Intelligent variable oil pump control system based on dynamic pressure compensation

Abstract

The invention discloses an intelligent variable oil pump control system based on dynamic pressure compensation, and relates to the technical field of hydraulic control, the system comprises an operation data acquisition module, a working condition clustering analysis module, a compensation parameter configuration module, a compensation execution control module and an online learning optimization module; according to the method, through multi-dimensional data collection and working condition clustering analysis, intelligent control over division of the oil pump operation working conditions and dynamic pressure compensation is achieved, three-dimensional parameter standardization mapping of loads, pressure deviation and the load change rate is adopted, original data are unified to the interval of [0, 1], quantifiable working condition feature vectors are formed, and the working condition feature vectors are quantified. Identifying three working condition types of instantaneous impact load, high-frequency light load and low-frequency heavy load through a clustering center positioning and working condition characteristic threshold value judgment formula, dynamically matching a basic compensation coefficient and a correction factor, quickly adjusting displacement output, avoiding the problem of over-voltage or under-voltage caused by a fixed compensation mode, and improving the working condition accuracy. And the pressure stability of the oil pump under different working conditions is improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of hydraulic control, in particular to an intelligent variable oil pump control system based on dynamic pressure compensation. BACKGROUND

[0002] With the acceleration of the global industrial intelligentization process, as a core power transmission device in the fields of equipment manufacturing, engineering machinery, aerospace, etc., the operation efficiency and reliability of the hydraulic system directly determine the performance index of the overall equipment. The oil pump, as a key executive element of the hydraulic system, needs to provide stable pressure output under different working conditions. However, the load characteristics in the industrial field present nonlinear and dynamic characteristics: for example, the engineering machinery needs to frequently cope with the transient impact load caused by the change of soil hardness in the digging operation, and the numerical control machine tool needs to maintain the pressure stability under low-frequency heavy load for a long time. Such working condition diversity poses a high challenge to the adaptability of the oil pump control system, which not only needs to sense the load change in real time, but also needs to quickly adjust the displacement parameter to avoid overpressure or underpressure.

[0003] However, the traditional oil pump control technology has some defects: firstly, the working condition recognition depends on manual experience or a single parameter threshold, and lacks multi-dimensional data fusion capability. For example, only the pressure sensor data is used to judge the load state, which cannot distinguish the difference between transient impact load and low-frequency heavy load, leading to mismatch of the compensation strategy. Secondly, the compensation mechanism is static or semi-dynamic mode, and the basic compensation coefficient needs to be manually adjusted, which cannot adapt to the working condition change or component aging. For example, after long-term operation of the hydraulic system, the internal leakage of the oil pump increases, but the traditional system still compensates according to the initial parameters, causing the pressure to be continuously low. Thirdly, it lacks closed-loop feedback and online learning function, and the compensation effect depends on offline calibration, which is difficult to cope with nonlinear disturbances in actual operation. SUMMARY

[0004] The purpose of the present application is to make up for the shortcomings of the prior art, and provide an intelligent variable oil pump control system based on dynamic pressure compensation. The present application realizes the division of the oil pump operating condition and the intelligent control of the dynamic pressure compensation through multi-dimensional data acquisition and working condition clustering analysis. The three-dimensional parameter standardization mapping of load, pressure deviation and load change rate is used to unify the original data to the [0, 1] interval to form a quantifiable working condition feature vector. Then, the clustering center positioning and working condition feature threshold judgment formula are used to identify three types of working conditions, namely, transient impact load, high-frequency light load and low-frequency heavy load, and dynamically match the basic compensation coefficient and the correction factor to quickly adjust the displacement output, avoid the overpressure or underpressure problem caused by the fixed compensation mode, and improve the pressure stability of the oil pump under different working conditions.

[0005] To solve the above technical problems, the present application provides the following technical scheme: an intelligent variable oil pump control system based on dynamic pressure compensation, which comprises:

[0006] Running data acquisition module: through multi-dimensional sensors, the load value and real-time pressure of the oil pump during operation are collected, and the real-time data of the load change rate is obtained according to the load difference of adjacent collection periods and the collection interval, and the rated maximum load value and rated maximum pressure value of the oil pump are stored;

[0007] Working condition clustering analysis module: based on multi-dimensional historical data, the three-dimensional parameters are mapped through a data feature vector standardization formula, and three cluster centers are determined, and a working condition feature threshold judgment formula is used to calculate a working condition feature comprehensive value, and three types of working conditions are determined based on the working condition feature comprehensive value;

[0008] Compensation parameter configuration module: according to the three types of working conditions, a preset basic compensation coefficient is stored, and a dynamic correction factor suitable for different working conditions is configured, and the value is determined through orthogonal test;

[0009] Compensation execution control module: based on the collected real-time data, the current data feature vector after standardization is calculated, and the current working condition type is determined; then the compensation coefficient is obtained through a dynamic compensation coefficient calculation formula; the output displacement is calculated through an execution displacement adjustment formula, and the output displacement is converted into a PWM control signal to drive the variable adjustment unit, and the actual pressure deviation after compensation is recorded;

[0010] Online learning optimization module: compare the actual pressure deviation after compensation with the preset target pressure deviation, and update when the deviation is more than 10%; calculate a new basic compensation coefficient through an online learning parameter update formula, and transmit the updated basic compensation coefficient to the compensation parameter configuration module for iterative optimization.

[0011] Further, in the running data acquisition module, multi-dimensional data of the oil pump during operation are collected through multi-dimensional sensors, the multi-dimensional sensors include: a load sensor for collecting the load value of the oil pump during operation, a pressure sensor for collecting the real-time pressure of the oil pump during operation, a preset pressure set value, and a load change rate obtained according to the load difference of adjacent collection periods and a fixed collection interval; the rated maximum load value and the rated maximum pressure set at the factory of the oil pump are stored, and the maximum load change rate is updated based on multi-dimensional historical data collected in the past 30 days.

[0012] Further, in the working condition clustering analysis module, based on multi-dimensional historical data, standardization processing is performed through a data feature vector standardization formula, parameters of three dimensions of load, pressure deviation, and load change rate are mapped to the [0, 1] interval, wherein each component respectively represents a standardized load proportion, a pressure deviation proportion, and a load change rate proportion, three cluster centers are determined according to an engineering common law of oil pump operation and a distribution characteristic of historical data, a working condition feature comprehensive value is calculated through a working condition feature threshold judgment formula, and three types of working conditions are determined based on the working condition feature comprehensive value.

[0013] Further, in the working condition clustering analysis module, standardization processing is performed through a data feature vector standardization formula, parameters of three dimensions of load, pressure deviation, and load change rate are mapped to the [0, 1] interval, and the data feature vector standardization formula is: wherein, is a standardized historical data feature vector, and is a three-dimensional dimensionless vector, is a real-time load value, is an oil pump rated maximum load value, is a real-time pressure value, is a pressure set value, is an oil pump rated maximum pressure value, is a load change rate, is a maximum load change rate.

[0014] Further, in the working condition clustering analysis module, a working condition feature comprehensive value is calculated through a working condition feature threshold judgment formula, and the working condition feature threshold judgment formula is: wherein, is a working condition feature comprehensive value, is a standardized load proportion, is a standardized pressure deviation proportion, is a standardized load change rate proportion.

[0015] Further, in the working condition clustering analysis module, three types of working conditions are determined based on the working condition feature comprehensive value: when , it is determined to be an instantaneous impact load; when , it is determined to be a high-frequency light load; and when , it is determined to be a low-frequency heavy load.

[0016] Further, in the compensation execution control module, based on the collected real-time data, the rated maximum load value, the rated maximum pressure value, and the maximum load change rate are called, a standardized current data feature vector is calculated through a data feature vector standardization formula, and a current working condition and a corresponding identifier are determined through a working condition feature threshold judgment formula combined with a current working condition feature comprehensive value ; the compensation coefficient is obtained through a dynamic compensation coefficient calculation formula according to the preset basic compensation coefficient, the real-time pressure deviation and the load change rate; then the output displacement is calculated through an output displacement adjustment formula, and the output displacement is converted into a PWM control signal to drive the variable adjustment unit, and the actual pressure deviation after compensation is recorded.

[0017] Further, in the compensation execution control module, the compensation coefficient is obtained through a dynamic compensation coefficient calculation formula, and the dynamic compensation coefficient calculation formula is: , wherein, is the dynamic compensation coefficient, quantifying the strength of compensation for the oil pump displacement parameter under the current working condition, is the basic compensation coefficient corresponding to the working condition , is the pressure deviation dynamic correction factor, is the real-time pressure deviation, is the load change rate dynamic correction factor, is the load change rate.

[0018] Further, in the compensation execution control module, the output displacement is calculated through an output displacement adjustment formula, and the output displacement adjustment formula is: , wherein, is the adjusted output displacement of the oil pump, is the current displacement of the oil pump, is the dynamic compensation coefficient, is the real-time pressure deviation, is the pressure set value, is the real-time pressure value, is a sign function, determining the adjustment direction of the displacement, when , the function value is +1, indicating that the displacement needs to be increased, and when , the function value is -1, indicating that the displacement needs to be reduced.

[0019] Further, in the online learning optimization module, the new basic compensation coefficient is calculated through an online learning parameter update formula, and the online learning parameter update formula is: , wherein, is the basic compensation coefficient corresponding to the working condition identifier after the nth online learning update, is the basic compensation coefficient corresponding to the working condition identifier before the nth online learning update, is the learning rate, is the preset target pressure deviation, is the actual pressure deviation after compensation. ​​

[0020] Compared with the prior art, the intelligent variable oil pump control system based on dynamic pressure compensation has the following beneficial effects:

[0021] Firstly, the present application realizes the division of oil pump operating conditions and the intelligent control of dynamic pressure compensation through multi-dimensional data acquisition and working condition clustering analysis, adopts three-dimensional parameter standardization mapping of load, pressure deviation and load change rate, unifies the original data to the [0, 1] interval to form a quantifiable working condition feature vector, and then identifies three working condition types of instantaneous impact load, high-frequency light load and low-frequency heavy load through clustering center positioning and working condition feature threshold judgment formula, and dynamically matches the basic compensation coefficient and the correction factor to quickly adjust the displacement output, thereby avoiding the overpressure or underpressure problem caused by the fixed compensation mode and improving the pressure stability of the oil pump under different working conditions.

[0022] Secondly, the present application introduces a closed-loop feedback mechanism through an online learning optimization module, compares the actual pressure deviation after compensation with the preset target pressure deviation, triggers the adaptive update of the basic compensation coefficient, and dynamically corrects the compensation strategy through the online learning parameter update formula when the actual deviation exceeds 10%, thereby solving the compensation failure problem of the traditional oil pump control system caused by working condition changes or component aging, realizing the leap from passive adjustment to active optimization, reducing the maintenance cost, and prolonging the service life of the oil pump.

[0023] Other advantages, objects, and features of the present application will be set forth in part in the following specification, and in part will become apparent to those skilled in the art from a consideration of the following specification, or can be learned from practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, without creative labor, other drawings can also be obtained from these drawings.

[0025] Figure 1 Flowchart of the intelligent variable oil pump control system based on dynamic pressure compensation;

[0026] Figure 2 Frame diagram of the intelligent variable oil pump control system based on dynamic pressure compensation. DETAILED DESCRIPTION

[0027] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined object of the present application, the specific embodiments, structures, features and effects according to the present application are described in detail below in combination with the drawings and preferred embodiments.

[0028] Embodiment one:

[0029] The running data acquisition module: in the intelligent variable pump control scene of the hydraulic excavator of the engineering machinery, multi-dimensional sensors are installed at the output end of the oil pump of the hydraulic excavator and the load actuator, wherein the load sensor acquires the load value of the oil pump in real time during the bucket excavation operation, the pressure sensor acquires the real-time pressure at the oil outlet of the oil pump, and the pressure set value corresponding to the excavation operation is preset, and the load change rate is calculated according to the load difference of the adjacent fixed collection period and the collection interval; and the rated maximum load value and the rated maximum pressure value of the oil pump are stored, and the maximum load change rate is dynamically updated based on the multi-dimensional historical data of the excavation operation in the past 30 days.

[0030] The working condition clustering analysis module: the multi-dimensional historical data of the excavation operation in the past 30 days (covering the load, pressure deviation, load change rate data under different geological conditions and operation actions) are called, the three-dimensional parameters are mapped to the [0, 1] interval through the data feature vector standardization formula, and the standardized load proportion, pressure deviation proportion and load change rate proportion are obtained, and the data feature vector standardization formula is: , wherein, is the standardized historical data feature vector, and is a three-dimensional dimensionless vector, is the real-time load value, is the rated maximum load value of the oil pump, is the real-time pressure value, is the pressure set value, is the rated maximum pressure value of the oil pump, is the load change rate, is the maximum load change rate; combined with the engineering common law of the hydraulic excavator excavation operation (such as high load and fast change in hard stratum excavation, low load and slow change in soft stratum excavation) and the distribution characteristics of the historical data, three cluster centers are determined, and the working condition feature comprehensive value is calculated through the working condition feature threshold judgment formula, and the working condition feature threshold judgment formula is: , wherein, is the working condition feature comprehensive value, is the standardized load proportion, is the standardized pressure deviation proportion, is the standardized load change rate proportion; and three types of working conditions are determined based on the working condition feature comprehensive value: when , it is determined as instantaneous impact load; when , it is determined as high-frequency light load; and when When this occurs, it is determined to be a low-frequency heavy load, such as... Figure 1 As shown.

[0031] Compensation parameter configuration module: For the three defined working conditions, the corresponding basic compensation coefficients are preset and stored. Then, combined with the influence characteristics of pressure deviation and load change rate on the compensation effect in the excavation operation, the dynamic correction factor of pressure deviation and the dynamic correction factor of load change rate are configured. Through orthogonal experiments, with pressure deviation and load change rate as factors and pressure stability as the evaluation index, the optimal correction factor value is determined.

[0032] The compensation execution control module, based on real-time collected load, pressure, and load change rate data, calls the rated maximum load value, rated maximum pressure value, and maximum load change rate. It calculates the standardized current data feature vector using a data feature vector standardization formula, and then obtains the comprehensive value of the current operating condition feature using a working condition feature threshold determination formula. This determines the current operating condition and its corresponding identifier. Based on the preset basic compensation coefficient for this operating condition, and combined with the real-time pressure deviation and load change rate, it obtains the dynamic compensation coefficient using a dynamic compensation coefficient calculation formula. The dynamic compensation coefficient calculation formula is as follows: ,in, The dynamic compensation coefficient quantifies the intensity of compensation for the oil pump displacement parameters under the current operating conditions. For corresponding working conditions The basic compensation coefficient, This is a dynamic correction factor for pressure deviation. For real-time pressure deviation, This is a dynamic correction factor for the load change rate. The real-time load change rate is used; then, the adjusted output displacement is calculated by executing the displacement adjustment formula, which is: ,in, The adjusted oil pump output displacement. This represents the current displacement of the oil pump. Dynamic compensation coefficient, For real-time pressure deviation, Set the pressure value. This is the real-time pressure value. As a sign function, it determines the direction of displacement adjustment. When the function value is +1, it indicates that the displacement needs to be increased. When the function value is -1, it indicates that the displacement needs to be reduced; the output displacement is converted into a PWM control signal to drive the variable adjustment unit to adjust the oil pump displacement, and the actual pressure deviation after compensation is recorded at the same time.

[0033] The online learning optimization module compares the compensated actual pressure deviation with the preset target pressure deviation, triggers parameter updating when the deviation exceeds 10%, calculates a new basic compensation coefficient through an online learning parameter updating formula, and the online learning parameter updating formula is: wherein, is the basic compensation coefficient corresponding to the working condition identifier after the first online learning update, is the basic compensation coefficient corresponding to the working condition identifier before the first online learning update, is the learning rate, is the preset target pressure deviation, is the compensated actual pressure deviation, and the new basic compensation coefficient is transmitted to the compensation parameter configuration module for iterative optimization.

[0034] In summary, in the hydraulic excavator scene, the running data acquisition module obtains load, pressure and load change rate data in the excavation operation through multi-dimensional sensors, stores the rated parameters and updates the maximum load change rate; the working condition clustering analysis module determines the cluster center based on the standardized historical data, and determines the working condition type through the comprehensive value; the compensation parameter configuration module presets three types of working condition basic compensation coefficients, and determines the correction factor through orthogonal test; the compensation execution control module determines the real-time working condition and calculates the compensation coefficient and output displacement, and converts the signal to drive the adjustment unit; the online learning optimization module compares the pressure deviation, updates the basic compensation coefficient when the threshold is exceeded, and iteratively optimizes the stability of the oil pump pressure and the operation efficiency in the complex working condition of the excavation operation.

[0035] Example Two:

[0036] The running data acquisition module: in the intelligent variable oil pump control scene of the industrial machine tool hydraulic system, multi-dimensional sensors are installed on the oil pump driven by the machine tool hydraulic spindle and the load end of the spindle, wherein the load sensor acquires the load value of the oil pump in real time during spindle cutting operation, the pressure sensor acquires the real-time pressure of the oil pump oil supply port, and the corresponding pressure set value of spindle machining is preset, and the load change rate is calculated according to the load difference value of adjacent fixed collection period and collection interval, and the rated maximum load value and rated maximum pressure value of the oil pump are stored, and the maximum load change rate is dynamically updated based on the multi-dimensional historical data of machine tool machining in the past 30 days.

[0037] ​​Working condition clustering analysis module: access the multi-dimensional historical data of machine tool machining in the past 30 days (covering load, pressure deviation, load change rate data under different cutting parameters and workpiece materials), map the three-dimensional parameters to the [0, 1] interval through the data feature vector standardization formula to obtain the standardized load proportion, pressure deviation proportion and load change rate proportion, and the data feature vector standardization formula is: ; and combined with the engineering common law of machine tool cutting operation (such as high heavy cutting load and slow change, medium speed precision cutting load and fast change) and the distribution characteristics of historical data, determine the three clustering centers, and then calculate the working condition characteristic comprehensive value through the working condition characteristic threshold judgment formula, and the working condition characteristic threshold judgment formula is: ; and based on the working condition characteristic comprehensive value, three types of working conditions are determined: when , it is determined as instantaneous impact load; when , it is determined as high-frequency light load; and when , it is determined as low-frequency heavy load.

[0038] Compensation parameter configuration module: for the determined three types of working conditions of the machine tool, the corresponding basic compensation coefficient is preset and stored, and then the pressure deviation dynamic correction factor and the load change rate dynamic correction factor are configured according to the influence of the pressure deviation and the load change rate on the compensation accuracy in the cutting process. The optimal correction factor value is selected through orthogonal test.

[0039] Compensation execution control module: based on the real-time collected load, pressure and load change rate data, the rated maximum load value, the rated maximum pressure value and the maximum load change rate are called, the standardized current data feature vector is calculated through the data feature vector standardization formula, and then the current working condition characteristic comprehensive value is obtained through the working condition characteristic threshold judgment formula, the current working condition and the corresponding identifier are determined, and the dynamic compensation coefficient is obtained through the dynamic compensation coefficient calculation formula according to the preset basic compensation coefficient of the working condition, combined with the real-time pressure deviation and the load change rate, the dynamic compensation coefficient calculation formula is: ; then the adjusted output displacement is calculated through the execution displacement adjustment formula, and the execution displacement adjustment formula is: , the output displacement is converted into a PWM control signal to drive the variable adjustment unit to adjust the oil pump displacement, and the actual pressure deviation after compensation is recorded, as shown in Figure 2 .

[0040] Online learning optimization module: compare the actual pressure deviation after compensation with the preset target pressure deviation, and trigger parameter update when the deviation exceeds 10%, calculate the new basic compensation coefficient through the online learning parameter update formula, and the online learning parameter update formula is: , and then the new basic compensation coefficient is transmitted to the compensation parameter configuration module to complete the iterative optimization.

[0041] In summary, in the industrial machine tool hydraulic system scenario, the operation data acquisition module collects the load and pressure data of the spindle cutting by means of sensors, calculates the load change rate, stores the rated parameters and updates the maximum change rate; the working condition clustering analysis module processes the historical machining data, divides the working conditions through standardized and comprehensive value calculation; the compensation parameter configuration module presets the working condition basic compensation coefficient, and optimizes the correction factor through orthogonal test; the compensation execution control module determines the real-time working condition, calculates the compensation coefficient and the adjusted displacement, converts the PWM signal to drive the adjustment; the online learning optimization module monitors the pressure deviation, and when the deviation is more than 10%, the basic compensation coefficient is updated and transmitted to the compensation parameter configuration module for iteration, thereby improving the hydraulic control precision of the machine tool machining.

[0042] The above is only a preferred embodiment of the present application, and does not limit the present application in any form. Although the present application has been disclosed as above with a preferred embodiment, it is not intended to limit the present application. Any person skilled in the art can make some changes or modifications to the above disclosed technical content without departing from the scope of the present application, and any equivalent embodiments with equivalent changes are equivalent to the above embodiments. Any modification, change and modification of the above embodiments according to the technical essence of the present application are still within the scope of the present application.

Claims

1. An intelligent variable oil pump control system based on dynamic pressure compensation, characterized in that, The system includes: Operational data acquisition module: Collects real-time data of load value and real-time pressure of oil pump during operation through multi-dimensional sensors, and obtains real-time data of load change rate based on the load difference between adjacent acquisition cycles and acquisition interval, and stores the rated maximum load value and rated maximum pressure value of oil pump. Working condition clustering analysis module: Based on multi-dimensional historical data, it processes the data feature vector standardization formula, maps the three-dimensional parameters, determines 3 cluster centers, calculates the comprehensive value of working condition features through the working condition feature threshold judgment formula, and determines three types of working conditions based on the comprehensive value of working condition features. Compensation parameter configuration module: Based on three types of working conditions, the basic compensation coefficients are preset and stored, then dynamic correction factors adapted to different working conditions are configured, and the values ​​are determined through orthogonal experiments; Compensation execution control module: Based on the collected real-time data, calculate the standardized current data feature vector and determine the current operating condition type; then obtain the compensation coefficient through the dynamic compensation coefficient calculation formula; calculate the output displacement through the displacement adjustment formula, and convert the output displacement into a PWM control signal to drive the variable adjustment unit, while recording the actual pressure deviation after compensation; Online learning optimization module: It compares the actual pressure deviation after compensation with the preset target pressure deviation. When the deviation exceeds 10%, it triggers an update. It calculates a new basic compensation coefficient through the online learning parameter update formula and transmits the updated basic compensation coefficient to the compensation parameter configuration module for iterative optimization.

2. The intelligent variable oil pump control system based on dynamic pressure compensation according to claim 1, characterized in that, The operational data acquisition module collects multi-dimensional data of the oil pump during operation through multi-dimensional sensors, including: a load sensor to collect the load value of the oil pump during operation, and a pressure sensor to collect the real-time pressure of the oil pump during operation. It also presets a pressure setpoint and obtains the load change rate based on the load difference between adjacent acquisition cycles and a fixed acquisition interval. Simultaneously, it stores the rated maximum load value and rated maximum pressure set at the time of the oil pump's manufacture and updates the maximum load change rate based on multi-dimensional historical data collected over the past 30 days.

3. The intelligent variable oil pump control system based on dynamic pressure compensation according to claim 1, characterized in that, In the operating condition clustering analysis module, based on multi-dimensional historical data, the parameters of the three dimensions of load, pressure deviation, and load change rate are standardized by using the data feature vector standardization formula. The parameters are mapped to the interval [0, 1], where each component represents the standardized load ratio, pressure deviation ratio, and load change rate ratio, respectively. Based on the common engineering laws of oil pump operation and the distribution characteristics of historical data, three cluster centers are determined. Then, the comprehensive value of operating condition characteristics is calculated by using the operating condition characteristic threshold determination formula. Based on the comprehensive value of operating condition characteristics, three types of operating conditions are determined.

4. The intelligent variable oil pump control system based on dynamic pressure compensation according to claim 3, characterized in that, In the operating condition clustering analysis module, the data feature vector is standardized using a standardization formula to map the parameters of the three dimensions—load, pressure deviation, and load change rate—to the [0, 1] interval. The standardization formula for the data feature vector is as follows: ,in, The standardized historical data feature vector, This is the real-time load value. This is the rated maximum load value of the oil pump. This is the real-time pressure value. Set the pressure value. This is the rated maximum pressure value of the oil pump. For the rate of load change, This represents the maximum load change rate.

5. The intelligent variable oil pump control system based on dynamic pressure compensation according to claim 3, characterized in that, In the operating condition clustering analysis module, the comprehensive value of operating condition characteristics is calculated using the operating condition characteristic threshold determination formula, which is as follows: ,in, This is the comprehensive value of the operating condition characteristics. This represents the standardized load percentage. This represents the standardized percentage of pressure deviation. This represents the percentage of the standardized load change rate.

6. The intelligent variable oil pump control system based on dynamic pressure compensation according to claim 5, characterized in that, In the operating condition clustering analysis module, three types of operating conditions are determined based on the comprehensive value of operating condition features: when When, it is determined to be an instantaneous impact load; when When, it is determined to be a high-frequency light load; when When this occurs, it is determined to be a low-frequency heavy load.

7. The intelligent variable oil pump control system based on dynamic pressure compensation according to claim 1, characterized in that, In the compensation execution control module, based on the collected real-time data, the rated maximum load value, rated maximum pressure value, and maximum load change rate are called. The standardized current data feature vector is calculated using the data feature vector standardization formula. Then, the current working condition and corresponding identifier are determined by combining the current working condition feature comprehensive value with the working condition feature threshold determination formula. ; Based on the preset basic compensation coefficient, combined with the real-time pressure deviation and load change rate, the compensation coefficient is obtained through the dynamic compensation coefficient calculation formula; then the output displacement is calculated by executing the displacement adjustment formula, and the output displacement is converted into a PWM control signal to drive the variable adjustment unit, while recording the actual pressure deviation after compensation.

8. The intelligent variable oil pump control system based on dynamic pressure compensation according to claim 7, characterized in that, In the compensation execution control module, the compensation coefficient is obtained through a dynamic compensation coefficient calculation formula, which is as follows: ,in, For dynamic compensation coefficients, For corresponding working conditions The basic compensation coefficient, This is a dynamic correction factor for pressure deviation. For real-time pressure deviation, This is a dynamic correction factor for the load change rate. This represents the rate of load change.

9. The intelligent variable oil pump control system based on dynamic pressure compensation according to claim 7, characterized in that, In the compensation execution control module, the output displacement is calculated by executing the displacement adjustment formula, which is: ,in, The adjusted oil pump output displacement. This represents the current displacement of the oil pump. Dynamic compensation coefficient, For real-time pressure deviation, Set the pressure value. This is the real-time pressure value. It is a sign function used to determine the direction of displacement adjustment.

10. The intelligent variable oil pump control system based on dynamic pressure compensation according to claim 1, characterized in that, In the online learning optimization module, a new basic compensation coefficient is calculated using the online learning parameter update formula, which is: ,in, For the first After the online learning update, the corresponding working condition label The basic compensation coefficient, For the first Before the last online learning update, the corresponding working condition label The basic compensation coefficient, For learning rate, To preset the target pressure deviation, This is the actual pressure deviation after compensation.

Images