Pressure cooperative control method and system for lubricating pump group

Abstract

The invention discloses a pressure cooperative control method and system for a lubricating pump group, and belongs to the technical field of industrial automation control, and the method comprises the steps: deploying a multi-sensor network in the lubricating pump group, and constructing the real state of a lubricating pump according to monitoring data; performing a time series analysis of the working device; taking the lubrication demand prediction result as a control target, taking each lubrication pump in the lubrication pump group as an independent agent, and establishing an executable scheme set; establishing a first fitness constraint; establishing a second fitness constraint and a third fitness constraint; and performing scheme collaborative analysis by using the first fitness constraint, the second fitness constraint and the third fitness constraint, and establishing a pressure collaborative control scheme. The lubricating pump group solves the technical problems that in the prior art, the working state of a lubricating pump group cannot be accurately adjusted, insufficient lubrication or excessive lubrication is prone to occurring, and therefore the equipment failure rate is high, energy consumption is wasted, and the lubricating efficiency is low.

Description

Technical Field

[0001] This invention relates to the field of industrial automation control technology, specifically to a pressure coordination control method and system for a lubrication pump group. Background Technology

[0002] Lubrication systems play a crucial role in various types of mechanical equipment, especially in equipment operating under high loads and for extended periods. The stability of the lubrication system directly affects the efficiency and lifespan of the equipment. Lubrication pump groups are key equipment for ensuring an effective supply of lubricating oil, and optimizing their operation is of great significance for energy conservation, emission reduction, and extending equipment life. Therefore, improving the coordinated control capabilities and working efficiency of lubrication pump groups has become an urgent need for the development of industrial automation and intelligentization.

[0003] Currently, most lubrication pump group control methods rely on simple timed start / stop or experience-based rules, which cannot adapt to changes in equipment status in real time, resulting in low lubrication efficiency, energy waste, and frequent equipment failures. Furthermore, existing lubrication pump control systems lack intelligence and adaptive capabilities, making it difficult to optimize scheduling under complex operating conditions. A more intelligent and precise control scheme is urgently needed to improve overall performance. Summary of the Invention

[0004] This application provides a pressure coordination control method and system for a lubrication pump group, aiming to solve the technical problems in the prior art where the lubrication pump group cannot accurately adjust its working state, is prone to insufficient or excessive lubrication, resulting in high equipment failure rate, energy waste and low lubrication efficiency.

[0005] In view of the above problems, this application provides a pressure coordination control method and system for a lubrication pump group.

[0006] The first aspect disclosed in this application provides a pressure collaborative control method for a lubrication pump group. The method includes: deploying a multi-sensor network in the lubrication pump group; constructing the actual state of the lubrication pumps based on monitoring data from the multi-sensor network; performing time-series analysis of the working equipment to establish a lubrication demand prediction result, wherein the lubrication demand prediction result includes a demand buffer node; using the lubrication demand prediction result as the control target, treating each lubrication pump in the lubrication pump group as an independent intelligent agent, and performing task collaborative execution analysis of the independent intelligent agents after synchronizing the actual state of the lubrication pumps to establish an executable scheme set; identifying the collaborative start-stop switching frequency of the executable scheme set based on the demand buffer node to establish a first fitness constraint; performing execution fitness analysis under the executable scheme set using the actual state of the lubrication pumps to establish a second fitness constraint; performing lubricant mixing penalty analysis based on the executable scheme set to establish a third fitness constraint; and performing scheme collaborative analysis using the first fitness constraint, the second fitness constraint, and the third fitness constraint to establish a pressure collaborative control scheme.

[0007] Another aspect of this application discloses a pressure collaborative control system for a lubrication pump group. This system includes: a lubrication pump real-state construction module, used to deploy a multi-sensor network in the lubrication pump group and construct the real-state of the lubrication pumps based on monitoring data from the multi-sensor network; a lubrication demand prediction result establishment module, used to perform time-series analysis of the working equipment and establish lubrication demand prediction results, wherein the lubrication demand prediction results include demand buffer nodes; and an executable scheme set establishment module, used to take the lubrication demand prediction results as the control target, treat each lubrication pump in the lubrication pump group as an independent intelligent agent, synchronize the real-state of the lubrication pumps, and then perform task collaborative execution analysis of the independent intelligent agents. An executable scheme set is established; a first fitness constraint establishment module is used to identify the collaborative start-stop switching frequency of the executable scheme set based on the demand buffer node and establish a first fitness constraint; a second fitness constraint establishment module is used to perform execution fitness analysis under the executable scheme set using the actual state of the lubrication pump and establish a second fitness constraint; a third fitness constraint establishment module is used to perform lubricant mixing penalty analysis based on the executable scheme set and establish a third fitness constraint; a pressure collaborative control scheme establishment module is used to perform scheme collaborative analysis using the first fitness constraint, the second fitness constraint, and the third fitness constraint to establish a pressure collaborative control scheme.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: By adopting a control target based on lubrication demand prediction, matching the working mode of the lubrication pump group with actual needs, and optimizing the start-stop frequency and load distribution of the lubrication pumps through an intelligent collaborative control strategy, this technical solution solves the technical problems in existing technologies where lubrication pump groups cannot accurately adjust their working state, are prone to insufficient or excessive lubrication, resulting in high equipment failure rates, energy waste, and low lubrication efficiency. This achieves the technical effects of improving lubrication efficiency, reducing energy consumption, reducing equipment wear and failure rates, extending equipment service life, and enhancing system stability and economic benefits.

[0009] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0010] Figure 1 This application provides a schematic flowchart of a pressure coordination control method for a lubrication pump group. Figure 2 This application provides a schematic diagram of the structure of a pressure coordination control system for a lubrication pump group.

[0011] Explanation of reference numerals in the attached diagram: Lubrication pump real state construction module 11, lubrication demand prediction result establishment module 12, executable scheme set establishment module 13, first fitness constraint establishment module 14, second fitness constraint establishment module 15, third fitness constraint establishment module 16, pressure collaborative control scheme establishment module 17. Detailed Implementation

[0012] The overall concept of the technical solution provided in this application is as follows: This application provides a pressure coordination control method and system for a lubrication pump group. By using a control objective based on lubrication demand prediction results, the operating state of the lubrication pump group is intelligently optimized. The start-stop frequency and load distribution of the lubrication pumps are matched with actual lubrication needs to avoid insufficient or excessive lubrication. By synchronizing the state of the lubrication pump group and employing a coordination control strategy, intelligent scheduling and efficient operation of each pump are achieved, thereby improving lubrication efficiency, reducing energy consumption, lowering equipment failure rate, extending equipment lifespan, and enhancing system reliability and stability.

[0013] After introducing the basic principles of this application, various non-limiting embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0014] Example 1 like Figure 1As shown in the embodiment of this application, a pressure coordination control method for a lubrication pump group is provided, the method comprising: Step S100: Deploy a multi-sensor network in the lubrication pump group and construct the real state of the lubrication pumps based on the monitoring data of the multi-sensor network.

[0015] Specifically, a lubrication pump group refers to a set of pumps used to supply lubricating oil to industrial equipment. A multi-sensor network refers to the collection of real-time data from the lubrication pump group through various sensors (such as pressure sensors, temperature sensors, flow sensors, etc.). The actual status of the lubrication pumps refers to their current actual operating status, including data such as their working pressure, flow rate, temperature, speed, and lubricating oil quantity.

[0016] A series of sensors are deployed within the lubrication pump group to collect real-time operating data. For example, pressure sensors monitor the operating pressure of the lubrication pumps; flow sensors detect the flow rate of the lubricating oil; and temperature sensors provide feedback on the pump's temperature. Through these sensors, the status data of the entire lubrication pump group is collected in real-time and sent to the central processing unit.

[0017] Next, the signals from different sensors are comprehensively analyzed to form a real-world model of the lubrication pump's state. Specifically, real-time data from each lubrication pump is collected through a multi-sensor network. This data is then preprocessed to remove noise and outliers, ensuring accuracy. Next, data fusion algorithms (such as Kalman filtering or weighted averaging) are applied to integrate the data from different sensors, optimizing accuracy and consistency. Subsequently, machine learning or statistical analysis methods are used to establish a lubrication pump operating state assessment model based on the sensor data, such as regression models, neural networks, or support vector machines. Finally, these models are applied to a real-time monitoring system to dynamically update the real-world state of the lubrication pump, providing data support for subsequent control decisions.

[0018] By deploying this multi-sensor network and applying data fusion technology, the working status of the lubrication pump group can be obtained accurately in real time.

[0019] Step S200: Perform time series analysis of the working equipment and establish lubrication demand prediction results, wherein the lubrication demand prediction results include demand buffer nodes.

[0020] Specifically, working equipment refers to industrial equipment or machinery that requires lubrication, such as motors, pumps, and compressors on a production line. Time series analysis predicts future trends by analyzing the changing trend of a variable over a period of time. Lubrication demand forecasting results refer to the predicted values ​​of future lubrication needs for working equipment, typically including information such as the amount of lubricating oil, replenishment cycle, and lubrication frequency. Demand buffer nodes refer to buffer areas or time points set in lubrication demand forecasting to address fluctuations in lubrication demand.

[0021] First, time series analysis is performed on the historical operating data of the equipment. This involves analyzing the trends in lubrication demand across different time periods to identify the equipment's lubrication patterns and regularities. Commonly used tools in time series analysis include ARIMA (Autoregressive Integral Moving Average) models and Long Short-Term Memory (LSTM) networks, which can predict future demand based on past lubrication demand data. The ARIMA model is used to predict the equipment's lubrication oil demand over a future period. Specifically, historical lubrication demand data is collected and formatted as a time series. Statistical methods are used to test the stationarity of the time series (e.g., ADF test). If the data is not stationary, it is stabilized through differencing. Then, the parameters (p, d, q) of the ARIMA model are determined using the Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF). Finally, the ARIMA model is fitted using training data, predictions are made, and the model's accuracy is evaluated to obtain the predicted future lubrication demand. If a sharp increase in demand is observed within a certain operating cycle, a demand buffer node is set based on the lubrication demand prediction results to ensure sufficient lubrication supply and avoid the risk of insufficient lubrication.

[0022] This forecasting process allows for accurate prediction of future lubrication needs based on the historical operating conditions of the equipment. By setting demand buffer nodes, it avoids problems of insufficient or excessive lubrication due to demand fluctuations.

[0023] Step S300: Using the lubrication demand prediction result as the control target, treat each lubrication pump in the lubrication pump group as an independent intelligent agent, synchronize the actual state of the lubrication pump, and perform task collaborative execution analysis of the independent intelligent agents to establish an executable solution set.

[0024] Specifically, the control objective refers to meeting the lubricant supply requirements predicted by future equipment lubrication needs, including the supply time, quantity, stability, and response speed. An independent intelligent agent means that each lubricating pump in the system is considered an autonomous decision-making unit with independent task execution and decision-making capabilities. Synchronized lubricating pump real-time status refers to the fact that each lubricating pump in the pump group updates its status information through real-time monitoring data, ensuring that the status of all lubricating pumps is synchronized for collaborative operation. The executable solution set refers to a set of executable optimization solutions generated by the lubricating pump group through collaborative analysis, considering the independent status and task requirements of each lubricating pump.

[0025] First, each lubrication pump in the lubrication pump group is considered an independent intelligent agent, meaning that each lubrication pump can make autonomous decisions based on its own operating status and future lubrication demand predictions. Each lubrication pump independently determines whether it needs to start, adjust its workload, or stop based on its own real-time status data and lubrication demand predictions.

[0026] To optimize the coordinated operation of the lubrication pumps, a task collaborative execution analysis method is employed. Combining the predicted lubrication demand, each agent exchanges information with other lubrication pump agents, analyzing its own tasks and objectives to formulate an optimal execution plan across the entire pump group. For example, if a device has high lubrication demand in the upcoming work cycle, some lubrication pumps in the group will, based on the task collaborative execution analysis, choose to start earlier and adjust their workload.

[0027] To address this, intelligent optimization algorithms (such as genetic algorithms and particle swarm optimization) are used to generate a set of executable solutions. These algorithms can dynamically adjust the start-up and shutdown times and workload of each lubrication pump based on multiple factors, such as the health status, load conditions, and lubrication requirements of each pump. Specifically, optimization objectives are defined, such as minimizing energy consumption or maximizing lubricant supply stability. Then, the intelligent algorithm generates multiple solutions by simulating the selection, crossover, and mutation of particles or genes, and evaluates the fitness of each solution (such as pump load balance and start-up / shutdown frequency). Through continuous iterative optimization, the algorithm eventually finds an optimal solution, where the lubrication pump group can operate efficiently and stably while meeting lubrication requirements, thus determining the optimal start-up and shutdown times and load allocation.

[0028] This step, through intelligent collaborative control, enables the lubrication pump group to automatically adjust the working task of each lubrication pump based on future lubrication demand predictions and the real-time status of the lubrication pumps, thereby minimizing energy waste and avoiding equipment failure due to excessive or insufficient lubrication oil supply.

[0029] Step S400: Identify the collaborative start-stop switching frequency of the executable scheme set based on the demand buffer node, and establish a first fitness constraint.

[0030] Specifically, the coordinated start-stop switching frequency refers to the start-stop operation frequency of each pump in the lubrication pump group. Coordinated start-stop means that multiple lubrication pumps perform start-stop operations together according to task requirements. The first fitness constraint is a constraint condition set based on the demand buffer node during the optimization process to ensure that the start-stop frequency and switching operation of the lubrication pumps do not exceed a certain threshold when lubrication demand fluctuates.

[0031] First, identify the demand buffer nodes in the lubrication demand forecast results. These are the points where significant fluctuations or sudden increases in lubrication demand should be anticipated and addressed proactively. Next, identifying the coordinated start-stop switching frequency involves analyzing the start-stop frequency of each pump in the lubrication pump group. Excessive start-stop switching frequency leads to excessive pump wear and energy waste, while insufficient frequency results in inadequate lubricant supply. Therefore, by analyzing lubrication demand and the actual operating conditions of the equipment, the start-stop times of the lubrication pumps can be rationally scheduled.

[0032] In this process, optimization algorithms (such as genetic algorithms or particle swarm optimization) are used to adjust the start-stop switching frequency. By analyzing and adjusting the start-stop frequency, it is ensured that each lubrication pump does not start and stop frequently near the demand buffer node, while maintaining the system's responsiveness to future lubrication needs. At this point, the generated first fitness constraint ensures that the start-stop frequency of the lubrication pumps is neither too high nor too low, achieving an optimal match between load balance and lubrication demand.

[0033] By identifying the frequency of coordinated start-stop switching and applying demand buffer nodes appropriately, corresponding measures can be taken in advance when lubrication demand fluctuates, thus optimizing the start-stop control of the lubrication pump.

[0034] Step S500: Perform execution fitness analysis under the set of executable schemes using the actual state of the lubrication pump, and establish a second fitness constraint.

[0035] Specifically, the execution fitness analysis refers to evaluating the effectiveness of the set of executable solutions based on the actual state of the lubrication pumps. The second fitness constraint is an optimization condition established based on the results of the execution fitness analysis to ensure that the lubrication pump group can maintain efficient and stable operation of the system while ensuring lubrication requirements are met and avoiding unreasonable loads or excessive consumption.

[0036] The system collects the real-time status of each lubrication pump in the lubrication pump group, i.e., monitors the operating status of each pump in real time through a multi-sensor network. Based on real-time data and lubrication demand prediction, an executable set of solutions is generated, including start-up and shutdown strategies for different lubrication pumps at different time points, workload allocation, etc. Then, execution fitness analysis is performed. Each execution solution is evaluated based on the real-time status of the lubrication pumps. Furthermore, the operating time of the lubrication pumps also needs to be considered to avoid wear caused by prolonged continuous operation. Tools such as load balancing algorithms and time-series decay models are used in the execution fitness analysis. The load balancing algorithm evaluates the workload of different lubrication pumps to ensure a reasonable distribution of workload for each pump, avoiding prolonged overload operation of some pumps, which could lead to efficiency degradation or damage. The time-series decay model simulates the performance degradation of lubrication pumps during continuous operation, helping to determine whether certain solutions will lead to excessive pump wear. Based on the results of the execution fitness analysis, a second fitness constraint is established.

[0037] By performing fitness analysis and establishing a second fitness constraint, the overall operation of the lubrication pump group can be optimized, ensuring that each lubrication pump meets lubrication requirements while avoiding overload or excessive operation.

[0038] Step S600: Perform a mixing penalty analysis of the lubricating oil based on the executable scheme set, and establish a third fitness constraint.

[0039] Specifically, lubricant mixing penalty analysis refers to analyzing the lubricants used in a lubrication pump group to assess the negative impacts of mixing different lubricants, such as decreased lubrication performance and increased equipment wear. Incompatible lubricant types can lead to insufficient lubrication or problems like carbon buildup and corrosion in the pump body. The third fitness constraint is a constraint established based on the results of the lubricant mixing penalty analysis to ensure that the lubricant combination used in the lubrication pump group effectively reduces the risks associated with mixing while maintaining optimal lubrication performance and system stability.

[0040] First, lubricating oil data is collected and analyzed, mainly including the quality parameters, oil type, and usage history of the different lubricating oils used in the lubrication pump group. Next, a mixing penalty analysis of the lubricating oils is performed based on the data. The negative impacts of mixing different lubricating oils are considered, such as incompatible chemical reactions and reduced lubrication effectiveness. The actual performance of the mixed lubricating oil is calculated to assess whether its performance meets the equipment's lubrication requirements. Based on the lubricating oil mixing penalty analysis, a third fitness constraint is generated according to the mixing results. This constraint ensures that the lubricating oil combination in the lubrication pump group avoids using mismatched lubricating oils during operation, ensuring that the equipment operates under efficient and stable lubrication conditions.

[0041] This process, through lubricant mixing penalty analysis, ensures that the use of lubricants does not cause equipment performance degradation or malfunction. It effectively optimizes lubricant selection and use, extending equipment lifespan, improving system operating efficiency, and reducing maintenance costs.

[0042] Step S700: Perform a collaborative analysis of the schemes using the first fitness constraint, the second fitness constraint, and the third fitness constraint to establish a collaborative pressure control scheme.

[0043] Specifically, the pressure coordination control scheme is to develop a set of optimal operating strategies by comprehensively considering the working status, lubrication requirements and operating constraints of each lubrication pump, so as to ensure that the lubrication pump group can achieve optimized lubrication effect, load distribution and energy efficiency while meeting the system pressure requirements.

[0044] The first, second, and third fitness constraints are considered comprehensively. By analyzing the operating status and task requirements of each lubrication pump and combining these constraints, the merits of each feasible solution are evaluated. When considering the start-up and shutdown frequency of the lubrication pumps, the first fitness constraint ensures that the start-up and shutdown operations are not too frequent, thereby avoiding energy waste or equipment wear. The second fitness constraint, by considering the cumulative operating time of the lubrication pumps, avoids long-term overload of the lubrication pumps, ensuring that the equipment is not damaged due to fatigue or excessive work. Next, the third fitness constraint, based on the analysis of lubricating oil quality, ensures that the quality of lubricating oil in the lubrication pump group is consistent, avoiding insufficient lubrication or excessive wear caused by oil mismatch.

[0045] By comprehensively analyzing these three constraints, a synergistic analysis of the solutions is conducted. This involves optimizing the lubrication pump's workload, start-up and shutdown times, and lubricant selection based on these constraints. This results in a coordinated pressure control scheme that ensures the lubrication needs of the equipment are effectively met under different operating conditions.

[0046] Furthermore, the step of identifying the coordinated start-stop switching frequency of the executable scheme set based on the demand buffer node and establishing a first fitness constraint includes: identifying the start-stop switching of the lubrication pump in the executable scheme set and establishing a first influence coefficient based on the total number of identifications; identifying the total number of identifications falling into the demand buffer node and establishing a second influence coefficient based on the identification result; obtaining a set of start-stop nodes that do not fall into the demand buffer node, identifying the start-stop influence based on the start-stop node set and the lubrication demand prediction result, and establishing a third influence coefficient; and establishing the first fitness constraint using the first influence coefficient, the second influence coefficient, and the third influence coefficient.

[0047] Specifically, the first influence coefficient is based on the start-stop switching frequency of each lubrication pump in the lubrication pump group, quantifying the impact of start-stop operation frequency on the overall system efficiency. Excessive start-stop frequency leads to excessive wear and energy waste, while insufficient frequency fails to meet lubrication requirements. The first influence coefficient measures the negative impact of this frequency variation on the system and reflects the improvement in system stability after adjusting the start-stop frequency.

[0048] The second impact coefficient quantifies the impact of demand fluctuations on start-stop switching based on whether the total number of start-stop operations falls within the demand buffer node range. The demand buffer node refers to a point where lubrication demand approaches a critical value, requiring the system to respond in advance to ensure an adequate supply of lubricating oil. If the number of start-stop operations occurs within the demand buffer node, the system needs to adjust these time points to optimize the operation of the lubrication pump group. The second impact coefficient measures the impact of demand fluctuations on the lubrication pump start-stop strategy, ensuring that lubrication pumps can start earlier when demand increases to avoid insufficient oil supply.

[0049] The third impact coefficient identifies the impact of start-stop operations based on the set of start-stop nodes that do not fall within the demand buffer node, quantifying the impact of these unadjusted start-stop operations on lubricant supply and equipment operation. Unadjusted start-stop nodes can lead to insufficient lubrication demand or the system failing to respond promptly during peak demand periods, thus affecting the lubrication performance of the equipment. The third impact coefficient reflects the potential risk of this factor to the overall system operation and considers these factors in solution optimization to ensure system stability and efficiency.

[0050] First, the start-stop switching of lubrication pumps in the executable scheme set is identified, that is, the start-stop behavior of each lubrication pump within a predetermined time period is analyzed, and the total number of start-stops is counted. A first influence coefficient is established based on the total number of start-stops. Next, these start-stop operations are further analyzed. If the total number of start-stops is close to the demand buffer node (i.e., the predicted lubrication demand), the time period requiring advance adjustment can be identified, and a second influence coefficient is established. This identification process ensures that the system can respond in advance when lubrication demand approaches the buffer node, optimizing the start-stop strategy of the lubrication pumps. Then, the set of start-stop nodes that do not fall within the demand buffer node is obtained, that is, the start-stop times of lubrication pumps outside the demand buffer node range. Based on the lubrication demand prediction results, the start-stop impact of these nodes is identified, thereby establishing a third influence coefficient. For example, if the start-stop operation of a certain node is not adjusted within the demand buffer node, it will lead to insufficient or excessive lubrication oil supply, thus requiring additional adjustments.

[0051] Finally, using the first, second, and third influence coefficients, a first fitness constraint is established. This constraint ensures that the lubrication pump group operates at a reasonable start-stop frequency when executing the set of executable schemes, preventing excessive wear or energy waste on the equipment. This constraint helps the system maintain overall efficiency and stability while meeting lubrication requirements by optimizing the start-stop frequency.

[0052] Furthermore, the step of identifying the impact of start-stop operations based on the start-stop node set and the lubrication demand prediction results, and establishing a third impact coefficient, includes: establishing task importance characteristics and lubrication demand stability characteristics of the work task based on the lubrication demand prediction results; performing fluctuation analysis on lubrication pump switching after locating the lubrication pump using the start-stop node set, and establishing fluctuation analysis characteristics; and using a matching identification channel to match and identify the task importance characteristics, lubrication demand stability characteristics, and fluctuation analysis characteristics to establish the third impact coefficient.

[0053] Specifically, task importance characteristics refer to the relative importance of a work task, usually judged based on the task's criticality, urgency, or impact on equipment. Lubrication demand stability characteristics indicate the stability of lubrication demand changes over time. Fluctuation analysis characteristics refer to analyzing the fluctuations in the lubrication pump switching frequency; by assessing the fluctuations in the lubrication pump's operating state, the stability or instability of start-up and shutdown operations can be identified.

[0054] Based on lubrication demand forecasts, task importance and lubrication demand stability characteristics are established for each work task. Task importance characteristics assess the priority of lubrication tasks, considering which equipment requires priority lubrication during specific time periods. Lubrication demand stability characteristics analyze the patterns of lubrication demand changes over time, identifying significant demand fluctuations. If lubrication demand changes drastically, stability characteristics will reflect instability, which helps in developing countermeasures.

[0055] Next, the lubrication pumps are located using data from the start / stop node set, and fluctuation analysis of lubrication pump switching is performed. By analyzing the volatility of lubrication pump start / stop, it is possible to identify which pumps start / stop more frequently or are unstable. Volatility analysis helps assess whether the operating state of the lubrication pumps is stable and whether the start / stop timing needs to be adjusted. Then, using a matching identification channel, task importance characteristics, lubrication demand stability characteristics, and volatility analysis characteristics are matched and identified. This process combines task priority, demand stability, and lubrication pump start / stop volatility, comprehensively analyzing their mutual influence to generate a comprehensive third influence coefficient. Finally, the third influence coefficient is used to optimize the lubrication pump start / stop strategy, ensuring that the lubrication pumps can provide a stable and efficient lubrication oil supply when task priority is high and demand is unstable.

[0056] This step allows for a more accurate assessment of the volatility of lubrication requirements and the importance of the task, thereby optimizing the start-up and shutdown strategy of the lubrication pump.

[0057] Furthermore, the step of performing execution fitness analysis under the executable scheme set using the actual state of the lubrication pumps and establishing a second fitness constraint includes: parsing the working records of the lubrication pump group to obtain the cumulative startup runtime of each lubrication pump in the lubrication pump group; fitting the time-series decay effect of the lubrication pumps based on the actual state of the lubrication pumps and the cumulative startup runtime, and generating a penalized fitness using the fitting result of the time-series decay effect and the executable scheme set; evaluating the load balance of the lubrication pumps based on the actual state of the lubrication pumps and the executable scheme set, and establishing a balance fitness; and establishing a second fitness constraint based on the penalized fitness and the balance fitness.

[0058] Specifically, the cumulative startup runtime refers to the total operating time of each lubrication pump from startup to the current moment. The time-series decay effect fitting involves analyzing the cumulative startup runtime and actual state data of the lubrication pumps to build a model that predicts the performance degradation of the lubrication pumps during long-term operation. This model can reveal the performance degradation trend of the lubrication pumps under different operating durations and calculate the impact of degradation on the system. Penalized fitness is a penalty score given in the performance fitness analysis by evaluating issues such as degradation and inappropriate workload during long-term operation of the lubrication pumps. Balance fitness is a fitness score based on the balance of the lubrication pump load. The load of each pump in the lubrication pump group should be distributed as evenly as possible to avoid some pumps working under overload, resulting in energy waste or equipment damage.

[0059] First, the operating records of the lubrication pump group are analyzed to collect the cumulative start-up runtime of each pump. This helps to understand the workload and long-term load conditions of each pump. Assume that lubrication pump A has a cumulative start-up runtime of 1000 hours, while lubrication pump B has 500 hours. Lubrication pump A faces a higher risk of wear, so this needs to be considered when implementing the scheme set. Next, a time-series decay effect fitting is performed based on the actual state of the lubrication pumps and their cumulative start-up runtime. This process establishes a decay model by analyzing the cumulative runtime and current operating state of the lubrication pumps. Specifically, historical operating data of the lubrication pumps is collected, including cumulative start-up runtime, load conditions, and real-time status. Statistical regression analysis or machine learning algorithms (such as linear regression, support vector machines) are used to fit the performance decay trend of the lubrication pumps, combining the pump runtime and load intensity to establish a time-series decay model. For example, assuming lubrication pump A operates under high load for a long time, the system can predict the risk of efficiency degradation or failure in the future. The time-series decay effect fitting result will take this decay into account and generate a penalty fitness, i.e., limiting the workload of lubrication pump A to avoid over-operation. For example, if lubrication pump A runs for a long time, its start-stop frequency may be increased or its load reduced to reduce wear.

[0060] Next, a load balance evaluation of the lubrication pumps is performed, assessing whether the load distribution among the pumps in the lubrication pump group is uniform. For example, if lubrication pump A has a very high load while lubrication pump B has a low load, the system needs to readjust the task allocation to ensure a balanced load within the pump group. Based on this load balance, a balance fitness is generated so that the optimization algorithm can adjust the solution set according to the priority of load balance. Finally, a second fitness constraint is established by combining the penalized fitness and the balance fitness.

[0061] This step allows for precise control of the operating status of each lubrication pump in the lubrication pump group, ensuring its long-term stable operation.

[0062] Furthermore, the step of using the first fitness constraint, the second fitness constraint, and the third fitness constraint to perform scheme collaborative analysis and establish a pressure collaborative control scheme includes: executing the historical operation data call of the lubrication pump group to establish a historical operation dataset; identifying the probability of abnormal operation of the lubrication pump group based on the historical operation dataset and establishing anomaly penalties; configuring emergency collaborative lubrication pumps with the anomaly penalties; performing scheme collaborative analysis and compensation based on the emergency collaborative lubrication pumps to reconstruct the pressure collaborative control scheme.

[0063] Specifically, historical operation datasets refer to the operational data of the lubrication pump group over a past period, including the start-up time, stop time, load, temperature, pressure, flow rate, and fault records of each lubrication pump. Anomaly probability identification involves analyzing historical operation data to determine the probability of faults or performance abnormalities occurring in the lubrication pump group. Anomaly penalty refers to the quantitative penalty applied to anomalies (such as overload or prolonged high temperatures) in the scheme collaboration analysis, limiting their negative impact on the overall system operation. Emergency collaborative lubrication pumps refer to pre-set backup pumps in the lubrication pump group. These pumps can be promptly deployed during peak lubrication demand periods or when a lubrication pump fails, ensuring the normal operation of the system.

[0064] First, historical operating data of the lubrication pump group is retrieved to collect its past operating records. By analyzing this historical data, the operating trends of the lubrication pump group can be understood, and factors affecting the stability of the lubrication system can be identified. For example, if lubrication pump A frequently operates in a high-temperature environment, the system can identify the potential risk of its high-temperature failure.

[0065] Next, based on this historical data, the system identifies the probability of operational anomalies in the lubrication pump group. This step aims to identify potential risks leading to system failure by analyzing frequently occurring anomaly patterns (such as overload and high temperature) in the operational data. For example, if lubrication pump B operates under high load for an extended period, the system will identify the probability of high-load operation and assess the impact of this risk on the lubrication pump's performance.

[0066] Then, based on the identified anomalies, anomaly penalties are established. For example, if lubrication pump A has frequently operated under overload conditions over a period of time, the system will impose a higher penalty value on this pump, limiting its continued operation under high load. To cope with anomalies, an emergency backup lubrication pump is configured. This backup pump is a pre-set standby pump that can quickly take over when other lubrication pumps malfunction. For instance, if lubrication pump A fails or operates under high load, the system will activate emergency lubrication pump B to ensure lubrication needs are met and prevent equipment damage due to lack of lubrication.

[0067] Next, using collaborative analysis, the operating scheme of the entire lubrication pump group is optimized by comprehensively considering historical data, anomaly penalties, and the activation status of emergency lubrication pumps. Intelligent algorithms (such as particle swarm optimization or genetic algorithms) are then used to adjust the task allocation and start-up / shutdown strategies of the lubrication pumps. Finally, these steps generate a pressure collaborative control scheme.

[0068] This process enables dynamic optimization of the lubrication pump group's operating strategy. The pressure coordination control scheme can flexibly adjust the working status and task allocation of each lubrication pump based on historical data, operational anomalies, and lubrication requirements, ensuring that the lubrication system maintains efficient and stable operation under different working conditions.

[0069] Furthermore, after reconstructing the pressure collaborative control scheme, the following steps are included: monitoring the lubricating oil supply of the working equipment and establishing supply monitoring feedback; when the supply monitoring feedback reports an abnormal feedback at any time point, performing abnormal source tracing and location; and calling the emergency collaborative lubrication pump to perform emergency management based on the abnormal source tracing and location results.

[0070] Specifically, anomaly feedback refers to situations where the monitoring system detects deviations from expectations during operation. Anomaly tracing and location refer to the system's analysis of relevant data and historical records to identify the root cause of the anomaly after detecting it. Emergency management refers to the system automatically taking a series of measures, such as activating emergency lubrication pumps and adjusting lubricant supply, to restore normal system operation and reduce the risk of equipment damage when a malfunction or anomaly occurs.

[0071] First, the system monitors the lubricating oil supply to the working equipment and establishes a supply monitoring feedback mechanism. A multi-sensor network collects relevant lubricating oil data in real time and transmits this data to the control system. The system analyzes this monitoring data to assess the lubricating oil supply and determine if it meets the equipment's needs. When the system receives abnormal feedback during monitoring (such as excessively low lubricating oil flow or excessively high pressure), it proceeds to troubleshoot and locate the source of the anomaly. This troubleshooting involves analyzing various parameters in the lubrication system to identify the root cause of the anomaly. Once the cause is determined, the emergency backup lubricating pump is activated, and emergency management is implemented. The emergency backup lubricating pump is a pre-configured standby pump that automatically activates to supplement the lubricating oil supply when a standby pump malfunctions, ensuring continuous lubrication of the equipment. At this time, the pump start-up and shutdown sequence or the lubricating oil flow distribution is adjusted to ensure the lubricating oil supply returns to normal levels, thereby preventing equipment failure due to insufficient lubrication.

[0072] This process enables timely detection of abnormalities in lubricant supply during equipment operation through real-time monitoring and feedback, and allows for tracing the source of the abnormality to identify the cause, thus preventing equipment damage due to insufficient lubrication.

[0073] Furthermore, the step of performing lubricant mixing penalty analysis based on the executable scheme set to establish a third fitness constraint includes: acquiring lubricant data within the lubricant pump group and establishing a first quality deviation based on the lubricant data; acquiring lubricant pump cleaning data within the lubricant pump group and establishing a second quality deviation; and performing lubricant mixing penalty analysis using the first quality deviation and the second quality deviation to establish a third fitness constraint.

[0074] Specifically, lubricating oil data refers to information related to the lubricating oil used in a lubrication pump group, including oil type, operating environment, usage time, and oil quality. The first quality deviation is an indicator established based on lubricating oil data, primarily reflecting the quality differences of the same type of lubricating oil under different operating times and environments. For example, lubricating oils behave differently under different temperature, humidity, and load conditions; even if they are the same type of lubricating oil, their quality and lubrication performance will vary. The second quality deviation is an indicator established based on lubrication pump cleaning data within the lubrication pump group, primarily reflecting changes in lubricating oil quality after pump cleaning. This quality difference is caused by residual contaminants during the cleaning process or changes in the oil itself during cleaning.

[0075] First, data on the lubricating oil within the lubrication pump group is acquired, such as the type of each lubricating oil, its operating environment, and operating duration. Even with the same lubricating oil type, different operating environments and usage durations can lead to differences in oil quality. By analyzing this data, the system can establish the first quality deviation, quantifying the changes in lubricating oil quality under different operating environments and usage durations.

[0076] Next, the cleaning data of the lubrication pumps within the lubrication pump group is acquired, and a second quality deviation is established based on this data. After cleaning the lubrication pumps, the quality of the lubricating oil may change due to residues or incomplete cleaning during the process. Using these two quality deviation data, the system performs a lubricating oil mixing penalty analysis to assess the negative impact of mixing lubricating oils.

[0077] Finally, based on the results of the lubricant mixing penalty analysis, the system establishes a third fitness constraint. This constraint restricts the lubrication pump group from using lubricant combinations with inconsistent quality when performing tasks. This constraint ensures that the quality of the lubricant meets the system's requirements, preventing equipment failure or efficiency degradation due to oil quality issues.

[0078] This process ensures consistency in the use of lubricating oil across the lubrication pump group, reducing equipment malfunctions and efficiency drops caused by lubricating oil quality issues. The third fitness constraint effectively prevents negative impacts from differences in lubricating oil quality or improper cleaning, guaranteeing the normal operation of the lubrication pumps.

[0079] Furthermore, after establishing the pressure collaborative control scheme, the process includes: establishing a prediction error compensation mechanism; after establishing the pressure collaborative control scheme, using the prediction error compensation mechanism to identify the deviation between the short-term actual lubrication demand and the predicted lubrication demand; and correcting the pressure collaborative control scheme based on the deviation identification results.

[0080] Specifically, the prediction error compensation mechanism is a method used to adjust the system's control strategy in a timely manner when there is a deviation between the predicted and actual lubrication demand, ensuring that lubrication demand is accurately met. This mechanism can identify prediction errors and correct them in real time. Short-term actual lubrication demand refers to the actual amount and frequency of lubricating oil required by the equipment in the short term. It is dynamically changed based on actual factors such as the equipment's current load and environmental conditions. Lubrication demand prediction results are obtained by analyzing historical operating data of the equipment and using algorithms to predict the amount and frequency of lubricating oil required by the equipment in the future. Deviation identification refers to comparing the actual lubrication demand with the predicted demand, detecting the difference (deviation) between the two, and analyzing whether the system has inaccurate predictions based on the difference. Pressure coordination control scheme correction refers to the correction based on the deviation between the actual and predicted lubrication demand.

[0081] After establishing a pressure-coordinated control scheme, a prediction error compensation mechanism is established. The aim is to identify the difference between actual lubrication demand and the lubrication demand obtained through the prediction model, ensuring the system can adjust in real time and avoid insufficient or excessive lubrication due to prediction errors. Specifically, deviation identification is performed by comparing actual and predicted lubrication demand. This process identifies the deviation between predicted and actual values ​​by real-time monitoring of the equipment's operating status and by predicting future demand based on historical data. For example, suppose the lubrication demand prediction shows that a piece of equipment needs 100L of lubricating oil in the next 2 hours, while actual monitoring data shows that the equipment's actual demand during that period is 120L. This deviation indicates that the system needs adjustment.

[0082] Next, the pressure coordination control scheme is modified based on the deviation identification results. Once a deviation between actual and predicted demand is identified, the workload of the lubrication pump group and the lubricating oil supply are adjusted in real time. For example, if actual demand is greater than predicted demand, the workload of the lubrication pumps is automatically increased or a standby pump is activated to ensure lubricating oil supply. Conversely, if actual demand is lower than predicted, the workload of the lubrication pumps can be reduced to save energy and reduce equipment burden. To this end, adaptive control algorithms (such as fuzzy control or PID control) are used to dynamically adjust the operating strategy of the lubrication pumps based on real-time data and prediction errors. These algorithms can automatically correct the control scheme, thereby improving the system's flexibility and stability.

[0083] This process allows for real-time correction of prediction errors, ensuring that the lubrication pump group can adjust its operating strategy in a timely manner according to actual lubrication needs.

[0084] Furthermore, after establishing the pressure coordination control scheme, the method further includes: establishing a health record for the lubrication pump group, continuously monitoring the lubrication pump group through a multi-sensor network, and establishing a continuous monitoring dataset; predicting abnormal trends based on the continuous monitoring dataset and the health record, and establishing a prediction compensation scheme based on the abnormal trend prediction results.

[0085] Specifically, the health record of the lubrication pump group is a database that records the operating status, historical faults, maintenance records, and performance indicators of each lubrication pump. It reflects the long-term operational health of each pump, providing data support for subsequent maintenance and prediction. The continuous monitoring dataset is a collection and storage of various operational data of the lubrication pump group in real time through a multi-sensor network, such as pressure, temperature, and flow rate. This is used for long-term trend analysis and anomaly detection. Anomaly trend prediction, based on historical monitoring data, uses statistical analysis or machine learning algorithms to predict future anomalies, such as equipment failures and performance degradation. Predictive compensation schemes refer to pre-set countermeasures for anomalies based on the results of anomaly trend predictions. For example, if a lubrication pump is predicted to fail, the system can adjust the workload of other pumps or activate a standby pump for compensation.

[0086] Establish health records for the lubrication pump group, recording key performance data, maintenance records, and any history of malfunctions and repairs for each pump. For example, the health record for lubrication pump A includes information such as malfunction reports, workload, and maintenance history from the past five years. These health records help assess the long-term performance and potential failure risks of the lubrication pumps. Next, continuous monitoring of the lubrication pump group is performed through a multi-sensor network, collecting real-time operating data, including pressure, flow rate, and temperature. This data provides real-time feedback on the pump status, enabling the system to analyze pump performance in real time.

[0087] After aggregating all real-time monitoring data, a continuous monitoring dataset is established. This dataset contains various real-time operating parameters of the lubrication pump group, such as pump start-up and stop times, operating temperature, and flow rate. This dataset will serve as the basis for further analysis to identify long-term operating trends or potential anomalies. Based on this, anomaly trend prediction is performed according to the monitoring data and the lubrication pump health records. Using historical data, future anomaly trends are predicted through statistical analysis methods (such as regression analysis) or machine learning algorithms (such as decision trees and neural networks). Specifically, historical operating data, such as sensor data for temperature, pressure, and flow rate, is collected and organized. Then, regression analysis is used to establish the relationship between historical data and equipment performance to predict future operating conditions. For more complex anomaly patterns, data preprocessing steps are used to clean and normalize the data for modeling. Appropriate machine learning algorithms, such as decision trees, random forests, or long short-term memory networks (LSTM), are selected to train the model to identify anomaly patterns in historical data. After training, the model predicts future operating data and identifies emerging anomaly trends. Based on the anomaly trend prediction results, a prediction compensation scheme is established and adjusted accordingly based on potential anomalies.

[0088] This step enables real-time monitoring of the lubrication pump's operating status and intelligent prediction of equipment performance based on historical data and health records. When the system predicts equipment malfunction or performance degradation, it can take proactive measures to compensate, thereby preventing malfunctions or minimizing their impact.

[0089] In summary, the pressure coordination control method for a lubrication pump group provided in this application has the following technical effects: 1. By using control objectives based on lubrication demand forecasts, the operation mode of the lubrication pump group is matched with actual needs. An intelligent collaborative control strategy optimizes the start-stop frequency and load distribution of the lubrication pumps. This not only improves lubrication efficiency but also reduces energy waste and equipment wear. Simultaneously, it can respond to changes in equipment status in real time, avoiding equipment failures caused by insufficient or excessive lubrication, extending equipment lifespan, and improving system reliability and economic benefits.

[0090] 2. By identifying the start-stop switching frequency of the executable scheme set based on demand buffer nodes, the start-stop timing of the lubrication pumps can be reasonably adjusted when lubrication demand fluctuates, avoiding energy waste and equipment wear caused by excessively frequent start-stop operations. This ensures that the pump group can respond in advance when lubrication demand is high, avoiding equipment failure due to insufficient supply and improving the stability and efficiency of system operation.

[0091] Example 2 Based on the same inventive concept as the pressure coordination control method for a lubrication pump group in the foregoing embodiments, such as Figure 2As shown in the figure, this application provides a pressure coordination control system for a lubrication pump group, the system including: The lubrication pump real-state construction module 11 is used to deploy a multi-sensor network in the lubrication pump group and construct the real-state of the lubrication pumps based on the monitoring data of the multi-sensor network; the lubrication demand prediction result establishment module 12 is used to perform time series analysis of the working equipment and establish lubrication demand prediction results, wherein the lubrication demand prediction results include demand buffer nodes; the executable solution set establishment module 13 is used to take the lubrication demand prediction results as the control target, treat each lubrication pump in the lubrication pump group as an independent intelligent agent, synchronize the real-state of the lubrication pumps, and then perform task collaborative execution analysis of the independent intelligent agents to establish an executable solution set; the first fitness constraint establishment module... Block 14 is used to identify the collaborative start-stop switching frequency based on the demand buffer node of the executable scheme set and establish a first fitness constraint; the second fitness constraint establishment module 15 is used to perform execution fitness analysis under the executable scheme set using the actual state of the lubrication pump and establish a second fitness constraint; the third fitness constraint establishment module 16 is used to perform lubricating oil mixing penalty analysis according to the executable scheme set and establish a third fitness constraint; the pressure collaborative control scheme establishment module 17 is used to perform scheme collaborative analysis using the first fitness constraint, the second fitness constraint, and the third fitness constraint and establish a pressure collaborative control scheme.

[0092] Furthermore, the first fitness constraint establishment module 14 is also used to perform the following steps: identify the start-stop switching of the lubrication pump in the executable scheme set, and establish a first influence coefficient based on the total number of identifications; identify whether the total number of identifications falls into the demand buffer node, and establish a second influence coefficient based on the identification result; obtain the start-stop node set that does not fall into the demand buffer node, identify the start-stop influence based on the start-stop node set and the lubrication demand prediction result, and establish a third influence coefficient; and establish the first fitness constraint using the first influence coefficient, the second influence coefficient, and the third influence coefficient.

[0093] Furthermore, the first fitness constraint establishment module 14 is also used to perform the following steps: establish task importance characteristics and lubrication demand stability characteristics of the work task based on the lubrication demand prediction results; after locating the lubrication pump using the start / stop node set, perform fluctuation analysis of lubrication pump switching and establish fluctuation analysis characteristics; and use the matching and identification channel to match and identify the task importance characteristics, lubrication demand stability characteristics and fluctuation analysis characteristics to establish the third influence coefficient.

[0094] Furthermore, the second fitness constraint establishment module 15 is also used to perform the following steps: parsing the working records of the lubrication pump group to obtain the cumulative running time of each lubrication pump in the lubrication pump group; fitting the time-series decay effect of the lubrication pumps based on the actual state of the lubrication pumps and the cumulative running time of startup, and generating a penalized fitness using the fitting result of the time-series decay effect and the set of executable schemes; evaluating the load balance of the lubrication pumps based on the actual state of the lubrication pumps and the set of executable schemes, and establishing a balance fitness; and establishing a second fitness constraint based on the penalized fitness and the balance fitness.

[0095] Furthermore, the pressure collaborative control scheme establishment module 17 is also used to perform the following steps: execute historical operation data retrieval of the lubrication pump group to establish a historical operation dataset; identify the probability of abnormal operation of the lubrication pump group based on the historical operation dataset and establish anomaly penalties; configure emergency collaborative lubrication pumps with the anomaly penalties, perform scheme collaborative analysis and compensation based on the emergency collaborative lubrication pumps, and reconstruct the pressure collaborative control scheme.

[0096] Furthermore, the system is also used to perform the following steps: monitor the lubricating oil supply of the working equipment and establish supply monitoring feedback; when the supply monitoring feedback reports an abnormality at any time point, perform abnormality tracing and location; and call the emergency collaborative lubrication pump to perform emergency management based on the abnormality tracing and location results.

[0097] Furthermore, the third fitness constraint establishment module 16 is also used to perform the following steps: acquiring lubricating oil data in the lubricating pump group, and establishing a first quality deviation based on the lubricating oil data; acquiring lubricating pump cleaning data in the lubricating pump group, and establishing a second quality deviation; and using the first quality deviation and the second quality deviation to perform lubricating oil mixing penalty analysis to establish a third fitness constraint.

[0098] Furthermore, the system is also used to perform the following steps: establishing a prediction error compensation mechanism; after establishing a pressure collaborative control scheme, using the prediction error compensation mechanism to identify the deviation between the short-term actual lubrication demand and the predicted lubrication demand; and correcting the pressure collaborative control scheme based on the deviation identification results.

[0099] Furthermore, the system is also used to perform the following steps: establish a health record for the lubrication pump group, and continuously monitor the lubrication pump group through a multi-sensor network to establish a continuous monitoring dataset; perform abnormal trend prediction based on the continuous monitoring dataset and the health record, and establish a prediction compensation scheme based on the abnormal trend prediction results.

[0100] In summary, any step of the method described above can be stored as a computer instruction or program in an unrestricted computer memory, and can be called and identified by an unrestricted computer processor to implement any method in the embodiments of this application, without any additional restrictions.

[0101] Furthermore, the "first" or "second" mentioned above not only represents a sequential relationship but also a specific concept and / or refers to the possibility of selecting individual or all of multiple elements. Clearly, those skilled in the art can make various modifications and variations to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A method for coordinated pressure control of a lubrication pump group, characterized in that, The method includes: A multi-sensor network is deployed in the lubrication pump group, and the real status of the lubrication pumps is constructed based on the monitoring data of the multi-sensor network; Perform time series analysis on the working equipment to establish lubrication demand forecast results, wherein the lubrication demand forecast results include demand buffer nodes; Using the predicted lubrication demand as the control target, each lubrication pump in the lubrication pump group is treated as an independent intelligent agent. After synchronizing the actual state of the lubrication pumps, the task collaborative execution analysis of the independent intelligent agents is performed to establish a set of executable solutions. The set of executable solutions is subjected to collaborative start-stop switching frequency identification based on the demand buffer nodes, and a first fitness constraint is established. Using the actual state of the lubrication pump, an execution fitness analysis is performed under the set of executable solutions to establish a second fitness constraint; Based on the set of executable schemes, a mixing penalty analysis of the lubricating oil is performed to establish a third fitness constraint; By utilizing the first fitness constraint, the second fitness constraint, and the third fitness constraint, a collaborative analysis of the schemes is conducted to establish a collaborative pressure control scheme.

2. The pressure coordination control method for a lubrication pump group as described in claim 1, characterized in that, The step of identifying the coordinated start / stop switching frequency of the executable scheme set based on the demand buffer nodes and establishing a first fitness constraint includes: The set of executable schemes is used to identify the start-stop switching of the lubrication pump, and a first influence coefficient is established based on the total number of identifications; The total number of identifications performed falls into the required buffer node identification, and a second influence coefficient is established based on the identification results. Obtain the set of start / stop nodes that do not fall into the demand buffer node, identify the start / stop impact based on the set of start / stop nodes and the lubrication demand prediction result, and establish a third impact coefficient; The first fitness constraint is established using the first influence coefficient, the second influence coefficient, and the third influence coefficient.

3. The pressure coordination control method for a lubrication pump group as described in claim 2, characterized in that, The step of identifying the start-stop impact based on the start-stop node set and the lubrication demand prediction results, and establishing a third impact coefficient, includes: Based on the lubrication demand prediction results, establish the task importance characteristics and lubrication demand stability characteristics of the work tasks; After locating the lubrication pump using the aforementioned start / stop node set, a fluctuation analysis of the lubrication pump switching is performed to establish fluctuation analysis characteristics; The third influence coefficient is established by matching and identifying task importance features, lubrication demand stability features, and fluctuation analysis features using the matching and identification channel.

4. The pressure coordination control method for a lubrication pump group as described in claim 1, characterized in that, The step of performing execution fitness analysis on the set of executable solutions using the actual state of the lubrication pump, and establishing a second fitness constraint, includes: Analyze the working records of the lubrication pump group to obtain the cumulative running time of each lubrication pump in the lubrication pump group. The time-series decay effect of the lubrication pump is fitted based on the actual state of the lubrication pump and the cumulative running time since startup. The time-series decay effect fitting result and the set of executable schemes are used to generate a penalty fitness. The load balance of the lubrication pump is evaluated based on the actual state of the lubrication pump and the set of executable solutions, and a balance fitness is established. A second fitness constraint is established based on the penalty fitness and the balance fitness.

5. The pressure coordination control method for a lubrication pump group as described in claim 1, characterized in that, The step of using the first fitness constraint, the second fitness constraint, and the third fitness constraint to perform collaborative analysis of the schemes and establish a collaborative pressure control scheme includes: Execute historical operation data retrieval of the lubrication pump group to establish a historical operation dataset; Based on the historical operation dataset, identify the probability of operational anomalies in the lubrication pump group and establish anomaly penalties; An emergency collaborative lubrication pump is configured with the aforementioned abnormal penalty, and a collaborative analysis and compensation of the scheme is performed based on the emergency collaborative lubrication pump to reconstruct the pressure collaborative control scheme.

6. The pressure coordination control method for a lubrication pump group as described in claim 5, characterized in that, Following the reconfigured pressure collaborative control scheme, the following is included: Monitor the lubricating oil supply of the working equipment and establish a supply monitoring feedback mechanism; When the supply monitoring feedback is reported as an abnormal feedback at any time point, perform abnormal source tracing and location; Based on the anomaly tracing and location results, the emergency collaborative lubrication pump is invoked to perform emergency management.

7. The pressure coordination control method for a lubrication pump group as described in claim 1, characterized in that, The step of performing a mixing penalty analysis of the lubricating oil based on the executable scheme set and establishing a third fitness constraint includes: Obtain lubricating oil data from the lubrication pump group, and establish a first quality deviation based on the lubricating oil data; Obtain cleaning data of the lubrication pumps within the lubrication pump group to establish a second quality deviation. The first quality deviation and the second quality deviation are used to perform lubricant mixing penalty analysis to establish a third fitness constraint.

8. The pressure coordination control method for a lubrication pump group as described in claim 1, characterized in that, After establishing the pressure coordination control scheme, the following is included: Establish a prediction error compensation mechanism; After establishing the pressure coordination control scheme, the prediction error compensation mechanism is used to identify the deviation between the short-term actual lubrication demand and the predicted lubrication demand. The pressure coordination control scheme is modified based on the deviation identification results.

9. The pressure coordination control method for a lubrication pump group as described in claim 1, characterized in that, After establishing the pressure coordination control scheme, it also includes: Establish health records for the lubrication pump group and continuously monitor the lubrication pump group through a multi-sensor network to create a continuous monitoring dataset; Based on the continuous monitoring dataset and the health records, abnormal trends are predicted, and a prediction compensation scheme is established based on the abnormal trend prediction results.

10. A pressure coordination control system for a group of lubrication pumps, characterized in that, The system is used to perform the pressure coordination control method for the lubrication pump group according to any one of claims 1 to 9, the system comprising: The lubrication pump real-state construction module is used to deploy a multi-sensor network in the lubrication pump group and construct the real-state of the lubrication pump based on the monitoring data of the multi-sensor network. The lubrication demand forecasting result establishment module is used to perform time series analysis of the working equipment and establish lubrication demand forecasting results, wherein the lubrication demand forecasting results include demand buffer nodes; The executable solution set establishment module is used to take the lubrication demand prediction result as the control target, treat each lubrication pump in the lubrication pump group as an independent intelligent agent, and perform task collaborative execution analysis of the independent intelligent agents after synchronizing the actual state of the lubrication pumps to establish an executable solution set. The first fitness constraint establishment module is used to identify the collaborative start-stop switching frequency of the executable scheme set based on the demand buffer node and establish the first fitness constraint. The second fitness constraint establishment module is used to perform execution fitness analysis under the set of executable solutions using the actual state of the lubrication pump, and establish the second fitness constraint. The third fitness constraint establishment module is used to perform a mixing penalty analysis of the lubricating oil based on the executable scheme set and establish a third fitness constraint. The pressure collaborative control scheme establishment module is used to perform collaborative analysis of schemes using the first fitness constraint, the second fitness constraint, and the third fitness constraint to establish a pressure collaborative control scheme.

Images