Turbine volute cleaning control method and platform based on twin simulation

Abstract

The present invention discloses a turbine volute cleaning control method and platform based on twin simulation, which relates to the field of intelligent control technology. The method includes: using a sensor device group to collect real-time data of a target turbine volute, building a three-dimensional twin model based on this and its structural information, setting multiple cleaning scenarios containing cleaning parameters, performing multiple cleaning simulations through models and parameters to obtain results and formulate strategies, evaluating the simulation results to optimize the control strategy, and finally combining the model to execute the optimization strategy to perform intelligent cleaning control on the target turbine volute. The technical problems of unsatisfactory cleaning effect, low degree of automation and poor adaptability to different turbine volutes in the existing turbine volute cleaning method are solved, and the intelligent, precise and efficient cleaning of the turbine volute is achieved, and the technical effect of the cleaning quality is guaranteed.

Description

Technical Field

[0001] The present application relates to the field of intelligent control technology, and in particular to a turbine volute cleaning control method and platform based on twin simulation. Background Art

[0002] In the turbocharger cleaning technology scenario, the demand for efficient cleaning of turbochargers of different specifications is extremely prominent, and the contradiction between cleaning effect and efficiency is relatively more obvious. Achieving efficient and accurate cleaning operations and better adapting to the cleaning needs of different specifications have become the key to improving turbocharger cleaning technology. Traditional turbocharger cleaning technology is usually extensive and one-sided, relying more on manual operation or simple equipment, and is insufficient in overall response to the complex structure of turbochargers. It lacks in-depth research and application of various cleaning data, and it is difficult to comprehensively and accurately evaluate the cleaning difficulty and needs of turbochargers of different specifications. There are unreasonable situations in the allocation of cleaning resources, resulting in incomplete cleaning of some turbochargers of complex specifications, and excessive use of cleaning resources for some turbochargers of simple specifications. The formulation of cleaning plans is relatively rigid and fixed, and cannot cope well with the diverse actual cleaning situations of turbochargers.

[0003] In the current related technologies, there are technical problems in the turbine volute cleaning method, such as unsatisfactory cleaning effect, low degree of automation and poor adaptability to different turbine volutes. Summary of the invention

[0004] The present application provides a turbine volute cleaning control method and platform based on twin simulation, adopts a sensor equipment group to collect real-time data of the target turbine volute, builds a three-dimensional twin model based on this and its structural information, sets multiple cleaning scenarios containing cleaning parameters, performs multiple cleaning simulations through the model and parameters to obtain results and formulate strategies, evaluates the simulation results to optimize the control strategy, and finally combines the model to execute the optimization strategy to perform intelligent cleaning control on the target turbine volute. By constructing a three-dimensional twin model and performing simulated cleaning, the cleaning control strategy is dynamically optimized to adapt to different operating environments and pollutant conditions, thereby achieving intelligent, precise and efficient cleaning of the turbine volute and ensuring the technical effect of cleaning quality.

[0005] The present application provides a turbine volute cleaning control method based on twin simulation, including:

[0006] A target turbine volute is collected in real time by a sensor device group to obtain multiple real-time sensor data groups; a three-dimensional twin model of the target turbine volute is constructed based on the multiple real-time sensor data groups and combined with the structural information of the target turbine volute; multiple operating environment information of the target turbine volute is traversed to set multiple cleaning scenarios, and the multiple cleaning scenarios include multiple cleaning parameters; multiple cleaning simulations are performed multiple times using the three-dimensional twin model of the target turbine volute in combination with the multiple cleaning parameters to obtain multiple cleaning simulation results and formulate a cleaning control strategy; the multiple cleaning simulation results are evaluated, and the cleaning control strategy is dynamically optimized according to the multiple cleaning evaluation results to generate a cleaning control optimization strategy; the cleaning control optimization strategy is executed in combination with the three-dimensional twin model of the target turbine volute to perform intelligent cleaning control on the target turbine volute.

[0007] This application also provides a turbine volute cleaning control platform based on twin simulation, including:

[0008] A sensor data group acquisition module, the sensor data group acquisition module is used to collect real-time data of the target turbine volute through a sensor device group to obtain multiple real-time sensor data groups; a three-dimensional twin model construction module, the three-dimensional twin model construction module is used to construct a three-dimensional twin model of the target turbine volute based on the multiple real-time sensor data groups and combined with the structural information of the target turbine volute; a cleaning scene setting module, the cleaning scene setting module is used to traverse multiple operating environment information of the target turbine volute to set multiple cleaning scenes, and the multiple cleaning scenes include multiple cleaning parameters; a cleaning control strategy formulation module, the cleaning control strategy formulation module is used to use the three-dimensional twin model of the target turbine volute, combined with the multiple cleaning parameters to perform multiple cleaning simulations, obtain multiple cleaning simulation results, and formulate a cleaning control strategy; a cleaning control optimization strategy generation module, the cleaning control optimization strategy generation module is used to evaluate the multiple cleaning simulation results, dynamically optimize the cleaning control strategy according to the multiple cleaning evaluation results, and generate a cleaning control optimization strategy; an intelligent cleaning control module, the intelligent cleaning control module is used to execute the cleaning control optimization strategy in combination with the three-dimensional twin model of the target turbine volute to perform intelligent cleaning control on the target turbine volute.

[0009] The turbine volute cleaning control method and platform based on twin simulation proposed in this application first collects data of the target turbine volute in real time through a sensor equipment group to obtain multiple real-time sensor data groups. Based on the multiple real-time sensor data groups and combined with the structural information of the target turbine volute, a three-dimensional twin model of the target turbine volute is constructed, and multiple operating environment information of the target turbine volute is traversed to set multiple cleaning scenarios. The three-dimensional twin model of the target turbine volute is used to perform multiple cleaning simulations in combination with multiple cleaning parameters to obtain multiple cleaning simulation results, formulate a cleaning control strategy, evaluate the multiple cleaning simulation results, dynamically optimize the cleaning control strategy according to the multiple cleaning evaluation results, generate a cleaning control optimization strategy, and execute the cleaning control optimization strategy in combination with the three-dimensional twin model of the target turbine volute to perform intelligent cleaning control of the target turbine volute, thereby achieving intelligent, precise and efficient cleaning of the turbine volute and ensuring the technical effect of cleaning quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0011] Figure 1 A schematic flow chart of a turbine volute cleaning control method based on twin simulation provided in an embodiment of the present application;

[0012] Figure 2 A schematic diagram of the structure of a turbine volute cleaning control platform based on twin simulation provided in an embodiment of the present application.

[0013] Explanation of the accompanying drawings: sensor data group acquisition module 10, three-dimensional twin model construction module 20, cleaning scene setting module 30, cleaning control strategy formulation module 40, cleaning control optimization strategy generation module 50, intelligent cleaning control module 60. DETAILED DESCRIPTION

[0014] 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.

[0015] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0016] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0017] The present application embodiment provides a turbine volute cleaning control method based on twin simulation, such as Figure 1 As shown, the method includes:

[0018] Step S100, real-time data collection of the target turbine volute is performed through a sensor device group to obtain multiple real-time sensor data groups.

[0019] Specifically, the real-time sensor data group refers to a combination of multiple sensor data recorded by the sensor equipment group when monitoring the target turbine volute. The corresponding sensor equipment group is prepared, and then the sensor equipment group is installed at the key position of the target turbine volute. After setting the relevant parameters, the sensor equipment group is started for real-time monitoring, thereby obtaining multiple real-time sensor data such as target temperature value recording data, target pressure value recording data, and target flow value recording data. The real-time sensor data are combined together to form multiple real-time sensor data groups, which reflect the various status information of the target turbine volute at a specific moment.

[0020] Step S200, based on the multiple real-time sensor data groups and combined with the structural information of the target turbine volute, construct a three-dimensional twin model of the target turbine volute.

[0021] Specifically, according to the structural characteristics, functional requirements and relevant technical standards of the target turbine volute, combined with the multiple real-time sensor data groups obtained, a three-dimensional twin model of the target turbine volute is constructed. Among them, various real-time status information about the target turbine volute, such as temperature distribution, pressure conditions, etc., is obtained by analyzing the real-time sensor data group. The structural information of the target turbine volute includes its overall appearance, internal structure, and specific parameters of each component. When this information is integrated with each other, professional modeling techniques and tools are used to build the model. In this process, the detailed performance of the model should be continuously adjusted and improved according to the real-time data to ensure that the model can accurately reflect the actual state of the target turbine volute. Similar to when the temperature data of a certain area in the model reaches a specific value, the corresponding model part needs to be adjusted accordingly, or when the pressure data shows a specific change, the relevant part of the model also needs to be simulated accordingly. Finally, through continuous adjustment and optimization, a three-dimensional twin model that can accurately reflect the actual situation of the target turbine volute is successfully constructed.

[0022] In a possible implementation, step S200 further includes step S210, scanning the target turbine volute by means of a scanning device, and obtaining a size information set and a shape information set of the target turbine volute based on the scanning data. Specifically, according to the scanning characteristics and information requirements of the target turbine volute, the number of dimensions of the size information set is set. The number of dimensions of the size information set is the number of different size parameters involved in describing the size information of the target turbine volute. This number is at least multiple, that is, there are at least multiple different size parameters to fully reflect the size of the target turbine volute. Similarly, the number of categories of the shape information set is set. The number of categories of the shape information set is the number of different shape features covered when describing the shape information of the target turbine volute. This number is also at least multiple to meet the requirements of the detailed characterization of the target turbine volute shape in many aspects.

[0023] Step S220, determine the structural information of the target turbine volute based on the size information set and the shape information set of the target turbine volute. Specifically, the structural information of the target turbine volute is determined based on the size information set, shape information set, performance requirements and actual application scenarios of the target turbine volute. The structural information is obtained when analyzing the target turbine volute. When these factors are comprehensively considered, it means that the structure of the target turbine volute is clearly understood and the next step can be performed. Similarly, the specific construction details of the target turbine volute are further clarified, that is, when the structural information is deeply explored, when these specific details are clarified, the structure of the target turbine volute is more deeply understood, and various parameter standards of the target turbine volute are set. The various parameter standards are when evaluating and using the target turbine volute. When various parameters reach or meet these standards, it is considered that the relevant processing of the target turbine volute in terms of structure has been completed.

[0024] Step S230, using digital twin technology, construct an initial three-dimensional model based on the structural information of the target turbine volute. Specifically, based on the specific needs, structural characteristics and functional requirements of the target turbine volute, make full use of digital twin technology to determine the construction parameters of the initial three-dimensional model. Digital twin technology uses digital mapping and simulation of physical entities. First, based on the actual situation of the target turbine volute, it uses its powerful data collection and analysis capabilities to obtain detailed information about the overall structure and dimensional relationships. Based on this information, the basic framework parameters of the model are accurately set in the digital twin system. When the framework construction of the model in the digital twin environment reaches the state specified by these parameters, the framework construction phase is declared over. With the help of digital twin technology, in-depth analysis of the target turbine volute is carried out. The specific shapes and features of the various components of the turbine volute are measured, and its advanced modeling algorithms and visualization tools are used to accurately determine the shaping parameters of each component. When each component is shaped in the virtual space of the digital twin and meets the requirements corresponding to these parameters, the shaping stage of the corresponding component is successfully completed. Using digital twin technology, special coordination parameters are set according to the overall coordination requirements of the model. During the simulation construction process of the digital twin, real-time monitoring and adjustment are carried out. When the model reaches the coordination and accuracy standards specified by the parameters in the virtual space, it means that the initial three-dimensional model has been completed, and the entire construction process using digital twin technology is successfully completed.

[0025] Step S240, mapping the multiple real-time sensor data groups to the initial three-dimensional model for updating, and constructing the three-dimensional twin model of the target turbine volute. Specifically, multiple real-time sensor data groups are obtained, and the data groups contain various real-time status information of the target turbine volute during actual operation, such as temperature, pressure, speed, etc. The digital twin technology platform is started, the initial three-dimensional model is imported into the system, and each real-time sensor data group is matched and mapped with the initial three-dimensional model one by one. Through the data interface, the specific values ​​in the real-time sensor data are associated with the corresponding positions or components on the model. In the mapping process, according to the changes in real-time data, the initial three-dimensional model is dynamically adjusted and updated. For example, when the temperature sensor data shows that the temperature in a certain area rises, the corresponding position on the model will be reflected in the form of color changes, display values, etc. For other real-time data such as pressure and speed, corresponding visualization updates are also performed on the model according to their characteristics and influences, such as changes in the shape of the model, changes in the motion state of the components, etc., and the real-time sensor data is continuously received and processed. The initial three-dimensional model gradually evolves into a three-dimensional twin model that can reflect the real state of the target turbine volute in real time. After continuous mapping and updating, the three-dimensional twin model of the target turbine volute is finally successfully constructed.

[0026] Step S300, traversing multiple operating environment information of a target turbine volute to set multiple cleaning scenarios, wherein the multiple cleaning scenarios include multiple cleaning parameters.

[0027] Specifically, multiple operating environment information of the target turbine volute is collected, including various factors such as different working scenarios, temperature ranges, humidity conditions, usage frequency, pollutant types, etc., and the operation is traversed to analyze each operating environment information one by one, and the corresponding cleaning scenario is set according to its characteristics and needs. According to the operating characteristics and cleaning needs of the target turbine volute, the incremental constraint range of the cleaning intensity is set, such as determining the appropriate cleaning method and cleaning agent for a specific type of pollutant; adjusting the cleaning intensity and frequency according to different temperatures and humidity; planning a reasonable cleaning cycle according to the frequency of use, etc. For each cleaning scenario, multiple cleaning parameters are set in detail. The cleaning parameters may include a series of specific and detailed indicators such as the specific steps of cleaning, the types and specifications of the required cleaning tools, the amount and concentration of the cleaning agent, the time arrangement of the cleaning operation, the configuration of the cleaning personnel, etc., and are demonstrated and optimized in combination with the actual situation, and multiple complete cleaning scenarios are gradually constructed. Each scenario is equipped with corresponding multiple cleaning parameters, and all the set cleaning scenarios and cleaning parameters are evaluated and reviewed as a whole to check whether there are omissions or unreasonableness, and to make corrections and improvements in time, providing a comprehensive, specific and effective guidance plan for the cleaning work of the target turbine volute under different operating environments.

[0028] In a possible implementation, step S300 further includes step S310, performing traversal analysis on the multiple operating environment information of the target turbine volute to determine a pollutant parameter set of the target turbine volute, wherein the pollutant parameter set includes a pollution property parameter, a pollution attachment parameter, and a pollution distribution parameter. Specifically, a traversal analysis is performed on the multiple operating environment information of the target turbine volute, each operating environment information is studied, and the pollutant parameter set of the target turbine volute is determined.

[0029] Step S320 , determining a plurality of cleaning devices according to the pollution property parameters, determining a plurality of cleaning agents according to the pollution attachment parameters, and determining a plurality of cleaning methods according to the pollution distribution parameters. Specifically, when determining the pollutant parameter set, for the pollution property parameters, the specific chemical properties, physical forms and other aspects of the pollutants are analyzed in detail to clarify what type of pollution it belongs to, such as dust, oil, chemicals, etc. For the pollution attachment parameters, the degree of attachment, viscosity and other characteristics of the pollutants to the surface of the turbine volute are deeply explored to understand the firmness of their attachment. For the pollution distribution parameters, the distribution of pollutants in various parts of the turbine volute is accurately grasped, whether they are concentrated in certain areas or distributed more evenly. According to the determined pollution property parameters, multiple cleaning equipment that matches them is selected from a large number of cleaning equipment. For example, for pollutants of certain specific properties, special vacuuming equipment, high-pressure cleaning equipment, etc. may be required. According to the pollution attachment parameters, multiple cleaning agents that can effectively remove pollutants in the corresponding attachment state are selected. Cleaners with strong decontamination ability or special dissolving properties may be required. According to the pollution distribution parameters, multiple appropriate cleaning methods are determined, such as local key cleaning, full coverage cleaning and other different strategies. The selected multiple cleaning equipment, multiple cleaning agents and multiple cleaning methods are added to the multiple cleaning parameters. The cleaning parameters will specifically guide the subsequent cleaning operations, including which equipment to use, what kind of cleaning agents and what cleaning methods to adopt.

[0030] Step S330, adding the multiple cleaning devices, the multiple cleaning agents, and the multiple cleaning methods to the multiple cleaning parameters, and combining the multiple operating environment information to set the multiple cleaning scenes. Specifically, combining the multiple operating environment information analyzed previously, taking into full consideration the influence of factors such as temperature, humidity, and frequency of use in the environment on cleaning, multiple cleaning scenes are set, and each cleaning scene includes the corresponding cleaning parameters under a specific operating environment, so as to ensure efficient, thorough, and safe cleaning effects in different operating environments, and to ensure the normal operation and performance of the target turbine volute.

[0031] Step S400, using the three-dimensional twin model of the target turbine volute and combining the multiple cleaning parameters to perform multiple cleaning simulations, obtain multiple cleaning simulation results, and formulate a cleaning control strategy.

[0032] Specifically, a 3D twin model of the target turbine volute is obtained, and multiple cleaning parameters are set, including specific information such as cleaning equipment, cleaning agents, and cleaning methods. The cleaning simulation program is started, and the 3D twin model is used as the basic scene. Different cleaning parameter combinations are input into the simulation system one by one. During each cleaning simulation, the system simulates the operation of the cleaning equipment, the effect of the cleaning agent, and the implementation process of the cleaning method according to the input cleaning parameters. For example, the working path and action of a specific cleaning equipment on the 3D twin model are simulated, how the cleaning agent interacts with and removes contaminants, and how the cleaning method covers the entire model area. As the simulation progresses, the system records and analyzes various data in real time, including the cleaning effect, time required, and energy consumption. Resource consumption and other aspects are taken into consideration to obtain a complete cleaning simulation result. Repeating the simulation of different cleaning parameter combinations for multiple times will result in multiple cleaning simulation results. Comprehensively evaluate and analyze the cleaning simulation results, compare the advantages and disadvantages of different parameter combinations, analyze cleaning effects, efficiency, costs and other factors. Based on the in-depth understanding and analysis of multiple cleaning simulation results, formulate the most optimized cleaning control strategy. The strategy clearly stipulates which cleaning parameter combinations should be selected for actual cleaning operations under different situations and requirements to achieve the best cleaning effect and resource utilization efficiency. The formulated cleaning control strategy will be archived and managed so that it can be quickly and accurately called and executed when the target turbine volute needs to be cleaned.

[0033] In a possible implementation, step S400 further includes step S410, setting simulation boundary conditions and simulation initial conditions based on the multiple cleaning parameters. Specifically, the multiple cleaning parameters are analyzed, and the cleaning parameters may include the specific type and performance parameters of the cleaning equipment, the chemical composition and concentration of the cleaning agent, the specific operation process and requirements of the cleaning method, etc. The simulation boundary conditions are set according to the relevant information in the cleaning parameters, for example, the boundaries of the simulation space are determined according to the working range and limitations of the cleaning equipment, and the areas in which the cleaning simulation is performed are specified; or the activity range of the relevant substances in the simulation is limited according to the effective range of action of the cleaning agent, and the initial state of the cleaning process is considered to set the simulation initial conditions, including the initial pollution distribution, the initial temperature, pressure and other environmental conditions, for example, the specific location and degree of pollution on the turbine volute at the initial time are determined, or the temperature and pressure values ​​in the simulated environment at the initial time are set. In the setting process, the mutual relationship and influence between the various cleaning parameters should be fully considered to ensure that the simulation boundary conditions and the simulation initial conditions can accurately reflect the key features and constraints of the actual cleaning scene, and the simulation boundary conditions and the simulation initial conditions are constantly checked and adjusted to ensure the rationality and accuracy of the setting, and provide a reliable foundation and framework for the subsequent cleaning simulation.

[0034] Step S420: randomly combine the multiple cleaning devices, the multiple cleaning agents, and the multiple cleaning methods to generate a first cleaning parameter, a second cleaning parameter, ... an Nth cleaning parameter, where N is an integer greater than 2. Specifically, it is clear that there are multiple cleaning devices, multiple cleaning agents and multiple cleaning methods, each of which contains a variety of different specific options, and a random combination operation is performed. A device is randomly selected from the multiple cleaning devices, and then a cleaning agent is randomly selected from the multiple cleaning agents, and then a cleaning method is randomly determined from the multiple cleaning methods. The equipment, cleaning agent and method constitute a preliminary combination. This combination is marked and defined as the first cleaning parameter. The above random selection process is repeated to select different cleaning devices, cleaning agents and cleaning methods to form a new combination, which is marked as the second cleaning parameter. The random selection and combination steps are repeated continuously, and a new combination is generated each time, which is marked as the third cleaning parameter, the fourth cleaning parameter... until the Nth cleaning parameter. In the whole process, due to the random combination, each cleaning parameter is unique, including different combinations of cleaning devices, cleaning agents and cleaning methods, resulting in a large number of diverse cleaning parameter combinations, which provides rich materials and possibilities for subsequent cleaning simulations and helps to comprehensively explore the cleaning effects and optimal solutions under different conditions.

[0035] Step S430, according to the simulation initial conditions, start the three-dimensional twin model to introduce the simulation boundary conditions as constraints, perform cleaning simulation according to the first cleaning parameters, and obtain a first cleaning record data set, wherein the first cleaning record data set includes first cleaning flow trajectory data, first cleaning flow velocity distribution data, and a first pollution removal rate. Specifically, according to the previously set simulation initial conditions, the three-dimensional twin model is started and operated. The model is in a specific starting state, representing the actual situation before the cleaning work begins. The simulation boundary conditions are introduced into the model. The boundary conditions are like adding restrictions and constraints to the operating range and behavior rules of the model to ensure that the simulation process conforms to the actual possible situation. The cleaning simulation is performed according to the first cleaning parameters, which means that the model will perform dynamic calculations and simulations according to the information such as cleaning equipment, cleaning agents and cleaning methods specified by the first cleaning parameters. During the simulation, the model will record various relevant data in real time. Specifically, the first cleaning flow trajectory data will be obtained, which describes in detail the specific path and direction of the material flow during the cleaning process, and can intuitively display the dynamic process of cleaning; the first cleaning flow velocity distribution data reflects the flow velocity changes and distribution at different positions, which is very important for understanding the cleaning effect and efficiency; at the same time, the first pollution removal rate will be obtained, which is a key indicator that directly reflects the degree and effect of pollution removal in this cleaning work. Through the above series of operations and records, the first cleaning record data set is finally formed, which contains the above-mentioned detailed first cleaning flow trajectory data, first cleaning flow velocity distribution data and first pollution removal rate and other important information.

[0036] Step S440, according to the simulation initial conditions, start the three-dimensional twin model to introduce the simulation boundary conditions as constraints, perform cleaning simulation according to the second cleaning parameters, and iterate until the cleaning simulation is performed according to the Nth cleaning parameters to obtain a second cleaning record data set...the Nth cleaning record data set, the second cleaning record data set includes second cleaning flow trajectory data, second cleaning flow velocity distribution data, and second pollution removal rate, and the Nth cleaning record data set includes Nth cleaning flow trajectory data, Nth cleaning flow velocity distribution data, and Nth pollution removal rate. Specifically, the three-dimensional twin model is started according to the set simulation initial conditions, and the model is allowed to enter a certain starting state. This state represents the initial situation of the cleaning scene, and the simulation boundary conditions are introduced into the model as constraints on the model operation to ensure that the simulation process is carried out within a reasonable range. The cleaning simulation is carried out according to the second cleaning parameters. The model will dynamically calculate and simulate the specific contents of the cleaning equipment, cleaning agents, cleaning methods, etc. in the second cleaning parameters. The model will record the data related to this simulation in detail, thereby forming a second cleaning record data set, which includes the second cleaning flow trajectory data that can reflect the cleaning process, showing the specific path of the material flow during the cleaning process; the second cleaning flow velocity distribution data, showing the changes in flow velocity in different areas condition; and the second pollution removal rate, which is the key indicator for evaluating the cleaning effect. After completing the simulation of the second cleaning parameter, continue to iterate and perform cleaning simulation according to the third cleaning parameter. Similarly, record the corresponding third cleaning record data set, including the third cleaning flow trajectory data, the third cleaning flow velocity distribution data and the third pollution removal rate, etc., and so on. Repeat this process until the cleaning simulation is performed according to the Nth cleaning parameter. Each iteration can obtain a unique cleaning record data set, which respectively contains the corresponding cleaning flow trajectory data, cleaning flow velocity distribution data and pollution removal rate. Comprehensively analyze and compare the cleaning simulation conditions under different cleaning parameter combinations, and provide rich and detailed data support for the final determination of the optimal cleaning solution.

[0037] Step S450, based on the first cleaning flow trajectory data, the first cleaning flow velocity distribution data, the first pollution removal rate...the Nth cleaning flow trajectory data, the Nth cleaning flow velocity distribution data, the Nth pollution removal rate are randomly extracted to obtain the i-th cleaning flow trajectory data, the i-th cleaning flow velocity distribution data, and the i-th pollution removal rate, where i is a random positive integer less than or equal to N. Specifically, an Nth cleaning record data set is obtained, each of which contains specific cleaning flow trajectory data, cleaning flow velocity distribution data and pollution removal rate, and a random extraction operation is started. A random number generation mechanism or other random selection method is used to extract a random positive integer i from these data sets, where i satisfies and is less than or equal to N. According to the determined i value, the corresponding i-th cleaning flow trajectory data, i-th cleaning flow velocity distribution data and i-th pollution removal rate are obtained from the corresponding i-th cleaning record data set. Due to random extraction, each operation may obtain a different i value, thereby obtaining different i-th cleaning flow trajectory data, i-th cleaning flow velocity distribution data and i-th pollution removal rate. Through random extraction, a part of a large amount of data is randomly selected for analysis and research, which provides sample diversity and randomness for further in-depth discussion, avoids focusing only on certain specific data, and can comprehensively examine the data performance under different circumstances, which helps to more comprehensively understand and evaluate various characteristics and effects in the cleaning process.

[0038] Step S460, analyze the i-th cleaning flow trajectory data, the i-th cleaning flow velocity distribution data, and the i-th pollution removal rate, generate the i-th cleaning simulation result according to the i-th analysis result, and add the i-th cleaning simulation result to the multiple cleaning simulation results. Specifically, analyze the i-th cleaning flow trajectory data, study the specific flow path and direction presented, analyze the characteristics, rules and possible abnormalities or special situations, deeply analyze the i-th cleaning flow velocity distribution data, observe the high and low changes and distribution patterns of flow velocities in different regions, consider the impact of these flow velocity distributions on the cleaning effect and the relationship with other factors, comprehensively consider the i-th pollution removal rate, evaluate the actual degree of pollution removal reflected by the data, combine the flow trajectory and flow velocity distribution information, and fully understand the effectiveness of this cleaning process. Through in-depth analysis of these three aspects of data, the i-th analysis result is obtained, and the analysis result includes a detailed interpretation and evaluation of the cleaning simulation under the i-th cleaning parameters. Based on the i-th analysis result, a specific algorithm, model or logical rule is used to generate the i-th cleaning simulation result. This result may include an evaluation of the cleaning effect, a summary of the cleaning process, suggestions for improvement, etc. The generated i-th cleaning simulation result will be added to a set of multiple cleaning simulation results. As this process is repeated, the cleaning simulation results in the set will become more and more abundant, covering various situations under different cleaning parameters. Through further analysis and comparison of these cleaning simulation results, the advantages and disadvantages of different cleaning schemes can be more comprehensively grasped, providing a strong basis for final decision-making and optimization.

[0039] In a possible implementation, step S400 further includes step S470, traversing the multiple cleaning simulation results and matching them with the multiple cleaning scenes, and extracting the i-th cleaning scene according to the matching results. Specifically, the multiple cleaning simulation results are traversed one by one, and the cleaning simulation results are compared and matched with the corresponding multiple cleaning scenes, and the fit and correlation between each cleaning simulation result and each cleaning scene are checked. After a careful matching process, the i-th cleaning scene is determined and extracted according to the matching results, and the i-th cleaning scene has the closest correlation with the specific cleaning simulation result.

[0040] Step 480, according to the i-th cleaning scene and in combination with the i-th analysis result, determine the first cleaning parameter set, the first cleaning parameter set including a first cleaning type parameter, a first cleaning concentration parameter, and a first cleaning time parameter. Specifically, based on the extracted i-th cleaning scene and in combination with the i-th analysis result obtained previously, a comprehensive and in-depth analysis is performed on the various features of the cleaning scene and the key information in the analysis results, and based on the comprehensive analysis, the first cleaning parameter set is determined, the parameter set including a first cleaning type parameter, that is, specifying the specific cleaning type to be used; a first cleaning concentration parameter, which specifies the concentration requirement of the cleaning substance; and a first cleaning time parameter, which sets the length of time required for the cleaning operation.

[0041] Step 490, adding the first cleaning type parameter, the first cleaning concentration parameter, and the first cleaning time parameter to the cleaning control strategy. Specifically, by adding the determined first cleaning type parameter, the first cleaning concentration parameter, and the first cleaning time parameter to the cleaning control strategy, the cleaning control strategy is further improved and refined, and can more accurately guide the actual cleaning operation, ensuring that the cleaning work can be performed according to the most optimized parameter combination in a specific cleaning scenario to achieve the best cleaning effect and efficiency.

[0042] Step S500 , evaluating the plurality of cleaning simulation results, dynamically optimizing the cleaning control strategy according to the plurality of cleaning evaluation results, and generating a cleaning control optimization strategy.

[0043] Specifically, an evaluation is carried out on multiple cleaning simulation results. During the evaluation process, various factors are comprehensively considered, such as the quality of cleaning effects, resource consumption, and impact on the environment. Through a series of indicators and standards, each cleaning simulation result is carefully analyzed and judged to obtain the corresponding cleaning evaluation results. The cleaning evaluation results are summarized and organized, and the differences and characteristics between different cleaning simulation results are compared to find out the advantages and disadvantages. Based on the cleaning evaluation results, the existing cleaning control strategies are analyzed in a targeted manner to see in which aspects the current strategies perform well and in which aspects there is room for improvement. Based on the in-depth understanding of the cleaning evaluation results and the analysis of the cleaning control strategies, the cleaning control strategies are dynamically optimized and the settings of the cleaning parameters are adjusted, such as changing the type of cleaning, optimizing the cleaning concentration, or adjusting the cleaning time. The execution order or combination of the strategies will be improved. During the optimization process, the problems and needs reflected by each cleaning evaluation result are fully considered to achieve better cleaning effects and higher efficiency. After continuous adjustment and improvement, a cleaning control optimization strategy is finally generated.

[0044] In a possible implementation, step S500 further includes step S510, evaluating multiple cleaning simulation results according to multiple cleaning flow trajectory data, multiple cleaning flow velocity distribution data, and multiple pollution removal rates to obtain the multiple cleaning evaluation results. Specifically, multiple cleaning flow trajectory data are obtained, and the data records in detail the flow path and changes of the material during the cleaning process. Each cleaning flow trajectory data is analyzed to observe the complexity and uniformity of its trajectory and whether it conforms to the expected cleaning path planning, etc. Multiple cleaning flow velocity distribution data are studied to check the flow velocity size, distribution uniformity and flow velocity change rules in different areas, etc. Consider the potential impact of these flow velocity distributions on the cleaning effect, such as whether they can effectively drive the removal of pollutants, etc. Analyze each pollution removal rate one by one to understand the actual effect of pollutant removal under different cleaning operations, evaluate whether it has achieved the expected goal or there is room for improvement, and convert the cleaning flow trajectory data into a complete set of cleaning simulation results. By comparing the actual trajectory with the expected ideal trajectory, the pros and cons of the actual trajectory are evaluated; combining the cleaning flow rate distribution data, the positive or negative impact of the flow rate on the cleaning effect is judged; and based on the pollution removal rate data, the actual effectiveness of cleaning is directly understood. A comprehensive evaluation is conducted through multiple cleaning simulation results, and judgment is made from multiple angles, such as the thoroughness of cleaning, efficiency, resource consumption, etc., to ultimately obtain multiple cleaning evaluation results. These evaluation results reflect the performance and quality of each cleaning simulation result in different aspects, and provide important basis and guidance for further optimization of cleaning control strategies or adjustment of cleaning operations in the future, so as to continuously improve the cleaning work and enhance the overall cleaning level and effect.

[0045] Step S520, construct a neural network optimization model, use the multiple cleaning assessment results as training data sets for supervised training, test the neural network optimization model according to the test data set, and when the test passes, output the neural network optimization model. Specifically, construct a neural network optimization model, organize the multiple cleaning assessment results obtained, and conduct supervised training. The neural network will continue to learn the patterns, features and laws in these cleaning assessment results. When the training reaches a certain stage, introduce a test data set. The test data set is independent of the training data set and contains some new cleaning assessment result data. By inputting the test data set into the neural network optimization model, observe the degree of matching between the output results of the model and the actual situation, and calculate the error between the output results of the model and the actual expected results. If the error is within an acceptable range, such as the average error is less than a certain set value, it is considered that the test passes. Once the test passes, the trained and tested neural network optimization model is output, which has the ability to accurately analyze and optimize according to the new cleaning assessment results, and can play an important role in practical applications, and provide strong support for further optimizing cleaning control strategies.

[0046] Step S530, input the cleaning control strategy into the neural network optimization model, optimize the cleaning control strategy according to the multiple cleaning evaluation results, and extract multiple cleaning parameter combinations that meet the preset cleaning effect. Specifically, the cleaning control strategy is accurately input into the neural network optimization model, and the neural network optimization model conducts a comprehensive optimization search based on the input cleaning control strategy and the existing multiple cleaning evaluation results, and conducts a detailed analysis and calculation of various possible situations and parameter combinations to find the path that can achieve the best cleaning effect, and extracts multiple cleaning parameter combinations that meet the preset cleaning effect. The combination includes various specific cleaning parameter settings, such as specific values ​​of cleaning intensity, time, frequency, etc., and further evaluates and verifies the parameter combination to ensure that the preset cleaning effect can be achieved in actual applications.

[0047] Step S540, based on the multiple cleaning parameter combinations, the cleaning control strategy is updated to generate the cleaning control optimization strategy. Specifically, multiple cleaning parameter combinations are analyzed, the cleaning parameter combinations are compared with the current cleaning control strategy one by one, the differences between the values ​​of each parameter in each parameter combination and the existing strategy are analyzed, and the aspects that can be improved and optimized are found. According to the analysis results, the cleaning control strategy is updated in a targeted manner, involving the adjustment of certain parameters, the redesign of certain operating processes, or the re-planning of resource allocation, etc., considering the mutual influence and correlation of various factors, and continuously adjusting and improving, and generating a cleaning control optimization strategy, so that the cleaning control strategy can adapt to different cleaning needs and environments, and better ensure the smooth progress and high-quality completion of cleaning work.

[0048] Step S600: Execute the cleaning control optimization strategy in combination with the three-dimensional twin model of the target turbine volute to perform intelligent cleaning control on the target turbine volute.

[0049] Specifically, a three-dimensional twin model of the target turbine volute is obtained. The model presents the characteristics of the target turbine volute, including its shape, structure, and size. The cleaning control optimization strategy is combined with the three-dimensional twin model, and the specific measures and parameters in the strategy are associated with the corresponding positions and areas in the model. According to the requirements of the cleaning control optimization strategy, the corresponding cleaning tools, methods, and parameters are used to carry out cleaning work on specific parts or areas of the target turbine volute. For example, according to the instructions of the model, the cleaning force, angle, or amount of cleaning fluid is adjusted on complex surfaces or channels. The three-dimensional twin model can be used to more accurately locate the parts that need to be cleaned to avoid omissions or excessive cleaning. The information provided by the model can be used to monitor the progress and effects of cleaning in real time, and to identify and adjust possible problems or deviations.

[0050] In a possible implementation, step S600 further includes step S610, executing the cleaning control optimization strategy based on the three-dimensional twin model of the target turbine volute to generate a cleaning control result. Specifically, based on the three-dimensional twin model of the target turbine volute, a specific cleaning operation is performed according to the cleaning control optimization strategy, and various relevant data are recorded and collected to generate a cleaning control result.

[0051] Step S620, verifying whether the cleaning control result reaches the preset expected value. Specifically, the cleaning control result is compared and verified with the preset expected value, and the cleaning control result is analyzed, such as the cleaning degree, cleaning range, and the impact on the turbine volute, to verify whether the preset standards and requirements are met.

[0052] Step S630: If the cleaning control result does not reach the preset expected value, the verification fails, and an exception instruction is generated. According to the exception instruction, the exception is traced to the source, and multiple abnormal response data sources are determined. Specifically, if it is found that the cleaning control result does not reach the preset expected value, which means that the verification fails, the system will automatically generate an exception instruction and start the abnormal tracing procedure. During the abnormal tracing process, the data, operations, equipment status and other aspects involved in the entire cleaning process are thoroughly investigated and analyzed, and multiple response data sources that may cause abnormalities are gradually determined. The data sources include various factors such as inaccurate cleaning parameter settings, abnormal equipment operation, and operational process errors.

[0053] Step S640, perform deviation correction on the multiple abnormal response data sources, and synchronize the deviation correction results to the cleaning control optimization strategy. Specifically, determine the abnormal response data source, perform deviation correction, adjust relevant parameters, repair equipment problems, and correct operation deviations to ensure that these data sources can be restored to a normal state, and synchronize the deviation correction results to the cleaning control optimization strategy to make the cleaning control optimization strategy more complete and accurate, so as to avoid similar problems in subsequent cleaning work and continuously improve the effect and quality of cleaning control.

[0054] The embodiment of the present application uses a sensor device group to collect real-time data of the target turbine volute, builds a three-dimensional twin model based on this and its structural information, sets multiple cleaning scenarios containing cleaning parameters, performs multiple cleaning simulations through the model and parameters to obtain results and formulate strategies, evaluates the simulation results to optimize the control strategy, and finally combines the model to execute the optimization strategy to perform intelligent cleaning control on the target turbine volute. By constructing a three-dimensional twin model and performing simulated cleaning, the cleaning control strategy is dynamically optimized to adapt to different operating environments and pollutant conditions, thereby achieving intelligent, precise and efficient cleaning of the turbine volute and ensuring the technical effect of cleaning quality.

[0055] In the above, refer to Figure 1 The turbine volute cleaning control method based on twin simulation according to an embodiment of the present invention is described in detail. Figure 2 A turbine volute cleaning control platform based on twin simulation according to an embodiment of the present invention is described.

[0056] The turbine volute cleaning control platform based on twin simulation according to the embodiment of the present invention is used to solve the technical problems of unsatisfactory cleaning effect, low degree of automation and poor adaptability to different turbine volutes in the existing turbine volute cleaning method, so as to achieve intelligent, precise and efficient cleaning of the turbine volute and ensure the technical effect of cleaning quality. The turbine volute cleaning control platform based on twin simulation includes: a sensor data group acquisition module 10, a three-dimensional twin model construction module 20, a cleaning scene setting module 30, a cleaning control strategy formulation module 40, a cleaning control optimization strategy generation module 50, and an intelligent cleaning control module 60.

[0057] The sensor data group acquisition module 10 is used to collect the target turbine volute in real time through the sensor device group to obtain multiple real-time sensor data groups;

[0058] The three-dimensional twin model construction module 20 is used to construct a three-dimensional twin model of the target turbine volute based on the multiple real-time sensor data groups and in combination with the structural information of the target turbine volute;

[0059] The cleaning scene setting module 30 is used to traverse multiple operating environment information of the target turbine volute to set multiple cleaning scenes, wherein the multiple cleaning scenes include multiple cleaning parameters;

[0060] The cleaning control strategy formulation module 40 is used to use the three-dimensional twin model of the target turbine volute and combine the multiple cleaning parameters to perform multiple cleaning simulations, obtain multiple cleaning simulation results, and formulate a cleaning control strategy;

[0061] The cleaning control optimization strategy generation module 50 is used to evaluate the multiple cleaning simulation results, dynamically optimize the cleaning control strategy according to the multiple cleaning evaluation results, and generate a cleaning control optimization strategy;

[0062] The intelligent cleaning control module 60 is used to execute the cleaning control optimization strategy in combination with the three-dimensional twin model of the target turbine volute to perform intelligent cleaning control on the target turbine volute.

[0063] Below, the specific configuration of the three-dimensional twin model construction module 20 will be described in detail. As described above, based on the multiple real-time sensor data groups and combined with the structural information of the target turbine volute, a three-dimensional twin model of the target turbine volute is constructed. The three-dimensional twin model construction module 20 may further include: a data scanning unit is used to scan the target turbine volute through a scanning device, and obtain a size information set and a shape information set of the target turbine volute according to the scanning data; a structural information unit is used to determine the structural information of the target turbine volute based on the size information set and the shape information set of the target turbine volute; an initial three-dimensional model construction unit is used to use digital twin technology to construct an initial three-dimensional model according to the structural information of the target turbine volute; a model update unit is used to map the multiple real-time sensor data groups to the initial three-dimensional model for updating, and construct the three-dimensional twin model of the target turbine volute.

[0064] Below, the specific configuration of the cleaning scene setting module 30 will be described in detail. As described above, multiple operating environment information of the target turbine volute is traversed to set multiple cleaning scenes, and the multiple cleaning scenes include multiple cleaning parameters. The cleaning scene setting module 30 may further include: a pollutant parameter set unit is used to traverse and analyze the multiple operating environment information of the target turbine volute, and determine the pollutant parameter set of the target turbine volute, and the pollutant parameter set includes pollution property parameters, pollution attachment parameters, and pollution distribution parameters; a cleaning method determination unit is used to determine multiple cleaning equipment according to the pollution property parameters, determine multiple cleaning agents according to the pollution attachment parameters, and determine multiple cleaning methods according to the pollution distribution parameters; a cleaning scene setting unit is used to add the multiple cleaning equipment, the multiple cleaning agents, and the multiple cleaning methods to the multiple cleaning parameters, and set the multiple cleaning scenes in combination with the multiple operating environment information.

[0065] Below, the specific configuration of the cleaning control strategy formulation module 40 will be described in detail. As described above, the three-dimensional twin model of the target turbine volute is used to perform multiple cleaning simulations in combination with the multiple cleaning parameters to obtain multiple cleaning simulation results and formulate a cleaning control strategy. The cleaning control strategy formulation module 40 may further include: a condition setting unit for setting simulation boundary conditions and simulation initial conditions based on the multiple cleaning parameters; a cleaning method combination unit for randomly combining the multiple cleaning equipment, the multiple cleaning agents, and the multiple cleaning methods to generate a first cleaning parameter, a second cleaning parameter... the Nth cleaning parameter, where N is an integer greater than 2; a first cleaning record data set acquisition unit for starting the three-dimensional twin model according to the simulation initial conditions, introducing the simulation boundary conditions as constraints, performing cleaning simulation according to the first cleaning parameters, and obtaining a first cleaning record data set, the first cleaning record data set comprising first cleaning flow trajectory data, first cleaning flow velocity distribution data, and first pollution removal rate; an iteration unit for starting the three-dimensional twin model according to the simulation initial conditions, introducing the simulation boundary conditions as constraints, and performing cleaning according to the second cleaning parameters. Simulation, thereby iterating until a cleaning simulation is performed according to the Nth cleaning parameter to obtain a second cleaning record data set... an Nth cleaning record data set, the second cleaning record data set includes second cleaning flow trajectory data, second cleaning flow velocity distribution data, and second pollution removal rate, and the Nth cleaning record data set includes Nth cleaning flow trajectory data, Nth cleaning flow velocity distribution data, and Nth pollution removal rate; a cleaning flow trajectory acquisition unit is used to randomly extract based on the first cleaning flow trajectory data, the first cleaning flow velocity distribution data, the first pollution removal rate... the Nth cleaning flow trajectory data, the Nth cleaning flow velocity distribution data, and the Nth pollution removal rate to obtain the i-th cleaning flow trajectory data, the i-th cleaning flow velocity distribution data, and the i-th pollution removal rate, where i is a random positive integer less than or equal to N; a cleaning simulation result acquisition unit is used to analyze the i-th cleaning flow trajectory data, the i-th cleaning flow velocity distribution data, and the i-th pollution removal rate, and generate an i-th cleaning simulation result according to the i-th analysis result, and add the i-th cleaning simulation result to the multiple cleaning simulation results.

[0066] Among them, the cleaning control strategy formulation module 40 may further include: a cleaning scene extraction unit for traversing the multiple cleaning simulation results and matching them with the multiple cleaning scenes, and extracting the i-th cleaning scene according to the matching results; a first cleaning parameter set determination unit for determining the first cleaning parameter set according to the i-th cleaning scene and the i-th analysis result, wherein the first cleaning parameter set includes a first cleaning type parameter, a first cleaning concentration parameter, and a first cleaning time parameter; a cleaning control strategy acquisition unit for adding the first cleaning type parameter, the first cleaning concentration parameter, and the first cleaning time parameter to the cleaning control strategy.

[0067] Below, the specific configuration of the cleaning control optimization strategy generation module 50 will be described in detail. As described above, the multiple cleaning simulation results are evaluated, the cleaning control strategy is dynamically optimized according to the multiple cleaning evaluation results, and the cleaning control optimization strategy is generated. The cleaning control optimization strategy generation module 50 may further include: a cleaning evaluation result acquisition unit is used to evaluate the multiple cleaning simulation results according to multiple cleaning flow trajectory data, multiple cleaning flow velocity distribution data, and multiple pollution removal rates to obtain the multiple cleaning evaluation results; a neural network optimization model acquisition unit is used to construct a neural network optimization model, and the multiple cleaning evaluation results are used as a training data set for supervised training, and the neural network optimization model is tested according to the test data set. When the test passes, the neural network optimization model is output; a cleaning parameter combination extraction unit is used to input the cleaning control strategy into the neural network optimization model, optimize the cleaning control strategy according to the multiple cleaning evaluation results, and extract multiple cleaning parameter combinations that meet the preset cleaning effect; a cleaning control optimization strategy generation unit is used to update the cleaning control strategy based on the multiple cleaning parameter combinations and generate the cleaning control optimization strategy.

[0068] Below, the specific configuration of the intelligent cleaning control module 60 will be described in detail. As described above, the cleaning control optimization strategy is executed in combination with the three-dimensional twin model of the target turbine volute to perform intelligent cleaning control on the target turbine volute. The intelligent cleaning control module 60 may further include: a cleaning control result generation unit is used to execute the cleaning control optimization strategy based on the three-dimensional twin model of the target turbine volute to generate a cleaning control result; a preset expected value verification unit is used to verify whether the cleaning control result reaches the preset expected value; an abnormal response data source determination unit is used to generate an abnormal instruction if the cleaning control result does not reach the preset expected value, and the verification fails, and an abnormality is traced according to the abnormal instruction to determine multiple abnormal response data sources; a correction result unit is used to perform deviation correction on the multiple abnormal response data sources, and synchronize the deviation correction results to the cleaning control optimization strategy.

[0069] The turbine volute cleaning control platform based on twin simulation provided in an embodiment of the present invention can execute the turbine volute cleaning control method based on twin simulation provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0070] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0071] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A turbine volute cleaning control method based on twin simulation, characterized in that: The method comprises: The target turbine volute is collected in real time by a sensor device group to obtain multiple real-time sensor data groups; Based on the multiple real-time sensor data groups and in combination with structural information of the target turbine volute, construct a three-dimensional twin model of the target turbine volute; Traversing multiple operating environment information of a target turbine volute to set multiple cleaning scenarios, wherein the multiple cleaning scenarios include multiple cleaning parameters; Using the three-dimensional twin model of the target turbine volute, combined with the multiple cleaning parameters, multiple cleaning simulations are performed to obtain multiple cleaning simulation results and formulate a cleaning control strategy; Evaluate the multiple cleaning simulation results, dynamically optimize the cleaning control strategy according to the multiple cleaning evaluation results, and generate a cleaning control optimization strategy; Executing the cleaning control optimization strategy in combination with the three-dimensional twin model of the target turbine volute to perform intelligent cleaning control on the target turbine volute; Traversing multiple operating environment information of a target turbine volute to set multiple cleaning scenarios, the method includes: Performing traversal analysis on the plurality of operating environment information of the target turbine volute to determine a pollutant parameter set of the target turbine volute, wherein the pollutant parameter set includes a pollution property parameter, a pollution attachment parameter, and a pollution distribution parameter; Determine a plurality of cleaning devices according to the pollution property parameters, determine a plurality of cleaning agents according to the pollution attachment parameters, and determine a plurality of cleaning methods according to the pollution distribution parameters; Adding the plurality of cleaning devices, the plurality of cleaning agents, and the plurality of cleaning methods to the plurality of cleaning parameters, and combining the plurality of operating environment information to set the plurality of cleaning scenes; Using the three-dimensional twin model of the target turbine volute and combining the multiple cleaning parameters to perform multiple cleaning simulations to obtain multiple cleaning simulation results, the method includes: Setting simulation boundary conditions and simulation initial conditions based on the plurality of cleaning parameters; Randomly combining multiple cleaning devices, multiple cleaning agents, and multiple cleaning methods to generate a first cleaning parameter, a second cleaning parameter, ... an Nth cleaning parameter, where N is an integer greater than 2; According to the simulation initial conditions, the three-dimensional twin model is started to introduce the simulation boundary conditions as constraints, and a cleaning simulation is performed according to the first cleaning parameters to obtain a first cleaning record data set, wherein the first cleaning record data set includes first cleaning flow trajectory data, first cleaning flow velocity distribution data, and a first pollution removal rate; According to the simulation initial condition, the three-dimensional twin model is started to introduce the simulation boundary condition as a constraint, and a cleaning simulation is performed according to the second cleaning parameter, thereby iterating until a cleaning simulation is performed according to the Nth cleaning parameter to obtain a second cleaning record data set... an Nth cleaning record data set, the second cleaning record data set comprising second cleaning flow trajectory data, second cleaning flow velocity distribution data, and a second pollution removal rate, and the Nth cleaning record data set comprises Nth cleaning flow trajectory data, Nth cleaning flow velocity distribution data, and Nth pollution removal rate; Based on the first cleaning flow trajectory data, the first cleaning flow velocity distribution data, the first pollution removal rate...the Nth cleaning flow trajectory data, the Nth cleaning flow velocity distribution data, the Nth pollution removal rate, randomly extracting to obtain the i-th cleaning flow trajectory data, the i-th cleaning flow velocity distribution data, the i-th pollution removal rate, where i is a random positive integer less than or equal to N; The i-th cleaning flow trajectory data, the i-th cleaning flow velocity distribution data, and the i-th pollution removal rate are analyzed, and an i-th cleaning simulation result is generated according to the i-th analysis result, and the i-th cleaning simulation result is added to the plurality of cleaning simulation results.

2. The turbine volute cleaning control method based on twin simulation according to claim 1, characterized in that: Based on multiple real-time sensor data sets and combined with structural information of a target turbine volute, a three-dimensional twin model of the target turbine volute is constructed, the method comprising: Scanning the target turbine volute by means of a scanning device, and obtaining a size information set and a shape information set of the target turbine volute according to the scanning data; Determining the structural information of the target turbine volute based on the size information set and the shape information set of the target turbine volute; Using digital twin technology, constructing an initial three-dimensional model according to the structural information of the target turbine volute; The multiple real-time sensor data groups are mapped to the initial three-dimensional model for updating, and the three-dimensional twin model of the target turbine volute is constructed.

3. The turbine volute cleaning control method based on twin simulation according to claim 1, characterized in that: Develop a cleaning control strategy by: Traversing the plurality of cleaning simulation results and matching them with the plurality of cleaning scenes, and extracting an i-th cleaning scene according to the matching results; According to the i-th cleaning scene and in combination with the i-th analysis result, determining a first cleaning parameter set, wherein the first cleaning parameter set includes a first cleaning type parameter, a first cleaning concentration parameter, and a first cleaning time parameter; The first cleaning type parameter, the first cleaning concentration parameter, and the first cleaning time parameter are added to a cleaning control strategy.

4. The turbine volute cleaning control method based on twin simulation according to claim 1, characterized in that: The plurality of cleaning simulation results are evaluated, and the cleaning control strategy is dynamically optimized according to the plurality of cleaning evaluation results to generate a cleaning control optimization strategy, the method comprising: Evaluate multiple cleaning simulation results according to multiple cleaning flow trajectory data, multiple cleaning flow velocity distribution data, and multiple pollution removal rates to obtain the multiple cleaning evaluation results; Constructing a neural network optimization model, using the multiple cleaning evaluation results as training data sets for supervised training, testing the neural network optimization model according to the test data sets, and outputting the neural network optimization model when the test passes; Inputting the cleaning control strategy into the neural network optimization model, optimizing and searching the cleaning control strategy according to the multiple cleaning evaluation results, and extracting multiple cleaning parameter combinations that meet the preset cleaning effect; The cleaning control strategy is updated based on the multiple cleaning parameter combinations to generate the cleaning control optimization strategy.

5. The turbine volute cleaning control method based on twin simulation according to claim 1, characterized in that: The cleaning control optimization strategy is executed in combination with the three-dimensional twin model of the target turbine volute to perform intelligent cleaning control on the target turbine volute, and the method includes: Executing the cleaning control optimization strategy based on the three-dimensional twin model of the target turbine volute to generate a cleaning control result; Verify whether the cleaning control result reaches the preset expected value; If the cleaning control result does not reach the preset expected value, the verification fails, and an abnormal instruction is generated, and the abnormality is traced according to the abnormal instruction to determine multiple abnormal response data sources; Deviation correction is performed on the multiple abnormal response data sources, and the deviation correction results are synchronized with the cleaning control optimization strategy.

6. The turbine volute cleaning control platform based on twin simulation is characterized by: The platform is used to implement the turbine volute cleaning control method based on twin simulation according to any one of claims 1 to 5, and the platform comprises: A sensor data group acquisition module, the sensor data group acquisition module is used to collect the target turbine volute in real time through a sensor device group to obtain multiple real-time sensor data groups; A three-dimensional twin model construction module, wherein the three-dimensional twin model construction module is used to construct a three-dimensional twin model of a target turbine volute based on the multiple real-time sensor data groups and in combination with structural information of the target turbine volute; A cleaning scene setting module, the cleaning scene setting module is used to traverse multiple operating environment information of the target turbine volute to set multiple cleaning scenes, the multiple cleaning scenes include multiple cleaning parameters; A cleaning control strategy formulation module, wherein the cleaning control strategy formulation module is used to use the three-dimensional twin model of the target turbine volute and combine the multiple cleaning parameters to perform multiple cleaning simulations, obtain multiple cleaning simulation results, and formulate a cleaning control strategy; A cleaning control optimization strategy generation module, wherein the cleaning control optimization strategy generation module is used to evaluate the multiple cleaning simulation results, dynamically optimize the cleaning control strategy according to the multiple cleaning evaluation results, and generate a cleaning control optimization strategy; An intelligent cleaning control module is used to execute the cleaning control optimization strategy in combination with the three-dimensional twin model of the target turbine volute to perform intelligent cleaning control on the target turbine volute.

Images