Intelligent optimization system based on self-adaptive control hydraulic cylinder

Abstract

The invention discloses an intelligent optimization system based on a self-adaptive control hydraulic cylinder, and relates to the technical field of hydraulic cylinder control, and the system comprises a monitoring data collection module which collects data of a flow field, a temperature field and a stress field in real time by means of various sensors arranged at different parts of the hydraulic cylinder, synchronously carries out the preprocessing and coding of the collected data, and transmits the data to a data processing module; the data is transmitted to the data processing and analyzing module in real time; detailed data of the hydraulic cylinder in different physical fields are acquired in real time through the monitoring data acquisition module, and the coupling coefficient is accurately calculated by using the multi-physical field coupling model, so that the system can deeply understand the specific influence of each physical field on the performance of the hydraulic cylinder; according to the method, the system can construct a more accurate hydraulic cylinder dynamic model in the model prediction control module, so that the future state of the hydraulic cylinder is accurately predicted, further, the system can obtain an optimal control input sequence through an objective function optimization algorithm, and the pertinence and effectiveness of a control strategy are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of hydraulic cylinder control, in particular to an intelligent optimization system based on adaptive control of hydraulic cylinders. Background Art

[0002] With the rapid development of industrial automation technology, hydraulic systems, as indispensable power transmission and control devices in industrial production, have performance and stability that are directly related to overall production efficiency and product quality. Hydraulic cylinders, as the core actuators of hydraulic systems, have dynamic response speed, control accuracy, and adaptability under different working conditions that have become key indicators for measuring system performance. However, in actual applications, the performance of hydraulic cylinders is often affected by uneven flow field distribution, oil viscosity fluctuations caused by temperature changes, and fatigue damage caused by stress concentration. The interaction of these factors makes the performance prediction and control of hydraulic cylinders particularly complex. Therefore, how to achieve precise control of hydraulic cylinders under the coupling of multiple physical fields has become a technical problem that needs to be solved urgently in the current field of industrial automation.

[0003] The publication number "CN116658491A Low-impact hydraulic cylinder dynamic control method and system based on fluid resistance optimization" focuses on solving the problem of position output error of hydraulic cylinders in high-speed, high-pressure and high-precision environments. The stroke sensor is corrected through real-time density calculation to reduce impact and improve control accuracy. Although this method can meet basic control needs to a certain extent, its limitations are increasingly prominent when faced with complex and changeable working conditions. Specifically, traditional technologies often ignore the coupling effects between multiple physical fields, which makes it difficult for control strategies to accurately match actual working conditions, thereby causing problems such as insufficient control accuracy, slow response speed and poor system stability. In addition, this method lacks adaptive adjustment capabilities and cannot automatically optimize control parameters according to real-time working condition changes, making it difficult to maintain an efficient and stable operating state when faced with emergencies or performance degradation after long-term operation. These problems not only limit the improvement of hydraulic system performance, but also increase equipment maintenance costs and downtime, affecting overall production efficiency.

[0004] Therefore, the development of an intelligent optimization system based on adaptive control of hydraulic cylinders not only significantly improves the control accuracy and response speed of the hydraulic cylinders, but also enhances the robustness and adaptability of the system, providing a new solution for the development of the industrial automation field. Summary of the Invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide an intelligent optimization system based on adaptive control of hydraulic cylinders. The flow field, temperature field and stress field data of the hydraulic cylinder are collected in real time through the monitoring data acquisition module, and transmitted to the data processing and analysis module. The module uses a multi-physical field coupling model to analyze the influence of each physical field on the performance of the hydraulic cylinder. The model prediction control module establishes a dynamic model of the hydraulic cylinder, predicts the future state and optimizes the control input sequence. The control strategy adjustment module corrects the control input sequence through an adaptive algorithm according to the error between the actual data and the prediction result. Finally, the instruction execution module adjusts the working state of the hydraulic cylinder to achieve intelligent optimization control.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent optimization system based on adaptive control of hydraulic cylinders, the system comprising:

[0007] Monitoring data acquisition module: With the help of various sensors arranged in different parts of the hydraulic cylinder, it collects data on flow field, temperature field and stress field in real time, pre-processes and encodes the collected data simultaneously, and transmits it to the data processing and analysis module in real time;

[0008] Data processing and analysis module: Receives data transmitted by the monitoring data acquisition module, calculates the coupling coefficient through the multi-physics field coupling model, analyzes the impact of each physical field on the hydraulic cylinder performance based on the coupling coefficient, and transmits the data to the model prediction control module;

[0009] Model Predictive Control Module: Based on the data transmitted by the Data Processing and Analysis Module, a dynamic model of the hydraulic cylinder is established, which includes the multi-physics field coupling relationship, system dynamic characteristics, and external interference factors. The model is used to predict the future state of the hydraulic cylinder. The optimal control input sequence is calculated through the objective function optimization algorithm and transmitted to the control strategy adjustment module.

[0010] Control strategy adjustment module: Receives the control strategy output by the model predictive control module as the initial solution, obtains the actual measurement data from the monitoring data acquisition module, compares the actual system state with the model prediction result to obtain the error, uses the adaptive algorithm to generate the adjustment coefficient matrix, corrects the control input sequence, converts it into execution instructions, and transmits it to the instruction execution module;

[0011] Instruction execution module: Receives control instructions from the control strategy adjustment module, adjusts the hydraulic pump output flow, controls the hydraulic oil temperature, changes the hydraulic cylinder working pressure and flow through the hydraulic pump, hydraulic oil heating or cooling device, pressure control valve and flow control valve, and monitors the working status of the actuator and feeds back to the control strategy adjustment module.

[0012] Furthermore, the sensors used in the monitoring data acquisition module are:

[0013] Flow rate sensor: symmetrically deployed at the center axis of the oil inlet and outlet of the hydraulic cylinder;

[0014] Pressure sensor: installed at the oil inlet, oil outlet and inside the cylinder of the hydraulic cylinder;

[0015] Temperature sensor: installed in the hydraulic cylinder barrel, hydraulic oil pipeline and hydraulic pump;

[0016] Strain gauge sensor: pasted on the surface of the hydraulic cylinder barrel and piston rod.

[0017] Furthermore, the data processing and analysis module calculates the multi-physics field coupling coefficient through the multi-physics field coupling model. Assuming the coupling coefficient of the physical field is ξ, the calculation formula is: ξ=∫ V ∫ t ρ(v,R,σ)×ω(v,R,σ)dvdt, where ρ(v,R,σ) is the density function related to flow velocity v, temperature R, and stress σ; ω(v,R,σ) is the weight function related to flow velocity v, temperature R, and stress σ; V is the spatial area; t is the time; v is the flow velocity, which refers to the flow velocity of the hydraulic oil at the oil inlet and outlet of the hydraulic cylinder; R is the temperature, which refers to the temperature of the hydraulic cylinder barrel, hydraulic oil pipeline, and hydraulic pump; σ is the stress, which refers to the stress on the surface of the hydraulic cylinder barrel and piston rod load-bearing parts.

[0018] Furthermore, the specific steps of analyzing the influence of each physical field on the performance of the hydraulic cylinder based on the multi-physical field coupling coefficient in the data processing and analysis module are as follows:

[0019] (1) Clarify the key performance indicators of the hydraulic cylinder and establish their correlation with the parameters of each physical field;

[0020] (2) Based on the multi-physics field coupling coefficient, calculate the change of each physical field parameter under the coupling effect;

[0021] (3) Analyze the impact of flow field parameter changes on the hydraulic cylinder output force fluctuation and motion stability performance;

[0022] (4) Evaluate the impact of temperature field changes on hydraulic oil viscosity, sealing performance, and component strength;

[0023] (5) Analyze the impact of stress field changes on the stress distribution, fatigue life and structural reliability of key components of hydraulic cylinders;

[0024] (6) Comprehensively consider the synergistic effect of the changes in each physical field and analyze the comprehensive impact of multi-physical field coupling on the overall performance of the hydraulic cylinder;

[0025] (7) Establish a relationship model between the multi-physics field coupling coefficient and the hydraulic cylinder performance indicators to predict the performance change trend.

[0026] Furthermore, the creation of the relational model in the data processing and analysis module assumes that the multi-physics field coupling coefficient is ξ, and the performance indicators of the hydraulic cylinder include the output force stability index P s , motion accuracy index M a , system efficiency index E f , define the comprehensive performance index function The calculation formula is: Among them: w1, w2, w3 are the weight coefficients of each performance indicator, which are determined according to the importance attached to different performance indicators in actual applications.

[0027] Furthermore, the construction of the hydraulic cylinder dynamic model in the model predictive control module assumes that the hydraulic cylinder state vector is X = [v, p, R, σ] T , the calculation formula is: X t+1 =A×X t +B×U t +I×W t , where A and B are coefficient matrices, and U t is the control input vector, I is the noise coefficient matrix, W t is the external disturbance vector, X t is the state vector of the hydraulic cylinder at time t, including flow velocity v, pressure p, temperature R, stress σ, X t+1 is the state vector of the hydraulic cylinder at time t+1, and T is the transpose symbol, which means that the row vector [v, p, R, σ] is converted into a column vector.

[0028] Furthermore, the steps of predicting the future state using the established dynamic model of the hydraulic cylinder in the model prediction control module are as follows:

[0029] (1) Extract the state vector of the current hydraulic cylinder flow rate, pressure, temperature, and stress based on real-time monitoring data;

[0030] (2) Set the prediction time domain length and determine the number of future time steps and time step length to be predicted;

[0031] (3) Based on the dynamic model of the hydraulic cylinder, the state prediction value of each future time step is calculated from the current state;

[0032] (4) Assuming the future control input sequence, the initial value adopts the current control strategy;

[0033] (5) Predict and process external interference based on statistical characteristics and real-time estimation;

[0034] (6) Incorporating the system's physical constraints regarding control inputs, state variables, and actuator limitations into the prediction process;

[0035] (7) Each control cycle repeats the prediction and optimization steps based on the latest data to achieve real-time tracking of system dynamic changes.

[0036] Furthermore, the model predictive control module calculates the optimal control input sequence through the objective function optimization algorithm, and the calculation formula is: Among them, X d The whole is the expected state vector, Q and R are weight matrices used to adjust the importance of state error and control input respectively, X t+i|t Based on the data at time t, the state prediction value at the future time t+i, N is the prediction time domain, which refers to the number of time steps for the model to predict the future state. is the objective function used to optimize the control strategy, minimize the state error and control input cost, T represents the transpose operation, and i is the index variable.

[0037] Furthermore, the control strategy adjustment module generates an adjustment coefficient matrix through an adaptive algorithm. Let the adjustment coefficient matrix be Δ, and the calculation formula is: Among them, η and ζ are coefficients used to adjust the degree of influence of the integral term and the differential term on the adjustment matrix, E is the error vector, X actual is the actual measurement data, E(τ) is the error vector, E T (τ) is the transpose of the error vector E(τ), where τ is the integral variable used to integrate the error vector-related operations over the time interval [0, t]. t is the time, the upper limit of integration, indicating that the error vector-related operations are integrated from the initial time 0 to the current time t. It is the derivative of the error vector E(t) with respect to time t, reflecting the rate of change of the error vector over time.

[0038] Compared with the existing technology, this intelligent optimization system based on adaptive control of hydraulic cylinders has the following beneficial effects:

[0039] 1. The present invention obtains detailed data of the hydraulic cylinder under different physical fields in real time through the monitoring data acquisition module, and uses the multi-physical field coupling model to accurately calculate the coupling coefficient. The system can deeply understand the specific impact of each physical field on the performance of the hydraulic cylinder, so that the system can construct a more accurate hydraulic cylinder dynamic model in the model prediction control module, thereby realizing accurate prediction of the future state of the hydraulic cylinder. Furthermore, through the objective function optimization algorithm, the system can derive the optimal control input sequence, significantly improving the pertinence and effectiveness of the control strategy. This control method based on real-time data and precise models not only shortens the system response time, but also greatly improves the control accuracy, so that the hydraulic cylinder can still maintain stable performance output under complex working conditions.

[0040] 2. By receiving the output of the model predictive control module and the actual measurement data of the monitoring data acquisition module, the present invention can compare the system status with the model prediction results in real time, accurately calculate the error, and use the adaptive algorithm to generate an adjustment coefficient matrix, so that the system can dynamically adjust the control input sequence according to the actual situation and automatically adapt to various working conditions without human intervention. In addition, through the precise control of the hydraulic pump, hydraulic oil heating or cooling device, pressure control valve and flow control valve by the instruction execution module, the system can adjust the working state of the hydraulic cylinder in real time to ensure that it can maintain optimal performance in various complex environments. This adaptive control strategy not only improves the reliability and stability of the system, but also reduces maintenance costs and extends the service life of the equipment, with significant economic and social benefits.

[0041] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0043] Figure 1 This is a flow chart of an intelligent optimization system based on adaptive control of hydraulic cylinders;

[0044] Figure 2 A framework diagram of an intelligent optimization system based on adaptive control of hydraulic cylinders. DETAILED DESCRIPTION

[0045] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0046] Example 1:

[0047] Intelligent optimization system for hydraulic actuators in the aerospace field.

[0048] It is used in the hydraulic control scenarios of the landing gear retraction and extension systems of civil aviation passenger aircraft, especially for the complex working conditions of the aircraft from high-altitude cruising (such as 12,000 meters above sea level) to landing. It solves the problems of sudden increase in hydraulic oil viscosity, seal elasticity attenuation and movement accuracy deviation caused by low temperature environment (below -40°C) and drastic changes in air pressure, ensuring the smooth and reliable retraction and extension of the landing gear during take-off and landing, and improving flight safety redundancy.

[0049] Monitoring data acquisition module: High-pressure, vibration-resistant flow rate sensors and pressure sensors are installed at the oil inlet and outlet of the hydraulic cylinder of the landing gear hydraulic actuator, respectively. When the aircraft descends rapidly from the stratosphere, the sensors can keenly capture the fluctuations in hydraulic oil flow rate caused by the sudden increase in external air pressure. For example, the flow rate at the oil inlet may fluctuate by ±10% at the moment of air pressure change. Platinum resistance temperature sensors are embedded in the outer wall of the cylinder, hydraulic oil pipeline and hydraulic pump housing to accurately monitor temperature changes. Especially when the aircraft passes through extremely cold clouds, the hydraulic oil temperature can be tracked in real time to see whether it is approaching the freezing point. At the same time, foil strain gauge sensors are attached to the key stress-bearing surfaces of the piston rod and cylinder to capture the dynamic stress and deformation signals generated by the components at the moment of landing gear touchdown (such as when the landing impact load reaches 3 times the weight of the fuselage). All data collected by the sensors are filtered and amplified by the signal conditioning circuit and transmitted in real time to the data processing and analysis module via aviation-grade data transmission cables (with electromagnetic interference shielding function). Figure 1 shown.

[0050] Data processing and analysis module: After receiving the multi-dimensional monitoring data, the data processing and analysis module calls the multi-physics field coupling model to calculate the multi-physics field coupling coefficient. Assuming the coupling coefficient of the physical field is ξ, the calculation formula is: ξ=∫ V ∫ tρ(v,R,σ)×ω(v,R,σ)dvdt, where ρ(v,R,σ) is a density function related to flow velocity v, temperature R, and stress σ, and ω(v,R,σ) is a weight function related to flow velocity v, temperature R, and stress σ. V is the spatial area, t is the time, v is the flow velocity, which refers to the flow velocity of the hydraulic oil at the oil inlet and outlet of the hydraulic cylinder, R is the temperature, which refers to the temperature of the hydraulic cylinder barrel, hydraulic oil pipeline and hydraulic pump, and σ is the stress, which refers to the stress on the surface of the hydraulic cylinder barrel and piston rod force-bearing parts. This model can quantitatively analyze the interaction between the temperature field and the flow field in the high-altitude environment. For example, when the hydraulic oil temperature drops from 25°C to -30°C, its viscosity change will be transmitted to the flow field parameters through the coupling coefficient, resulting in an increase of about 40% in the oil circuit pressure loss. The system further analyzes the impact of each physical field on the performance of the actuator: in terms of flow field , pay attention to the cavitation phenomenon that may occur in hydraulic oil in high-altitude and low-pressure environments, which will cause the actuator to jerk (such as a 0.5-second stagnation during the lowering of the landing gear); in terms of temperature field, evaluate the impact of low temperature on the sealing material (such as fluororubber). When the temperature is below -20°C, the elastic modulus of the seal may increase by 2 times, causing oil leakage from tiny gaps; the stress field focuses on monitoring the fatigue damage trend of the piston rod in repeated retraction and extension cycles (such as passenger aircraft with an average of 8 take-offs and landings per day), especially the stress concentration area of the threaded connection. Comprehensively consider the synergistic effect of the changes in various physical fields, analyze the comprehensive impact of multi-physical field coupling on the overall performance of the hydraulic cylinder, establish a relationship model between the multi-physical field coupling coefficient and the hydraulic cylinder performance indicators, and predict the performance change trend. Let the multi-physical field coupling coefficient be ξ. The performance indicators of the hydraulic cylinder include the output force stability index P s , motion accuracy index M a , system efficiency index E f , define the comprehensive performance index function The calculation formula is: Among them: w1, w2, w3 are the weight coefficients of each performance indicator, which are determined according to the importance attached to different performance indicators in actual applications.

[0051] Model Predictive Control Module: The model predictive control module combines the special requirements of aviation hydraulic systems to build a hydraulic cylinder dynamic model that includes high-pressure changes, low-temperature viscosity-temperature characteristics, actuator dynamic parameters (such as landing gear moment of inertia and air resistance coefficient), and external interference (air turbulence). The hydraulic cylinder state vector is X = [v, p, R, σ] T , the calculation formula is: X t+1 =A×X t +B×U t +I×W t , where A and B are coefficient matrices, and U t is the control input vector, I is the noise coefficient matrix, W t is the external disturbance vector, Xt is the state vector of the hydraulic cylinder at time t, including flow velocity v, pressure p, temperature R, stress σ, X t+1 is the state vector of the hydraulic cylinder at time t+1. T is the transpose symbol, indicating that the row vector [v, p, R, σ] is converted into a column vector. During the aircraft's approach phase (below 1000 meters in altitude), the operator sets the predicted time domain length (such as the landing gear lowering process in the next 20 seconds) through the flight control system. The system predicts the state change at each time step based on the current state (such as the hydraulic oil temperature of -15°C and the system pressure of 18 MPa at an altitude of 500 meters). When it is predicted that the landing gear is about to touch the ground, the model will estimate the peak impact stress on the piston rod in advance. Through the objective function optimization algorithm, the optimal control strategy is calculated with the goal of minimizing the landing gear lowering time deviation (controlled within ±0.3 seconds) and maximizing the system response speed. The calculation formula is: Among them, X d The whole is the expected state vector, Q and R are weight matrices used to adjust the importance of state error and control input respectively, X t+i|t Based on the data at time t, the state prediction value at the future time t+i, N is the prediction time domain, which refers to the number of time steps for the model to predict the future state. is the objective function used to optimize the control strategy and minimize the state error and control input cost. T represents the transpose operation, and i is the index variable. For example, the pressure control valve opening is pre-adjusted 5 seconds before landing to ensure that the buffer has the appropriate damping force at the moment of touchdown.

[0052] Control strategy adjustment module: The control strategy adjustment module uses the control plan predicted by the model (for example, setting the heating power to 500W and pre-adjusting the flow valve opening to 70%) as the initial benchmark, while continuously collecting the actual operating data of the actuator. If the aircraft encounters a strong crosswind (wind speed exceeding 15 m / s) during landing, causing the actual landing gear extension angle to deviate by 2° from the predicted value, the system immediately calls the adaptive algorithm to generate the adjustment coefficient matrix Δ, calculated as follows: Among them, η and ζ are coefficients used to adjust the degree of influence of the integral term and the differential term on the adjustment matrix, E is the error vector, X actual is the actual measurement data, E(τ) is the error vector, E T (τ) is the transpose of the error vector E(τ), where τ is the integral variable used to integrate the error vector-related operations over the time interval [0, t]. t is the time, the upper limit of integration, indicating that the error vector-related operations are integrated from the initial time 0 to the current time t. It is the derivative of the error vector E(t) with respect to time t, reflecting the rate of change of the error vector over time. The matrix will dynamically correct the control command based on the accumulated amount of deviation (such as the deviation exceeds 1° for three consecutive sampling cycles) and the rate of change (the deviation increases by 0.5° per second). For example, the flow valve opening can be temporarily increased to 85% to compensate for wind load interference. The corrected command is transmitted to the actuator through a redundantly designed aviation relay group to ensure the reliability of command transmission.

[0053] Instruction execution and feedback: After receiving the control instruction, the instruction execution module starts multiple actuators synchronously: the hydraulic oil heating device (electric heating film) heats up with gradient power in a low temperature environment to avoid thermal stress of components caused by sudden temperature change; the variable piston pump adjusts the swash plate angle in real time according to the instruction, increasing the output flow from the initial 80L / min to 100L / min, ensuring that the actuator piston rod extends at a stable speed of 0.1m / s; the pressure control valve accurately adjusts the valve core displacement through the proportional solenoid to maintain the system pressure within the safe range of 16-20MPa, and executes the process. During the process, the LVDT (Linear Variable Differential Transformer) displacement sensor installed on the landing gear strut provides real-time feedback on the retraction and extension position with an accuracy of up to ±0.1mm; the angular velocity sensor monitors the movement rate of the piston rod. When the rate exceeds 0.3m / s at the moment of touchdown, the system automatically triggers the hydraulic buffer circuit. All feedback data is transmitted back to the control strategy adjustment module via the ARINC664 bus to form a closed-loop control. For example, during the aircraft's taxiing phase, the system adjusts the locking force of the hydraulic lock based on real-time feedback to prevent accidental retraction of the landing gear, thereby achieving intelligent optimization of the entire process from high altitude to ground.

[0054] In summary, the intelligent optimization system for hydraulic actuators in the aerospace field targets the harsh environment of high altitude, low temperature and sudden changes in air pressure. It uses low-temperature resistant sensors to monitor multi-physics field data, predicts the actuator status through multi-physics field coupling models and dynamic models, and combines objective function optimization with adaptive algorithms to correct control strategies. The system can respond to changes in hydraulic oil viscosity and seal performance degradation in real time, accurately control the retraction and extension of the landing gear, and ensure that the hydraulic system responds quickly and moves accurately in civil aircraft take-off and landing scenarios, significantly improving the safety and reliability of key flight links.

[0055] Example 2:

[0056] Adaptive control system for hydraulic excavator arm of construction machinery.

[0057] It is suitable for large hydraulic excavators to perform excavation operations in complex terrains such as mines and construction projects. It solves problems such as excavation force fluctuations caused by sudden changes in soil hardness and long-term high-intensity work, hydraulic system overheating, and component fatigue wear, thereby improving operating efficiency and equipment life.

[0058] Monitoring data acquisition module: Flow rate sensors and pressure sensors that can capture the flow status of hydraulic oil in real time are deployed at the oil inlet and outlet of the hydraulic cylinder of the excavator arm respectively. When the excavator bucket is inserted into hard soil, the oil inlet flow rate sensor can quickly sense the sudden change in the impact flow rate of the hydraulic oil, and the oil outlet pressure sensor synchronously monitors the change in the back pressure of the oil circuit. High-precision temperature sensors are installed on the outer wall of the cylinder, hydraulic oil pipeline and key parts of the hydraulic pump housing. Especially during high-temperature operations in summer, the temperature rise trend of the hydraulic oil caused by frequent circulation can be tracked in real time; at the same time, strain gauge sensors are attached to the surface of the cylinder and piston rod to capture the stress deformation signals generated by the components in the excavation process due to the alternating loads (such as the impact force when the bucket is digging and the tensile force when lifting). Figure 2 As shown, all sensors filter and pre-process the collected flow field, temperature field and stress field data, convert them into a coding format that can be recognized by the system, and then transmit them to the data processing and analysis module in real time through a high-speed data transmission line.

[0059] Data processing and analysis module: After receiving the multi-dimensional data from the sensor group, the data processing and analysis module calls the multi-physics field coupling model to calculate the data. The calculation formula is: ξ=∫ V ∫ t ρ(v,R,σ)×ω(v,R,σ)dvdt, this model can quantitatively analyze the interaction between different physical fields. For example, when the excavation resistance suddenly increases, the changes in flow field parameters (flow rate, pressure) will be transmitted to the temperature field through the coupling coefficient, resulting in increased frictional heating of the hydraulic oil. Based on the coupling coefficient calculated by the model, the system further analyzes the impact of flow field changes on the performance of the excavator arm. For example, when the bucket cuts into the rock, the sudden drop in flow rate will cause instantaneous fluctuations in the excavation force, resulting in a decrease in the smoothness of the movement. Changes in the temperature field will affect the viscosity of the hydraulic oil. Increased viscosity at low temperatures in winter may cause slow valve core movement, while decreased viscosity at high temperatures in summer may cause aging of the seals. Changes in the stress field focus on the stress concentration area of the piston rod during repeated excavation actions to avoid component fracture due to fatigue accumulation. The synergistic effects of the changes in various physical fields are comprehensively considered to analyze the comprehensive impact of multi-physical field coupling on the overall performance of the hydraulic cylinder. A relationship model between the multi-physical field coupling coefficient and the hydraulic cylinder performance indicators is established to predict the performance change trend. The calculation formula is:

[0060] Model Predictive Control Module: Based on the data processing results, the model predictive control module constructs a dynamic model of the hydraulic cylinder that includes the multi-physics field coupling relationship, the dynamic characteristics of the excavator arm (such as the arm mass and the moment of inertia), and the external load interference (soil resistance and gravity torque). The calculation formula is: X t+1 =A×X t +B×U t +I×W tThe operator can set the prediction time domain length according to the operation requirements. For example, in continuous excavation operations, the system state at different excavation depths within the next 10 seconds is predicted. Starting from the current state (such as the flow rate, pressure, temperature, and stress values when the bucket is 0.5 meters deep in the soil), the system calculates the state prediction value for each future time step. When it is predicted that the excavation will reach a hard soil layer at the next moment, the model will estimate the trend of decreasing flow rate and increasing pressure in advance. Subsequently, the control strategy is iteratively optimized using the objective function optimization algorithm. The calculation formula is: The algorithm aims to minimize excavation force fluctuations and maximize system efficiency, and calculates the optimal control input sequence, such as increasing the hydraulic pump output flow in advance to meet the resistance requirements when excavating in hard soil.

[0061] Control strategy adjustment module: The control strategy adjustment module uses the control strategy predicted by the model (such as the hydraulic pump flow regulation scheme and the pressure valve opening setting) as the initial scheme, and simultaneously obtains the actual measurement data of the monitoring data acquisition module in real time. When the bucket's penetration depth exceeds the expected level during the actual excavation process, the system compares the error between the actual state and the predicted result, and calls the adaptive algorithm to generate the adjustment coefficient matrix. The calculation formula is: This matrix can dynamically correct the initial control input sequence based on the degree of error accumulation and the rate of change. For example, if the actual digging force is 15% lower than the predicted value, the adjustment coefficient matrix will instruct the hydraulic pump flow to increase by 5% to ensure that the digging force meets the operating requirements. The corrected instruction is transmitted to the instruction execution module in the form of an electrical signal.

[0062] Instruction execution module: After receiving the control instruction, the instruction execution module drives the hydraulic pump through the servo motor to adjust the output flow. When excavating hard soil, the flow rate is increased from the initial 100L / min to 120L / min; at the same time, the hydraulic oil cooling device is started. When the temperature sensor detects that the oil temperature exceeds 60°C, the fan automatically turns on to cool down; the pressure control valve and flow control valve accurately adjust the working pressure and flow of the hydraulic cylinder according to the instruction, so that the excavation arm cuts into the soil at a steady speed. While the actuator is in action, the position sensor installed at the joint of the excavation arm will provide real-time feedback on the action status (such as excavation angle and lifting speed). These data are then transmitted back to the control strategy adjustment module to form a closed-loop control to ensure that each excavation action can be dynamically optimized according to the actual working conditions.

[0063] In summary, the adaptive control system of the hydraulic excavator arm of construction machinery collects flow field, temperature field and stress field data in real time through multiple sensors, and realizes intelligent regulation of the hydraulic system through multi-physics field coupling model analysis and dynamic model prediction, combined with objective function optimization algorithm and adaptive algorithm. The system can accurately respond to the problems of sudden changes in excavation resistance and increased oil temperature in complex terrain operations, and dynamically adjust the parameters of hydraulic pump flow and pressure through closed-loop control, effectively improving the stability of excavation force and component life, and providing efficient and reliable hydraulic control solutions for mining and construction scenarios.

[0064] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An intelligent optimization system based on adaptive control of hydraulic cylinders, characterized in that: The system includes: Monitoring data acquisition module: With the help of various sensors arranged in different parts of the hydraulic cylinder, it collects data on flow field, temperature field and stress field in real time, pre-processes and encodes the collected data simultaneously, and transmits it to the data processing and analysis module in real time; Data processing and analysis module: Receives data transmitted by the monitoring data acquisition module, calculates the coupling coefficient through the multi-physics field coupling model, analyzes the impact of each physical field on the hydraulic cylinder performance based on the coupling coefficient, and transmits the data to the model prediction control module; Model Predictive Control Module: Based on the data transmitted by the Data Processing and Analysis Module, a dynamic model of the hydraulic cylinder is established, which includes the multi-physics field coupling relationship, system dynamic characteristics, and external interference factors. The model is used to predict the future state of the hydraulic cylinder. The optimal control input sequence is calculated through the objective function optimization algorithm and transmitted to the control strategy adjustment module. Control strategy adjustment module: Receives the control strategy output by the model predictive control module as the initial solution, obtains the actual measurement data from the monitoring data acquisition module, compares the actual system state with the model prediction result to obtain the error, uses the adaptive algorithm to generate the adjustment coefficient matrix, corrects the control input sequence, converts it into execution instructions, and transmits it to the instruction execution module; Instruction execution module: Receives control instructions from the control strategy adjustment module, adjusts the hydraulic pump output flow, controls the hydraulic oil temperature, changes the hydraulic cylinder working pressure and flow through the hydraulic pump, hydraulic oil heating or cooling device, pressure control valve and flow control valve, and monitors the working status of the actuator and feeds back to the control strategy adjustment module.

2. The intelligent optimization system based on adaptive control of hydraulic cylinder according to claim 1, characterized in that: The sensors used in the monitoring data acquisition module are: Flow rate sensor: symmetrically deployed at the center axis of the oil inlet and outlet of the hydraulic cylinder; Pressure sensor: installed at the oil inlet, oil outlet and inside the cylinder of the hydraulic cylinder; Temperature sensor: installed in the hydraulic cylinder barrel, hydraulic oil pipeline and hydraulic pump; Strain gauge sensor: pasted on the surface of the hydraulic cylinder barrel and piston rod.

3. The intelligent optimization system based on adaptive control of hydraulic cylinder according to claim 1, characterized in that: In the data processing and analysis module, the multi-physics field coupling coefficient is calculated by the multi-physics field coupling model. Assuming the coupling coefficient of the physical field is ξ, the calculation formula is: ξ=∫ V ∫ t ρ(v,R,σ)×ω(v,R,σ)dvdt, where ρ(v,R,σ) is the density function related to flow velocity v, temperature R, and stress σ; ω(v,R,σ) is the weight function related to flow velocity v, temperature R, and stress σ; V is the spatial area; t is the time; v is the flow velocity, which refers to the flow velocity of the hydraulic oil at the oil inlet and outlet of the hydraulic cylinder; R is the temperature, which refers to the temperature of the hydraulic cylinder barrel, hydraulic oil pipeline, and hydraulic pump; σ is the stress, which refers to the stress on the surface of the hydraulic cylinder barrel and piston rod load-bearing parts.

4. The intelligent optimization system based on adaptive control of hydraulic cylinder according to claim 1, characterized in that: The specific steps of analyzing the influence of each physical field on the performance of the hydraulic cylinder based on the multi-physical field coupling coefficient in the data processing and analysis module are as follows: (1) Clarify the key performance indicators of the hydraulic cylinder and establish their correlation with the parameters of each physical field; (2) Based on the multi-physics field coupling coefficient, calculate the change of each physical field parameter under the coupling effect; (3) Analyze the impact of flow field parameter changes on the hydraulic cylinder output force fluctuation and motion stability performance; (4) Evaluate the impact of temperature field changes on hydraulic oil viscosity, sealing performance, and component strength; (5) Analyze the impact of stress field changes on the stress distribution, fatigue life and structural reliability of key components of hydraulic cylinders; (6) Comprehensively consider the synergistic effect of the changes in each physical field and analyze the comprehensive impact of multi-physical field coupling on the overall performance of the hydraulic cylinder; (7) Establish a relationship model between the multi-physics field coupling coefficient and the hydraulic cylinder performance indicators to predict the performance change trend.

5. The intelligent optimization system based on adaptive control of hydraulic cylinders according to claim 4 is characterized in that: The relationship model in the data processing and analysis module is created by assuming that the multi-physics field coupling coefficient is ξ, and the performance indicators of the hydraulic cylinder include the output force stability index P s , motion accuracy index M a , system efficiency index E f , define the comprehensive performance index function The calculation formula is: Among them: w1, w2, w3 are the weight coefficients of each performance indicator, which are determined according to the importance attached to different performance indicators in actual applications.

6. The intelligent optimization system based on adaptive control of hydraulic cylinders according to claim 1, characterized in that: The construction of the hydraulic cylinder dynamic model in the model predictive control module is as follows: the hydraulic cylinder state vector is X = [v, p, R, σ] T , the calculation formula is: X t+1 =A×X t +B×U t +I×W t , where A and B are coefficient matrices, and U t is the control input vector, I is the noise coefficient matrix, W t is the external disturbance vector, X t is the state vector of the hydraulic cylinder at time t, including flow velocity v, pressure p, temperature R, stress σ, X t+1 is the state vector of the hydraulic cylinder at time t+1, and T is the transpose symbol, which means that the row vector [v, p, R, σ] is converted into a column vector.

7. The intelligent optimization system based on adaptive control of hydraulic cylinders according to claim 6, characterized in that: The steps of predicting the future state using the established hydraulic cylinder dynamic model in the model predictive control module are as follows: (1) Extract the state vector of the current hydraulic cylinder flow rate, pressure, temperature, and stress based on real-time monitoring data; (2) Set the prediction time domain length and determine the number of future time steps and time step length to be predicted; (3) Based on the dynamic model of the hydraulic cylinder, the state prediction value of each future time step is calculated from the current state; (4) Assuming the future control input sequence, the initial value adopts the current control strategy; (5) Predict and process external interference based on statistical characteristics and real-time estimation; (6) Incorporating the system's physical constraints regarding control inputs, state variables, and actuator limitations into the prediction process; (7) Each control cycle repeats the prediction and optimization steps based on the latest data to achieve real-time tracking of system dynamic changes.

8. The intelligent optimization system based on adaptive control of hydraulic cylinders according to claim 7, characterized in that: The model predictive control module calculates the optimal control input sequence through the objective function optimization algorithm, and the calculation formula is: Among them, X d The whole is the expected state vector, Q and R are weight matrices used to adjust the importance of state error and control input respectively, X t+i|t Based on the data at time t, the state prediction value at the future time t+i, N is the prediction time domain, which refers to the number of time steps for the model to predict the future state. is the objective function used to optimize the control strategy, minimize the state error and control input cost, T represents the transpose operation, and i is the index variable.

9. The intelligent optimization system based on adaptive control of hydraulic cylinders according to claim 1, characterized in that: The control strategy adjustment module generates an adjustment coefficient matrix through an adaptive algorithm. Assuming the adjustment coefficient matrix is Δ, the calculation formula is: Among them, η and ζ are coefficients used to adjust the degree of influence of the integral term and the differential term on the adjustment matrix, E is the error vector, X actual is the actual measurement data, E(τ) is the error vector, and E T (τ) is the transpose of the error vector E(τ), where τ is the integral variable used to integrate the error vector-related operations over the time interval [0, t]. t is the time, the upper limit of integration, indicating that the error vector-related operations are integrated from the initial time 0 to the current time t. It is the derivative of the error vector E(t) with respect to time t, reflecting the rate of change of the error vector over time.

Images