A method and system for controlling liquid usage of a lubricating oil pump station

Abstract

The present invention discloses a method and system for controlling the use of liquid in a lubricating oil pump station, and relates to the field of liquid control. The method comprises: performing data collection to obtain a plurality of initial control data sets; extracting change fluctuation data to determine whether the change fluctuation data is within a preset fluctuation range; when within a preset fluctuation range, performing a liquid operation evaluation to generate a liquid operation control evaluation result; performing control optimization to generate optimal liquid control parameters; formulating a liquid control strategy, and executing the liquid control strategy on the lubricating oil pump station. The method solves the technical problem in the prior art that when the control valve adjusts the flow and pressure of the lubricating oil, there is a large error, which makes it difficult to meet the requirements of high-precision control, resulting in insufficient or excessive lubrication of the equipment during operation, thereby affecting the performance and life of the equipment. By analyzing the monitoring data and then optimizing it according to the genetic algorithm, the technical effect of improving the accuracy and stability of liquid control is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of fluid control, and specifically to a fluid control method and system for a lubricating oil pump station. Background Art

[0002] The lubricating oil pump station is an indispensable part of industrial equipment. It is responsible for providing the right amount of lubricating oil to the equipment to ensure the normal operation of the equipment and extend its service life. Therefore, the control and management of the lubricating oil pump station is crucial to the stability and efficiency of industrial production. Traditional lubricating oil pump stations usually use mechanical or electric control valves to adjust the flow and pressure of lubricating oil, but this control method has many shortcomings. Traditional mechanical or electric control valves often have large errors when adjusting the flow and pressure of lubricating oil, and it is difficult to meet the needs of high-precision control. This may cause insufficient or excessive lubrication of the equipment during operation, thereby affecting the performance and life of the equipment.

[0003] In summary, the prior art has a technical problem in which the control valve has a large error when adjusting the flow and pressure of the lubricating oil, making it difficult to meet the requirements of high-precision control, resulting in insufficient or excessive lubrication of the equipment during operation, thereby affecting the performance and life of the equipment. Summary of the invention

[0004] Based on this, it is necessary to provide a method and system for controlling the use of lubricating oil pumping stations in response to the above technical problems. By analyzing the monitoring data and then optimizing it according to the genetic algorithm, the technical effect of improving the accuracy and stability of the control of the use of lubricating oil is achieved.

[0005] In a first aspect, a method for controlling fluid usage of a lubricating oil pumping station is provided, the method comprising: collecting data on the lubricating oil pumping station to obtain a plurality of initial control data sets; extracting change fluctuation data of the plurality of initial control data sets, monitoring the change fluctuation data in real time, and determining whether the change fluctuation data is within a preset fluctuation range; when the change fluctuation data is within the preset fluctuation range, traversing the plurality of initial control data to perform fluid usage operation evaluation of the lubricating oil pumping station, and generating a fluid usage operation control evaluation result; performing control optimization on the plurality of initial control data sets based on the fluid usage operation control evaluation result, and generating optimal fluid usage control parameters; formulating a fluid usage control strategy based on the optimal fluid usage control parameters, and performing intelligent fluid usage control optimization on the lubricating oil pumping station by executing the fluid usage control strategy.

[0006] In a second aspect, a fluid control system for a lubricating oil pump station is provided, the system comprising: a data acquisition module, the data acquisition module is used to collect data for the lubricating oil pump station and obtain a plurality of initial control data sets; a real-time monitoring module, the real-time monitoring module is used to extract change fluctuation data of the plurality of initial control data sets, monitor the change fluctuation data in real time, and determine whether the change fluctuation data is within a preset fluctuation range; a fluid operation evaluation module, the fluid operation evaluation module is used to traverse the plurality of initial control data to perform fluid operation evaluation of the lubricating oil pump station when the change fluctuation data is within the preset fluctuation range, and generate a fluid operation control evaluation result; an optimal fluid control parameter generation module, the optimal fluid control parameter generation module is used to perform control optimization on the plurality of initial control data sets based on the fluid operation control evaluation result, and generate an optimal fluid control parameter; a fluid intelligent control optimization module, the fluid intelligent control optimization module is used to formulate a fluid control strategy based on the optimal fluid control parameters, and perform fluid intelligent control optimization on the lubricating oil pump station executing the fluid control strategy.

[0007] The above-mentioned liquid control method and system for a lubricating oil pump station solves the technical problem in the prior art that the control valve has large errors when adjusting the lubricating oil flow and pressure, making it difficult to meet the needs of high-precision control, resulting in insufficient or excessive lubrication of the equipment during operation, thereby affecting the performance and life of the equipment. By analyzing the monitoring data and then optimizing it according to the genetic algorithm, the technical effect of improving the accuracy and stability of liquid control is achieved.

[0008] 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

[0009] Figure 1 A schematic diagram of a flow chart of a method for controlling the use of liquid in a lubricating oil pump station in one embodiment;

[0010] Figure 2 A schematic diagram of a flow chart showing generation of change fluctuation data of a method for controlling the use of lubricating oil pumping station in one embodiment;

[0011] Figure 3 The present invention is a structural block diagram of a liquid control system of a lubricating oil pump station in one embodiment.

[0012] Explanation of the reference numerals: data acquisition module 11 , real-time monitoring module 12 , liquid operation evaluation module 13 , optimal liquid control parameter generation module 14 , liquid intelligent control optimization module 15 . DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0014] like Figure 1 As shown, the present application provides a method for controlling the use of lubricating oil in a lubricating oil pump station, the method comprising:

[0015] Data collection is performed on the lubricating oil pump station to obtain multiple initial control data sets.

[0016] The lubricating oil pump station is a system dedicated to providing lubricating oil. Its main purpose is to ensure that mechanical equipment obtains the necessary lubrication during operation to reduce wear, friction and heat generation, thereby extending the service life of the equipment and improving its operating efficiency. The working principle is to extract the lubricating oil from the oil storage tank through the lubrication pump and transport it to the equipment parts that need lubrication through pipelines. The control system can adjust the working parameters of the lubrication pump according to the lubrication requirements of the equipment to ensure that the equipment is properly lubricated. The lubricating oil forms an oil film at the lubrication point to reduce direct contact between metals, thereby preventing wear and friction and improving the operating efficiency and service life of the equipment. Liquid control refers to the process of monitoring, adjusting and managing the use of lubricating oil in the lubricating oil pump station. This process ensures that during the operation of mechanical equipment, the lubricating oil pump station can provide the right amount of lubricating oil to the lubrication point on demand, in a timely and accurate manner to meet the lubrication needs of the equipment. Traditional mechanical or electric control valves often have large errors when adjusting the flow and pressure of lubricating oil, and it is difficult to meet the needs of high-precision control, resulting in insufficient or excessive lubrication of the equipment during operation, thereby affecting the performance and life of the equipment. To this end, the present application provides a liquid control method for a lubricating oil pump station to improve the accuracy and stability of liquid control.

[0017] Data collection is performed on the lubricating oil pump station to determine the collection parameters. The parameters in this application include flow, pressure, temperature, and liquid level. Appropriate sensors and instruments are selected to ensure that the above parameters can be accurately and reliably measured. The data collection equipment is started to collect relevant data of the lubricating oil pump station. Based on the relevant data, multiple initial control data sets are generated. The multiple initial control data sets include flow, pressure, temperature, and liquid level. Each control data is a set of data for controlling the liquid. Through the above method, data collection is performed on the lubricating oil pump station, and multiple initial control data sets are obtained. The multiple initial control data sets will provide strong support for subsequent pump station management and optimization.

[0018] Extract the change fluctuation data of the multiple initial control data sets, monitor the change fluctuation data in real time, and determine whether the change fluctuation data is within a preset fluctuation range.

[0019] Extract the change fluctuation data of the multiple initial control data sets, calculate the change amount or change rate of each control parameter, such as lubricating oil flow, pressure, oil level, etc. at continuous time points, and calculate the difference or percentage change between adjacent data points to obtain the change fluctuation data. According to the operating experience, equipment specifications or industry standards of the pump station, a reasonable preset fluctuation range is set for each control parameter. The preset fluctuation range can reflect normal operating fluctuations and capture potential abnormalities or faults. Compare the real-time monitored change fluctuation data with the preset fluctuation range. If the change fluctuation data is within the preset range, it is considered that the pump station is in normal operation. If the change fluctuation data exceeds the preset range, an alarm or notification is triggered so that corresponding measures can be taken in time. Through the above method, the change fluctuation data of the initial control data set can be effectively extracted, and it can be monitored and judged in real time. This helps to discover potential problems or abnormalities in a timely manner and ensure the safe and stable operation of the pump station.

[0020] like Figure 2 As shown, a longitudinal coordinate axis is constructed based on the control data, and a transverse coordinate axis is constructed based on the change period of the control data; a control fluctuation coordinate system is constructed through the longitudinal coordinate axis and the transverse coordinate axis; the multiple initial control data are monitored regularly, and the multiple control monitoring data are synchronized to the control fluctuation coordinate system as coordinate points, and fluctuation calculations are performed on the multiple control monitoring data to generate the change fluctuation data.

[0021] Based on the numerical range of the control data, for example, the pressure, flow, oil level, etc. of the lubricating oil, it is defined to ensure that the vertical coordinate axis can cover all possible control data values, and consider appropriate scale intervals to clearly display the data. Based on the change cycle of the control data, it can be defined as time, such as hours, days, weeks, etc., or the number of operation cycles, batches, etc., to ensure that the horizontal coordinate axis can clearly display the changes of data over time or operation cycles. Use drawing tools to draw a control fluctuation coordinate system based on the vertical coordinate axis and the horizontal coordinate axis, set the scales and labels of the vertical coordinate axis and the horizontal coordinate axis, and regularly monitor the multiple initial control data, that is, regularly, such as every hour, every day, etc., obtain the initial control data of the lubricating oil pump station, and synchronize multiple control monitoring data as coordinate points to the control fluctuation coordinate system. For each data point on the coordinate system, the difference between it and the previous or next data point can be calculated as the fluctuation value of the point. More complex fluctuation calculation methods can also be used, such as calculating the standard deviation or variance of data points over a period of time to evaluate the fluctuation of the entire time period. Through the above method, an intuitive control fluctuation coordinate system is constructed, and it is used to monitor and analyze the fluctuation of the control data of the lubricating oil pump station, which helps to timely discover potential problems and take corresponding measures to deal with them, ensuring the safe and stable operation of the lubricating oil pump station.

[0022] When the change fluctuation data is within the preset fluctuation range, the plurality of initial control data are traversed to perform a fluid operation evaluation of the lubricating oil pump station, and a fluid operation control evaluation result is generated.

[0023] Determine whether the change fluctuation data is within the preset fluctuation range. When the change fluctuation data is within the preset fluctuation range, it indicates that the operating state of the lubricating oil pump station is relatively stable and within an acceptable range. In this case, it is reasonable to conduct a fluid operation evaluation of the lubricating oil pump station in order to understand the operating efficiency and performance of the pump station. Traverse all the collected multiple initial control data, analyze each parameter, extract key information from the data, and evaluate the fluid efficiency of the lubricating oil pump station. For example, analyze whether the consumption rate of the lubricating oil is consistent with expectations, whether there is waste or shortage, evaluate whether the pressure and flow of the lubricating oil pump station are stable, and whether they meet the needs of equipment operation; evaluate whether the temperature of the lubricating oil is stable, whether it will cause danger, etc.; based on the results of the fluid operation evaluation, generate a detailed control evaluation report, that is, the fluid operation control evaluation results, and the fluid operation control evaluation results at least include the overall operating status of the pump station, the fluctuation of key parameters, and the fluid efficiency analysis.

[0024] The fluctuation boundary extreme value is set based on the historical control data, and the preset fluctuation range is determined according to the fluctuation boundary extreme value; it is judged whether the change fluctuation data is within the preset fluctuation range; when the change fluctuation data is not within the preset fluctuation range, an alarm mechanism is triggered, and an alarm instruction is generated through the alarm mechanism; based on the alarm instruction, the change fluctuation data is traversed to extract an exceeded data set, and the exceeded data set includes initial control data points and initial control data volume that exceed the preset fluctuation range; based on the initial control data points and the initial control data volume that exceed the preset fluctuation range, the source is traced to obtain the source of abnormal fluctuation; the source of abnormal fluctuation is added as alarm content to the alarm instruction to perform abnormal correction on the multiple initial control data sets.

[0025] Based on the historical control data, the distribution and change characteristics of the data are analyzed, and the fluctuation boundary extreme value is set. The fluctuation boundary can be calculated based on the maximum value, minimum value, etc. of the historical data, and refers to the maximum value of the change fluctuation data. According to the set fluctuation boundary extreme value, the preset fluctuation range is determined. The preset fluctuation range is a range that can cover normal change fluctuations but is strict enough to avoid underreporting. The control data of the lubricating oil pump station is monitored in real time, and its change fluctuation data is calculated. The calculated change fluctuation data is compared with the preset fluctuation range. If the change fluctuation data exceeds the preset fluctuation range, the alarm mechanism is triggered. The alarm mechanism can be a logical judgment inside the software, or it can be an interface connected to an external alarm system, such as SMS, email, sound and light alarm, etc., which can also be referred to as triggering an alarm in this application. After the alarm mechanism is triggered, an alarm instruction is generated, and the alarm instruction should contain key information that exceeds the fluctuation range, such as a timestamp, a specific value that exceeds the range, etc. Traverse the change fluctuation data, extract the data set that exceeds the preset fluctuation range, including all the initial control data points that exceed the preset fluctuation range and the corresponding initial control data volume. Analyze the extracted excess data set to find out the source of abnormal fluctuations, including analysis of equipment status, operation records, environmental factors, etc. Add the source of abnormal fluctuations as alarm content to the alarm instruction, and clearly and accurately describe the situation and possible causes of abnormal fluctuations. According to the cause of abnormal fluctuations, perform abnormal correction on multiple initial control data sets. Corrective measures may include adjusting control parameters, repairing equipment, replacing parts, etc. The purpose of abnormal correction is to find out the abnormality of control data before optimizing the control data, eliminate the abnormal control data, and then proceed to the next step of optimizing the control data. Through the above method, an effective alarm mechanism is constructed to handle the change fluctuation data that exceeds the preset fluctuation range, and take corrective measures in time, which provides basic support for the subsequent optimization of liquid control.

[0026] Based on the fluid operation control evaluation result, control optimization is performed on the multiple initial control data sets to generate optimal fluid control parameters.

[0027] Based on the fluid operation control evaluation results, the multiple initial control data sets are controlled and optimized, and the fluid operation control evaluation results are analyzed to understand the performance of the lubricating oil pump station in terms of fluid efficiency, pressure stability, flow distribution, etc., identify the problems and bottlenecks in the current control strategy, such as excessive consumption, large pressure fluctuations, and uneven flow distribution, and the evaluation results are correlated with the initial control data sets to determine which control parameters have a significant impact on the fluid operation performance. According to the evaluation results and correlation analysis, a control optimization strategy is formulated, and key control parameters such as lubricating oil flow, pressure setting value, and oil pump duty cycle are considered to improve the fluid operation performance. A genetic algorithm is used to control and optimize the multiple initial control data sets. Through continuous monitoring and optimization, a set of optimal fluid control parameters is finally determined to maximize fluid efficiency, reduce energy consumption, and reduce maintenance costs while ensuring stable system operation. Through the above method, multiple initial control data sets are controlled and optimized based on the fluid operation control evaluation results to generate optimal fluid control parameters, thereby improving the operation efficiency and stability of the lubricating oil pump station.

[0028] The plurality of initial control data sets are encoded by using a genetic algorithm to generate individual encoded data sets; based on the individual encoded data sets, random selection and merging are performed to obtain an initialized population; the fitness of the initialized population is calculated according to the liquid operation control evaluation result to determine the fitness value of the i-th individual encoded data; it is determined whether the fitness value of the i-th individual encoded data is greater than or equal to a preset fitness threshold; if the fitness value of the i-th individual encoded data is less than the preset fitness threshold, the i-th individual encoded data corresponding to the fitness value of the i-th individual encoded data is added to the first data group, and the fitness value of the i+1-th individual encoded data is compared; whether the fitness value is greater than or equal to the preset fitness threshold; if the fitness value of the i+1th individual coded data is greater than or equal to the preset fitness threshold, then the i+1th individual coded data corresponding to the fitness value of the i+1th individual coded data is added to the second data group, and it is iterated until the fitness values ​​of all individual coded data in the initialized population are compared with the preset fitness threshold, and the first data group and the second data group are obtained; based on the second data group, the initialized population is iteratively optimized to output the optimal solution; the optimal solution is added to the optimal liquid control parameter for output.

[0029] Genetic algorithms are used to find optimal fluid control parameters in multiple initial control data sets. Multiple initial control data sets are encoded to generate individual encoded data sets, each of which represents a possible solution. Random selections are made from the individual encoded data sets and merged to form an initialization population. This population will serve as the starting point of the genetic algorithm. For each individual in the population, that is, each encoded control data set, its fitness value is calculated by the fluid operation control evaluation result, and the fitness value is used to measure the pros and cons of the individual in solving the problem. Determining the fitness value of the i-th individual coding data refers to the fitness value of the i-th individual coding data in the initialization population, studying it, and judging whether the fitness value of the i-th individual coding data is greater than or equal to the preset fitness threshold. The preset fitness threshold is set by the technician. If it is less than the threshold, the individual is added to the first data group, representing a poor solution, and finally all data with insufficient fitness are screened out, so the first data group is the eliminated data group; if it is greater than or equal to the threshold, and comparing whether the fitness value of the i+1th individual coding data is greater than or equal to the preset fitness threshold; if the fitness value of the i+1th individual coding data is greater than or equal to the preset fitness threshold, the i+1th individual coding data corresponding to the fitness value of the i+1th individual coding data is added to the second data group, and added to the second data group, that is, it represents a better solution. Use the second data group to perform subsequent operations of the genetic algorithm, such as selection, crossover, mutation, etc., to generate a new population. Repeat the fitness calculation, grouping operation and iterative optimization until the termination conditions are met, such as reaching the maximum number of iterations, finding a good enough solution, etc. After the iteration is completed, select the individual with the highest fitness value in the population as the optimal solution. Add the actual liquid control parameters to the optimal solution and output it. For example, there is a simple liquid control system whose initial control data set contains two parameters: pump speed (P) and liquid level (L). It is hoped that the genetic algorithm can find the best combination of pump speed and liquid level to maximize the system efficiency. Assuming that the range of pump speed (P) is [10, 50] and the range of liquid level (L) is [20, 80], real number coding can be used, and the pump speed and liquid level are directly used as coded individuals. Ten individuals, i.e., 10 combinations of pump speed and liquid level, are randomly generated as the initial population. For each individual, i.e., the combination of pump speed and liquid level, the fitness value is taken according to the evaluation results of liquid operation control, such as system efficiency, etc. Assuming that the preset fitness threshold is 80, each individual in the population is traversed. If its fitness value is less than 80, it is added to the first data group; if the fitness value is greater than or equal to 80, it is added to the second data group. The individuals in the second data group are used to perform genetic algorithm selection, crossover, mutation and other operations to generate a new population, and the fitness calculation and grouping operations are repeated until an individual with a sufficiently high fitness value is found or the maximum number of iterations is reached.After the iteration is completed, the individual with the highest fitness value is selected as the optimal solution, assuming that the pump speed is 45 and the liquid level is 60. This optimal solution is decoded and output, that is, the recommended optimal pump speed is 45 and the optimal liquid level is 60. Due to the complexity of the liquid control system, traditional optimization methods may have difficulty in finding the global optimal solution or dealing with the interaction between multiple control parameters. The global search capability and adaptability of the genetic algorithm enable it to effectively solve these problems, providing an efficient and flexible method for optimizing liquid control parameters.

[0030] All individual coding data in the second data group are used as parent individual data; cross-validation is performed based on the parent individual data, the individual coding data is updated, and offspring individual data is generated; new gene information is introduced to perform mutation operations on the offspring individual data, and the initialized population is iteratively optimized until the number of iterations reaches a preset number of iterations, and the optimal solution is output.

[0031] After fitness evaluation and grouping, the second data group, that is, individuals with fitness values ​​greater than or equal to the preset fitness threshold, is selected as the parent individual data, representing the better solution in the current population. Cross-validation is usually used to evaluate the performance of the model on unseen data, but in genetic algorithms, it refers to selecting two individuals from the parent individuals for crossover operation, which is a key step in genetic algorithms and simulates gene recombination in biological evolution. By randomly selecting crossover points, some genes of the two parent individuals are exchanged to generate new offspring individuals. This process can generate new gene combinations and help explore new solution space areas. Mutation operation is another important step in genetic algorithms, which simulates gene mutations in biological evolution. During the mutation process, some gene bits in the offspring individuals are randomly selected and changed, such as 0 to 1 and 1 to 0 in binary coding; adding noise in real number coding, etc. Introducing new gene information helps maintain the diversity of the population and prevents the algorithm from converging to the local optimal solution too early. Mutation operation has an important impact on the search ability and solution quality of the genetic algorithm. After crossover and mutation operations, new offspring individuals are obtained. These offspring individuals form a new population together with the parent individuals. Then, the individuals in the new population are evaluated according to the fitness function, and the selection, crossover, mutation and other operations are repeated for iterative optimization. In the iterative process, the elite retention strategy is used, that is, a certain number of optimal individuals are retained to directly enter the next generation to ensure that the algorithm can retain the optimal solution currently found. The iterative process will continue until the preset number of iterations is reached or other termination conditions are met, such as no significant improvement in the fitness value for multiple consecutive generations. After the iteration is completed, the individual with the highest fitness value in the population is selected as the optimal solution, representing the optimal combination of liquid control parameters. The optimal solution is decoded back to the actual liquid control parameters and output. These parameters can be used in actual systems to improve the operating efficiency and stability of the system. Through the above method, the genetic algorithm is used to effectively optimize the liquid control parameters and find the global optimal solution or a solution close to the global optimal solution. It has the advantages of strong global search ability, good adaptability, and easy implementation, and is suitable for various complex optimization problems.

[0032] A fluid control strategy is formulated based on the optimal fluid control parameters, and the fluid control strategy is executed on the lubricating oil pump station to perform intelligent fluid control optimization.

[0033] The optimal fluid control parameters output by the genetic algorithm are analyzed, including key control variables such as the operating speed of the pump, the flow rate of the lubricating oil, pressure, and temperature, to ensure that the optimal fluid control parameters correspond to which control points in the system. Based on the optimal fluid control parameters, a detailed fluid control strategy is formulated, including control objectives, control variables, control logic, and safety restrictions. The formulated fluid control strategy is converted into an executable program or instruction and imported into the control system of the lubricating oil pump station. Ensure that the control system can read the sensor data in real time and adjust the control variables according to the fluid control strategy. The fluid control strategy is executed on the lubricating oil pump station, and the lubricating oil pump station is controlled according to the fluid control strategy. Through the above method, the fluid control strategy formulated based on the optimal fluid control parameters can be effectively applied to the lubricating oil pump station to achieve intelligent fluid control optimization and improve the operating efficiency and stability of the system.

[0034] The optimal fluid control parameters are traversed to simulate fluid control of the lubricating oil pump station to obtain multiple fluid usage information, wherein the multiple fluid usage information includes usage condition information, usage quantity information, and usage frequency information; based on the usage condition information and the optimization target, the usage quantity information is detected for abnormality according to the usage frequency information to generate fluid abnormality information; the fluid abnormality information is traversed to match and extract with the fluid control parameters to formulate a fluid emergency plan; and the fluid emergency plan is added to the fluid control strategy.

[0035] Use the optimal fluid control parameters to simulate the fluid control of the lubricating oil pump station. Use simulation software or simulation system to simulate the operation of the lubricating oil pump station under different usage conditions and record relevant fluid usage information. Collect multiple fluid usage information from the simulation results, including usage condition information, such as equipment load, ambient temperature, operating time, etc.; usage information, the actual usage or consumption rate of lubricating oil; usage frequency information, the filling or circulation frequency of lubricating oil. Based on the usage condition information combined with the optimization goals, such as reducing energy consumption and increasing equipment life, the usage information is detected for anomalies according to the usage frequency information. The anomaly detection method includes: comparing the usage information with a preset threshold, and considering it as an anomaly if it exceeds the threshold. Through anomaly detection, abnormal fluid usage information is generated, which describes in detail the conditions, location, time and possible causes of the anomaly. Traverse the abnormal information of liquid usage and match and extract the liquid usage control parameters, analyze the relationship between the abnormality and the parameter setting, and formulate a liquid usage emergency plan, including emergency treatment measures, how to respond quickly and reduce losses when the abnormality occurs; parameter adjustment suggestions, propose suggestions for adjusting the liquid usage control parameters according to the cause of the abnormality; preventive measures, preventive measures or improvement measures proposed to prevent similar abnormalities from happening again. Add the formulated liquid usage emergency plan to the liquid usage control strategy to ensure that abnormal situations can be responded to quickly in actual operations. At the same time, according to the results of simulation and abnormality detection, make necessary adjustments and optimizations to the liquid usage control strategy to improve its adaptability and effectiveness. Through the above methods, the operation of the lubricating oil pump station is continuously monitored, and the liquid usage control strategy and emergency plan are adjusted and improved as necessary according to the actual situation. Through continuous practice and optimization, the efficiency and stability of the liquid usage control of the lubricating oil pump station can be improved.

[0036] Execute the fluid usage control strategy, and continuously monitor the lubricating oil pump station to obtain fluid usage monitoring data; set a fluid usage self-check cycle based on the fluid usage period record log of the lubricating oil pump station; retrieve fluid usage detection sample data from the fluid usage monitoring data set according to the fluid usage self-check cycle; control and track the fluid usage detection sample data, generate tracking data for evaluation, and optimize fluid usage intelligent control based on the evaluation results.

[0037] According to the established and verified fluid control strategy, the lubricating oil pump station is actually controlled. Ensure that all fluid equipment, sensors and control systems operate according to the predetermined strategy. Continuously monitor the lubricating oil pump station and collect fluid monitoring data in real time. These data should include key parameters such as lubricating oil usage, frequency of use, temperature, pressure, flow, etc. Analyze the periodic laws and patterns of lubricating oil use based on the fluid usage period record log of the lubricating oil pump station. According to these laws and patterns, set a reasonable fluid self-inspection cycle. The self-inspection cycle can be adjusted according to the actual operation and maintenance needs of the equipment. According to the set fluid self-inspection cycle, retrieve the corresponding fluid detection sample data from the fluid monitoring data set. These data should be able to reflect the operation and fluid status of the lubricating oil pump station during the cycle. Control and track the retrieved fluid detection sample data to generate tracking data. Evaluate the tracking data by comparing it with the preset standard value or historical data. The evaluation results can reflect the fluid efficiency, stability and potential problems of the lubricating oil pump station during the cycle. According to the evaluation results, intelligently optimize the fluid control strategy. This can include adjusting the amount, frequency or method of lubricating oil to adapt to the actual conditions and changes in equipment operation. The optimized control strategy should be able to improve the utilization efficiency of lubricating oil, reduce waste, and extend the service life of the equipment. In terms of executing the liquid control strategy and continuously monitoring the lubricating oil pumping station to achieve intelligent control optimization of liquid usage, the above method has the advantages of real-time collection and analysis of liquid monitoring data to ensure the accuracy and real-time nature of the data. Through data-based intelligent control optimization, the method can automatically adjust the control strategy to adapt to the actual operation and changes of the lubricating oil pumping station. The flexibility and adaptability of the control strategy are improved, which helps to achieve the advantages of more efficient liquid control.

[0038] like Figure 3 As shown, the embodiment of the present application includes a liquid control system of a lubricating oil pump station, the system comprising:

[0039] A data acquisition module 11, wherein the data acquisition module 11 is used to collect data from the lubricating oil pump station and obtain a plurality of initial control data sets;

[0040] A real-time monitoring module 12, the real-time monitoring module 12 is used to extract the change fluctuation data of the multiple initial control data sets, monitor the change fluctuation data in real time, and determine whether the change fluctuation data is within a preset fluctuation range;

[0041] A fluid operation evaluation module 13, wherein the fluid operation evaluation module 13 is used to traverse the plurality of initial control data to perform fluid operation evaluation of the lubricating oil pump station when the change fluctuation data is within the preset fluctuation range, and generate a fluid operation control evaluation result;

[0042] An optimal liquid usage control parameter generation module 14, the optimal liquid usage control parameter generation module 14 is used to perform control optimization on the multiple initial control data sets based on the liquid usage operation control evaluation result to generate optimal liquid usage control parameters;

[0043] The intelligent fluid control optimization module 15 is used to formulate a fluid control strategy based on the optimal fluid control parameters, and to optimize the intelligent fluid control of the lubricating oil pump station by executing the fluid control strategy.

[0044] Furthermore, the embodiment of the present application also includes:

[0045] A coordinate axis construction module, the coordinate axis construction module is used to construct a longitudinal coordinate axis based on the control data, and to construct a transverse coordinate axis based on a change period of the control data;

[0046] A coordinate system construction module, wherein the coordinate system construction module is used to construct a control fluctuation coordinate system through the longitudinal coordinate axis and the transverse coordinate axis;

[0047] A fluctuation calculation module is used to regularly monitor the multiple initial control data, synchronize the multiple control monitoring data as coordinate points to the control fluctuation coordinate system, perform fluctuation calculation on the multiple control monitoring data, and generate the change fluctuation data.

[0048] Furthermore, the embodiment of the present application also includes:

[0049] Setting a fluctuation boundary extreme value based on historical control data, and determining the preset fluctuation range according to the fluctuation boundary extreme value;

[0050] A change fluctuation data judgment module, the change fluctuation data judgment module is used to judge whether the change fluctuation data is within the preset fluctuation range;

[0051] An alarm mechanism triggering module, wherein the alarm mechanism triggering module is used to trigger an alarm mechanism when the change fluctuation data is not within the preset fluctuation range, and generate an alarm instruction through the alarm mechanism;

[0052] An exceeded data set extraction module, the exceeded data set extraction module is used to traverse the change fluctuation data based on the alarm instruction to extract the exceeded data set, the exceeded data set includes the initial control data points and the initial control data volume that exceed the preset fluctuation range;

[0053] An abnormal fluctuation source acquisition module, the abnormal fluctuation source acquisition module is used to trace the source based on the initial control data point and the initial control data volume that exceed the preset fluctuation range, and acquire the source of the abnormal fluctuation;

[0054] An abnormality correction module is used to add the abnormal fluctuation source as an alarm content to the alarm instruction to perform abnormality correction on the multiple initial control data sets.

[0055] Furthermore, the embodiment of the present application also includes:

[0056] An individual coded data set generation module, the individual coded data set generation module is used to encode the multiple initial control data sets using a genetic algorithm to generate an individual coded data set;

[0057] An initialization population acquisition module, the initialization population acquisition module is used to randomly select and merge based on the individual coding data sets to obtain an initialization population;

[0058] A fitness calculation module, the fitness calculation module is used to perform fitness calculation on the initialized population according to the liquid operation control evaluation result, and determine the fitness value of the i-th individual encoding data;

[0059] An individual coding data fitness value judgment module, wherein the individual coding data fitness value judgment module is used to judge whether the fitness value of the i-th individual coding data is greater than or equal to a preset fitness threshold;

[0060] An individual coding data fitness value adding module, wherein if the fitness value of the i-th individual coding data is less than a preset fitness threshold, the i-th individual coding data corresponding to the fitness value of the i-th individual coding data is added to the first data group, and the fitness value of the i+1-th individual coding data is compared to see whether it is greater than or equal to the preset fitness threshold;

[0061] An iteration module, wherein if the fitness value of the i+1th individual encoded data is greater than or equal to the preset fitness threshold, the i+1th individual encoded data corresponding to the fitness value of the i+1th individual encoded data is added to the second data group, thereby iterating until the fitness values ​​of all individual encoded data in the initialized population are compared with the preset fitness threshold, and the first data group and the second data group are obtained;

[0062] An optimal solution output module, the optimal solution output module is used to iteratively optimize the initialized population based on the second data group and output an optimal solution;

[0063] An optimal solution adding module is used to add the optimal solution to the optimal liquid usage control parameter for output.

[0064] Furthermore, the embodiment of the present application also includes:

[0065] A parent individual data module, the parent individual data module is used to use all individual coded data in the second data group as parent individual data;

[0066] A child individual data module, the child individual data module is used to perform cross-validation based on the parent individual data, update the individual coding data, and generate child individual data;

[0067] An iterative optimization module is used to introduce new gene information to perform mutation operations on the offspring individual data, iteratively optimize the initialized population until the number of iterations reaches a preset number of iterations, and output the optimal solution.

[0068] Furthermore, the embodiment of the present application also includes:

[0069] A liquid usage information acquisition module, the liquid usage information acquisition module is used to traverse the optimal liquid control parameters to simulate the liquid control of the lubricating oil pump station, and obtain a plurality of liquid usage information, wherein the plurality of liquid usage information includes usage condition information, usage amount information, and usage frequency information;

[0070] An abnormality detection module, the abnormality detection module is used to perform abnormality detection on the usage amount information according to the usage frequency information based on the usage condition information combined with the optimization target, and generate abnormal liquid usage information;

[0071] A matching and extraction module, the matching and extraction module is used to traverse the abnormal liquid usage information and the liquid usage control parameters for matching and extraction, and formulate a liquid usage emergency plan;

[0072] A liquid usage emergency plan adding module is used to add the liquid usage emergency plan to the liquid usage control strategy.

[0073] Furthermore, the embodiment of the present application also includes:

[0074] A continuous monitoring module, which is used to execute the fluid usage control strategy and continuously monitor the lubricating oil pump station to obtain fluid usage monitoring data;

[0075] A liquid usage self-check cycle setting module, which is used to set the liquid usage self-check cycle based on the liquid usage period record log of the lubricating oil pump station;

[0076] A liquid detection sample data calling module, the liquid detection sample data calling module is used to call the liquid detection sample data from the liquid monitoring data set according to the liquid self-test cycle;

[0077] A control tracking module is used to control and track the liquid detection sample data, generate tracking data for evaluation, and perform intelligent liquid control optimization according to the evaluation results.

[0078] For a specific embodiment of a liquid control system for a lubricating oil pump station, please refer to the embodiment of a liquid control method for a lubricating oil pump station described above, which will not be described in detail here. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0079] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0080] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application.

Claims

1. A method for controlling the use of lubricating oil in a lubricating oil pump station, characterized in that: The method comprises: Carry out data collection on the lubricating oil pump station to obtain multiple initial control data sets; Extracting change fluctuation data of the plurality of initial control data sets, monitoring the change fluctuation data in real time, and determining whether the change fluctuation data is within a preset fluctuation range; When the change fluctuation data is within the preset fluctuation range, the plurality of initial control data are traversed to perform a fluid operation evaluation of the lubricating oil pump station, and a fluid operation control evaluation result is generated; Based on the liquid operation control evaluation result, control optimization is performed on the multiple initial control data sets to generate optimal liquid control parameters; Formulate a fluid control strategy based on the optimal fluid control parameters, and optimize fluid intelligent control by executing the fluid control strategy on the lubricating oil pump station; Execute the fluid usage control strategy, and continuously monitor the lubricating oil pump station to obtain fluid usage monitoring data; Based on the lubricating oil pump station's lubricating oil usage period record log, set the lubricating oil usage self-check cycle; Retrieving liquid detection sample data from the liquid monitoring data set according to the liquid self-test cycle; Control and track the sample data of the liquid test, generate tracking data for evaluation, and optimize the liquid intelligent control according to the evaluation results; Wherein, the method comprises: Setting a fluctuation boundary extreme value based on historical control data, and determining the preset fluctuation range according to the fluctuation boundary extreme value; Determining whether the change fluctuation data is within the preset fluctuation range; When the change fluctuation data is not within the preset fluctuation range, an alarm mechanism is triggered, and an alarm instruction is generated through the alarm mechanism; Based on the alarm instruction, the change fluctuation data is traversed to extract an excess data set, wherein the excess data set includes initial control data points and initial control data amounts that exceed a preset fluctuation range; Tracing the source based on the initial control data point and the initial control data volume that exceed the preset fluctuation range to obtain the source of the abnormal fluctuation; adding the abnormal fluctuation source as alarm content to the alarm instruction to perform abnormal correction on the multiple initial control data sets; The method of performing control optimization on the multiple initial control data sets based on the liquid operation control evaluation result to generate optimal liquid control parameters includes: encoding the plurality of initial control data sets using a genetic algorithm to generate individual coded data sets; Perform random selection and merging based on the individual coding data sets to obtain an initialized population; Performing fitness calculation on the initialized population according to the evaluation result of the liquid operation control, and determining the fitness value of the i-th individual encoding data; Determine whether the fitness value of the i-th individual encoding data is greater than or equal to a preset fitness threshold; If the fitness value of the i-th individual encoded data is less than a preset fitness threshold, then the i-th individual encoded data corresponding to the fitness value of the i-th individual encoded data is added to the first data group, and the fitness value of the i+1-th individual encoded data is compared to see whether it is greater than or equal to the preset fitness threshold; If the fitness value of the i+1th individual coded data is greater than or equal to the preset fitness threshold, then the i+1th individual coded data corresponding to the fitness value of the i+1th individual coded data is added to the second data group, and the iteration is performed until the fitness values ​​of all individual coded data in the initialized population are compared with the preset fitness threshold, and the first data group and the second data group are obtained; Iteratively optimize the initialized population based on the second data group and output an optimal solution; The optimal solution is added to the optimal liquid usage control parameters for output.

2. A method for controlling the use of lubricating oil in a lubricating oil pump station as claimed in claim 1, characterized in that: Extracting the change fluctuation data of the plurality of initial control data sets, the method comprising: A vertical coordinate axis is constructed based on the control data, and a horizontal coordinate axis is constructed based on the change cycle of the control data; Constructing a controlled wave coordinate system through the longitudinal coordinate axis and the transverse coordinate axis; The multiple initial control data are monitored regularly, the multiple control monitoring data are synchronized to the control fluctuation coordinate system as coordinate points, and fluctuation calculation is performed on the multiple control monitoring data to generate the change fluctuation data.

3. A method for controlling the use of lubricating oil in a lubricating oil pump station as claimed in claim 1, characterized in that: Iteratively optimizing the initialization population based on the second data group and outputting an optimal solution, the method comprising: Taking all individual coded data in the second data group as parent individual data; Perform cross-validation based on the parent individual data, update the individual coding data, and generate the child individual data; New gene information is introduced to perform mutation operations on the individual data of the offspring, and the initialized population is iteratively optimized until the number of iterations reaches a preset number of iterations, and the optimal solution is output.

4. A method for controlling the use of lubricating oil in a lubricating oil pump station as claimed in claim 1, characterized in that: Methods include: Traversing the optimal fluid control parameters to simulate fluid control of the lubricating oil pump station, and obtaining a plurality of fluid usage information, wherein the plurality of fluid usage information includes usage condition information, usage amount information, and usage frequency information; Based on the usage condition information and the optimization target, the usage amount information is subjected to abnormality detection according to the usage frequency information to generate abnormal liquid usage information; Traversing the abnormal liquid usage information and matching and extracting the liquid usage control parameters, and formulating a liquid usage emergency plan; The fluid usage emergency plan is added to the fluid usage control strategy.

5. A liquid control system for a lubricating oil pump station, characterized in that: The system is used to implement the liquid control method of a lubricating oil pump station according to any one of claims 1 to 4, and the system comprises: A data acquisition module, wherein the data acquisition module is used to collect data from the lubricating oil pump station and obtain multiple initial control data sets; A real-time monitoring module, the real-time monitoring module is used to extract the change fluctuation data of the multiple initial control data sets, monitor the change fluctuation data in real time, and determine whether the change fluctuation data is within a preset fluctuation range; A fluid operation evaluation module, wherein when the change fluctuation data is within the preset fluctuation range, the fluid operation evaluation module traverses the plurality of initial control data to perform a fluid operation evaluation of the lubricating oil pump station and generates a fluid operation control evaluation result; An optimal liquid usage control parameter generation module, the optimal liquid usage control parameter generation module is used to perform control optimization on the multiple initial control data sets based on the liquid usage operation control evaluation result to generate optimal liquid usage control parameters; The intelligent fluid control optimization module is used to formulate a fluid control strategy based on the optimal fluid control parameters, and to optimize the intelligent fluid control of the lubricating oil pump station by executing the fluid control strategy.

Images