Intelligent control method and system for turbocharging electric control actuator

Abstract

The invention provides an intelligent control method and system for a turbocharging electric control actuator and relates to the technical field of industrial control, the method comprises the steps that current working parameters of a turbocharging system are obtained in real time, and the working parameters at least comprise the turbine rotating speed, the turbine blade surface temperature and the installation position and displacement of the electric control actuator; inputting the working parameters into a pre-established turbine blade rigidity analysis model to obtain first rigidity data of the turbine blade; on the basis of the working parameters, rigid data of the turbine blade in a future set time period are predicted, and second rigid data are obtained; the electronic control actuator is controlled based on the second rigidity data, the rigidity variable quantity of the turbine blade is calculated in real time based on parameters such as the rotating speed and the temperature, displacement deviation caused by mechanical abrasion and thermal expansion is automatically compensated through an intelligent control algorithm, and the performance of the turbocharging electronic control actuator is improved; the turbocharging system can operate efficiently and stably, and development of an industrial control system is accelerated.

Description

Technical Field

[0001] The present application generally relates to the field of industrial control technology. More specifically, the present application relates to an intelligent control method and system for a turbocharger electronically controlled actuator. Background Art

[0002] Turbocharging technology occupies a core position in the power systems of industrial control systems (such as those in the automotive and aviation industries). Its efficient energy conversion capabilities directly determine equipment performance and energy consumption. Due to rapid changes in speed and temperature, the rigidity of the turbine blades undergoes nonlinear fluctuations. Traditional static models have difficulty capturing this dynamic characteristic, resulting in the actuator being unable to accurately locate the target position. The uncertainty of this rigidity change directly affects the control system's ability to adjust the actuator position in real time. A deeper challenge is that mechanical wear and thermal expansion effects accumulate over time, causing the actual displacement of the actuator to deviate from the design value, and existing methods lack automatic compensation mechanisms for these long-term effects. The uncertainty of rigidity changes leads to deviations in position control, and the accumulation of deviations further amplifies the impact of life-related factors, forming an interconnected technical problem.

[0003] Existing control methods for electronically controlled actuators in turbocharging systems generally suffer from insufficient precision, particularly under high-temperature and high-speed operating conditions. Existing control strategies struggle to adapt to complex environmental changes, leading to performance degradation and shortened component life. In particular, the rigidity changes of turbine blades under extreme operating conditions are difficult to accurately predict, and existing control strategies often ignore the dynamic effects of speed and temperature, resulting in actuator position deviations. Furthermore, mechanical wear and thermal expansion effects accumulate with service life, further exacerbating the loss of control accuracy. These limitations prevent turbocharging systems from achieving efficient and stable operation, directly impacting the development of industrial control systems.

[0004] Therefore, how to calculate the change in turbine blade rigidity in real time based on parameters such as speed and temperature, and automatically compensate for the displacement deviation caused by mechanical wear and thermal expansion through intelligent control algorithms, has become a key issue in improving the performance of turbocharged electronic control actuators. Summary of the Invention

[0005] In order to at least solve one or more of the technical problems mentioned above, the present application proposes an intelligent control method and system for a turbocharger electronically controlled actuator in multiple aspects.

[0006] In a first aspect, the intelligent control method of a turbocharger electronically controlled actuator provided by the present application includes: Acquire the current operating parameters of the turbocharger system in real time, wherein the operating parameters include at least turbine speed, turbine blade surface temperature, and installation position and displacement of the electronically controlled actuator; Inputting the operating parameters into a pre-established turbine blade rigidity analysis model to obtain first rigidity data of the turbine blade; Based on the operating parameters, predicting the rigidity data of the turbine blade within a future set time period to obtain second rigidity data; The electronically controlled actuator is controlled based on the second stiffness data.

[0007] In some examples, inputting the operating parameters into a pre-established turbine blade rigidity analysis model to obtain first rigidity data of the turbine blade includes: Based on the operating parameters, the turbine blade rigidity analysis model performs the following operations: Based on the turbine speed and the surface temperature of the turbine blade, a finite element analysis tool is used to calculate the current initial rigidity value of the turbine blade to obtain initial rigidity data; Obtaining the thermal expansion coefficient of the turbine blade, and using a thermal-mechanical coupling analysis method to calculate the current thermal expansion deformation of the blade; determining whether the thermal expansion deformation is greater than a preset first threshold, and if not, using the initial rigidity data as the first rigidity data; On the contrary, a numerical integration method is used to calculate the rigidity data of the turbine blade under preset constraint conditions, and the rigidity data under the constraint conditions is used as the first rigidity data, wherein the constraint conditions include the turbine fixed end speed constraint and the material fatigue property constraint.

[0008] In some examples, based on the operating parameters, the rigidity data of the turbine blade within a future set time period is predicted to obtain second rigidity data: According to the working parameters, the pre-established turbine blade rigidity analysis model adopts a support vector regression algorithm to determine the nonlinear fluctuation trend of the turbine blade rigidity, and predicts the rigidity data of the turbine blade within a future set time period based on the nonlinear fluctuation trend of the turbine blade rigidity.

[0009] In some examples, controlling the electronically controlled actuator based on the second stiffness data includes: determining whether to adjust the current installation position of the electronically controlled actuator according to a deviation value between the second rigidity data and the first rigidity data; If the deviation value is greater than a preset second threshold, an adaptive control algorithm is used to adjust the current installation position of the electronically controlled actuator to generate a target installation position of the electronically controlled actuator; A position control signal is generated according to the target installation position and the current installation position of the electronically controlled actuator, and the electronically controlled actuator is controlled according to the position control signal.

[0010] In some examples, after generating the position control signal, the method further includes: Calculating the wear trend of the electronically controlled actuator within a future set time period based on the current load of the electronically controlled actuator; Calculating the expansion trend of the electronically controlled actuator within a set future time period based on the current ambient temperature of the electronically controlled actuator; calculating a displacement deviation of the electronically controlled actuator within a future set time period based on a wear trend and an expansion trend of the electronically controlled actuator; A displacement control signal is generated according to the displacement deviation, and the electronically controlled actuator is controlled according to the position control signal.

[0011] In some examples, generating a displacement control signal according to the displacement deviation includes: determining whether the displacement deviation is greater than a preset third threshold, and if so, adjusting the displacement deviation based on the magnitude of the displacement deviation to generate an adjusted displacement deviation; Based on the signal superposition method, the adjusted displacement deviation is combined with the original displacement data to obtain the corrected displacement data; A displacement control signal is generated according to the corrected displacement data.

[0012] In some examples, after obtaining the current operating parameters of the turbocharger system in real time, the method further includes: A Kalman filter algorithm is used to perform denoising on the working parameters.

[0013] Secondly, the intelligent control system of the turbocharger electronically controlled actuator approved by this application includes: an acquisition module configured to acquire, in real time, current operating parameters of the turbocharger system, wherein the operating parameters include at least turbine speed, turbine blade surface temperature, and installation position and displacement of the electronically controlled actuator; an input module configured to input the operating parameters into a pre-established turbine blade rigidity analysis model to obtain first rigidity data of the turbine blade; a prediction module configured to predict stiffness data of the turbine blade within a future set time period based on the operating parameters to obtain second stiffness data; The control module is configured to control the electronically controlled actuator based on the second stiffness data.

[0014] In a third aspect, the computer-readable storage medium provided in the present application contains program instructions, which, when executed by a processor, implement the method described in the first aspect above.

[0015] In a fourth aspect, the electronic device provided by this application includes: A processor; and a memory storing computer instructions, which, when the computer instructions are executed by the processor, causes the electronic device to execute the method described in the first aspect above.

[0016] Compared with the existing technology, this application calculates the change in turbine blade rigidity in real time based on parameters such as speed and temperature, and automatically compensates for installation position deviation and stroke deviation caused by mechanical wear and thermal expansion through intelligent control algorithms, generates corresponding control signals to control the electronic actuator, improves the performance of the electronic actuator, enables the turbocharger system to achieve efficient and stable operation, and accelerates the development of industrial control systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other objects, features and advantages of the exemplary embodiments of the present application will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 An exemplary flow chart of an intelligent control method for a turbocharged electronically controlled actuator provided by an embodiment of the present application is shown; Figure 2 An exemplary structural block diagram of an intelligent control system for a turbocharged electronically controlled actuator provided in an embodiment of the present application is shown; Figure 3 An exemplary structural block diagram of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0019] It should be understood that the terms "include" and "comprising" used in the description and claims of this application indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0020] It should also be understood that the terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this specification and claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" as used in this specification and claims refers to any and all possible combinations of one or more of the associated listed items, including and including these combinations.

[0021] As used in this specification and claims, the term “if” can be interpreted as “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context. Similarly, the phrase “if it is determined” or “if [described condition or event] is detected” can be interpreted as meaning “upon determination” or “in response to determining” or “upon detection of [described condition or event]” or “in response to detecting [described condition or event],” depending on the context.

[0022] The specific implementation of the present application will be described in detail below with reference to the accompanying drawings.

[0023] like Figure 1 As shown, the intelligent control method of the turbocharger electronically controlled actuator provided in the embodiment of the present application includes the following steps: S101, obtaining current operating parameters of the turbocharger system in real time, wherein the operating parameters at least include turbine speed, turbine blade surface temperature, and installation position and displacement of the electronically controlled actuator.

[0024] In some examples, after obtaining the current operating parameters of the turbocharger system, a Kalman filter algorithm is used to perform denoising on the operating parameters to obtain smoothed operating parameters.

[0025] Specifically, sensors installed in the turbocharger system acquire a raw data set corresponding to operating parameters, including turbine speed, blade surface temperature, and actuator installation position and displacement. A real-time acquisition module timestamps the raw data to produce a time-series raw data set. A Kalman filter algorithm is used to process the turbine speed, turbine blade temperature, and actuator installation position and displacement in the raw data set. Through state estimation and covariance updating, a denoised first smoothed data set is generated. The turbine speed, blade temperature, or actuator installation position and displacement in the first smoothed data set are then determined to determine whether they exceed corresponding preset thresholds. If so, the signal processing module performs secondary filtering on the above-threshold parameters to produce a second smoothed data set. Based on this second smoothed data set, a data fusion algorithm is used to perform a weighted combination of turbine speed, blade temperature, and actuator position to determine a comprehensive state parameter.

[0026] Specifically, determine whether the first smoothed data set exceeds a preset threshold. Assume the speed threshold is 130,000 rpm, the temperature threshold is 700°C, and the actuator position threshold is 80%. If the temperature of 648°C is found to be within the specified threshold but requires continuous monitoring, then the over-threshold parameters require secondary filtering.

[0027] For example, if the speed reaches 135,000 rpm, exceeding the threshold, the signal processing module performs low-pass filtering to remove high-frequency noise and generate a second smoothed data set, such as when the speed drops to 134,500 rpm. This secondary filtering further improves data stability, reduces false alarms, and ensures safe system operation.

[0028] Optionally, based on the second smoothed data set, a data fusion algorithm is used to perform a weighted combination of the rotational speed, temperature and actuator position to determine the comprehensive state parameter.

[0029] For example, we assign a weight of 40% to speed, 30% to temperature, 15% to actuator location, and 15% to actuator displacement, and calculate the overall status value through weighted average. Assume the fused status value is "good," indicating that the system is operating normally. Data fusion integrates multidimensional information to comprehensively assess system health and optimize control strategies.

[0030] For example, when the state value is low, the actuator opening can be adjusted to improve the boost efficiency.

[0031] In some examples, various sensors are deployed in key areas of a turbocharger. For example, a turbine speed sensor is mounted on the turbine shaft, measuring rpm in real time (e.g., 120,000 rpm at a time). A temperature sensor is attached to the blade surface, recording a temperature of, for example, 650°C. An actuator position sensor monitors the control valve opening, outputting a position value such as 75%. This data is timestamped by a real-time acquisition module, forming a raw data set with a time series.

[0032] For example, a data point might be "2025-05-08 10:00:00.123, 120,000 rpm, 650°C, 75%." This ensures data traceability, facilitates subsequent analysis of time correlation, and improves the accuracy of subsequent processing.

[0033] Specifically, the Kalman filter algorithm is used to process the original data set. Kalman filter predicts the system state and corrects noise through state estimation and covariance update.

[0034] For example, speed data can be affected by electromagnetic interference, resulting in significant fluctuations in the original data. Kalman filtering utilizes historical data and sensor measurements to generate a smoothed first dataset. Assume that after processing, the speed stabilizes at 119,800 rpm, the temperature is 648°C, and the actuator position is 74.8%. This denoising effect reduces the risk of misjudgment in the industrial control system, improves data reliability, and provides an accurate basis for subsequent judgments.

[0035] As you can see, the above method has achieved significant technical results. Timestamping ensures data consistency, facilitating fault tracing. Kalman filtering and secondary filtering effectively reduce noise and improve data quality. Threshold determination and data fusion enable precise status assessment, reducing the risk of industrial control system failures and extending turbocharger life.

[0036] For example, after applying this method to an industrial control system (automotive manufacturing plant), the failure rate decreased by 15% and maintenance costs were reduced by 20%. These technologies work together to form a strict logical chain, ensuring the efficient and stable operation of the turbocharging system.

[0037] S102: Input the operating parameters into a pre-established turbine blade rigidity analysis model to obtain first rigidity data of the turbine blade.

[0038] In some examples, step S102 specifically includes: Based on the operating parameters, the turbine blade rigidity analysis model performs the following operations: Based on the turbine speed and the surface temperature of the turbine blade, a finite element analysis tool is used to calculate the current initial rigidity value of the turbine blade to obtain initial rigidity data; Obtaining the thermal expansion coefficient of the turbine blade, and using a thermal-mechanical coupling analysis method to calculate the current thermal expansion deformation of the blade; determining whether the thermal expansion deformation is greater than a preset first threshold, and if not, using the initial rigidity data as the current rigidity data of the turbine blade; On the contrary, a numerical integration method is used to calculate the rigidity data of the turbine blade under preset constraint conditions, and the rigidity data under the constraint conditions is used as the current rigidity data of the turbine blade, wherein the constraint conditions include the turbine fixed end speed constraint and the material fatigue property constraint.

[0039] Specifically, real-time rigidity data is acquired from the blade sensor, and the data acquisition module uses a mean filtering method to perform denoising on the real-time rigidity data to obtain smoothed rigidity data.

[0040] S103 , based on the operating parameters, predicting the rigidity data of the turbine blade within a future set time period to obtain second rigidity data.

[0041] In some examples, this step specifically includes: According to the first rigidity data, the pre-established turbine blade rigidity analysis model adopts a support vector regression algorithm to determine the nonlinear fluctuation trend of the turbine blade rigidity, and predicts the rigidity data of the turbine blade within a future set time period based on the nonlinear fluctuation trend of the turbine blade rigidity.

[0042] Specifically, consider an aircraft engine blade operating at 20,000 rpm and 800°C. The stress data collected by sensors exhibits periodic fluctuations. The analysis tool can extract the periodic characteristics of the data, such as the frequency and amplitude of the fluctuations, and calculate the stress fluctuation coefficient.

[0043] For example, in one analysis, the stress fluctuation coefficient was 0.15, indicating relatively stable stress changes. This method captures patterns over time, providing a reliable basis for subsequent predictions.

[0044] In one embodiment, corresponding rigidity change data is obtained from historical data, and a support vector regression algorithm is used to predict the rigidity nonlinear fluctuation trend. Support vector regression is good at processing nonlinear relationships and is suitable for the change of blade rigidity under complex working conditions.

[0045] For example, historical data shows that when the temperature rises from 600°C to 800°C, rigidity decreases by approximately 5%. Through algorithm training, the rigidity fluctuation trend over the next 10 minutes can be predicted, yielding a value such as 4.8%. This prediction can identify potential rigidity anomalies in advance and support maintenance decisions.

[0046] Specifically, determining whether the predicted stiffness fluctuation exceeds a preset threshold is a critical step. Assuming a 5% threshold, a predicted value of 4.8% is within the safe range; a value of 5.2% requires correction. During this correction, the predicted value is adjusted using numerical integration methods, taking into account the model's correction coefficients and boundary conditions, such as the blade's fixed-end constraints and material fatigue properties.

[0047] For example, a correction factor of 0.95 reduces the stiffness fluctuation to 4.9%, which is closer to the actual working conditions. This correction ensures the accuracy of the prediction.

[0048] For example, after obtaining the corrected rigidity fluctuation data, the rigidity fluctuation characteristics can be further analyzed in combination with the thermal expansion parameters, which reflect the deformation characteristics of the blade material at high temperatures.

[0049] For example, the thermal expansion coefficient of a nickel-based alloy is 1.3e-5 / °C. At 800°C, blade length increases by 0.02mm. Using time series analysis tools, combined with thermal expansion data, we calculate the stiffness fluctuation characteristics and obtain a final prediction value, such as 4.85%. This analysis comprehensively considers both thermal and mechanical effects, improving the comprehensiveness of the prediction.

[0050] In one embodiment, the above method achieves accurate prediction of blade rigidity fluctuations through multi-dimensional data fusion.

[0051] For example, the combination of stress fluctuation coefficients, historical stiffness data, and thermal expansion parameters forms an analytical framework for multi-lateral support. The predicted results can be used to optimize blade design or adjust operating parameters to extend service life.

[0052] Specifically, finite element analysis tools, such as commercial software such as ANSYS, are used to calculate the initial stiffness of turbine blades. A smoothed rotational speed of 79,950 revolutions per second and a temperature of 748 degrees Celsius are input into the finite element model. Considering the properties of the turbine blades, which are made of nickel-based alloys, the stress distribution of the turbine blades under high-temperature and high-speed operating conditions is simulated.

[0053] For example, the initial stiffness of the stress concentration area at the root of a turbine blade was calculated to be 2.5 × 10^8 Pa, reflecting the blade's ability to resist deformation under these operating conditions. This method, through meshing and boundary condition setting, accurately captures the mechanical behavior of the turbine blade.

[0054] Specifically, after obtaining the thermal expansion coefficient and geometric parameters of the turbine blade material, thermal-mechanical coupling analysis is used to calculate the thermal expansion deformation.

[0055] For example, the thermal expansion coefficient of nickel-based alloys is 1.3 × 10^-5 per degree Celsius, and the turbine blade length is 0.1 meter. At 748 degrees Celsius, coupled thermal-mechanical analysis calculates the turbine blade's thermal expansion deformation to be 0.00097 meters. This process considers the interaction between the temperature and stress fields to ensure the accuracy of the deformation data. If the deformation exceeds the preset threshold of 0.0008 meters, further analysis of stiffness changes is required.

[0056] For example, numerical integration methods can be used to calculate the change in stiffness, combined with boundary condition constraints. Assuming a turbine blade with a fixed end constrained and a rotational speed of 79,950 revolutions per second, numerical integration analysis shows a decrease in stiffness from 2.5 × 10^8 Pa to 2.3 × 10^8 Pa, a change of 0.2 × 10^8 Pa. This method simulates the dynamic response of turbine blades under high-speed rotation through step-by-step integration, capturing the trend of decreasing stiffness and providing a basis for turbine blade life assessment.

[0057] In one possible implementation, a real-time data acquisition tool may acquire rigidity change data through an embedded system.

[0058] For example, a sensor collects rigidity data every 0.01 seconds to generate a time series dataset. Time series analysis methods, such as autoregressive models, are used to analyze the trend of rigidity changes.

[0059] For example, it is predicted that after 100 hours of continuous operation, the stiffness of the turbine blades may further decrease to 2.2×10^8 Pa. This analysis helps to monitor the status of the turbine blades in real time and optimize the operating strategy of the turbocharger system.

[0060] It should be noted that the above method is closely centered around the mechanical and thermal performance analysis of the turbocharger system blades. The generated rigidity change data can be used to guide the design optimization and maintenance plan formulation of turbine blades, ensuring the stability and durability of the turbocharger system under high-temperature and high-speed conditions.

[0061] It should be noted that this method relies on high-quality data acquisition and algorithm training. In practical applications, sensor accuracy and data integrity must be ensured to fully utilize its technical advantages.

[0062] S104: Control the electronically controlled actuator based on the second rigidity data.

[0063] In some examples, this step specifically includes: determining whether to adjust the current installation position of the electronically controlled actuator according to a deviation value between the second rigidity data and the first rigidity data; If the deviation value is greater than a preset second threshold, an adaptive control algorithm is used to adjust the current installation position of the electronically controlled actuator to generate a target installation position of the electronically controlled actuator; A position control signal is generated according to the target installation position and the current installation position of the electronically controlled actuator, and the electronically controlled actuator is controlled according to the position control signal.

[0064] For example, if the preset threshold is 5%, the actual stiffness data is 100 N / m, and the predicted value is 95 N / m, a deviation of 5.26%, exceeding the preset threshold. The comparison module calculates the difference and outputs a deviation value of 5 N / m. This intuitive and efficient method can quickly identify data anomalies and provide a basis for subsequent adjustments.

[0065] Optionally, the preset threshold value can be dynamically adjusted according to the blade material and operating conditions to improve adaptability.

[0066] In one embodiment, based on the deviation value, an adaptive control algorithm is used to adjust the control gain parameters using a gradient update rule. The adaptive control adapts to the changes in blade operating conditions by optimizing the gain in real time.

[0067] For example, if the initial gain is 0.8 and a deviation of 5 N / m triggers a gradient update with a step size of 0.01, the updated gain is 0.82. This method dynamically balances control accuracy and response speed, avoiding overshoot or undershoot.

[0068] It should be noted that the step size selection needs to take into account both convergence speed and stability.

[0069] For example, the corrected gain is used to generate an optimized control signal, which is then converted into the driving force of the actuator through gain adjustment.

[0070] For example, a gain of 0.82 generates a control signal that drives the actuator to adjust the blade angle by 2 degrees. This approach allows for precise control of blade attitude and adapts to real-time operating conditions.

[0071] Optionally, the generation of control signals needs to take into account actuator response delays to ensure real-time control.

[0072] In a possible implementation, the signal conversion module converts the control signal into an actuator position instruction.

[0073] For example, a 5V control signal is mapped to an actuator displacement of 0.5mm by the conversion module. This conversion is based on a pre-calibrated mapping table, ensuring that the command is accurately transmitted to the actuator.

[0074] Specifically, a PID control algorithm is used to calculate the proportional term, integral term, and differential term for the control deviation. The proportional term is the control deviation multiplied by the proportional coefficient, the integral term is the cumulative sum of the control deviations multiplied by the integral coefficient, and the differential term is the rate of change of the control deviation multiplied by the differential coefficient to obtain the preliminary adjustment value. If the response delay is greater than a preset threshold, the preliminary adjustment value is compensated based on the response delay time, and a delay compensation term is added to obtain the corrected adjustment value. The actuator position is updated based on the corrected adjustment value, and the corrected adjustment value is applied to the current actual position to obtain the precise position adjustment data.

[0075] For example, in a blade control system, the target position and actual position are obtained from the optimized actuator position command and smoothed position data, and the difference between the two is calculated to obtain the control deviation. The target position is generated by the control algorithm based on the turbine blade operating conditions. For example, the command requires the turbine blade angle to be adjusted to 10 degrees. The actual position is collected by a high-precision position sensor, such as an optical encoder installed on the actuator output shaft with a sampling frequency of 500Hz, which obtains the actual angle of the turbine blade in real time, such as 9.8 degrees. The control deviation is calculated from the difference between the two and is 0.2 degrees. This method relies on the high resolution and fast response of the sensor to ensure the accuracy of the deviation calculation, providing a reliable basis for subsequent control.

[0076] In one possible implementation, a PID control algorithm is used to process control deviations. The proportional term is generated by multiplying the deviation by a proportional coefficient. For example, if the deviation is 0.2 degrees and the proportional coefficient is set to 2, the proportional term is 0.4. The integral term is based on the cumulative sum of the deviations multiplied by the integral coefficient. For example, if the cumulative deviation is 0.5 degrees and the integral coefficient is 0.1, the integral term is 0.05. The differential term is calculated by multiplying the rate of change of the deviation by the differential coefficient. For example, if the rate of change of the deviation is 0.1 degrees / second and the differential coefficient is 0.5, the differential term is 0.05. The three terms are added together to obtain the initial adjustment value of 0.5. This method balances rapid control and stability through multi-dimensional adjustment.

[0077] It's important to note that if the actuator response delay exceeds a preset threshold—for example, if the threshold is set at 10 milliseconds and the actual delay is measured at 12 milliseconds—the initial adjustment must be compensated. The delay compensation term is calculated based on the delay time. For example, if the delay exceeds 2 milliseconds, a compensation factor of 0.01 is used, resulting in a compensation term of 0.02. Adding the initial adjustment of 0.5 to the compensation term yields a revised adjustment of 0.52. This compensation mechanism ensures the real-time nature of actuator action by predicting the impact of delay on the controlled variable.

[0078] For example, the corrected adjustment is used to update the actuator's installed position. If the current position is 9.8 degrees, applying an adjustment of 0.52 results in a precise installation position of 10.32 degrees. The actuator adjusts the blade angle based on this data, for example, by driving a servo motor. The adjustment is mapped to the number of motor rotation steps, such as 0.52 degrees corresponding to 50 steps. This mapping table, based on system calibration, ensures accurate command transmission. This approach allows for precise position updates, adapting to the dynamic operating conditions of blades under high-temperature, high-speed rotation.

[0079] Specifically, the position sensor needs to be calibrated regularly to account for blade wear or environmental changes.

[0080] For example, zero-point calibration is performed every 100 hours of operation to prevent cumulative errors. During calibration, the sensor records the blade's static reference position, such as 0 degrees, which serves as a reference for subsequent measurements. This regular maintenance ensures long-term data acquisition reliability and provides stable support for deviation calculation and control adjustments.

[0081] In some examples, step S104 specifically further includes: Calculating the wear trend of the electronically controlled actuator within a future set time period based on the current load of the electronically controlled actuator; Calculating the expansion trend of the electronically controlled actuator within a set future time period based on the current ambient temperature of the electronically controlled actuator; calculating a displacement deviation of the electronically controlled actuator within a future set time period based on a wear trend and an expansion trend of the electronically controlled actuator; A displacement control signal is generated according to the displacement deviation, and the electronically controlled actuator is controlled according to the position control signal.

[0082] Specifically, time series data is obtained from a historical displacement deviation database, and the time series data is preprocessed using a sequence analysis method to extract the deviation sequences of wear trends and thermal expansion to obtain a structured deviation sequence data set. If the integrity of the deviation sequence data set is higher than a preset threshold, the deviation sequence data set is trained using a long short-term memory network algorithm to generate a cumulative trend model and determine the prediction model parameters for wear trends and thermal expansion. Based on the prediction model parameters, the deviation values of wear trends and thermal expansion are calculated for the latest input of the time series data to obtain a preliminary displacement deviation prediction value. The preliminary displacement deviation prediction value is corrected using a trend prediction method, and the corrected prediction value is determined in combination with the sequence analysis results of the historical deviation to obtain the final displacement deviation prediction value.

[0083] For example, when acquiring time series data from a historical displacement deviation database, database query tools can be used to extract records of actuator position deviation under specific operating conditions. This data typically includes timestamps, deviation values, and environmental parameters such as temperature and load. Assume that deviation data for the past 30 days is collected, recorded once per second, resulting in a time series consisting of 2,592,000 data points. During the preprocessing phase, sequence analysis methods can use moving average filtering to remove noise and retain key trends. For wear trends, cumulative changes in long-term deviations can be analyzed. For example, if the deviation value gradually increases under a fixed load each day, this indicates that the actuator component may be experiencing displacement deviation due to wear. Thermal expansion deviation series are obtained by extracting short-term temperature-related fluctuations. For example, when the temperature rises from 20°C to 50°C, the deviation value shows a periodic increase of approximately 0.02 mm.

[0084] Specifically, after extracting the wear trend and thermal expansion deviation series, the dataset integrity needs to be assessed. Assuming a 95% integrity threshold, the dataset meets the requirements by counting the percentage of valid data points.

[0085] For example, missing data accounts for only 2% and can be supplemented through interpolation. During the training phase of the LSTM algorithm, the deviation sequence is divided into a 70% training set and a 30% test set, training the model to identify temporal patterns of wear and thermal expansion. The model outputs predictive parameters, such as a slope of 0.01 mm per week for the wear trend and a linear relationship between the cyclical deviation of thermal expansion and temperature with a coefficient of 0.001 mm / °C.

[0086] In some embodiments, a deviation value is calculated based on the prediction model parameters for the latest input data, such as a current ambient temperature of 45°C and a load of 1000N. The deviation contributed by the wear trend is 0.03 mm, the thermal expansion deviation is 0.025 mm, and the initial displacement deviation prediction value is 0.055 mm. The correction phase of the trend prediction method can incorporate the statistical characteristics of the historical deviation sequence, for example, by adjusting the predicted value through weighted averaging to reduce the interference of short-term fluctuations. The deviation value after correction may be 0.052 mm. In the final judgment, if the correction value is consistent with the fluctuation range of the historical deviation, its reliability is confirmed.

[0087] It should be noted that the above process is closely centered around the deviation analysis of actuator position control, and the generated prediction values can be used to optimize control instructions.

[0088] For example, a predicted deviation of 0.052 mm can be directly used to adjust the actuator displacement to ensure positioning accuracy. This approach improves the accuracy of deviation prediction by integrating historical data with real-time input, taking into account the effects of long-term wear and short-term thermal expansion, providing a reliable basis for subsequent position adjustments.

[0089] In some examples, generating a displacement control signal according to the displacement deviation includes: determining whether the displacement deviation is greater than a preset third threshold, and if so, adjusting the displacement deviation based on the magnitude of the displacement deviation to generate an adjusted displacement deviation; Based on the signal superposition method, the adjusted displacement deviation is combined with the original displacement data to obtain the corrected displacement data; A displacement control signal is generated according to the corrected displacement data.

[0090] Specifically, the current displacement data of the electronically controlled actuator is acquired through a sensor. A linear regression algorithm is used to calculate a weighted combination of the current displacement data and historical displacement data to obtain an estimated displacement deviation. If the estimated displacement deviation exceeds a preset deviation threshold, a weight is assigned based on the magnitude of the estimated displacement deviation to generate a compensation signal amplitude. This compensation signal amplitude is then combined with the displacement data using signal superposition to generate corrected displacement control data. This corrected displacement control data is then used to generate the final actuator control command and determine the actuator's movement amplitude.

[0091] Specifically, the process of acquiring current displacement data and historical displacement deviation data can be understood as extracting key information from the mechanical system's real-time monitoring equipment and database. Current displacement data typically includes the electronic actuator's real-time position, speed, and ambient temperature, while historical displacement data records the equipment's deviation performance under different operating conditions.

[0092] For example, when a robotic arm is running continuously, the sensor collects displacement data every second and records it as 10.5 mm, 10.6 mm, etc. The historical data includes the displacement deviation values of each operation in the past month, such as 0.02 mm, 0.03 mm, etc. These data provide the basis for subsequent analysis.

[0093] In one possible implementation, a linear regression algorithm is used to calculate a weighted combination of current and historical displacement data, aiming to capture the correlation between real-time status and long-term trends. Linear regression fits the data to determine the weight of each data point.

[0094] For example, the current displacement data might be weighted 0.7, while the historical data might be weighted 0.3, reflecting the priority of real-time data. Assuming the current displacement data indicates a current displacement deviation of 0.05 mm and the historical average deviation of 0.02 mm, the weighted calculation yields an estimated displacement deviation of approximately 0.041 mm. This approach ensures the stability and accuracy of the predicted value.

[0095] It should be noted that if the predicted displacement deviation exceeds a preset deviation threshold, such as 0.04 mm, a compensation signal amplitude needs to be generated.

[0096] Specifically, the larger the displacement deviation, the higher the weight assigned, thereby generating a stronger compensation signal.

[0097] For example, when the displacement deviation is 0.045 mm, the weight may be 1.2, generating a compensation signal amplitude of 0.054 mm; when the deviation is 0.05 mm, the weight increases to 1.5, and the signal amplitude is 0.075 mm. This dynamic adjustment method can effectively cope with different degrees of deviation.

[0098] In one embodiment, the signal superposition method combines the compensation signal amplitude with the displacement data to generate the corrected displacement control data.

[0099] For example, if the original displacement adjustment data instructs the electronic actuator to move to 10.0 mm, the compensation signal amplitude is 0.054 mm, and the corrected position after superposition is 10.054 mm. This process ensures the accuracy of the control instructions and reduces the accumulation of deviations.

[0100] Optionally, the corrected position control data is used to generate a final control instruction for the electronically controlled actuator to determine the amplitude of the movement.

[0101] For example, based on displacement data of 10.054 mm, a control instruction is generated to drive the actuator to the target position with an accuracy of 0.001 mm. This refined control improves the stability of industrial control systems.

[0102] This application calculates the change in turbine blade rigidity in real time based on parameters such as speed and temperature, and automatically compensates for installation position deviation and stroke deviation caused by mechanical wear and thermal expansion through intelligent control algorithms, generating corresponding control signals to control the electronic actuator, thereby improving the performance of the electronic actuator, enabling the turbocharger system to achieve efficient and stable operation, and accelerating the development of industrial control systems.

[0103] like Figure 2 As shown, the intelligent control system of the turbocharger electronically controlled actuator provided in the embodiment of the present application includes: an acquisition module configured to acquire, in real time, current operating parameters of the turbocharger system, wherein the operating parameters include at least turbine speed, turbine blade surface temperature, and installation position and displacement of the electronically controlled actuator; an input module configured to input the operating parameters into a pre-established turbine blade rigidity analysis model to obtain first rigidity data of the turbine blade; a prediction module configured to predict stiffness data of the turbine blade within a future set time period based on the operating parameters to obtain second stiffness data; The control module is configured to control the electronically controlled actuator based on the second stiffness data.

[0104] On the other hand, the present invention also provides an electronic device. Figure 3 , Figure 3 is an exemplary structural block diagram of an electronic device according to an embodiment of the present application, such as Figure 3 As shown, the electronic device includes a processor and a memory, wherein the memory stores computer instructions, and the processor executes the method provided in the present application when running the computer instructions.

[0105] Specifically, processor 601 may include a central processing unit (CPU) or a graphics processing unit (GPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application. Memory 602 may include storage for data or instructions. For example, memory 602 may be at least one of the following: a hard disk drive (HDD), read-only memory (ROM), random access memory (RAM), a floppy disk drive, flash memory, an optical disk, a magneto-optical disk, magnetic tape, a universal serial bus (USB) drive, or other physical / tangible memory storage device. For another example, memory 602 may include removable or non-removable (or fixed) media. For another example, memory 602 may be internal or external to the integrated gateway disaster recovery device. Memory 602 may be non-volatile solid-state memory. In other words, memory 602 typically includes a tangible (non-transitory) computer-readable storage medium (such as a memory device) encoded with executable instructions. When the stored executable instructions are executed by processor 601 (e.g., by one or more processors), the methods of the embodiments of the present application can be implemented.

[0106] In one example, Figure 3 The electronic device shown may also include a communication interface 603 and a bus 610. The processor 601, memory 602, and communication interface 603 are connected via bus 610 and communicate with each other. The communication interface 603 is primarily used to facilitate communication between various modules, devices, units, and / or devices within the electronic device. Bus 610, which may comprise hardware, software, or both, couples the components of the online data traffic metering device. For example, the bus may include at least one of the following: an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industrial Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses. Bus 610 may include one or more buses. Although the embodiments of the present application describe or illustrate a specific bus, the embodiments of the present application may consider any suitable bus or interconnection method.

[0107] In another aspect, embodiments of the present application further provide a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the aforementioned method. The computer-readable storage medium may be, for example, a conventional computer-readable storage medium, such as a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, or an electrical, optical, or other physical / tangible memory storage device.

[0108] In another aspect, embodiments of the present application further provide a computer program product comprising computer program instructions that, when executed by a processor, implement the methods provided by embodiments of the present application. Examples of such computer program products include software installation packages and plug-ins compatible with related software systems.

[0109] The flowcharts and / or block diagrams of the methods and systems of the embodiments of the present application are described above by way of example, along with various related aspects. It should be understood that each block in the flowcharts and / or block diagrams, or a combination thereof, may be implemented by computer program instructions, by dedicated hardware that performs a specified function or action, or by a combination of dedicated hardware and computer instructions. When implemented in hardware, it may be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc.; when implemented in software, it may be a program or code segment used to perform the required task. The program or code segment may be stored in a memory or transmitted over a transmission medium or communication link via a data signal carried in a carrier wave. The code segment may be downloaded via a computer network such as the Internet or an intranet.

[0110] In addition, the terms "first", "second" and the like used in the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different parts.

[0111] Although multiple embodiments of the present application have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art can conceive of many changes, modifications, and alternatives without departing from the thought and spirit of the present application. It should be understood that in the process of practicing the present application, various alternatives to the embodiments of the present application described herein can be adopted. The accompanying claims are intended to define the scope of protection of the present application and therefore cover equivalents or alternatives within the scope of these claims.

Claims

1. An intelligent control method for a turbocharger electronically controlled actuator, characterized in that: include: Acquire the current operating parameters of the turbocharger system in real time, wherein the operating parameters include at least turbine speed, turbine blade surface temperature, and installation position and displacement of the electronically controlled actuator; Inputting the operating parameters into a pre-established turbine blade rigidity analysis model to obtain first rigidity data of the turbine blade; Based on the operating parameters, predicting the rigidity data of the turbine blade within a future set time period to obtain second rigidity data; The electronically controlled actuator is controlled based on the second stiffness data.

2. The intelligent control method for a turbocharger electronically controlled actuator according to claim 1, characterized in that: Inputting the operating parameters into a pre-established turbine blade rigidity analysis model to obtain first rigidity data of the turbine blade includes: Based on the operating parameters, the turbine blade rigidity analysis model performs the following operations: Based on the turbine speed and the surface temperature of the turbine blade, a finite element analysis tool is used to calculate the current initial rigidity value of the turbine blade to obtain initial rigidity data; Obtaining the thermal expansion coefficient of the turbine blade, and using a thermal-mechanical coupling analysis method to calculate the current thermal expansion deformation of the blade; determining whether the thermal expansion deformation is greater than a preset first threshold, and if not, using the initial rigidity data as the first rigidity data; On the contrary, a numerical integration method is used to calculate the rigidity data of the turbine blade under preset constraint conditions, and the rigidity data under the constraint conditions is used as the first rigidity data, wherein the constraint conditions include the turbine fixed end speed constraint and the material fatigue property constraint.

3. The intelligent control method for a turbocharged electronically controlled actuator according to claim 1, characterized in that: Predicting the rigidity data of the turbine blade within a future set time period based on the operating parameters to obtain the second rigidity data includes: According to the working parameters, a support vector regression algorithm is used to determine the nonlinear fluctuation trend of the turbine blade rigidity, and according to the nonlinear fluctuation trend of the turbine blade rigidity, the rigidity data of the turbine blade within a future set time period is predicted.

4. The intelligent control method for a turbocharged electronically controlled actuator according to claim 3, characterized in that: Controlling the electronically controlled actuator based on the second rigidity data includes: determining whether to adjust the current installation position of the electronically controlled actuator according to a deviation value between the second rigidity data and the first rigidity data; If the deviation value is greater than a preset second threshold, an adaptive control algorithm is used to adjust the current installation position of the electronically controlled actuator to generate a target installation position of the electronically controlled actuator; A position control signal is generated according to the target installation position and the current installation position of the electronically controlled actuator, and the electronically controlled actuator is controlled according to the position control signal.

5. The intelligent control method for a turbocharged electronically controlled actuator according to claim 3, characterized in that: After generating the position control signal, the method further includes: Calculating the wear trend of the electronically controlled actuator within a future set time period based on the current load of the electronically controlled actuator; Calculating the expansion trend of the electronically controlled actuator within a set future time period based on the current ambient temperature of the electronically controlled actuator; calculating a displacement deviation of the electronically controlled actuator within a future set time period based on a wear trend and an expansion trend of the electronically controlled actuator; A displacement control signal is generated according to the displacement deviation, and the electronically controlled actuator is controlled according to the position control signal.

6. The intelligent control method for a turbocharged electronically controlled actuator according to claim 5, characterized in that: Generating a displacement control signal according to the displacement deviation includes: determining whether the displacement deviation is greater than a preset third threshold, and if so, adjusting the displacement deviation based on the magnitude of the displacement deviation to generate an adjusted displacement deviation; Based on the signal superposition method, the adjusted displacement deviation is combined with the original displacement data to obtain the corrected displacement data; A displacement control signal is generated according to the corrected displacement data.

7. The intelligent control method for a turbocharged electronically controlled actuator according to claim 1, characterized in that: After obtaining the current operating parameters of the turbocharger system in real time, the method further includes: A Kalman filter algorithm is used to perform denoising on the working parameters.

8. An intelligent control system for a turbocharger electronically controlled actuator, characterized in that: include: an acquisition module configured to acquire, in real time, current operating parameters of the turbocharger system, wherein the operating parameters include at least turbine speed, turbine blade surface temperature, and installation position and displacement of the electronically controlled actuator; an input module configured to input the operating parameters into a pre-established turbine blade rigidity analysis model to obtain first rigidity data of the turbine blade; a prediction module configured to predict stiffness data of the turbine blade within a future set time period based on the operating parameters to obtain second stiffness data; The control module is configured to control the electronically controlled actuator based on the second stiffness data.

9. A computer-readable storage medium, characterized in that The method comprises program instructions, which, when executed by a processor, implement the method according to any one of claims 1 to 8.

10. An electronic device, characterized in that: include: processor; as well as A memory storing computer instructions, wherein when the computer instructions are executed by the processor, the electronic device executes the method according to any one of claims 1 to 8.

Images