Intelligent sprinkler control method and system

Abstract

This invention provides a smart sprinkler control method and system, relating to the field of intelligent environmental control technology. The method includes: collecting environmental parameters of the sprinkler area; constructing a multi-dimensional numerical simulation model; inputting the environmental parameters into the multi-dimensional numerical simulation model to determine simulation data; extracting features from the simulation data to obtain data features; constructing a drying time proxy model based on an improved neural network model; inputting the data features into the drying time proxy model to predict the drying state of the sprinkler area; using a Bayesian optimization algorithm to generate an optimal sprinkler strategy with the goal of minimizing drying time and energy consumption; and triggering a three-level linkage control of the sprinkler equipment based on the optimal sprinkler strategy when the user selects an automatic moisture content trigger mode and the moisture content of the sprinkler area is less than a threshold. This invention significantly improves the intelligence and energy efficiency of sprinkler equipment operation, enhances dust suppression and humidity control effects, and is suitable for intelligent sprinkler applications in various complex environments.

Description

Technical Field

[0001] This invention relates to the field of intelligent environmental control technology, and in particular to an intelligent sprinkler control method and system. Background Technology

[0002] The intelligent sprinkler control method is an automated control technology based on sensor monitoring, the Internet of Things, and intelligent algorithms. By collecting environmental parameters in real time and combining data analysis and intelligent decision-making models, it dynamically adjusts the sprinkler system to achieve precise control of dust, heat, and air humidity. This method is particularly suitable for scenarios such as port yards, coal mines, industrial parks, and municipal roads. It can improve the utilization efficiency of water resources and energy while ensuring the safety and comfort of the working environment.

[0003] Dust control, temperature and humidity regulation, and heat reduction are long-standing challenges in environments such as port yards, coal mines, industrial parks, and municipal roads. Traditional spraying methods often rely on manual experience and lack real-time adjustment capabilities, leading to resource waste and unstable treatment effects. Therefore, a spraying management system that can achieve automation, precision, and energy saving is needed.

[0004] However, existing sprinkler methods mostly use timed or manually triggered methods, which are difficult to achieve intelligent response according to actual environmental changes. This results in problems such as water waste and poor dust suppression. Some sprinkler equipment with sensor control has a low level of intelligence due to its simple algorithm model, which cannot make decisions and controls based on multiple factors such as wind speed, soil moisture and actual working scenario. It is difficult to achieve the goal of balancing water conservation and efficiency. Summary of the Invention

[0005] To address the problems of existing sprinkler systems that rely on timed or manual triggering, making it difficult to achieve intelligent responses based on actual environmental changes, resulting in water waste and poor dust suppression, and the fact that some sensor-controlled sprinkler systems have simple algorithm models that cannot comprehensively consider multiple factors such as wind speed, soil moisture, and actual operating scenarios for decision-making and control, thus having a low level of intelligence and failing to achieve the goal of balancing water conservation and efficiency, this invention provides a smart sprinkler control method and system.

[0006] The technical solutions provided by the embodiments of the present invention are as follows: First aspect: An embodiment of the present invention provides a smart sprinkler control method, comprising: S1: Collect environmental parameters of the spraying area; S2: Construct a multidimensional numerical simulation model; S3: Input the environmental parameters into the multidimensional numerical simulation model to determine the simulation data, wherein the simulation data specifically includes: temperature field distribution, humidity field distribution and steam concentration field distribution; S4: Perform feature extraction on the simulation data to obtain data features; S5: Construct a drying time proxy model based on an improved neural network model, wherein the improved neural network model specifically refers to: introducing deep residual learning and physical constraint modules into the neural network model; S6: Input the data features into the drying time proxy model to predict the drying status of the spray area; S7: Based on the drying state, with the goal of minimizing drying time and energy consumption, a Bayesian optimization algorithm is used to generate the optimal spraying strategy; S8: When the user selects the automatic moisture content trigger mode and the moisture content of the spray area is less than the threshold, the three-level linkage control of the spray equipment is triggered based on the optimal spraying strategy.

[0007] The second aspect: An embodiment of the present invention provides a smart sprinkler control system, comprising: processor; A memory storing computer-readable instructions, which, when executed by the processor, implement the intelligent sprinkler control method as described in the first aspect.

[0008] Third aspect: The present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the intelligent sprinkler control method as described in the first aspect.

[0009] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: In this embodiment of the invention, by collecting multidimensional environmental parameters of the spraying area and combining them with multiphysics numerical simulation, the internal hydrothermal coupling state of the pile is realistically reflected, providing physical support for decision-making. By introducing an improved neural network model with residual learning and physical constraint mechanisms, the drying state of the spraying area can be accurately predicted by combining various environmental factors. By generating an optimal spraying strategy with the goal of minimizing drying time and energy consumption, over-spraying or under-spraying can be effectively avoided, improving water resource utilization and reducing energy consumption. By combining an automatic moisture content triggering mode to achieve local autonomous operation and three-level linkage control, the spraying process can be dynamically adjusted according to real-time environmental changes, effectively avoiding the slow response and water waste caused by timed or manual triggering. This achieves a balance between water conservation and efficiency, significantly improving the intelligence, energy efficiency, and stability of the spraying equipment, and enhancing the dust suppression and humidity control effects. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a flowchart illustrating a smart sprinkler control method provided in an embodiment of the present invention.

[0012] Figure 2 This is a schematic diagram of a smart sprinkler control system provided in an embodiment of the present invention. Detailed Implementation

[0013] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0014] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0015] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0016] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0017] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0018] Reference manual attached Figure 1 The diagram shows a flowchart of a smart sprinkler control method provided by an embodiment of the present invention.

[0019] This invention provides a smart sprinkler control method, which can be implemented by a smart sprinkler control device, which can be a terminal or a server. The processing flow of the smart sprinkler control method may include the following steps: In this embodiment of the invention, the invention provides a smart sprinkler hardware architecture, which consists of a sensor network, an edge computing device, a high-performance server, and a sprinkler control system. Data transmission between the components is achieved through a communication transmission network.

[0020] S1: Collect environmental parameters of the spraying area.

[0021] In one possible implementation, the environmental parameters specifically include: wind speed, temperature, humidity, solar radiation intensity, and spray flow rate.

[0022] In this embodiment of the invention, the spraying area is specifically a ore pile. A sensor network is deployed in the required spraying area to realize real-time monitoring of environmental data in the spraying area and transmit the data to the edge computing device through a communication transmission network.

[0023] S2: Construct a multidimensional numerical simulation model.

[0024] Among them, the multidimensional numerical simulation model refers to a comprehensive computational model established in the computational domain based on mathematical physics equations (such as fluid flow equations, energy equations, and mass transfer equations). It is used to simulate the multi-physical field coupling process such as fluid flow, heat transfer, and moisture migration in the spray area, and can output spatiotemporal distribution data such as temperature field, humidity field, and steam concentration field.

[0025] It should be noted that by constructing a multidimensional numerical simulation model, the dynamic changes in temperature, humidity and moisture content within the spray area can be realistically reproduced, thereby providing high-quality sample data for subsequent neural network training. This avoids the high cost and limitations of relying solely on on-site experiments and significantly improves the accuracy and generalization ability of model predictions.

[0026] In one possible implementation, S2 specifically refers to: Using COMSOL Multiphysics, a multidimensional numerical simulation model was constructed, including a fluid flow module, a heat transfer process module, and a mass transfer process module.

[0027] S3: Input environmental parameters into the multidimensional numerical simulation model to determine the simulation data, which specifically includes: temperature field distribution, humidity field distribution and steam concentration field distribution.

[0028] It should be noted that inputting environmental parameters into a multidimensional numerical simulation model can quickly generate temperature, humidity, and steam concentration distribution data covering various environmental conditions without the need for extensive field experiments. This provides a comprehensive and accurate physical reference for neural network training and spray strategy optimization, reducing experimental costs while significantly improving the reliability and adaptability of the model.

[0029] In one possible implementation, the fluid flow module specifically includes: a porous media control equation inside the ore pile and a free flow control equation outside the ore pile.

[0030] The governing equations for the porous media inside the ore pile are as follows:

[0031] in, Indicates fluid density, u Indicates fluid velocity. This represents the gradient operator. Indicates the partial derivative sign. p Indicates pressure, Indicates the dynamic viscosity of a fluid. K Indicates the permeability of porous media. t Indicates time.

[0032] In this embodiment of the invention, the interior of the ore pile is a porous medium, and the fluid flow is subject to the combined effects of viscous force and seepage resistance. Therefore, the above-mentioned control equation for the porous medium inside the ore pile is adopted.

[0033] The governing equations for the free flow outside the ore pile are as follows:

[0034] In this embodiment of the invention, the airflow outside the ore pile is free-flowing and mainly driven by viscous forces. A laminar flow model is adopted, and therefore the above-mentioned free-flow control equation outside the ore pile is used.

[0035] The heat transfer process module is specifically defined by the energy equation:

[0036]

[0037] in, T Indicates temperature. c p This represents the specific heat capacity of a fluid at constant pressure. k eff Indicates effective thermal conductivity. Q phase This represents the latent heat source term for phase change. ε Indicates porosity. k fluid Indicates the thermal conductivity of a fluid. k solid This represents the thermal conductivity of a solid.

[0038] The mass transfer process module specifically includes: the liquid water seepage control equation and the water vapor diffusion control equation.

[0039] The governing equation for liquid water seepage is as follows:

[0040] in, p l Indicates capillary pressure. S l Indicates the saturation level of liquid water. This represents the relative density of liquid water. This represents the phase velocity vector of liquid water.

[0041] The governing equation for water vapor diffusion is as follows:

[0042] in, This represents the density of the gas phase. y i Indicates water vapor i mass fraction, R i Indicates water vapor i The phase transition rate, Indicates water vapor i The effective diffusion coefficient.

[0043] S4: Extract features from the simulation data to obtain data features.

[0044] It should be noted that by extracting features from complex multidimensional simulation data, the dimensionality and redundancy of the data can be effectively reduced, highlighting the core information most relevant to the dry state. This not only improves the efficiency and convergence speed of neural network training, but also enhances the generalization ability and stability of the prediction model for multiple working conditions.

[0045] In this embodiment of the invention, during feature extraction, COMSOL multiphysics simulation is used to simulate the drying process of ore piles under different working conditions (such as different temperatures, wind speeds, humidity, etc.), generating 1000 samples that cover rich physical field information, as detailed below: Features were selected from a database of ore pile drying data. Input features were chosen based on dimensions such as operating parameters, environmental parameters, and drying time, and preprocessed to include inlet temperature T (range 283-323K), inlet wind velocity v (range 0.5-5m / s), and relative humidity RH (range 20%-80%). Z-score standardization was used to eliminate the influence of dimensions. Then, the target to be predicted by the model, the moisture content of the ore pile, and the required drying time were determined. Simultaneously, during data processing, physical constraints such as energy conservation and mass conservation were enforced to ensure the rationality of the data.

[0046] S5: Construct a drying time surrogate model based on an improved neural network model, wherein the improved neural network model specifically involves introducing deep residual learning and physical constraint modules into the neural network model.

[0047] It should be noted that by introducing deep residual learning and physical constraint modules into the neural network, not only are the problems of gradient vanishing and convergence difficulties in deep network training solved, but the prediction results are also ensured to conform to physical laws such as energy conservation and mass conservation, thereby significantly improving the accuracy, stability and interpretability of drying time prediction.

[0048] In this embodiment of the invention, an improved neural network model based on a multilayer perceptron framework, integrating deep residual learning and physical constraint mechanisms, is employed. Residual paths are added between every 2-3 fully connected layers (i.e., the input directly skips intermediate layers and is added to the output). A physical constraint layer is added before the network output layer to correct the prediction results through hard constraints (energy conservation equation). A structure with a shared feature extraction layer and a task-specific output layer is adopted, simultaneously learning multiple related tasks such as moisture content and drying time, leveraging the correlation between tasks to improve the prediction accuracy of individual tasks.

[0049] The training framework uses a core closed loop of "batch iteration - two-stage evaluation - dynamic termination". The preprocessed dataset is divided into batches of 64 samples each. After each batch of data is input into the network, forward propagation is used to obtain the predicted dryness state (temperature, humidity, etc.), and then the error between this prediction and the true label is calculated (using weighted mean square error, with humidity prediction given a 1.5x weight to highlight the key indicator). Subsequently, backpropagation is performed using the AdamW optimizer. This optimizer not only adaptively adjusts the learning rate (initially set to 0.001) but also suppresses overfitting through weight decay, making it particularly suitable for handling the high noise and nonlinear characteristics caused by multi-physics coupling in dry mine pile data. In each iteration, the model evaluates its performance on both the training set (updating parameters) and the validation set (freezing parameters). An early stopping mechanism is triggered when the validation loss does not decrease for 20 consecutive iterations, avoiding invalid training and preserving the optimal parameter state.

[0050] In one possible implementation, the loss function of the drying time surrogate model is specifically a composite physical constraint loss function.

[0051] The composite physical constraint loss function is as follows:

[0052]

[0053]

[0054]

[0055] in, L Represents the composite physical constraint loss function. λ 1, λ 2, λ 3, λ 4 represents the weight coefficient of the corresponding sub-loss function. L MSE Represents the error loss function. L mass Represents the mass conservation loss function. L energy Represents the energy conservation loss function. L mono Indicates supplementary constraints. N This represents the total number of data features. T s Indicates the first s The true temperature of each data feature H s Indicates the first s The true humidity of each data feature M s Indicates the first s The true moisture content of each data feature Indicates the first s Predicted temperature based on data features Indicates the first s Predicted humidity based on data features Indicates the first s Predicted moisture content based on data features w T Indicates the weighting coefficients related to temperature. w H Indicates the weighting coefficient related to humidity. w M This represents the weighting coefficient related to moisture content. This represents the relative density of liquid water. This represents the phase velocity vector of liquid water. R i Indicates water vapor i The phase transition rate.

[0056] S6: Input the data features into the drying time surrogate model to predict the drying status of the sprayed area.

[0057] Specifically, by inputting the extracted data features into the drying time surrogate model, the drying state of the spray area can be quickly predicted under complex and variable environmental conditions. This not only significantly improves prediction efficiency and avoids reliance on a large number of complex physical simulation calculations, but also maintains stable generalization ability under various working conditions, thereby providing real-time and reliable decision-making basis for subsequent spray strategy optimization and automatic control.

[0058] S7: Based on the drying status, with the goal of minimizing drying time and energy consumption, a Bayesian optimization algorithm is used to generate the optimal spraying strategy.

[0059] It should be noted that by introducing a Bayesian optimization algorithm based on the predicted drying state, with the goal of minimizing drying time and energy consumption, the optimal spraying strategy can be found efficiently within a limited number of search attempts. By taking into account multiple factors such as drying time and energy consumption, over-spraying or under-spraying is avoided, which not only improves water resource utilization and energy efficiency, but also ensures the accuracy and stability of the spraying process.

[0060] In one possible implementation, S7 specifically includes: S701: The objective function is defined with the goal of minimizing drying time and energy consumption.

[0061] Where min represents minimization. J Describe the objective function. p Indicates the drying end time. q Indicates the spray flow rate. T spray Indicates the temperature of the spray medium. J 1 indicates the first sub-objective function related to drying time. J 2 represents the second sub-objective function related to the total consumption of the spraying process. This represents the weight corresponding to the first sub-objective function. This represents the weight corresponding to the second sub-objective function. t end This indicates the drying end time, and `max` means to maximize. r This represents the coordinates of different spatial points in the ore pile. y target Indicates the moisture content threshold. E total This indicates the total consumption of spraying media. C p This indicates the specific heat capacity of the spray medium. T ambient Indicates ambient temperature. d Represents the differential operator. t Represents a time variable.

[0062] S702: The Bayesian optimization algorithm is used to solve the objective function and generate the optimal spraying strategy.

[0063] In one possible implementation, the Bayesian optimization algorithm is specifically as follows:

[0064]

[0065] Where EI() represents the desired improvement function, This represents the parameter vector to be optimized. Represents the proxy model. This represents the known optimal objective function value. Represents the balance parameters. Let Z represent the cumulative distribution function of the standard normal distribution, and let Z represent the standardized variable. This represents the standard deviation of the surrogate model's predictions. This represents the probability density function of the standard normal distribution.

[0066] In this embodiment of the invention, several initial combinations are first selected within the spray parameter space, and their drying time and energy consumption performance are evaluated using a surrogate model. Then, a probabilistic surrogate model of the objective function is established using a Gaussian process to obtain the predicted mean and uncertainty of each parameter point. Based on this, acquisition functions such as expected improvement are introduced to dynamically balance exploration and utilization, selecting the most promising spray strategy point from the parameter space for evaluation and continuously updating the model. After iterative optimization, the optimal spray strategy that minimizes drying time and energy consumption is finally obtained under multi-objective constraints, including control parameters such as spray time, intensity, frequency, and duration.

[0067] S8: When the user selects the automatic moisture content trigger mode and the moisture content of the spray area is less than the threshold, the three-level linkage control of the spray equipment is triggered based on the optimal spraying strategy.

[0068] It should be noted that by combining the real-time monitored moisture content with the set threshold after the user selects the automatic moisture content trigger mode, the system ensures that the spraying operation is only performed in actual water shortage situations. Based on the optimal strategy, the system triggers three-level linkage control, automating the entire process from water replenishment and spraying to status updates. This avoids the lag and misjudgment caused by manual intervention, ensuring the rapid response and efficient operation of the spraying system, while also improving the system's robustness and resource utilization.

[0069] In this embodiment of the invention, the system deploys multi-region distributed moisture content sensors (laid out along the stacking line, covering different locations and lengths) to collect data in real time and construct a "heat map of stack moisture content distribution". The algorithm then calculates the "percentage of stack lengths with low moisture content," i.e., the moisture content of the spraying area.

[0070] in, R This indicates the moisture content of the sprayed area. L low Indicates the length of the low-moisture section of the spraying area. L total This indicates the total length of the line in the spray area.

[0071] When R < ( When the water content is at a preset threshold (e.g., 30%), it is judged as "line-level overall water shortage". The principle is that if the water content of the ore pile (spraying area) is too low, it will cause problems such as dust and abnormal material hardness. Through line-level global assessment, it avoids misjudgment due to local small-scale water shortage, which may lead to "overspraying" (only local water is replenished but triggers the whole line spraying) or "insufficient spraying" (local severe water shortage but does not meet the single pile triggering conditions).

[0072] In one possible implementation, the three-level linkage control specifically includes: Level 1: Based on the water tank level setting parameters, the sprinkler truck is automatically replenished with water until the set value is reached.

[0073] Level 2: The spray equipment is started and the optimal spraying strategy is executed.

[0074] Level 3: Update the sprinkler status and notify the user.

[0075] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: In this embodiment of the invention, by collecting multidimensional environmental parameters of the spraying area and combining them with multiphysics numerical simulation, the internal hydrothermal coupling state of the pile is realistically reflected, providing physical support for decision-making. By introducing an improved neural network model with residual learning and physical constraint mechanisms, the drying state of the spraying area can be accurately predicted by combining various environmental factors. By generating an optimal spraying strategy with the goal of minimizing drying time and energy consumption, over-spraying or under-spraying can be effectively avoided, improving water resource utilization and reducing energy consumption. By combining an automatic moisture content triggering mode to achieve local autonomous operation and three-level linkage control, the spraying process can be dynamically adjusted according to real-time environmental changes, effectively avoiding the slow response and water waste caused by timed or manual triggering. This achieves a balance between water conservation and efficiency, significantly improving the intelligence, energy efficiency, and stability of the spraying equipment, and enhancing the dust suppression and humidity control effects.

[0076] Reference manual attached Figure 2 The diagram shows a structural schematic of an intelligent sprinkler control system provided by the present invention.

[0077] The present invention also provides a smart sprinkler control system 20, applied to the above-mentioned smart sprinkler control method, comprising: Processor 201.

[0078] The memory 202 stores computer-readable instructions, which, when executed by the processor 201, implement the intelligent sprinkler control method as described in the method embodiment.

[0079] The intelligent sprinkler control system 20 provided by the present invention can execute the above-mentioned intelligent sprinkler control method and achieve the same or similar technical effects. To avoid repetition, the present invention will not elaborate further.

[0080] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0081] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0082] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0083] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0084] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0085] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0086] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0087] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0088] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0089] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0090] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0091] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0092] This invention provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the intelligent sprinkler control method as described in the method embodiment.

[0093] The present invention provides a computer-readable storage medium that can realize the steps and effects of the intelligent sprinkler control method in the above-described method embodiments. To avoid repetition, the present invention will not repeat them.

[0094] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0095] The following points need to be explained: (1) The accompanying drawings of the embodiments of the present invention only involve the structures involved in the embodiments of the present invention. Other structures can refer to the general design.

[0096] (2) For clarity, the thickness of layers or regions is enlarged or reduced in the drawings used to describe embodiments of the invention, i.e., these drawings are not drawn to scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being “above” or “below” another element, the element may be “directly” located “above” or “below” the other element or there may be intermediate elements.

[0097] (3) Where there is no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0098] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A smart sprinkler control method, characterized in that, include: S1: Collect environmental parameters of the spraying area; S2: Construct a multidimensional numerical simulation model; S3: Input the environmental parameters into the multidimensional numerical simulation model to determine the simulation data, wherein the simulation data specifically includes: temperature field distribution, humidity field distribution and steam concentration field distribution; S4: Perform feature extraction on the simulation data to obtain data features; S5: Construct a drying time proxy model based on an improved neural network model, wherein the improved neural network model specifically refers to: introducing deep residual learning and physical constraint modules into the neural network model; S6: Input the data features into the drying time proxy model to predict the drying status of the spray area; S7: Based on the drying state, with the goal of minimizing drying time and energy consumption, a Bayesian optimization algorithm is used to generate the optimal spraying strategy; S8: When the user selects the automatic moisture content trigger mode and the moisture content of the spray area is less than the threshold, the three-level linkage control of the spray equipment is triggered based on the optimal spray strategy.

2. The intelligent sprinkler control method according to claim 1, characterized in that, The environmental parameters specifically include: wind speed, temperature, humidity, solar radiation intensity, and spray flow rate.

3. The intelligent sprinkler control method according to claim 1, characterized in that, Specifically, S2 is: Using COMSOL Multiphysics, a multidimensional numerical simulation model was constructed, including a fluid flow module, a heat transfer process module, and a mass transfer process module.

4. The intelligent sprinkler control method according to claim 3, characterized in that, The fluid flow module specifically includes: the control equation for the porous medium inside the ore pile and the control equation for free flow outside the ore pile. The governing equation for the porous media inside the ore pile is as follows: ； in, Indicates fluid density, u Indicates fluid velocity. This represents the gradient operator. Indicates the partial derivative sign. p Indicates pressure, Indicates the dynamic viscosity of a fluid. K Indicates the permeability of porous media. t Indicates time; The specific governing equation for the free flow outside the ore pile is as follows: ； The heat transfer process module is specifically defined by the energy equation: ； ； in, T Indicates temperature. c p This represents the specific heat capacity of a fluid at constant pressure. k eff Indicates effective thermal conductivity. Q phase This represents the latent heat source term for phase change. ε Indicates porosity. k fluid Indicates the thermal conductivity of a fluid. k solid Indicates the thermal conductivity of a solid; The mass transfer process module specifically includes: liquid water seepage control equation and water vapor diffusion control equation; The specific governing equation for the liquid water seepage is as follows: ； in, p l Indicates capillary pressure. S l Indicates the degree of saturation of liquid water. This represents the relative density of liquid water. Represents the phase velocity vector of liquid water; The governing equation for water vapor diffusion is as follows: ； in, Indicates gas phase density, y i Indicates water vapor i mass fraction, R i Indicates water vapor i The phase transition rate, Indicates water vapor i The effective diffusion coefficient.

5. The intelligent sprinkler control method according to claim 1, characterized in that, The loss function of the drying time proxy model is specifically: the composite physical constraint loss function; The composite physical constraint loss function is specifically as follows: ； ； ； ； in, L Represents the loss function of composite physical constraints. λ 1, λ 2, λ 3, λ 4 represents the weight coefficient of the corresponding sub-loss function. L MSE Represents the error loss function. L mass Represents the mass conservation loss function. L energy This represents the energy conservation loss function. L mono Indicates supplementary constraints. N This represents the total number of data features. T s Indicates the first s The true temperature of each data feature H s Indicates the first s The true humidity of each data feature M s Indicates the first s The true moisture content of each data feature Indicates the first s Predicted temperature based on data features Indicates the first s Predicted humidity based on data features Indicates the first s Predicted moisture content based on data features w T This represents the weighting coefficient related to temperature. w H Indicates the weighting coefficient related to humidity. w M This represents the weighting coefficient related to moisture content. This represents the relative density of liquid water. This represents the phase velocity vector of liquid water. R i Indicates water vapor i The phase transition rate.

6. The intelligent sprinkler control method according to claim 1, characterized in that, Specifically, S7 includes: S701: The objective function is defined with the goal of minimizing drying time and energy consumption. ； Where min represents minimization. J Describe the objective function. p Indicates the drying end time. q Indicates the spray flow rate. T spray Indicates the temperature of the spray medium. J 1 indicates the first sub-objective function related to drying time. J 2 represents the second sub-objective function related to the total consumption of the spraying process. This represents the weight corresponding to the first sub-objective function. This represents the weight corresponding to the second sub-objective function. t end This indicates the drying end time, and `max` means to maximize. r This represents the coordinates of different spatial points in the ore pile. y target Indicates the moisture content threshold. E total This indicates the total consumption of spraying media. C p This indicates the specific heat capacity of the spray medium. T ambient Indicates ambient temperature. d Represents the differential operator. t Represents a time variable; S702: Using the Bayesian optimization algorithm, solve the objective function to generate the optimal spraying strategy.

7. The intelligent sprinkler control method according to claim 6, characterized in that, The Bayesian optimization algorithm is specifically as follows: ； ； Where EI() represents the desired improvement function, This represents the parameter vector to be optimized. This represents the proxy model. This represents the known optimal objective function value. Represents the balance parameters. Let Z represent the cumulative distribution function of the standard normal distribution, and let Z represent the standardized variable. This represents the standard deviation of the surrogate model's predictions. It represents the probability density function of the standard normal distribution.

8. The intelligent sprinkler control method according to claim 1, characterized in that, The three-level linkage control specifically includes: Level 1: Based on the water tank level setting parameters, automatically replenish the water to the sprinkler truck until the set value is reached; Level 2: The sprinkler system starts and executes the optimal sprinkler strategy. Level 3: Update the sprinkler status and notify the user.

9. A smart sprinkler control system, characterized in that, include: processor; A memory storing computer-readable instructions, which, when executed by the processor, implement the intelligent sprinkler control method as described in any one of claims 1 to 8.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the satellite data packet parsing method as described in any one of claims 1 to 8.

Images