Lubricating oil pump station optimization control method and system based on artificial intelligence

Through the optimization control method of lubricating oil pump station based on artificial intelligence, the finite element model is used to optimize the lubricating oil flow rate and oil temperature, the problem that traditional control methods cannot be accurately controlled is solved, and the efficiency and reliability of the oil pump are improved.

CN118757380BActive Publication Date: 2024-12-06JIANGSU JIANGHAI LUBRICANTS HYDRAULIC EQUIP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411240173.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-05
Publication Date
2024-12-06
Estimated Expiration
2044-09-05

AI Technical Summary

Technical Problem

Traditional oil pump station control methods cannot perform precise lubrication control based on the real-time friction pair status and service load, resulting in large friction losses, low oil pump efficiency and poor reliability.

Method used

Using the optimization control method of lubricating oil pump station based on artificial intelligence, the finite element model is constructed by collecting service modeling information of friction pairs, obtaining service load and flow test samples, conducting friction confrontation analysis, optimizing lubricating oil flow and oil temperature to achieve accurate control.

Benefits of technology

It realizes efficient and precise control of the lubricating oil pump station, reduces friction losses, and improves the efficiency and reliability of the oil pump.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118757380B_ABST
    Figure CN118757380B_ABST
Patent Text Reader

Abstract

The present application relates to the field of oil pump station control technology, and provides an optimization control method and system for lubricating oil pump stations based on artificial intelligence. The method includes: collecting friction pair service modeling information to construct a finite element model; obtaining the service load of the friction pair; adjusting the flow control valve to obtain a flow sample; combining the service load and the flow sample, and obtaining a countermeasure index through the model; optimizing the lubricating oil flow based on the index to obtain the flow control parameter; combining the service load and the flow parameter, and optimizing the oil temperature through the finite element model; controlling the lubricating oil pump flow through the flow control module, and the cooling device controls the oil inlet temperature according to the oil temperature. The present application solves the technical problem that the traditional oil pump station control method cannot perform precise lubrication control according to the real-time friction pair state and service load, resulting in large friction loss, low oil pump efficiency and poor reliability, and achieves the effect of accurately adjusting the lubricating oil flow and oil temperature, reducing friction loss, and improving the efficiency and reliability of the oil pump.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of industrial automation control technology, specifically to the field of oil pump station control technology, and in particular to an optimization control method and system for a lubricating oil pump station based on artificial intelligence. Background Art

[0002] With the rapid development of industrial production, oil pump stations play a key role in mechanical lubrication. However, traditional oil pump station control methods often fail to accurately control the state of the friction pair and the service load in real time, which leads to increased friction loss, reduced oil pump efficiency and decreased reliability. The limitations of this traditional control method are becoming increasingly prominent, especially in the context of expanding production scale and increasing process complexity. It is difficult to meet the needs of modern industrial production for efficiency, precision and safety. Summary of the invention

[0003] This application provides an artificial intelligence-based lubricating oil pump station optimization control method and system, aiming to solve the technical problem that traditional oil pump station control methods are unable to perform precise lubrication control according to the real-time friction pair state and service load, resulting in large friction losses, low oil pump efficiency and poor reliability.

[0004] In view of the above problems, the present application provides an optimization control method and system for a lubricating oil pump station based on artificial intelligence.

[0005] In a first aspect disclosed in the present application, an optimization control method for a lubricating oil pump station based on artificial intelligence is provided, the method comprising: collecting service modeling information of a first friction pair of a first friction pair connected to a first lubricating oil pump in a target lubricating oil pump station, and constructing a finite element model of the first friction pair with the service modeling information of the first friction pair; collecting a first service load of the first friction pair in a preset control time zone; adjusting a flow control valve through a flow control module of the first lubricating oil pump to obtain a plurality of flow test samples; combining the first service load and the plurality of flow test samples, performing friction antagonism analysis through the finite element model of the first friction pair to obtain a plurality of friction antagonism indicators, wherein the plurality of friction antagonism indicators represent the magnitude of the service lubrication effect of the plurality of flow test samples on the first friction pair; optimizing the lubricating oil flow based on the plurality of friction antagonism indicators to obtain a first flow control parameter; combining the first service load and the first flow control parameter, performing oil heat optimization through the finite element model of the first friction pair to obtain a first oil temperature; controlling the flow of the first lubricating oil pump according to the first flow control parameter through the flow control module, and controlling the oil inlet temperature of the first lubricating oil pump and the first friction pair according to the first oil temperature through a cooling device connected to the first lubricating oil pump.

[0006] Another aspect disclosed in the present application provides an artificial intelligence-based lubricating oil pump station optimization control system, the system comprising: a model building unit, the model building unit is used to collect the first friction pair service modeling information of the first friction pair connected to the first lubricating oil pump in the target lubricating oil pump station, and build a first friction pair finite element model with the first friction pair service modeling information; a load acquisition unit, the load acquisition unit is used to collect the first service load of the first friction pair under a preset control time zone; a control valve adjustment unit, the control valve adjustment unit is used to adjust the flow control valve through the flow control module of the first lubricating oil pump to obtain multiple groups of flow test samples; and a confrontation analysis unit, the confrontation analysis unit is used to combine the first service load and the multiple groups of flow test samples, and perform friction confrontation analysis through the first friction pair finite element model to obtain multiple A friction antagonism index, wherein the multiple friction antagonism indexes represent the magnitude of the service lubrication effect of the multiple groups of flow test samples on the first friction pair; a flow optimization unit, the flow optimization unit is used to optimize the lubricating oil flow based on the multiple friction antagonism indexes to obtain a first flow control parameter; a heat optimization unit, the heat optimization unit is used to combine the first service load and the first flow control parameter, perform oil heat optimization through the first friction pair finite element model, and obtain a first oil temperature; a flow temperature control unit, the flow temperature control unit is used to control the flow of the first lubricating oil pump according to the first flow control parameter through the flow control module, and control the oil inlet temperature of the first lubricating oil pump and the first friction pair according to the first oil temperature through a cooling device connected to the first lubricating oil pump.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The above-mentioned artificial intelligence-based optimization control method for lubricating oil pump station collects the service modeling information of the first friction pair connected to the first lubricating oil pump in the target lubricating oil pump station, and uses this information to construct a finite element model to simulate the service state of the friction pair. Subsequently, the service load of the first friction pair in the preset control period is recorded, which is an important parameter for evaluating the lubrication effect. After that, by adjusting the flow control valve of the lubricating oil pump, multiple groups of different flow test samples are obtained to observe the influence of these different flow rates on the lubrication effect of the friction pair. In order to evaluate the lubrication effect under different flow rates, the established finite element model is used to perform friction confrontation analysis and obtain multiple friction confrontation indicators. These indicators intuitively show the magnitude of the lubrication effect of different flow rates on the friction pair. Then, based on these friction confrontation indicators, the lubricating oil flow rate is optimized and calculated to determine the optimal flow control parameters. Combined with the service load and flow control parameters, the finite element model is used again to perform the optimization calculation of the oil heat to determine the optimal oil temperature. Finally, according to the calculated first flow control parameter, the flow control module controls the flow of the first lubricating oil pump. At the same time, the connected cooling device controls the oil inlet temperature of the lubricating oil pump and the friction pair according to the calculated first oil temperature. This method achieves efficient and precise control of the lubricating oil pump station through real-time monitoring and intelligent analysis, effectively reduces friction loss, and improves the efficiency and reliability of the oil pump.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] 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.

[0011] Figure 1 The figure is a flow chart of an optimization control method for a lubricating oil pump station based on artificial intelligence in one embodiment.

[0012] Figure 2 This is an architecture diagram of an artificial intelligence-based lubricating oil pump station optimization control system in one embodiment.

[0013] Explanation of the accompanying drawings: model building unit 1, load collection unit 2, control valve adjustment unit 3, confrontation analysis unit 4, flow optimization unit 5, heat optimization unit 6, flow temperature control unit 7. DETAILED DESCRIPTION

[0014] The embodiments of the present application provide an artificial intelligence-based lubricating oil pump station optimization control method and system to solve the technical problem that traditional oil pump station control methods are unable to perform precise lubrication control according to the real-time friction pair state and service load, resulting in large friction losses, low oil pump efficiency and poor reliability.

[0015] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0016] It should be noted that the terms "including" and "having" and any variations thereof 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 explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0017] Embodiment 1

[0018] like Figure 1 As shown, the present application provides an optimization control method for a lubricating oil pump station based on artificial intelligence, the method comprising:

[0019] The first friction pair service modeling information of the first friction pair connected to the first lubricating oil pump in the target lubricating oil pump station is collected, and a finite element model of the first friction pair is constructed based on the first friction pair service modeling information.

[0020] Lubrication means that the oil pump extracts the lubricating oil from the oil tank, filters it through the oil filter, and then transports it to each lubrication point through the pipeline. The lubricating oil lubricates the friction pair at the lubrication point and then flows back to the oil tank, and the cycle repeats.

[0021] In an embodiment of the present application, the system terminal obtains information about a lubricating oil pump randomly selected as the first lubricating oil pump in the target lubricating oil pump station, and collects service modeling information of the first friction pair connected to the first lubricating oil pump. Among them, the first friction pair is a system composed of two components that are directly connected to the first lubricating oil pump in the target lubricating oil pump station and are in contact with each other and produce relative friction motion. In this system, friction and wear will be generated due to contact and relative motion between components, such as bearings, gears, etc. The service modeling information of the first friction pair describes in detail the various parameters and characteristics of the friction pair under normal service conditions, including geometric dimensions, material properties, service environment, expected load distribution, etc. Subsequently, based on the collected service modeling information, the system terminal uses a finite element modeling component to define a geometric model of the friction pair. This model can accurately reflect the actual shape and size of the friction pair. Then, according to the material used by the friction pair, its material properties in the finite element model are set. These properties include elastic modulus, Poisson's ratio, yield strength, thermal conductivity, etc. of the material. Afterwards, the defined geometric model is meshed, that is, it is decomposed into a series of small, discrete units, such as triangles or quadrilaterals. These units will be used for subsequent numerical calculations. The fineness of the mesh will affect the accuracy and computational efficiency of the model. Then, according to the actual situation of the friction pair during service, the boundary conditions and loads are defined in the finite element model. This includes fixed constraints, sliding constraints, pressure loads, friction, etc. Then, set the relevant parameters of the solver of the finite element modeling component, such as solution accuracy, number of iterations, convergence criteria, etc. These parameters will affect the stability of the solution process and the accuracy of the results. Then run the set solver to perform numerical calculations on the divided mesh and the defined boundary conditions and loads. Finally, check the solution results, including stress distribution, deformation, temperature distribution, etc. Optimize and adjust the model according to actual needs until satisfactory results are obtained. After the optimization and adjustment is completed, the system terminal outputs the adjusted finite element model to obtain the first friction pair finite element model. This model is used for subsequent friction confrontation analysis and oil heat optimization. In this way, the service status of the friction pair can be better understood and support can be provided for subsequent optimization control.

[0022] The first service load of the first friction pair in a preset control time zone is collected.

[0023] In one embodiment, in order to more accurately control the supply of lubricating oil and the lubrication effect of the friction pair, the system terminal pre-sets a control time zone, and performs real-time monitoring and data collection on the load condition of the first friction pair within the time zone. This first service load refers to the actual service load borne by the first friction pair within the preset control time zone. Specifically, this load includes various forces, torques, vibrations, etc., which reflect the motion state and force conditions of the friction pair in actual service. By collecting and analyzing these load data, the service state of the friction pair can be more accurately understood, and then the supply and distribution of lubricating oil can be optimized to ensure that the friction pair is fully lubricated, reduce wear and friction losses, and improve the operating efficiency and reliability of the oil pump.

[0024] The flow control valve is adjusted by the flow control module of the first lubricating oil pump to obtain multiple groups of flow test samples.

[0025] In one embodiment, in order to achieve more precise lubrication control, the system terminal operates the flow control valve through the flow control module of the first lubricating oil pump. The main purpose of this operation is to adjust the flow of lubricating oil so as to provide a suitable lubrication effect for the first friction pair under different service conditions. In order to find the optimal lubricating oil flow, the system terminal adjusts the flow control valve multiple times to obtain multiple sets of different flow test samples. These test samples represent the lubrication conditions under different flow rates, and they will be used for subsequent analysis and comparison to determine which flow setting can bring the best lubrication effect and friction pair performance.

[0026] In combination with the first service load and the multiple groups of flow test samples, friction antagonism analysis is performed through the finite element model of the first friction pair to obtain multiple friction antagonism indicators, wherein the multiple friction antagonism indicators represent the magnitude of the service lubrication effect of the multiple groups of flow test samples on the first friction pair.

[0027] In one embodiment, in order to optimize the lubrication effect of the first friction pair, the system terminal combines the service load of the first friction pair and multiple groups of flow test samples, and uses the constructed finite element model of the first friction pair to perform friction confrontation analysis. The core of this analysis process is to perform lubrication simulation on multiple groups of flow test samples, and then perform confrontation analysis based on the simulation results and the benchmark service friction force to generate multiple friction confrontation indicators. This confrontation analysis process evaluates the lubrication effect of different flow test samples on the first friction pair. Since the friction pair will generate friction during the service process, the role of the lubricating oil is to reduce this friction. Therefore, the generated friction confrontation index is the key parameter for evaluating the ability of the lubricating oil to reduce friction under different flow rates. Through this friction confrontation index, it can be ensured that the first friction pair can obtain sufficient lubrication during the service process, thereby reducing wear and improving the operating efficiency and reliability of the oil pump.

[0028] Furthermore, the present application provides a method of combining the first service load and the plurality of flow test samples, performing friction confrontation analysis through the first friction pair finite element model, and obtaining a plurality of friction confrontation indicators, including:

[0029] Obtain a benchmark service friction force, wherein the benchmark service friction force is the service friction force of the first friction pair when there is no lubrication under the first service load; perform lubrication simulation on the multiple groups of flow test samples through the finite element model of the first friction pair to generate multiple groups of friction force test data; perform friction resistance analysis on the multiple groups of friction force test data based on the benchmark service friction force to generate the multiple friction resistance indicators.

[0030] Preferably, when evaluating the lubrication effect of the first friction pair, the system terminal first determines a reference point, namely, a reference service friction force, which refers to the friction force of the first friction pair when there is no lubrication under the service load. This reference value represents the friction performance of the friction pair under the condition of no lubrication. Subsequently, the system terminal sets the initial conditions of the simulation, such as the initial temperature, the initial stress distribution, etc. Then, multiple groups of flow test samples are loaded into the finite element model as input parameters. These parameters will be used to simulate the flow and distribution of lubricating oil under different flow rates. After that, the flow and distribution of lubricating oil are simulated in the finite element model. This involves solving fluid mechanics equations to simulate the flow characteristics of lubricating oil, such as the Navier-Stokes equations. During the simulation, the system terminal calculates the friction between the contact surfaces of the friction pair. This involves solving contact mechanics equations to simulate the interaction between the contact surfaces and the generation of friction, such as the normal contact force equation. Then, the system terminal records the friction data calculated during the simulation to form multiple groups of friction test data. Each group of data corresponds to a flow test sample. Finally, based on the obtained baseline service friction force, these friction test data are subjected to friction confrontation analysis. This analysis process is to compare the friction test data at different flow rates with the baseline service friction force, so as to evaluate the lubrication effect of the lubricant, that is, the ability of the lubrication effect to reduce friction. Then calculate the difference between the baseline service friction force and the friction test data as the friction confrontation index of a flow test sample. Through this process, multiple friction confrontation indexes can be generated, which directly reflect the service lubrication effect of different flow test samples on the first friction pair.

[0031] Furthermore, the present application provides a method for obtaining a baseline service friction force, the method further comprising:

[0032] Taking the first friction pair model, the first service load and the absence of lubrication as constraint conditions, a plurality of service friction force record values ​​are collected; the plurality of service friction force record values ​​are clustered according to a preset friction force deviation threshold to generate a plurality of service friction force record value sets.

[0033] Optionally, in order to obtain the baseline service friction and evaluate the friction performance of the first friction pair under different conditions, the system terminal firstly performs multiple friction tests with the first friction pair model, the first service load and the absence of lubrication as fixed constraints. In these tests, the system terminal records multiple service friction values, which reflect the friction performance of the friction pair under given conditions. In order to better analyze these data, the system terminal adopts a clustering method. Specifically, the system terminal first presets a friction deviation threshold. This threshold is determined based on actual engineering requirements and data distribution, and represents the lower limit of the difference between two friction record values. Subsequently, the system terminal initializes clustering, regards each friction record value as a separate cluster, and constructs a cluster list. Then two clusters are selected and the distance between them is calculated. This is done by calculating the average distance of all point pairs in the two clusters using the average link method. If the calculated distance is less than or equal to the preset threshold, the two clusters are merged into a new cluster. After that, the merged new cluster is added to the cluster list, and the original two clusters are deleted from the list. Repeat the above process until the distance between all clusters is greater than the preset friction deviation threshold. After the hierarchical clustering algorithm is completed, the system terminal obtains a cluster tree. In this cluster tree, the system terminal determines a suitable cutting point based on the distance between clusters and business needs, and divides the cluster tree according to this cutting point to generate multiple service friction record value sets. In this way, the system terminal can more clearly understand how the friction performance of the first friction pair is distributed under different test conditions, and which conditions may cause significant changes in friction. This is of great significance for subsequent performance optimization.

[0034] Calculate the ratio of the number of clusters of the multiple service friction record value sets to the total number of the multiple service friction record value sets to obtain multiple cluster concentration coefficients; delete the service friction record value sets whose cluster concentration coefficients are less than the predetermined clustering coefficients to obtain the service friction concentration value set; perform mean calculation on the friction concentration value set to generate the benchmark service friction.

[0035] Optionally, after obtaining multiple service friction record value sets, the system terminal counts the number of clusters in each service friction record value set, and then calculates the ratio of the number of clusters in each service friction record value set to the total number of service friction record values ​​to obtain a cluster concentration coefficient. The cluster concentration coefficient reflects the degree of concentration of data distribution, that is, the ratio of the number of clusters into which the data is divided to the total amount of data. Subsequently, the calculated cluster concentration coefficient is compared with a predetermined cluster coefficient. This predetermined cluster coefficient is set according to business requirements and data analysis needs. If the cluster concentration coefficient is less than this threshold, the system terminal deletes the data in this cluster from the service friction record value set. Repeat this process until multiple service friction record value sets are compared and a service friction concentration value set is obtained. Afterwards, the system terminal calculates the mean of the friction record values ​​in the service friction concentration value set, that is, all the friction record values ​​in the set are added and divided by the number of data in the set to obtain an average value. This average value is the baseline service friction, which is a statistically significant value that can reflect the concentration trend of the overall data set.

[0036] The lubricating oil flow rate is optimized based on the multiple friction resistance indicators to obtain a first flow control parameter.

[0037] In one embodiment, the system terminal evaluates the obtained friction resistance index, and this evaluation process is performed by calculating and comparing the index deviations of adjacent indicators. Subsequently, the system terminal performs flow optimization based on the evaluation results. This flow optimization is based on the finite element model of the first friction pair. The entire optimization process is to find a flow value so that each friction resistance index reaches a relatively balanced and optimal state. Specifically, the finite element model of the first friction pair generates an oil dripping risk index by identifying the lubrication viscosity of the evaluation results. The system terminal then generates a first flow control parameter by comparing the oil dripping risk index with the preset risk index. This parameter is a specific value of the lubricating oil flow rate, which can meet the lubrication requirements of the first friction pair during normal service and minimize the adverse effects of friction on the performance of the oil pump.

[0038] Furthermore, the present application provides a method for optimizing the lubricating oil flow rate based on the multiple friction resistance indicators to obtain a first flow control parameter, and the method further includes:

[0039] The multiple friction confrontation indicators are serialized from small to large to obtain a friction confrontation indicator sequence; based on the friction confrontation indicator sequence, indicator deviations of adjacent confrontation indicators are calculated in sequence to generate a first adjacent indicator deviation, a second adjacent indicator deviation, and finally an N-1th adjacent indicator deviation, wherein N is the number of indicators in the friction confrontation indicator sequence.

[0040] Preferably, when processing multiple friction confrontation indicators, in order to better understand the relative relationship and difference between them, the system terminal performs serialization processing on these indicators, that is, arranges them in ascending order according to their size, and obtains the friction confrontation indicator sequence. This serialization can help the system terminal intuitively understand which indicators are smaller, which indicators are larger, and the relative positions between them. After obtaining the friction confrontation indicator sequence, the system terminal calculates the deviation between adjacent indicators. The indicator deviation reflects the degree of difference between two adjacent indicators. In this process, the deviation value of each pair of adjacent indicators in the sequence is calculated in turn, that is, the difference between adjacent indicators is calculated, and N-1 adjacent indicator deviations are obtained. Wherein, N is the number of indicators in the friction confrontation indicator sequence. For example, the deviation between the first indicator and the second indicator is the first adjacent indicator deviation, the deviation between the second indicator and the third indicator is the second adjacent indicator deviation, and so on, until the deviation between the second to last indicator and the last indicator, that is, the N-1th adjacent indicator deviation. Through the above steps, it is helpful for the system terminal to have a deeper understanding of the relative relationship and difference between the friction confrontation indicators, and provide a basis for subsequent analysis and optimization.

[0041] Compare the first adjacent indicator deviation, the second adjacent indicator deviation, and the N-1th adjacent indicator deviation with a predetermined indicator deviation threshold. When any adjacent indicator deviation and the adjacent indicator deviation thereafter are less than the predetermined indicator deviation threshold, obtain a target friction confrontation indicator set; obtain a flow test sample set corresponding to the target friction confrontation indicator set, perform flow optimization based on the flow test sample set, and generate the first flow control parameter.

[0042] Preferably, when processing multiple friction resistance indicators to optimize the lubricating oil flow, the system terminal compares the obtained adjacent indicator deviations with the predetermined indicator deviation threshold. During the comparison process, if it is found that any adjacent indicator deviation and all the adjacent indicator deviations thereafter are less than the predetermined indicator deviation threshold, the system terminal sorts out the friction resistance indicators corresponding to these adjacent indicator deviations and constructs a target friction resistance indicator set. The friction resistance indicators in this set reflect that when the lubricating oil flow increases to a certain extent, the effect of reducing friction becomes less significant, that is, it is in a relatively balanced state. In this state, no matter how much the flow is increased, it cannot bring about a significant reduction in friction, but will lead to waste of lubricating oil, such as dripping and other problems. Subsequently, the system terminal obtains the flow test sample set corresponding to this target friction resistance indicator set. Based on this flow test sample set, the system terminal performs a flow optimization process. The goal of this optimization process is to find an optimal lubricating oil flow value, which can meet the demand for reducing friction while avoiding excessive increase in flow and waste of lubricating oil. Finally, this optimization process will generate a first flow control parameter as the control basis of the lubricating oil flow.

[0043] Furthermore, the present application provides a method for performing flow optimization based on the flow test sample set, and the method further includes:

[0044] Extract the minimum flow test sample from the flow test sample set, use the first friction pair finite element model to perform lubrication viscosity identification on the minimum flow test sample, and obtain a first oil dripping risk index; if the first oil dripping risk index meets the preset risk index, obtain the first adjacent flow test sample in the flow test sample set that is greater than the minimum flow test sample, and obtain the second oil dripping risk index; if the second oil dripping risk index does not meet the preset risk index, generate the first flow control parameter with the minimum flow test sample.

[0045] Optionally, when processing the flow test sample to optimize the lubricating oil flow, the system terminal extracts the minimum flow test sample from the flow test sample set. This is because from the perspective of lubrication effect, it is hoped to find a flow value that can meet the lubrication demand and does not cause the lubricating oil to drip. Specifically, the system terminal extracts the minimum flow test sample from the flow test sample set and sets the parameters corresponding to the minimum flow test sample in the first friction pair finite element model. This includes physical properties such as the flow rate, viscosity, and temperature of the lubricating oil. Subsequently, according to the requirements of the minimum flow test sample, the corresponding boundary conditions are loaded in the finite element model. These boundary conditions include inlet flow, outlet pressure, wall conditions, etc., which are used to simulate the flow and distribution of the lubricating oil in the friction pair. Afterwards, the first friction pair finite element model with set parameters and boundary conditions is solved to simulate the flow and distribution process of the lubricating oil in the friction pair. This process calculates key information such as the pressure distribution, velocity distribution, and viscosity distribution of the oil on the friction pair surface. Then, information related to lubrication viscosity is extracted from the results of the finite element analysis. This information includes the viscosity distribution and viscous shear stress of the oil on the friction pair surface, which can reflect the lubrication effect and stability of the lubricant. Based on the extracted lubrication viscosity information, the flow state of the oil at the edge of the friction pair is evaluated to determine whether there is a possibility of oil accumulation or dripping. This involves a comprehensive analysis of factors such as the velocity distribution and pressure gradient of the oil at the edge of the friction pair. Finally, the first friction pair finite element model converts the evaluation results into a specific oil dripping risk index, namely the first oil dripping risk index. This index is used to quantify the risk level of oil dripping.

[0046] After obtaining the first oil dripping risk index, the system terminal compares the first oil dripping risk index with the preset risk index. If the first oil dripping risk index meets the preset risk index, that is, the dripping risk is within an acceptable range, then the system terminal determines that the minimum flow test sample is a suitable flow control parameter. Subsequently, the system terminal extracts the first flow value in the flow test sample set that is greater than the minimum flow test sample, that is, the first adjacent flow test sample, and repeats the above steps for this sample to generate a second oil dripping risk index. If the second oil dripping risk index does not meet the preset risk index, it means that the flow test sample represented by this oil dripping risk index will have the risk of oil dripping. At this time, the system terminal will use the minimum flow test sample as the first flow control parameter, that is, the flow test sample represented by the previous oil dripping risk index as the first flow control parameter. If the second oil drop risk index also meets the preset risk index, the system terminal will extract the flow test sample adjacent to the first adjacent flow test sample, and repeat the above comparison process until a flow test sample that does not meet the preset risk index is found, and output the previous flow test sample of the flow test sample that does not meet the preset risk index as the first flow control parameter. This is because when ensuring that the drop risk meets the preset risk index, the larger the flow rate, the better the lubrication effect.

[0047] In combination with the first service load and the first flow control parameter, the first friction pair finite element model is used to perform oil heat optimization to obtain a first oil temperature.

[0048] In one embodiment, the system terminal uses the established finite element model of the first friction pair to simulate and analyze the thermal behavior of the oil temperature sample in the friction pair under given load and flow control parameters. Subsequently, the system terminal optimizes the simulation results by the preset temperature, that is, finds the oil temperature sample that meets the preset temperature. After that, the system terminal obtains the first oil temperature through the sample optimized by the oil heat, which is the stable temperature that the oil will reach under given load and flow control parameters. This temperature is crucial to ensure the performance and life of the oil pump.

[0049] Further, the present application provides combining the first service load and the first flow control parameter, performing oil heat optimization through the first friction pair finite element model to obtain a first oil temperature, and the method also includes:

[0050] Acquire multiple groups of oil temperature samples; perform service simulation tests on the multiple groups of oil temperature samples according to the first service load and the first flow control parameter through the first friction pair finite element model to generate multiple groups of service simulation temperatures; based on the multiple groups of service simulation temperatures, acquire oil temperature samples whose service simulation temperatures meet a preset temperature to generate the first oil temperature.

[0051] Preferably, when optimizing the oil temperature, the system terminal first collects multiple groups of oil temperature samples. These samples come from different working environments and operating conditions. Subsequently, the system terminal loads the established first friction pair finite element model and sets the first service load and the first flow control parameter as the input conditions of the simulation. In the finite element model, the initial oil temperature is set according to each group of oil temperature samples. After that, the system terminal runs the simulation according to the set parameters and conditions. During the simulation, the first friction pair finite element model calculates the flow, heat transfer, temperature distribution, etc. of the oil in the friction pair, and simulates the influence of these conditions on the oil temperature according to the first service load and the first flow control parameter. After the simulation is completed, the system terminal extracts the key temperature data, namely the service simulation temperature, from the simulation results. This service simulation temperature is the temperature that the oil temperature sample may reach under a given service load and flow control parameter, including the temperature distribution on the friction pair surface, the average temperature of the oil, the maximum temperature, etc. Then, the system terminal performs the same operation on the remaining multiple groups of oil temperature samples to generate multiple groups of one-to-one corresponding service simulation temperatures, which represent the stable temperatures that may be reached under different oil temperature samples. Furthermore, the system terminal evaluates the generated multiple sets of service simulation temperatures to determine whether these service simulation temperatures meet the preset temperature requirements. This preset temperature is set based on factors such as material properties and safety requirements. Subsequently, the system terminal extracts the service simulation temperatures that meet the preset temperature from the multiple sets of service simulation temperatures, and obtains the corresponding oil temperature samples based on these service simulation temperatures. After that, the system terminal selects a set of oil temperature samples that are closest to the preset temperature from the screened oil temperature samples as the first oil temperature. This ensures that the oil pump temperature is as close to the optimal state as possible.

[0052] The flow control module controls the flow of the first lubricating oil pump according to the first flow control parameter, and the cooling device connected to the first lubricating oil pump controls the oil inlet temperature of the first lubricating oil pump and the first friction pair according to the first oil temperature.

[0053] In one embodiment, the system terminal transmits the obtained first flow control parameter and the first oil temperature to the flow control module and the cooling device respectively. The flow control module adjusts the flow of the first lubricating oil pump according to the transmitted first flow control parameter to ensure that the lubricating oil is supplied to the first friction pair according to the flow obtained by analysis, so as to achieve the best lubrication effect on the friction pair. At the same time, the cooling device will control the temperature of the oil entering the first lubricating oil pump and the first friction pair according to the first oil temperature. This means that the cooling device will adjust its working state, such as adjusting the flow and temperature of the cooling water to ensure that the oil reaches the first oil temperature before entering the friction pair. In this way, it can be ensured that the best lubrication conditions are formed at the friction pair, and neither poor lubrication will be caused by insufficient lubricating oil flow, nor will the performance and life of the friction pair be affected by excessive oil temperature.

[0054] Furthermore, the present application provides flow monitoring for an oil delivery pipeline, and the method further includes:

[0055] Obtain an oil delivery pipeline between the first lubricating oil pump and the first friction pair, perform flow monitoring at the starting point and the end point of the oil delivery pipeline, and obtain a first flow loss; determine whether the first flow loss is greater than a preset loss threshold, and if not, perform feedback optimization on the first flow control parameter based on the first flow loss, and if so, generate pipeline abnormality information; wherein the preset loss threshold is obtained based on analysis of the pipeline material, pipeline length, and pipeline inflection point of the oil delivery pipeline.

[0056] Preferably, the system terminal first determines the oil delivery pipeline between the first lubricating oil pump and the first friction pair, and performs flow monitoring at the starting point and the end point of the pipeline. The purpose of this is to understand the flow loss of the oil during the delivery process, which is the first flow loss. Specifically, the system terminal measures and records the flow data of the oil in real time through the flow monitoring points set at the starting point and the end point of the oil delivery pipeline. Subsequently, according to the flow data at the starting point and the end point, the flow loss of the oil during the delivery process is obtained by performing a difference calculation between the flow data at the starting point and the end point. The size of the difference represents the amount of loss of the oil during the delivery process, that is, the first flow loss. Afterwards, the system terminal determines whether the first flow loss exceeds a preset loss threshold. The preset loss threshold is set based on parameters such as the pipeline material, length and inflection point of the oil delivery pipeline. This is because different pipeline materials and structures will have different flow loss characteristics. If the first flow loss does not exceed the preset loss threshold, it means that there is no abnormality in the oil delivery pipeline, but it is just a normal flow loss. At this time, the system terminal performs feedback optimization on the first flow control parameter based on this flow loss, and adjusts the flow output of the lubricating oil pump to ensure that the flow loss can be reduced as much as possible during the transportation process while ensuring the lubrication effect. For example, adjust the speed, output pressure and other parameters of the lubricating oil pump. However, if the first flow loss exceeds the preset loss threshold, the system terminal determines that there is an abnormality in the current oil delivery pipeline, such as pipeline leakage, blockage, etc. In this case, the system terminal will generate pipeline abnormality information so that maintenance personnel can check and repair in time to ensure the normal lubrication of the oil pump.

[0057] In summary, the embodiments of the present application have at least the following technical effects:

[0058] The embodiment of the present application collects the service modeling information of the first friction pair connected to the first lubricating oil pump in the target lubricating oil pump station, and constructs the finite element model of the first friction pair accordingly. Subsequently, the service load of the first friction pair under the preset control time zone is collected, and multiple groups of flow test samples are obtained by adjusting the flow control valve. In combination with the flow test sample and the service load, the first friction pair finite element model is used to perform friction antagonism analysis, and multiple friction antagonism indicators reflecting the magnitude of the lubrication effect are obtained. Based on these friction antagonism indicators, the lubricating oil flow is optimized and the first flow control parameter is determined. Afterwards, in combination with the first service load and the first flow control parameter, the oil heat is optimized through the first friction pair finite element model to determine the appropriate oil temperature, that is, the first oil temperature. In the control process, the flow control module controls the flow of the first lubricating oil pump according to the first flow control parameter, and the cooling device connected to the first lubricating oil pump controls the oil inlet temperature of the lubricating oil pump and the friction pair according to the first oil temperature. In addition, in order to ensure the normal operation of the oil delivery pipeline, the flow monitoring is performed at the starting point and the end point of the oil delivery pipeline to obtain the first flow loss, and it is judged whether it exceeds the preset loss threshold. If it does not exceed, the first flow control parameter is optimized by feedback; if it exceeds, pipeline abnormality information is generated for further processing. These technical effects jointly solve the technical problem that the traditional oil pump station control method cannot perform accurate lubrication control according to the real-time friction pair state and service load, resulting in large friction loss, low oil pump efficiency and poor reliability, and achieve the effect of accurately adjusting the lubricating oil flow and oil temperature, reducing friction loss, and improving the efficiency and reliability of the oil pump.

[0059] Embodiment 2

[0060] Based on the same inventive concept as the lubricating oil pump station optimization control method based on artificial intelligence in the aforementioned embodiment, Figure 2 As shown, the present application provides an optimization control system for a lubricating oil pump station based on artificial intelligence, the system comprising:

[0061] Model building unit 1: the model building unit 1 is used to collect the first friction pair service modeling information of the first friction pair connected to the first lubricating oil pump in the target lubricating oil pump station, and build a finite element model of the first friction pair based on the first friction pair service modeling information;

[0062] Load collection unit 2: the load collection unit 2 is used to collect the first service load of the first friction pair in a preset control time zone;

[0063] Control valve regulating unit 3: the control valve regulating unit 3 is used to regulate the flow control valve through the flow control module of the first lubricating oil pump to obtain multiple groups of flow test samples;

[0064] The confrontation analysis unit 4 is used to combine the first service load and the multiple groups of flow test samples, perform friction confrontation analysis through the first friction pair finite element model, and obtain multiple friction confrontation indicators, wherein the multiple friction confrontation indicators represent the magnitude of the service lubrication effect of the multiple groups of flow test samples on the first friction pair;

[0065] Flow optimization unit 5: the flow optimization unit 5 is used to optimize the lubricating oil flow based on the multiple friction resistance indicators to obtain a first flow control parameter;

[0066] Heat optimization unit 6: the heat optimization unit 6 is used to combine the first service load and the first flow control parameter, perform oil heat optimization through the first friction pair finite element model, and obtain a first oil temperature;

[0067] Flow rate and temperature control unit 7: The flow rate and temperature control unit 7 is used to control the flow rate of the first lubricating oil pump according to the first flow rate control parameter through the flow control module, and to control the oil inlet temperature of the first lubricating oil pump and the first friction pair according to the first oil temperature through a cooling device connected to the first lubricating oil pump.

[0068] Furthermore, the confrontation analysis unit 4 is also used to perform the following method:

[0069] Acquire a reference service friction force, wherein the reference service friction force is a service friction force of the first friction pair without lubrication under the first service load;

[0070] Performing lubrication simulation on the plurality of groups of flow test samples through the first friction pair finite element model to generate a plurality of groups of friction force test data;

[0071] Friction resistance analysis is performed on the multiple groups of friction force test data based on the benchmark service friction force to generate the multiple friction resistance indicators.

[0072] Furthermore, the confrontation analysis unit 4 is also used to perform the following method:

[0073] Taking the first friction pair model, the first service load and no lubrication effect as constraint conditions, collecting a plurality of service friction force record values;

[0074] Clustering the plurality of service friction force record values ​​according to a preset friction force deviation threshold value to generate a plurality of service friction force record value sets;

[0075] Calculating a ratio of the number of clusters of the plurality of service friction force record value sets to the total number of the plurality of service friction force record values ​​to obtain a plurality of cluster concentration coefficients;

[0076] The service friction force record value set whose cluster concentration coefficient is less than the predetermined clustering coefficient is deleted to obtain the service friction force concentration value set;

[0077] The mean value of the concentrated friction force value set is calculated to generate the reference service friction force.

[0078] Furthermore, the traffic optimization unit 5 is also used to perform the following method:

[0079] Performing serial processing on the multiple friction confrontation indicators from small to large to obtain a friction confrontation indicator sequence;

[0080] Based on the friction confrontation indicator sequence, sequentially calculating indicator deviations of adjacent confrontation indicators to generate a first adjacent indicator deviation, a second adjacent indicator deviation, and finally an N-1th adjacent indicator deviation, wherein N is the number of indicators in the friction confrontation indicator sequence;

[0081] Comparing the first adjacent indicator deviation, the second adjacent indicator deviation, and up to the N-1th adjacent indicator deviation with a predetermined indicator deviation threshold, and when any adjacent indicator deviation and the adjacent indicator deviations thereafter are all less than the predetermined indicator deviation threshold, acquiring a target friction confrontation indicator set;

[0082] A flow test sample set corresponding to the target friction countermeasure index set is obtained, flow optimization is performed based on the flow test sample set, and the first flow control parameter is generated.

[0083] Furthermore, the traffic optimization unit 5 is also used to perform the following method:

[0084] Extracting a minimum flow test sample from the flow test sample set, and using the first friction pair finite element model to perform lubrication viscosity identification on the minimum flow test sample to obtain a first oil dripping risk index;

[0085] If the first oil drop risk index meets the preset risk index, obtaining a first adjacent flow test sample in the flow test sample set that is greater than the minimum flow test sample, and obtaining a second oil drop risk index;

[0086] If the second oil dripping risk index does not meet the preset risk index, the first flow control parameter is generated using the minimum flow test sample.

[0087] Furthermore, the heat optimization unit 6 is also used to perform the following method:

[0088] Obtain multiple sets of oil temperature samples;

[0089] Performing a service simulation test on the plurality of groups of oil temperature samples according to the first service load and the first flow control parameter through the first friction pair finite element model to generate a plurality of groups of service simulation temperatures;

[0090] Based on the multiple groups of service simulation temperatures, oil temperature samples whose service simulation temperatures meet a preset temperature are obtained to generate the first oil temperature.

[0091] Furthermore, the flow and temperature control unit 7 is also used to perform the following method:

[0092] Acquire an oil delivery pipeline between the first lubricating oil pump and the first friction pair, perform flow monitoring at a starting point and an end point of the oil delivery pipeline, and obtain a first flow loss;

[0093] determining whether the first flow loss is greater than a preset loss threshold, and if not, performing feedback optimization on the first flow control parameter based on the first flow loss, and if so, generating pipeline abnormality information;

[0094] The preset loss threshold is obtained based on the pipeline material, pipeline length and pipeline inflection point analysis of the oil delivery pipeline.

[0095] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0096] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0097] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. Lubricating oil pump station optimization control method based on artificial intelligence, It is characterized in that The method comprises: Collecting first friction pair service modeling information of a first friction pair connected to a first lubricating oil pump in a target lubricating oil pump station, and constructing a finite element model of the first friction pair based on the first friction pair service modeling information; collecting a first service load of the first friction pair in a preset control time zone; By adjusting the flow control valve through the flow control module of the first lubricating oil pump, a plurality of groups of flow test samples are obtained; In combination with the first service load and the plurality of flow test samples, a friction confrontation analysis is performed through the finite element model of the first friction pair to obtain a plurality of friction confrontation indices, wherein the plurality of friction confrontation indices represent the magnitude of the service lubrication effect of the plurality of flow test samples on the first friction pair; Optimize the lubricating oil flow rate based on the multiple friction resistance indicators to obtain a first flow control parameter; In combination with the first service load and the first flow control parameter, the first friction pair finite element model is used to perform oil heat optimization to obtain a first oil temperature; Controlling the flow rate of the first lubricating oil pump according to the first flow rate control parameter by the flow control module, and controlling the oil inlet temperature of the first lubricating oil pump and the first friction pair according to the first oil temperature by a cooling device connected to the first lubricating oil pump; In combination with the first service load and the plurality of flow test samples, a friction confrontation analysis is performed through the first friction pair finite element model to obtain a plurality of friction confrontation indicators, including: Acquire a reference service friction force, wherein the reference service friction force is a service friction force of the first friction pair without lubrication under the first service load; Performing lubrication simulation on the plurality of groups of flow test samples through the first friction pair finite element model to generate a plurality of groups of friction force test data; Performing friction confrontation analysis on the plurality of groups of friction force test data based on the benchmark service friction force to generate the plurality of friction confrontation indicators; Obtain baseline service friction, including: Taking the first friction pair model, the first service load and no lubrication effect as constraint conditions, collecting a plurality of service friction force record values; Clustering the plurality of service friction force record values ​​according to a preset friction force deviation threshold value to generate a plurality of service friction force record value sets; Calculating a ratio of the number of clusters of the plurality of service friction force record value sets to the total number of the plurality of service friction force record values ​​to obtain a plurality of cluster concentration coefficients; The service friction force record value set whose cluster concentration coefficient is less than the predetermined clustering coefficient is deleted to obtain the service friction force concentration value set; Calculating the mean of the concentrated friction force value set to generate the reference service friction force; Optimizing the lubricating oil flow rate based on the multiple friction resistance indicators to obtain a first flow control parameter includes: Performing serial processing on the multiple friction confrontation indicators from small to large to obtain a friction confrontation indicator sequence; Based on the friction confrontation indicator sequence, sequentially calculating indicator deviations of adjacent confrontation indicators to generate a first adjacent indicator deviation, a second adjacent indicator deviation, and finally an N-1th adjacent indicator deviation, wherein N is the number of indicators in the friction confrontation indicator sequence; Comparing the first adjacent indicator deviation, the second adjacent indicator deviation, and up to the N-1th adjacent indicator deviation with a predetermined indicator deviation threshold, and when any adjacent indicator deviation and the adjacent indicator deviations thereafter are all less than the predetermined indicator deviation threshold, acquiring a target friction confrontation indicator set; A flow test sample set corresponding to the target friction countermeasure index set is obtained, flow optimization is performed based on the flow test sample set, and the first flow control parameter is generated.

2. The method according to claim 1, It is characterized in that Performing flow optimization based on the flow test sample set includes: Extracting a minimum flow test sample from the flow test sample set, and using the first friction pair finite element model to perform lubrication viscosity identification on the minimum flow test sample to obtain a first oil dripping risk index; If the first oil drop risk index meets the preset risk index, obtaining a first adjacent flow test sample in the flow test sample set that is greater than the minimum flow test sample, and obtaining a second oil drop risk index; If the second oil dripping risk index does not meet the preset risk index, the first flow control parameter is generated using the minimum flow test sample.

3. The method according to claim 1, It is characterized in that In combination with the first service load and the first flow control parameter, the first friction pair finite element model is used to perform oil heat optimization to obtain a first oil temperature, including: Obtain multiple sets of oil temperature samples; Performing a service simulation test on the plurality of groups of oil temperature samples according to the first service load and the first flow control parameter through the first friction pair finite element model to generate a plurality of groups of service simulation temperatures; Based on the multiple groups of service simulation temperatures, oil temperature samples whose service simulation temperatures meet preset temperatures are obtained to generate the first oil temperature.

4. The method according to claim 1, It is characterized in that The method further comprises: Acquire an oil delivery pipeline between the first lubricating oil pump and the first friction pair, perform flow monitoring at a starting point and an end point of the oil delivery pipeline, and obtain a first flow loss; determining whether the first flow loss is greater than a preset loss threshold, and if not, performing feedback optimization on the first flow control parameter based on the first flow loss, and if so, generating pipeline abnormality information; The preset loss threshold is obtained based on the pipeline material, pipeline length and pipeline inflection point analysis of the oil delivery pipeline.

5. Lubricating oil pump station optimization control system based on artificial intelligence, It is characterized in that The steps for implementing the artificial intelligence-based lubricating oil pump station optimization control method according to any one of claims 1 to 4 include: A model building unit: collecting first friction pair service modeling information of a first friction pair connected to a first lubricating oil pump in a target lubricating oil pump station, and building a finite element model of the first friction pair based on the first friction pair service modeling information; A load collection unit is used to collect the first service load of the first friction pair in a preset control time zone; Control valve regulating unit: regulating the flow control valve through the flow control module of the first lubricating oil pump to obtain multiple groups of flow test samples; A confrontation analysis unit: combining the first service load and the plurality of flow test samples, performing friction confrontation analysis through the first friction pair finite element model to obtain a plurality of friction confrontation indicators, wherein the plurality of friction confrontation indicators represent the magnitude of the service lubrication effect of the plurality of flow test samples on the first friction pair; A flow optimization unit: optimizing the lubricating oil flow based on the multiple friction resistance indicators to obtain a first flow control parameter; A heat optimization unit: combining the first service load and the first flow control parameter, performing oil heat optimization through the first friction pair finite element model, and obtaining a first oil temperature; Flow and temperature control unit: the flow of the first lubricating oil pump is controlled according to the first flow control parameter through the flow control module, and the oil inlet temperature of the first lubricating oil pump and the first friction pair is controlled according to the first oil temperature through the cooling device connected to the first lubricating oil pump.