraulic systems for mining transportation, or hydraulic transmission systems for large ships. The system includes multiple hydraulic pumps, multiple hydraulic motors, a controller, a pressure sensor, a flow sensor, a temperature sensor, and a vibration sensor. The hydraulic pumps and hydraulic motors are connected by hydraulic pipelines to form a multi-power flow coupling structure.

[0024] The control method in this embodiment includes the following steps: Step S1: Establish a dynamic coupling model of power flow in a multi-pump, multi-motor system.

[0025] Specifically, the controller first collects the outlet pressure, flow rate, and speed of each hydraulic pump, as well as the load torque, input pressure, and output speed of each hydraulic motor, and establishes a dynamic coupling model of the system power flow based on the fluid continuity equation and the power conservation principle.

[0026] In this embodiment, the hydraulic pump output flow rate satisfies: Among them, Q pi Let D be the output flow rate of the i-th hydraulic pump. pi n represents the displacement of the hydraulic pump. pi C represents the hydraulic pump speed. tpi P is the leakage coefficient. pi P is the pump outlet pressure. t This refers to the return oil pressure.

[0027] The hydraulic motor output torque satisfies: Among them, T mj D is the output torque of the j-th hydraulic motor. mj For the displacement of the hydraulic motor, η mj For mechanical efficiency.

[0028] Furthermore, to characterize the dynamic coupling relationship between different pumps and motors, a pump-motor cross-coupling term is introduced into the model: Among them, P ij For the coupling power term, k ij is the coupling coefficient.

[0029] Meanwhile, to reflect the pressure fluctuations and dynamic hysteresis effects in the hydraulic pipeline, a dynamic response model for the hydraulic pipeline is introduced: Where, β e V is the equivalent bulk elastic modulus of the hydraulic oil, and V is the control volume.

[0030] In this embodiment, the unknown parameters in the model include leakage coefficient, coupling coefficient, and dynamic damping coefficient, which are identified through system calibration tests. Specifically, by collecting system pressure, flow rate, and speed data under different load conditions, the model parameters are iteratively corrected using a least squares identification algorithm to improve model accuracy.

[0031] By establishing the above dynamic coupling model, the power flow distribution and dynamic coupling relationship within the multi-pump, multi-motor system can be accurately reflected, thus providing a predictive basis for subsequent power optimization control and improving the system's power scheduling accuracy and dynamic response capability.

[0032] Step S2: Collect system sensor signals in real time and use an adaptive fuzzy inference system to identify the current operating conditions online.

[0033] Specifically, the controller acquires the rate of change of outlet pressure of each hydraulic pump, the rate of change of speed of each hydraulic motor, and the total power demand parameters of the system in real time, and uses these parameters as input features of the adaptive fuzzy inference system.

[0034] The rate of change of pressure is defined as follows: The rate of change of rotational speed is defined as: The controller classifies and identifies the current operating conditions based on the fuzzy membership function, dividing the system operating conditions into categories such as steady-state light load, steady-state heavy load, rapid acceleration, and impact load.

[0035] Furthermore, when the pressure change rate and power demand are detected to increase rapidly at the same time, the system predicts that the control mode will switch from steady-state power distribution mode to transient power compensation mode; when the system fluctuation decreases, it will switch back to steady-state power distribution mode.

[0036] By adopting an adaptive fuzzy inference system, the accuracy of operating condition identification under complex operating conditions can be improved, enabling the controller to predict the trend of operating condition changes in advance, thereby reducing the control lag problem during mode switching.

[0037] Step S3: Use model predictive control algorithm to solve for the target displacement of each pump and each motor online.

[0038] Specifically, the controller uses the power flow dynamic coupling model established in step S1 as the prediction model and constructs the following optimization objective function: Among them, P ref For the target power, P k To predict power, E k For the system power loss, ΔD k For the change in displacement, w1, w2, and w3 are weighting coefficients.

[0039] In this embodiment, when the system is in a steady-state condition, the controller uses a longer prediction time domain to improve the steady-state optimization capability; when the system is in a rapidly changing condition, the prediction time domain is shortened and the dynamic response weight is increased.

[0040] Subsequently, the controller solves for the target displacement of each hydraulic pump and hydraulic motor online through rolling optimization and generates initial control commands.

[0041] Model predictive control algorithms can achieve dynamic matching between system power demand and execution capability, thereby reducing system energy loss and minimizing fluctuations during displacement adjustment.

[0042] Step S4: Use a multi-agent negotiation mechanism to coordinate the target displacement in a distributed manner.

[0043] Specifically, each hydraulic pump drive unit and hydraulic motor drive unit is modeled as an independent intelligent agent, and the intelligent agents interact with each other using a distributed communication method.

[0044] In this embodiment, the information exchanged by each intelligent agent includes current efficiency parameters, oil temperature parameters, real-time operating status parameters, and remaining load capacity parameters.

[0045] Subsequently, the agents negotiate based on a non-cooperative game mechanism, and the payoff function for each agent is defined as follows: Among them, U i Let η be the reward function for the i-th agent. i For operational efficiency, L i For load level, T i This refers to the temperature rise parameter.

[0046] Each agent iteratively updates its strategy to gradually reach a Nash equilibrium state and eventually generates the final displacement command to be executed.

[0047] By adopting a distributed negotiation control method, the computational load of a single control center can be reduced, and the coordination efficiency between multiple execution units can be improved, thereby enhancing the overall operational stability of the system.

[0048] Step S5: Calculate the health index of each unit in real time and perform fault-tolerant control.

[0049] Specifically, the controller acquires pressure, temperature, vibration, and runtime data of each hydraulic unit in real time, and calculates the health index by combining the physical degradation model and anomaly detection results.

[0050] In this embodiment, the health index is defined as: Among them, HI i Let S be the health index of the i-th unit. pi Score your stress health. ti Score the temperature for health. vi For vibration health scoring, S hi Assess life expectancy and health score.

[0051] When the health index falls below the first threshold, the system automatically triggers a power reduction operation strategy, limiting the output power of the corresponding unit and redistributing some of the load to other healthy units.

[0052] When the health index falls below the second threshold, the controller issues a maintenance warning signal and prompts the corresponding hydraulic unit to be inspected and maintained, wherein the second threshold is lower than the first threshold.

[0053] By introducing a health index assessment and fault-tolerant control mechanism, dynamic load reconfiguration can be achieved when the performance of the hydraulic unit degrades, thereby reducing the risk of system failure propagation and improving the system's continuous operation capability.

[0054] Example 2 The difference between this embodiment and Embodiment 1 is that the multi-pump multi-motor system in this embodiment is applied to the hydraulic drive platform of tracked engineering machinery.

[0055] The system includes two variable hydraulic pumps and four hydraulic motors. The two variable hydraulic pumps supply oil to the left and right track drive circuits respectively.

[0056] During system operation, when one track is detected to be in a high-resistance condition, the adaptive fuzzy inference system identifies that the system is in a transient power compensation mode. Subsequently, the model predictive control algorithm increases the target displacement of the corresponding hydraulic pump and coordinates the other side loop to appropriately reduce the load power through a multi-agent negotiation mechanism, thereby maintaining the overall power balance of the machine.

[0057] Furthermore, when the temperature of one of the hydraulic motors continues to rise and the vibration amplitude exceeds the preset range, the health index drops below the first threshold, the system automatically reduces the output power of that hydraulic motor, and distributes some of the driving force to other hydraulic motors.

[0058] The above methods can improve the traction stability and system reliability of construction machinery under complex working conditions, while reducing the risk of failure caused by long-term overload operation of local hydraulic units.

[0059] Example 3 This embodiment provides a specific application case of the power coordination control method of the present invention in a large mining hydraulic transport vehicle.

[0060] The mining hydraulic transport vehicle in this embodiment adopts a four-pump, eight-motor hydraulic drive structure, including four variable displacement piston pumps P1 to P4 and eight hydraulic motors M1 to M8, with each pair of hydraulic motors corresponding to one hydraulic pump for oil supply. The total vehicle mass is 92t, the rated transport load is 65t, and the rated hydraulic pressure of the system is 35MPa.

[0061] In this embodiment, the vehicle is in a heavy-load uphill transportation condition in a mine, with a slope of 12° and a vehicle speed of 18 km / h. The system detects that the total power demand of the vehicle is 610 kW.

[0062] Step S1: Establish a dynamic coupling model of power flow in a multi-pump, multi-motor system.

[0063] The system first collects the real-time operating parameters of each hydraulic pump and hydraulic motor.

[0064] The real-time parameters of the first hydraulic pump P1 are as follows: Hydraulic pump displacement: D p1 =210mL / r Hydraulic pump speed: n p1 =1850r / min Pump outlet pressure: P p1 =31.5MPa Return oil pressure: P t =0.8MPa Leakage coefficient: C tp1 =0.00042 L / (min·MPa) According to the hydraulic pump flow model in Example 1: Qp1 =D p1 ·n p1 -C tp1 (P p1 -P t ) After substituting the actual data, we get: Q p1 =210×1850-0.00042×(31.5-0.8) After unit conversion, we get: Q p1 ≈388.5L / min Subsequently, the system calculates the output torque of the first hydraulic motor M1.

[0065] in: Hydraulic motor displacement: D m1 =160mL / r Motor inlet pressure: P in1 =30.8MPa Motor outlet pressure: P out1 =2.1MPa Mechanical efficiency: η m1 =0.93 Based on the hydraulic motor output torque model, after substituting the data: The calculation yields: T m1 ≈680 N·m Furthermore, the system calculates the coupling power term between pump P1 and motor M1.

[0066] Set the coupling coefficient: k 11 =0.018 Motor flow rate: Q m1 =372L / min Based on the coupling model, substituting the data: P 11 =0.018×388.5×372 Calculation yields: P 11 ≈2601 This parameter is used to characterize the dynamic coupling strength between the pump and the motor.

[0067] At the same time, the system calculates the dynamic changes in hydraulic pipeline pressure.

[0068] in: Equivalent bulk modulus of hydraulic oil: β e =1.45×10⁹ Pa Controlled volume: V = 0.018 m³ 3 Inflow: Q in =0.00648m 3 / s Outflow: Q out =0.00596m 3 / s Based on the dynamic model of the hydraulic pipeline, substitute the data: The calculation yielded: This indicates that the system is currently experiencing significant dynamic load fluctuations.

[0069] Step S2: Perform online identification of operating conditions.

[0070] The system detects in real time: Pump outlet pressure change rate: R p =5.6MPa / s Motor speed change rate: R n =148r / (min·s) Total system power requirement: P req =610kW According to the fuzzy inference rules in Example 1: When the pressure change rate is high, the speed change rate is large, and the total power demand exceeds 85% of the rated power, the system determines the current operating condition as "transient heavy load condition".

[0071] Therefore, the controller determines that the system is about to switch from steady-state power distribution mode to transient power compensation mode.

[0072] Step S3: Use model predictive control algorithm to optimize displacement.

[0073] System settings: Prediction time domain: N p =12 Power tracking weight: w1=0.55 Energy consumption weight: w2=0.30 Displacement fluctuation weight: w3=0.15 Based on the optimization objective function: The system performs rolling optimization calculations for the next 12 control cycles.

[0074] During the first control cycle: Target power: P ref =610kW Predicted power: P k =586kW System losses: E k =18.6kW Displacement change: ΔDk =11mL / r Substituting into the objective function: J1 = 0.55 × (610 - 586)² + 0.30 × 18.6 + 0.15 × 11² The calculation yields: J1≈340.23 The controller then obtains a new target displacement through iterative optimization: P1 target displacement is: 210 mL / r Adjusted to: 236mL / r P2 target displacement is: 205 mL / r Adjusted to: 228mL / r This improves the system's output capability.

[0075] Step S4: The agents negotiate control.

[0076] The system treats the four hydraulic pumps and eight hydraulic motors as independent intelligent agents.

[0077] The current parameters of agent M1 are as follows: Operating efficiency: η1 = 0.91 Load factor: L1 = 0.86 Temperature rise parameter: T1=72℃ Set the weights of the payoff function as follows: α1=0.6; β1=0.25; γ1=0.15.

[0078] Based on the payoff function: Substitute the data: U1=0.6×0.91-0.25×0.86-0.15×0.72 The calculation yields: U1≈0.223 Meanwhile, due to its lower temperature rise and higher efficiency, the M3 agent achieves the following benefit value: U3=0.31 Therefore, the system will transfer part of the load from M1 to M3 to reduce the risk of local overload.

[0079] Step S5: Conduct health index assessment and fault tolerance control.

[0080] After running for 45 minutes, the system detected an abnormal temperature rise in the M1 hydraulic motor.

[0081] in: Stress Health Score: S p1 =0.82 Temperature health rating: S t1 =0.58 Vibration Health Score: Sv1 =0.63 Life expectancy and health score: S h1 =0.76 The weights for each score are: λ1=0.30; λ2=0.35; λ3=0.20; λ4=0.15.

[0082] According to the health index model: The calculation yields: H I1 =0.689 In this embodiment: First threshold: 0.72 Second threshold: 0.55 Because: 0.55 < 0.689 < 0.72 Therefore, the system automatically triggers a power reduction operation strategy.

[0083] The controller reduces the output power of M1 by 20% and redistributes the corresponding load to the hydraulic motors M2 and M3, while sending maintenance warning information to the driver terminal.

[0084] Through actual operation testing, the control method in this embodiment, compared with the traditional fixed power distribution method, under the same transportation conditions: The system's total energy consumption was reduced by approximately 11.6%; The peak hydraulic shock value decreased by approximately 18.3%; The speed fluctuation of the vehicle during heavy-load climbing is reduced by approximately 22.5%; The continuous operating time under abnormal conditions of a single hydraulic unit is increased by approximately 35%.

[0085] This demonstrates that the present invention can effectively improve the power coordination capability, dynamic stability, and fault-tolerant operation capability of multi-pump and multi-motor hydraulic systems under complex heavy-load conditions.

[0086] In this application, the terms "upper," "lower," "left," "right," "front," "rear," "top," "bottom," "inner," "outer," "middle," "vertical," "horizontal," "lateral," and "longitudinal" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are primarily for the purpose of better describing the invention and its embodiments, and are not intended to limit the indicated device, element, or component to having a specific orientation, or to be constructed and operated in a specific orientation.

[0087] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A power coordinated control method for multi-pump, multi-motor systems, characterized in that, Includes the following steps: Step S1: Establish a dynamic coupling model of power flow for a multi-pump, multi-motor system. The dynamic coupling model of power flow is established based on the real-time operating parameters of each hydraulic pump and each hydraulic motor. Step S2: Collect system sensor signals in real time, use an adaptive fuzzy inference system to identify the current working condition online, and predict the control mode switching trend based on the identification results; Step S3: Using the power flow dynamic coupling model as the prediction model, the target displacement of each pump and each motor is solved online using the model predictive control algorithm; Step S4: Model each pump drive unit and each motor drive unit as an independent intelligent agent. Each intelligent agent adjusts the target displacement obtained in step S3 based on a distributed negotiation mechanism and generates the final displacement command. Step S5: Calculate the health index of each unit in real time. When the health index of a certain unit is detected to be lower than the preset threshold, the fault-tolerant control strategy is automatically triggered and the power allocation of the corresponding unit is dynamically adjusted.

2. The power coordinated control method for multi-pump multi-motor systems according to claim 1, characterized in that: The power flow dynamic coupling model described in step S1 is established based on the fluid continuity equation and the power conservation principle, and introduces pump-motor cross-coupling terms and dynamic effects of hydraulic pipelines.

3. The power coordinated control method for multi-pump multi-motor systems according to claim 2, characterized in that: The power flow dynamic coupling model described in step S1 includes unknown parameters used to characterize the dynamic response characteristics of the hydraulic system. These unknown parameters are identified through system calibration test data.

4. The power coordinated control method for multi-pump multi-motor systems according to claim 1, characterized in that: The adaptive fuzzy inference system described in step S2 uses the rate of change of outlet pressure of each pump, the rate of change of speed of each motor, and the system power demand parameters as input features to classify and identify the system operating conditions.

5. The power coordinated control method for multi-pump multi-motor systems according to claim 1, characterized in that: In step S2, the switching trend of the control mode between steady-state power distribution mode and transient power compensation mode is determined based on the identified operating condition category.

6. The power coordinated control method for multi-pump multi-motor systems according to claim 1, characterized in that: The model predictive control algorithm described in step S3 aims to reduce power tracking error, reduce system power loss, and reduce displacement regulation fluctuations, and dynamically adjusts the prediction time domain and weight coefficients according to the operating condition category.

7. The power coordinated control method for multi-pump multi-motor systems according to claim 1, characterized in that: In step S4, each agent uses a distributed communication method to exchange information. The information exchange content includes at least efficiency parameters, temperature parameters, and operating status parameters.

8. The power coordinated control method for multi-pump multi-motor systems according to claim 7, characterized in that: In step S4, each agent negotiates based on a non-cooperative game mechanism to achieve dynamic allocation of system power load among multiple units.

9. The power coordinated control method for multi-pump multi-motor systems according to claim 1, characterized in that: The health index mentioned in step S5 is calculated based on pressure data, temperature data, vibration data, and runtime data, and is comprehensively evaluated by combining physical degradation model and abnormal detection results.

10. The power coordinated control method for multi-pump multi-motor systems according to claim 9, characterized in that: When the health index is lower than a first threshold, a power reduction operation strategy is triggered; when the health index is lower than a second threshold, a maintenance warning signal is issued, wherein the second threshold is lower than the first threshold.

Images