Intelligent control method and system of multi-working-condition self-adaptive plunger pump driving system
Through dynamic adjustment of real-time operating conditions characteristics and driving parameters, combined with wear evaluation and swash plate angle influence, an independent iterative optimization mechanism is built, which solves the problem of insufficient control adaptability of the plunger pump under variable operating conditions, and improves operating performance and reliability.
Patent Information
- Application Number
- CN202511026375.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-24
- Publication Date
- 2025-09-02
AI Technical Summary
The existing plunger pump control technology cannot adapt to variable operating conditions, resulting in increased system response hysteresis and wear.
By obtaining working conditions characteristics and driving parameters in real time, random adjustments and analysis are performed, combining wear evaluation and swash plate angle influence, an independent iterative optimization mechanism is built, and driving parameters are dynamically adjusted to achieve optimal control.
The operating performance and reliability of the plunger pump under complex variable operating conditions is significantly improved, and the reliability deterioration caused by wear accumulation in traditional methods is avoided, thereby achieving high robustness control.
Smart Images
Figure CN120576076A_ABST
Abstract
Description
[0001] The present invention relates to the technical field of intelligent control of plunger pumps, and in particular to an intelligent control method and system for a multi-working-condition adaptive plunger pump drive system. Background Art
[0002] As the core power element of hydraulic systems, plunger pumps are widely used in fields such as engineering machinery and aerospace. Existing control technologies primarily maintain stable pump operation through preset parameters or simple feedback mechanisms. These drive parameters are typically designed based on static operating conditions or determined through limited operating condition calibration. However, in actual operation, plunger pumps often face complex operating conditions such as sudden load changes and dynamically changing flow demands. Existing technologies are unable to adapt to these changing conditions, resulting in delayed system response and increased wear on the plunger pump, which requires urgent solutions. Summary of the Invention
[0003] The present application provides an intelligent control method and system for a multi-working-condition adaptive plunger pump drive system, which is used to solve the technical problem in the prior art that the plunger pump control has insufficient adaptability and is prone to wear.
[0004] In view of the above problems, the present application provides an intelligent control method and system for a multi-working condition adaptive plunger pump drive system.
[0005] In a first aspect, the present application provides an intelligent control method for a multi-working-condition adaptive plunger pump drive system, the method comprising: During the operation of the plunger pump, the real-time working condition characteristics and the real-time driving parameters of the plunger pump drive system are obtained, and when the working condition changes, the changing working condition characteristics are collected.
[0006] The real-time driving parameters are randomly adjusted to obtain adjusted driving parameters, and working condition adaptation parameters are obtained through analysis based on the adjusted driving parameters and the characteristics of the changed working conditions.
[0007] A wear analysis of the plunger pump is performed based on the adjusted drive parameters and the changed operating condition characteristics to obtain a first wear parameter, and an influence analysis of the swash plate angle is performed to obtain an influencing swash plate angle. A wear analysis of the plunger pump is performed to obtain a second wear parameter, and an operating condition cost parameter is calculated in combination with the first wear parameter.
[0008] According to the influencing swash plate angle, the working condition adaptation parameter is corrected, and in combination with the working condition cost parameter, the driving adaptability is calculated and obtained, and iterative optimization is performed to obtain the optimal driving parameter, and the plunger pump driving control is performed.
[0009] In a second aspect, the present application provides an intelligent control system for a multi-working-condition adaptive plunger pump drive system, comprising: The feature acquisition module is used to obtain real-time working condition features and real-time driving parameters of the plunger pump drive system during the operation of the plunger pump, and to acquire changing working condition features when the working condition changes.
[0010] The adaptation parameter acquisition module is used to randomly adjust the real-time driving parameters to obtain the adjusted driving parameters, and to analyze and obtain the working condition adaptation parameters based on the adjusted driving parameters and the characteristics of the changed working condition.
[0011] The operating condition cost calculation module is used to perform a wear analysis of the plunger pump based on the adjusted drive parameters and the changed operating condition characteristics to obtain a first wear parameter, perform an influence analysis of the swash plate angle to obtain an influencing swash plate angle, perform a wear analysis of the plunger pump to obtain a second wear parameter, and calculate the operating condition cost parameter in combination with the first wear parameter.
[0012] The optimization control module is used to modify the working condition adaptation parameter according to the influencing swash plate angle, calculate the driving adaptability in combination with the working condition cost parameter, perform iterative optimization to obtain the optimal driving parameter, and perform plunger pump driving control.
[0013] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application proposes an intelligent control method and system for a multi-condition adaptive plunger pump drive system. By dynamically collecting the characteristics of working condition changes and constructing an autonomous iterative optimization mechanism for drive parameters, the comprehensive operating performance of the plunger pump under complex and variable working conditions is significantly improved. Compared with traditional methods, the technical solution provided by this application significantly overcomes the rigidity defects of fixed parameter strategies and the limitations of single-objective optimization: first, a collaborative drive mechanism based on real-time working condition characteristics and random adjustment ensures the stability of control parameters; second, the abnormal wear caused by the oscillation of the swash plate angle is incorporated into the real-time evaluation system. By quantitatively analyzing the wear parameters under different drive parameters, the optimization process simultaneously takes into account the life cost, avoiding the reliability degradation caused by the traditional method due to ignoring the accumulation of wear; third, by constructing a dynamic balance model of working condition adaptation parameters and working condition cost parameters, and introducing feedback correction of the influence of the swash plate angle, the drive fitness parameters can accurately represent the global performance of the system. Combined with iterative optimization, the constraints of the empirical threshold are broken through, and the optimal solution that takes into account both operating effect and equipment durability is efficiently converged.
[0014] This application achieves the technical effect of autonomously coordinating the operating parameters of the plunger pump under variable working conditions, realizing intelligent and highly robust control of the drive system, and providing a more reliable parameter solution for the control of the plunger pump under complex working conditions. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0016] Figure 1 A flow chart of the intelligent control method for a multi-condition adaptive plunger pump drive system provided in an embodiment of the present application.
[0017] Figure 2 A schematic structural diagram of the intelligent control system of the multi-condition adaptive plunger pump drive system provided in an embodiment of the present application.
[0018] In the accompanying drawings, the components represented by the reference numerals are described as follows: Feature collection module 100, adaptation parameter acquisition module 200, working condition cost calculation module 300, optimization control module 400. DETAILED DESCRIPTION
[0019] The present application provides an intelligent control method and system for a multi-working-condition adaptive plunger pump drive system, which is used to solve the technical problem in the prior art that the plunger pump control has insufficient adaptability and is prone to wear.
[0020] 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 only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.
[0021] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.
[0022] Example 1, as Figure 1 As shown, the present application provides an intelligent control method for a multi-working-condition adaptive plunger pump drive system, wherein the method includes: S10: During the operation of the plunger pump, real-time working condition characteristics and real-time driving parameters of the plunger pump driving system are obtained, and when the working condition changes, the changed working condition characteristics are collected.
[0023] Step S10 in the method provided in the embodiment of the present application includes: During the operation of the plunger pump, real-time operating condition characteristics and real-time driving parameters of the plunger pump driving system are obtained, wherein the operating condition characteristics include the operating condition load.
[0024] When the working conditions change, the characteristics of the changed working conditions are collected.
[0025] In the embodiment of the present application, during the operation of the plunger pump, real-time operating characteristics are obtained, including the operating load, which is the load pressure during the operation of the plunger pump, in MPa, and real-time drive parameters of the plunger pump drive system, such as the speed, in revolutions per minute.
[0026] When the working condition changes, the changed working condition characteristics are collected. The changed working condition characteristics are the working condition load after the working condition changes, and the unit is MPa.
[0027] By synchronously acquiring real-time operating condition characteristics and drive parameters, and actively collecting changing characteristics as operating conditions change, a dynamic operating condition parameter set is constructed. Compared to traditional passive monitoring, this significantly improves the sensitivity of capturing transient operating conditions such as sudden load changes, laying the data foundation for subsequent parameter optimization.
[0028] S20: Randomly adjust the real-time driving parameters to obtain adjusted driving parameters, and analyze and obtain working condition adaptation parameters based on the adjusted driving parameters and the characteristics of the changed working condition.
[0029] Existing parameter adjustment strategies mostly use fixed step sizes or rule searches such as gradient descent, which face two major limitations under variable operating conditions: first, the fixed adjustment mode makes it difficult to explore discontinuous parameter spaces and is prone to falling into local optimal solutions; second, a real-time mapping relationship between drive parameters and operating condition characteristics is not established, and only historical data or static models are relied upon, resulting in poor adaptability of control parameters under new operating conditions.
[0030] Step S20 in the method provided in the embodiment of the present application includes: Get the driving parameter range of the plunger pump drive system.
[0031] Within the driving parameter range, the real-time driving parameters are randomly adjusted to obtain adjusted driving parameters.
[0032] The adjusted driving parameters and the changed working condition characteristics are input into the working condition adaptation analyzer, and the working condition adaptation parameters are output.
[0033] The training step of the operating condition adaptation analyzer includes: Based on the plunger pump operation data in historical time, a sample driving parameter set and a sample operating condition feature set are collected.
[0034] According to the operating pressure stability under different sample driving parameters and sample working condition characteristics, the sample working condition adaptation parameter set is marked.
[0035] A machine learning-based working condition adaptation analyzer is constructed, and supervised training is performed using the sample driving parameter set, the sample working condition feature set, and the sample working condition adaptation parameter set, and the training is completed after convergence.
[0036] In the embodiment of the present application, the driving parameter range of the driving system, such as the rotational speed, is obtained based on the factory settings of the piston pump.
[0037] Within the driving parameter range, the real-time driving parameter is randomly adjusted, for example, the real-time driving parameter is randomly added or subtracted to obtain the adjusted driving parameter.
[0038] Based on the historical operating data of the plunger pump, a set of sample drive parameters and a set of sample operating condition characteristics are collected. There is a one-to-one correspondence between the drive parameters and the operating condition characteristics.
[0039] Based on the operating pressure stability under different sample drive parameters and sample operating condition characteristics, a set of sample operating condition adaptation parameters is annotated. For example, the ratio of the standard deviation of the operating pressure to the mean operating pressure under different drive parameters and operating condition characteristics is calculated as a parameter representing the operating pressure stability, namely the operating condition adaptation parameter. The larger the operating condition adaptation parameter, the smaller the operating pressure fluctuation and the more adapted the drive parameters are to the current operating conditions. Operating condition adaptation parameter = standard deviation of operating pressure ÷ mean operating pressure. The operating condition adaptation parameter is calculated for each set of sample drive parameters and sample operating condition characteristics, and the sample drive parameter set and sample operating condition characteristic set are annotated.
[0040] A working condition adaptation analyzer is constructed based on machine learning. The input layer receives drive parameters and working condition characteristics. The hidden layer uses 16 nodes activated by the ReLU function. The output layer uses one node activated by the Sigmoid function. Supervised training is performed using a set of sample drive parameters, a set of sample working condition characteristics, and a set of sample working condition adaptation parameters until convergence. For example, if the error range of the output working condition adaptation parameters for the input drive parameters and working condition characteristics is within ±0.05, the working condition adapter is considered trained.
[0041] The adjusted drive parameters and the changed operating condition characteristics are input into an operating condition adaptation analyzer, which outputs an operating condition adaptation parameter. The output operating condition adaptation parameter reflects the adaptability of the adjusted drive parameters to the changed operating condition characteristics. A larger operating condition adaptation parameter indicates that the adjusted drive parameters are more adaptable to the changed operating condition.
[0042] This application introduces a random adjustment mechanism for drive parameters, combining changing operating condition characteristics to generate operating condition adaptation parameters in real time, breaking through the rigid constraints of traditional adjustment models. Random adjustment can proactively explore multi-dimensional parameter combinations, avoiding local optimality. Based on dynamic analysis of adjustment parameters and operating condition characteristics, it can directly quantify the adaptability of current parameters to new operating conditions. This mechanism significantly improves parameter exploration efficiency and shortens optimization convergence time, providing key input for the coordinated optimization of wear and efficiency.
[0043] S30: Perform a wear analysis on the plunger pump based on the adjusted drive parameters and the changed operating condition characteristics to obtain a first wear parameter, perform a swash plate angle influence analysis to obtain an influencing swash plate angle, perform a wear analysis on the plunger pump to obtain a second wear parameter, and calculate and obtain an operating condition cost parameter in combination with the first wear parameter.
[0044] Existing wear assessments only focus on a single mechanical wear factor and ignore the secondary wear caused by swash plate angle oscillation, resulting in poor optimization results.
[0045] Step S30 in the method provided in the embodiment of the present application includes: A plunger pump wear classifier is obtained, wherein the plunger pump wear classifier is trained using sample drive parameters, sample operating condition characteristics, and sample wear parameters in plunger pump wear test data, and the sample first wear parameter includes a wear rate.
[0046] The adjusted driving parameters and the changed working condition characteristics are input into the wear classifier of the plunger pump, and the classification output is used to obtain the first wear parameter.
[0047] The real-time operating condition characteristics, real-time driving parameters, adjusted driving parameters and changed operating condition characteristics are input into a swash plate angle impact analyzer, and the output is the influencing swash plate angle, wherein the swash plate angle impact analyzer is trained using sample real-time operating condition characteristics, sample real-time driving parameters, sample adjusted driving parameters, sample changed operating condition characteristics and sample swash plate angles.
[0048] According to the influencing swash plate angle, the second wear parameter is obtained by classification, wherein the influencing swash plate angle is input into a swash plate oscillation wear classification table for classification, and the swash plate oscillation wear classification table is constructed based on the mapping relationship between the sample influencing swash plate angle and the sample second wear parameter.
[0049] A total wear parameter is calculated based on the first wear parameter and the second wear parameter.
[0050] The ratio of the total wear parameter to the preset wear parameter is calculated to obtain the working condition cost parameter.
[0051] In the present embodiment, a wear test is performed on a plunger pump to obtain wear test data. A first wear parameter of the plunger pump is obtained from the sample drive parameters and the sample variable operating condition characteristics. The first wear parameter of the plunger pump is calculated as follows: wear amount ÷ wear time. The wear amount, for example, is the reduction in the plunger radius of the plunger pump due to wear, measured in mm; the wear time is measured in minutes.
[0052] A support vector machine is used to construct a plunger pump wear classifier. The sample drive parameters and sample operating condition characteristics are input, and training is performed using the maximum classification interval to obtain the first wear parameter. The deviation between the first wear parameter and the sample is compared, and the model parameters are adjusted until convergence. For example, if the accuracy of the wear parameter obtained by classification is above 90%, the training of the plunger pump wear classifier is completed.
[0053] The adjusted drive parameters and the changing operating condition characteristics are input into the plunger pump wear classifier, which then outputs the first wear parameter. This first wear parameter reflects the wear of the plunger pump and provides a quantifiable reference for subsequent control parameter optimization.
[0054] The swash plate angle during actual operation of the plunger pump is collected as the sample swash plate angle. The sample swash plate angle corresponds to the sample real-time operating condition characteristics, sample real-time drive parameters, sample adjusted drive parameters, and sample variable operating condition characteristics during actual operation. During actual operation, flow shocks can cause the plunger to oscillate, which is transmitted to the swash plate through the slipper, causing the swash plate angle to change and resulting in wear.
[0055] A multi-layer perceptron (MLP) was used to construct a swash plate angle impact analyzer. The input layer received real-time operating condition characteristics, real-time drive parameters, adjusted drive parameters, and variable operating condition characteristics. The hidden layer used 12 nodes with tanh activation, and the output layer used 1 node with linear activation to output the factors affecting the swash plate angle. The swash plate angle impact analyzer was trained using sample real-time operating condition characteristics, sample real-time drive parameters, sample adjusted drive parameters, sample variable operating condition characteristics, and sample swash plate angles until convergence. For example, if the output of the swash plate angle impact analyzer, with the input of real-time operating condition characteristics, real-time drive parameters, adjusted drive parameters, and variable operating condition characteristics, is within ±1°, the swash plate angle impact analyzer is considered trained.
[0056] The real-time working condition characteristics, real-time driving parameters, adjusted driving parameters and changed working condition characteristics are input into the swash plate angle impact analyzer, and the output is the impact swash plate angle.
[0057] A support vector machine is used to construct a classification table for oscillating wear of the swash plate. Samples that affect the swash plate angle are input, and training is performed using the maximum classification interval to obtain the second wear parameter. The second wear parameter can, for example, be the amount of reduction in the plunger radius of the plunger pump due to wear caused by the swash plate angle, in mm, and the wear time in minutes. The second wear parameter = wear amount ÷ wear time. The deviation of the second wear parameter of the comparison sample is compared, and the model parameters are adjusted until convergence. For example, if the accuracy of the wear parameter obtained by classification is above 90%, the training of the swash plate oscillation wear classification table is completed. The factors that affect the swash plate angle are input into the swash plate oscillation wear classification table for classification to obtain the second wear parameter. The second wear parameter reflects the wear caused by the change in the swash plate angle, further refines the wear situation and considers multiple source factors, providing more accurate reference data for subsequent control parameter optimization.
[0058] The total wear parameter is calculated based on the first and second wear parameters. Total wear parameter = (first wear parameter + second wear parameter) ÷ 2. For example, if the first wear parameter is 0.2 and the second wear parameter is 0.3, then the total wear parameter = (0.2 + 0.3) ÷ 2 = 0.25.
[0059] Calculate the ratio of the total wear parameter to the preset wear parameter to obtain the working condition cost parameter. For example, if the total wear parameter is 0.25 and the preset wear parameter is 0.3, then the working condition cost parameter = 0.25 ÷ 0.3 = 0.83.
[0060] This application integrates mechanical wear and swash plate angle-related wear to construct a dual-dimensional wear assessment system. By analyzing the impact of swash plate angle, it quantifies hidden wear. Combined with the operating cost parameters generated by the dual wear parameters, it accurately characterizes the comprehensive impact of drive parameter selection on system life, fundamentally avoiding the reliability degradation caused by traditional methods that underestimate wear.
[0061] S40: According to the influencing swash plate angle, the operating condition adaptation parameter is modified, and the driving adaptability is calculated in combination with the operating condition cost parameter. The optimal driving parameter is obtained by iterative optimization, and the plunger pump driving control is performed.
[0062] In multi-objective optimization, efficiency and lifespan often conflict. For example, high-efficiency parameters can exacerbate wear. Existing methods, lacking a dynamic weighting mechanism, rely solely on a fixed trade-off between the two. This can overlook the indirect effects of the swash plate angle on flow stability. Furthermore, static weighting cannot adapt to changing operating conditions, causing optimization results to deviate from the global optimum. For example, excessively suppressing wear under high loads can actually lead to degraded energy efficiency.
[0063] Step S40 in the method provided in the embodiment of the present application includes: The flow rate variation amplitude is calculated based on the influencing swash plate angle.
[0064] The flow rate variation range is used to correct and compensate the operating condition adaptation parameter to obtain a corrected operating condition adaptation parameter.
[0065] The driving fitness is calculated based on the modified operating condition adaptation parameter and the operating condition cost parameter.
[0066] According to the drive adaptability, the drive parameters are iteratively optimized to obtain the optimal drive parameters and perform plunger pump drive control.
[0067] According to the drive adaptability, iterative optimization of the drive parameters is performed to obtain the optimal drive parameters and to control the plunger pump drive, including: Continue to randomly adjust the drive parameters and calculate the drive fitness.
[0068] The driving parameters are iteratively optimized. After reaching the optimization convergence condition, the driving parameters corresponding to the maximum driving fitness are retained as the optimal driving parameters for plunger pump drive control.
[0069] In the embodiment of the present application, the flow rate variation range is calculated based on the influencing swash plate angle, and the flow rate variation range is the variation range of the pump flow rate, and the unit is %.
[0070] The flow rate change amplitude is used to modify and compensate the working condition adaptation parameter to obtain the modified working condition adaptation parameter. The modified working condition adaptation parameter = (1 + flow rate change amplitude) × working condition adaptation parameter. For example, if the flow rate change amplitude is 2% and the working condition adaptation parameter is 0.8, then the modified working condition adaptation parameter = (1 + 2%) × 0.8 = 0.816.
[0071] A weighted calculation is performed based on the modified operating condition adaptation parameter and the operating condition cost parameter to obtain the drive fitness. Drive fitness = (1 ÷ operating condition cost parameter) × cost weight + modified operating condition adaptation parameter × operating condition weight, where cost weight + operating condition weight = 1. For example, if the operating condition standby parameter is 0.823, the cost weight is 0.4, the modified operating condition adaptation parameter is 0.816, and the operating condition weight is 0.6, then the drive fitness = (1 ÷ 0.823) × 0.4 + 0.816 × 0.6 = 0.97.
[0072] Continue to randomly adjust the drive parameters and calculate the drive fitness.
[0073] The drive parameters are iteratively optimized. After reaching the optimization convergence condition, such as the drive fitness reaching 99% or 30 optimization iterations, the drive parameters corresponding to the maximum drive fitness are retained as the optimal drive parameters for driving control of the plunger pump.
[0074] By dynamically modifying the operating condition adaptation parameters through the swash plate angle and integrating the operating condition cost parameters to generate the drive fitness, a multi-objective collaborative optimization mechanism is established. Feedback correction of the swash plate angle ensures the accuracy of efficiency evaluation. The fitness function simultaneously integrates efficiency adaptability and wear cost, allowing the optimization process to automatically balance objective weights. Combined with iterative optimization, it quickly converges to the optimal solution for the operating condition, significantly improving the overall system performance.
[0075] Example 2, as Figure 2 As shown, based on the same inventive concept as the intelligent control method of the multi-working condition adaptive plunger pump drive system provided in Example 1, an embodiment of the present invention also provides an intelligent control system for the multi-working condition adaptive plunger pump drive system, including: The feature acquisition module 100 is used to acquire real-time working condition features and real-time driving parameters of the plunger pump drive system during the operation of the plunger pump, and to acquire changing working condition features when the working condition changes.
[0076] The adaptation parameter acquisition module 200 is used to randomly adjust the real-time driving parameters to obtain adjusted driving parameters, and to analyze and obtain working condition adaptation parameters based on the adjusted driving parameters and the characteristics of the changed working condition.
[0077] The operating condition cost calculation module 300 is used to perform a wear analysis of the plunger pump based on the adjusted drive parameters and the changed operating condition characteristics to obtain a first wear parameter, perform a swash plate angle influence analysis to obtain the influencing swash plate angle, perform a wear analysis of the plunger pump to obtain a second wear parameter, and calculate the operating condition cost parameter in combination with the first wear parameter.
[0078] The optimization control module 400 is used to modify the working condition adaptation parameter according to the influencing swash plate angle, calculate the driving adaptability in combination with the working condition cost parameter, perform iterative optimization to obtain the optimal driving parameter, and perform plunger pump driving control.
[0079] In one embodiment, the feature collection module 100 is further configured to: During the operation of the plunger pump, real-time operating condition characteristics and real-time driving parameters of the plunger pump driving system are obtained, wherein the operating condition characteristics include the operating condition load.
[0080] When the working conditions change, the characteristics of the changed working conditions are collected.
[0081] In one embodiment, the adaptation parameter acquisition module 200 is further configured to: Get the driving parameter range of the plunger pump drive system.
[0082] Within the driving parameter range, the real-time driving parameters are randomly adjusted to obtain adjusted driving parameters.
[0083] The adjusted driving parameters and the changed working condition characteristics are input into the working condition adaptation analyzer, and the working condition adaptation parameters are output.
[0084] The training step of the operating condition adaptation analyzer includes: Based on the plunger pump operation data in historical time, a sample driving parameter set and a sample operating condition feature set are collected.
[0085] According to the operating pressure stability under different sample driving parameters and sample working condition characteristics, the sample working condition adaptation parameter set is marked.
[0086] A machine learning-based working condition adaptation analyzer is constructed, and supervised training is performed using the sample driving parameter set, the sample working condition feature set, and the sample working condition adaptation parameter set, and the training is completed after convergence.
[0087] In one embodiment, the operating condition cost calculation module 300 is further configured to: A plunger pump wear classifier is obtained, wherein the plunger pump wear classifier is trained using sample drive parameters, sample operating condition characteristics, and sample wear parameters in plunger pump wear test data, and the sample first wear parameter includes a wear rate.
[0088] The adjusted driving parameters and the changed working condition characteristics are input into the wear classifier of the plunger pump, and the classification output is used to obtain the first wear parameter.
[0089] The real-time operating condition characteristics, real-time driving parameters, adjusted driving parameters and changed operating condition characteristics are input into a swash plate angle impact analyzer, and the output is the influencing swash plate angle, wherein the swash plate angle impact analyzer is trained using sample real-time operating condition characteristics, sample real-time driving parameters, sample adjusted driving parameters, sample changed operating condition characteristics and sample swash plate angles.
[0090] According to the influencing swash plate angle, the second wear parameter is obtained by classification, wherein the influencing swash plate angle is input into a swash plate oscillation wear classification table for classification, and the swash plate oscillation wear classification table is constructed based on the mapping relationship between the sample influencing swash plate angle and the sample second wear parameter.
[0091] A total wear parameter is calculated based on the first wear parameter and the second wear parameter.
[0092] The ratio of the total wear parameter to the preset wear parameter is calculated to obtain the working condition cost parameter.
[0093] In one embodiment, the optimization control module 400 is further configured to: The flow rate variation amplitude is calculated based on the influencing swash plate angle.
[0094] The flow rate variation range is used to correct and compensate the operating condition adaptation parameter to obtain a corrected operating condition adaptation parameter.
[0095] The driving fitness is calculated based on the modified operating condition adaptation parameter and the operating condition cost parameter.
[0096] According to the drive adaptability, the drive parameters are iteratively optimized to obtain the optimal drive parameters and perform plunger pump drive control.
[0097] According to the drive adaptability, iterative optimization of the drive parameters is performed to obtain the optimal drive parameters and to control the plunger pump drive, including: Continue to randomly adjust the drive parameters and calculate the drive fitness.
[0098] The driving parameters are iteratively optimized. After reaching the optimization convergence condition, the driving parameters corresponding to the maximum driving fitness are retained as the optimal driving parameters for plunger pump drive control.
[0099] In summary, the embodiments of the present application have at least the following technical effects: This application proposes an intelligent control method and system for a multi-condition adaptive plunger pump drive system. By dynamically collecting the characteristics of working condition changes and constructing an autonomous iterative optimization mechanism for drive parameters, the comprehensive operating performance of the plunger pump under complex and variable working conditions is significantly improved. Compared with traditional methods, the technical solution provided by this application significantly overcomes the rigidity defects of fixed parameter strategies and the limitations of single-objective optimization: first, a collaborative drive mechanism based on real-time working condition characteristics and random adjustment ensures the stability of control parameters; second, the abnormal wear caused by the oscillation of the swash plate angle is incorporated into the real-time evaluation system. By quantitatively analyzing the wear parameters under different drive parameters, the optimization process simultaneously takes into account the life cost, avoiding the reliability degradation caused by the traditional method due to ignoring the accumulation of wear; third, by constructing a dynamic balance model of working condition adaptation parameters and working condition cost parameters, and introducing feedback correction of the influence of the swash plate angle, the drive fitness parameters can accurately represent the global performance of the system. Combined with iterative optimization, the constraints of the empirical threshold are broken through, and the optimal solution that takes into account both operating effect and equipment durability is efficiently converged.
[0100] This application achieves the technical effect of autonomously coordinating the operating parameters of the plunger pump under variable working conditions, realizing intelligent and highly robust control of the drive system, and providing a more reliable parameter solution for the control of the plunger pump under complex working conditions.
[0101] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0102] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.
[0103] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.
Claims
1. An intelligent control method for a multi-condition adaptive plunger pump drive system, characterized in that: The method comprises: During the operation of the plunger pump, the real-time working condition characteristics and the real-time driving parameters of the plunger pump drive system are obtained, and when the working condition changes, the changing working condition characteristics are collected; Randomly adjusting the real-time driving parameters to obtain adjusted driving parameters, and analyzing and obtaining working condition adaptation parameters based on the adjusted driving parameters and the characteristics of the changed working condition; Performing a wear analysis on the plunger pump based on the adjusted drive parameters and the changed operating condition characteristics to obtain a first wear parameter, performing a swash plate angle influence analysis to obtain an influence swash plate angle, performing a wear analysis on the plunger pump to obtain a second wear parameter, and calculating an operating condition cost parameter based on the first wear parameter; According to the influencing swash plate angle, the working condition adaptation parameter is corrected, and in combination with the working condition cost parameter, the driving adaptability is calculated and obtained, and iterative optimization is performed to obtain the optimal driving parameter, and the plunger pump driving control is performed.
2. The intelligent control method of the multi-mode adaptive plunger pump drive system according to claim 1, characterized in that: During the operation of the plunger pump, the real-time operating condition characteristics and the real-time driving parameters of the plunger pump drive system are obtained. When the operating condition changes, the changing operating condition characteristics are collected, including: During the operation of the plunger pump, real-time working condition characteristics and real-time driving parameters of the plunger pump driving system are obtained, wherein the working condition characteristics include working condition load; When the working conditions change, the characteristics of the changed working conditions are collected.
3. The intelligent control method for a multi-mode adaptive plunger pump drive system according to claim 1, characterized in that: Randomly adjusting the real-time driving parameters to obtain adjusted driving parameters, and analyzing and obtaining working condition adaptation parameters based on the adjusted driving parameters and the characteristics of the changed working condition, including: Obtain the driving parameter range of the plunger pump driving system; Randomly adjusting the real-time driving parameters within the driving parameter range to obtain adjusted driving parameters; The adjusted driving parameters and the changed working condition characteristics are input into the working condition adaptation analyzer, and the working condition adaptation parameters are output.
4. The intelligent control method for a multi-mode adaptive plunger pump drive system according to claim 3, characterized in that: The training step of the operating condition adaptation analyzer includes: Based on the historical operating data of the plunger pump, a sample driving parameter set and a sample operating condition feature set are collected; According to the operating pressure stability under different sample driving parameters and sample working condition characteristics, the sample working condition adaptation parameter set is marked; A machine learning-based working condition adaptation analyzer is constructed, and supervised training is performed using the sample driving parameter set, the sample working condition feature set, and the sample working condition adaptation parameter set, and the training is completed after convergence.
5. The intelligent control method for a multi-mode adaptive plunger pump drive system according to claim 1, characterized in that: Performing a wear analysis on the plunger pump according to the adjusted drive parameter and the changed operating condition characteristics to obtain a first wear parameter includes: Obtaining a plunger pump wear classifier, wherein the plunger pump wear classifier is trained using sample drive parameters, sample operating condition characteristics, and sample wear parameters in plunger pump wear test data, wherein the sample first wear parameter includes a wear rate; The adjusted driving parameters and the changed working condition characteristics are input into the wear classifier of the plunger pump, and the classification output is used to obtain the first wear parameter.
6. The intelligent control method for a multi-mode adaptive plunger pump drive system according to claim 1, characterized in that: Performing a swash plate angle influence analysis to obtain the influencing swash plate angle, performing a plunger pump wear analysis to obtain a second wear parameter, and combining the first wear parameter to calculate a working condition cost parameter, including: Inputting the real-time operating condition characteristics, real-time driving parameters, adjusted driving parameters, and changed operating condition characteristics into a swash plate angle impact analyzer, and outputting the impact swash plate angle, wherein the swash plate angle impact analyzer is trained using sample real-time operating condition characteristics, sample real-time driving parameters, sample adjusted driving parameters, sample changed operating condition characteristics, and sample swash plate angles; Classifying and obtaining a second wear parameter according to the influencing swash plate angle, wherein the influencing swash plate angle is input into a swash plate oscillation wear classification table for classification, wherein the swash plate oscillation wear classification table is constructed based on a mapping relationship between sample influencing swash plate angles and sample second wear parameters; Calculating a total wear parameter based on the first wear parameter and the second wear parameter; The ratio of the total wear parameter to the preset wear parameter is calculated to obtain the working condition cost parameter.
7. The intelligent control method for a multi-mode adaptive plunger pump drive system according to claim 1, characterized in that: According to the influencing swash plate angle, the working condition adaptation parameter is corrected, and in combination with the working condition cost parameter, the driving adaptability is calculated and obtained, and iterative optimization is performed to obtain the optimal driving parameter, and the plunger pump driving control is performed, including: Calculating the flow rate variation amplitude according to the influencing swash plate angle; Using the flow rate variation amplitude, correcting and compensating the operating condition adaptation parameter to obtain a corrected operating condition adaptation parameter; Calculating the driving fitness according to the modified working condition adaptation parameter and the working condition cost parameter; According to the drive adaptability, the drive parameters are iteratively optimized to obtain the optimal drive parameters and perform plunger pump drive control.
8. The intelligent control method for a multi-mode adaptive plunger pump drive system according to claim 7, characterized in that: According to the drive adaptability, iterative optimization of the drive parameters is performed to obtain the optimal drive parameters and perform plunger pump drive control, including: Continue to randomly adjust the driving parameters and calculate the driving fitness; The driving parameters are iteratively optimized. After reaching the optimization convergence condition, the driving parameters corresponding to the maximum driving fitness are retained as the optimal driving parameters for plunger pump drive control.
9. The intelligent control system of the multi-working-condition adaptive plunger pump drive system is characterized by: An intelligent control method for implementing the multi-condition adaptive plunger pump drive system according to any one of claims 1 to 8, the system comprising: The feature acquisition module is used to obtain the real-time working condition characteristics and the real-time driving parameters of the plunger pump drive system during the operation of the plunger pump, and to collect the changing working condition characteristics when the working condition changes; an adaptation parameter acquisition module, configured to randomly adjust the real-time driving parameters to obtain adjusted driving parameters, and to analyze and obtain working condition adaptation parameters based on the adjusted driving parameters and the characteristics of the changed working condition; a working condition cost calculation module, configured to perform a wear analysis on the plunger pump based on the adjusted drive parameter and the changed working condition characteristics to obtain a first wear parameter, perform a swash plate angle influence analysis to obtain an influence on the swash plate angle, perform a wear analysis on the plunger pump to obtain a second wear parameter, and calculate a working condition cost parameter based on the first wear parameter; The optimization control module is used to modify the working condition adaptation parameter according to the influencing swash plate angle, calculate the driving adaptability in combination with the working condition cost parameter, perform iterative optimization to obtain the optimal driving parameter, and perform plunger pump driving control.