A dynamic spraying dust-settling method based on a machine learning algorithm and related devices

Abstract

The application discloses a dynamic spraying dust-settling method based on a machine learning algorithm and a related device, and relates to the field of spraying dust-settling. The method comprises the following steps: acquiring dust concentration, wind speed, water supply pressure, gas supply pressure, nozzle flow, nozzle angle and surfactant concentration of a site, and determining an ideal atomization parameter by using an atomization parameter determination model and site spraying dust-settling data; and then, the spraying dust-settling system of the site can be adjusted according to the ideal atomization parameter, so that the actual atomization parameter of the spraying dust-settling system is close to the ideal atomization parameter. The scheme of the application solves the problems that the spraying dust-settling system cannot adapt to the dynamic change process of dust concentration, the effect of the spraying dust-settling system is poor, water resources are wasted, and dust-settling cost is high, reduces the pressure of dust control personnel, saves dust control cost, and realizes automatic and accurate dust-settling.

Description

Technical Field

[0001] This invention relates to the field of spray dust suppression, and in particular to a dynamic spray dust suppression method and related apparatus based on machine learning algorithms. Background Technology

[0002] With the increasing level of intelligence, mechanization and automation in mines, dust pollution has become increasingly serious. Among them, respirable dust has the characteristics of small particle size, strong dispersion ability, large surface area and easy adsorption of toxic substances. It will be distributed in the working environment with the airflow. Traditional dust suppression methods are not easy to make it settle, causing serious harm in the coal mine system.

[0003] Spray dust suppression, a commonly used method, is widely applied in various coal mines due to its economic efficiency and effectiveness. It works by breaking up water flow into fine droplets that are sprayed into the air. These droplets interact with dust particles, capturing and settling them. However, in practice, spray parameters are fixed, while dust concentration is a dynamic process. The inability to automatically adjust spray parameters based on actual conditions leads to poor dust suppression results, water waste, and high costs. Summary of the Invention

[0004] The purpose of this invention is to provide a dynamic spray dust suppression method and related device based on machine learning algorithms, which achieves the effect of dynamic spray dust suppression based on the on-site environment.

[0005] To achieve the above objectives, the present invention provides the following solution:

[0006] On the one hand, the present invention provides a dynamic spray dust suppression method based on machine learning algorithms, comprising the following steps:

[0007] Acquire on-site dust suppression data via spraying. On-site dust suppression data includes dust concentration, wind speed, water supply pressure, air supply pressure, nozzle flow rate, nozzle angle, and surfactant concentration.

[0008] The on-site dust suppression spray data is input into the atomization parameter determination model to obtain the ideal atomization parameters. The atomization parameter determination model is a model constructed based on machine learning algorithms.

[0009] Based on the ideal atomization parameters, control the on-site spray dust suppression system to make the actual atomization parameters of the spray dust suppression system close to the ideal atomization parameters.

[0010] Optionally, the atomization parameter determination model is obtained through the following steps:

[0011] Construct a simulated environment for dust suppression using spray; simulate the dust movement in the simulated environment to mimic the dust movement on-site.

[0012] A dust suppression simulation experiment was conducted in a simulated dust suppression environment, and a dust suppression experiment dataset was collected. The dust suppression experiment dataset includes simulated dust suppression data and simulated atomization parameters from the dust suppression simulation experiment. The simulated dust suppression data includes environmental dust concentration, environmental temperature, environmental humidity, environmental wind speed, water supply pressure, air supply pressure, nozzle flow rate, nozzle angle, surfactant concentration, surface tension, contact angle, and settling rate. The simulated atomization parameters include D10, D50, D90, VAD, SMD, and NAD.

[0013] Based on the strong correlation analysis between the simulated spray dust suppression data and the simulated atomization parameters, the simulated spray dust suppression data that had little impact on the simulated atomization parameters in the spray dust suppression test dataset were removed to obtain the spray dust suppression training dataset.

[0014] Based on the simulated spray dust suppression data and simulated atomization parameters in the spray dust suppression training dataset, a model for determining atomization parameters is constructed using machine learning algorithms.

[0015] Optionally, after collecting the spray dust suppression test dataset, the following may also be included:

[0016] Based on Min-Max standardization, the data in the spray dust suppression test dataset are standardized.

[0017] Optionally, the data can be standardized according to the following formula:

[0018]

[0019] Where x is the original data, x new For the standardized data, x min x is the minimum value of the data. max This represents the maximum value of the data.

[0020] Optionally, based on a strong correlation analysis of the simulated spray dust suppression data and simulated atomization parameters, simulated spray dust suppression data that have little impact on the simulated atomization parameters are removed from the spray dust suppression test dataset to obtain the spray dust suppression training dataset, which specifically includes:

[0021] Based on simulated spray dust suppression data and simulated atomization parameters, multiple correlation models were constructed using the random forest algorithm.

[0022] Based on multiple correlation models, the degree of influence of each data point in the simulated spray dust suppression data on the simulated atomization parameters was determined.

[0023] Based on the degree of influence of each data point in the simulated spray dust suppression data on the simulated atomization parameters, simulated spray dust suppression data that have little impact on the simulated atomization parameters are removed from the spray dust suppression test dataset to obtain the spray dust suppression training dataset.

[0024] Optionally, the on-site spray dust suppression system is controlled according to ideal atomization parameters, specifically including:

[0025] Based on the ideal atomization parameters and the actual atomization parameters of the spray dust suppression system, adjust the water supply pressure, air supply pressure, nozzle flow rate, nozzle angle, and surfactant concentration of the spray dust suppression system to make the actual atomization parameters of the spray dust suppression system close to the ideal atomization parameters.

[0026] Optionally, it also includes: after a preset time interval, updating the atomization parameters to determine the model parameters based on the on-site spray dust suppression data and actual atomization parameters for the preset time interval before the current moment.

[0027] On the other hand, the present invention provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the dynamic spray dust suppression method based on machine learning algorithm described in any of the preceding claims.

[0028] On the other hand, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the dynamic spray dust suppression method based on machine learning algorithm described in any of the preceding claims.

[0029] On the other hand, the present invention provides a computer program product, including a computer program, characterized in that, when the computer program is executed by a processor, it implements the steps of the dynamic spray dust suppression method based on machine learning algorithm described in any of the above claims.

[0030] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0031] This invention provides a dynamic spray dust suppression method and related device based on machine learning algorithms. The method includes the following steps: acquiring on-site data including dust concentration, wind speed, water supply pressure, air supply pressure, nozzle flow rate, nozzle angle, and surfactant concentration; determining ideal atomization parameters using an atomization parameter determination model and on-site spray dust suppression data; and then appropriately adjusting the on-site spray dust suppression system according to the ideal atomization parameters so that the actual atomization parameters of the spray dust suppression system are close to the ideal atomization parameters. The present invention constructs an atomization parameter determination model based on machine learning algorithms. This model accurately predicts ideal atomization parameters based on on-site dust concentration, wind speed, water supply pressure, air supply pressure, nozzle flow rate, nozzle angle, and surfactant concentration. Based on the ideal atomization parameters output by this model, the system automatically adjusts the on-site spray dust suppression system to perform atomization. This achieves automatic adjustment of the spray dust suppression system according to actual on-site conditions, enabling the system to operate with near-ideal atomization parameters. It solves the problems of inability to adapt to dynamic changes in dust concentration, poor system performance, water waste, and high dust suppression costs. This reduces the workload of dust control personnel, saves dust control costs, and achieves automated and precise dust suppression. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the 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.

[0033] Figure 1 A flowchart of a dynamic spray dust suppression method based on machine learning algorithm provided in Embodiment 1 of the present invention;

[0034] Figure 2 This is a flowchart illustrating the construction of an atomization parameter determination model in a dynamic spray dust suppression method based on machine learning algorithms provided in Embodiment 1 of the present invention.

[0035] Figure 3 This is a flowchart of step B3 in a dynamic spray dust suppression method based on machine learning algorithm provided in Embodiment 1 of the present invention.

[0036] Figure 4 This is a diagram of the internal structure of a computer device. Detailed Implementation

[0037] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] The purpose of this invention is to provide a dynamic spray dust suppression method and related device based on machine learning algorithms, which aims to solve the problems of traditional spray dust suppression systems being unable to adapt to the dynamic changes in dust concentration, resulting in poor spray dust suppression effects, water waste, and high dust suppression costs. This invention also aims to reduce the pressure on dust control personnel, save dust control costs, and achieve automated and precise dust suppression.

[0039] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0040] Example 1

[0041] like Figure 1 The flowchart shown illustrates a dynamic spray dust suppression method based on machine learning algorithms in this embodiment, comprising the following steps:

[0042] A1. Obtain on-site dust suppression spray data. On-site dust suppression spray data includes dust concentration, wind speed, water supply pressure, air supply pressure, nozzle flow rate, nozzle angle, and surfactant concentration.

[0043] A2. Input the on-site spray dust suppression data into the atomization parameter determination model to obtain the ideal atomization parameters. The atomization parameter determination model is a model built based on machine learning algorithms.

[0044] A3. Based on the ideal atomization parameters, control the on-site spray dust suppression system to make the actual atomization parameters of the spray dust suppression system close to the ideal atomization parameters. Step A3, controlling the on-site spray dust suppression system based on the ideal atomization parameters, specifically includes the following steps:

[0045] Based on the ideal atomization parameters and the actual atomization parameters of the spray dust suppression system, adjust the water supply pressure, air supply pressure, nozzle flow rate, nozzle angle, and surfactant concentration of the spray dust suppression system to make the actual atomization parameters of the spray dust suppression system close to the ideal atomization parameters.

[0046] Considering the dynamic changes in on-site dust transport and the limited capacity of model training samples, the model dataset is iteratively updated. Therefore, after step A3, the method provided in this embodiment further includes:

[0047] A4. After a preset time interval, based on the on-site spray dust suppression data and actual atomization parameters from the preset time prior to the current moment, update the atomization parameters to determine the model parameters; then return to step A1 to continue acquiring on-site spray dust suppression data. In this embodiment, the model is retrained using on-site data from every 3 hours of dust suppression to update the model parameters and complete the closed loop of data prediction.

[0048] In real-world environments, considering the dynamic changes in various factors affecting dust control, this embodiment combines machine learning algorithms with a spray dust suppression system. Specifically, for example... Figure 2 The flowchart shown illustrates how the atomization parameter determination model in this embodiment is obtained through the following steps:

[0049] B1. Construct a simulated dust suppression spray environment. The dust transport in the simulated dust suppression spray environment will simulate the dust transport in the actual site.

[0050] B2. Conduct a spray dust suppression simulation experiment in a simulated spray dust suppression environment and collect the spray dust suppression test dataset. The spray dust suppression test dataset includes simulated spray dust suppression data and simulated atomization parameters from the spray dust suppression simulation experiment; the simulated spray dust suppression data includes environmental dust concentration, environmental temperature, environmental humidity, environmental wind speed, water supply pressure, air supply pressure, nozzle flow rate, nozzle angle, surfactant concentration, surface tension, contact angle, and settling rate; the simulated atomization parameters include D10, D50, D90, VAD, SMD, and NAD. D10, D50, and D90 represent the percentage of particles with a different diameter than the current particle in the current fog. D10 indicates that 10% of the particles in the current fog have a different diameter, meaning that most particles in the current fog have the same diameter. Similarly, D90 indicates that 90% of the particles in the current fog have a different diameter, meaning that most particles in the current fog have different diameters. SMD is the surface area-weighted average particle size, NAD is the number-weighted average particle size, and VAD is the volume-weighted average particle size.

[0051] B3. A strong correlation analysis is performed on the simulated spray dust suppression data and simulated atomization parameters to obtain the spray dust suppression training dataset. Specifically, based on the strong correlation analysis, simulated spray dust suppression data that have little impact on the simulated atomization parameters are removed from the spray dust suppression experimental dataset to obtain the spray dust suppression training dataset. For example... Figure 3 The flowchart shown, step B3 specifically includes the following steps:

[0052] B31. Based on simulated spray dust suppression data and simulated atomization parameters, multiple correlation models are constructed using the random forest algorithm. Using surfactant-related parameters (surfactant concentration, surface tension, contact angle, and settling rate), spray atomization-related parameters (water supply pressure, air supply pressure, nozzle flow rate, and nozzle angle), and simulated environmental parameters (temperature, humidity, wind speed, and dust concentration) as input values, and various atomization particle size-related parameters (D10, D50, D90, VAD, SMD, NAD) as output values, multiple correlation models are constructed using the random forest algorithm, and hyperparameter grid search and model training are performed.

[0053] B32. Based on multiple correlation models, determine the degree of influence of each data point in the simulated spray dust suppression data on the simulated atomization parameters. Calculate the importance of each input value to the output value, i.e., the degree of influence, and sort them according to their importance after taking the absolute value.

[0054] B33. Based on the influence of each data point in the simulated spray dust suppression data on the simulated atomization parameters, a spray dust suppression training dataset is obtained. Specifically, based on the influence of each data point in the simulated spray dust suppression data on the simulated atomization parameters, simulated spray dust suppression data with little influence on the simulated atomization parameters are removed from the spray dust suppression test dataset to obtain the spray dust suppression training dataset. In this embodiment, the analysis shows that surface tension, contact angle, and sedimentation rate are strongly correlated with surfactant concentration and do not need to be considered repeatedly; therefore, only surfactant concentration is considered as an input value. Temperature and humidity conditions are difficult to effectively adjust on-site and cannot be significantly changed on-site; therefore, they are not considered as input values.

[0055] B4. Based on the simulated spray dust suppression data and simulated atomization parameters in the spray dust suppression training dataset, an atomization parameter determination model is constructed using a machine learning algorithm. Specifically, in this embodiment, the machine learning algorithm used is the multiple linear regression algorithm. In this embodiment, using multiple linear regression analysis—normalization equations—surfactant concentration, water supply pressure, air supply pressure, nozzle flow rate and nozzle angle, wind speed, and dust concentration as input values, the model is trained with each atomization particle size-related parameter: D10, D50, D90, VAD, SMD, and NAD to construct the atomization parameter determination model.

[0056] Because of the differences in the physical dimensions of the data collected above, in order to reduce fitting errors, parameters with large data deviations are standardized. That is, after collecting the spray dust suppression test dataset, the following steps are also taken:

[0057] Based on Min-Max standardization, the data in the spray dust suppression experiment dataset are standardized. Min-Max standardization, also known as minimum-maximum standardization, is a linear transformation of the data, mapping the resulting values ​​to the range [0, 1]. The data is standardized according to the following formula:

[0058]

[0059] Where x is the original data, x new For the standardized data, x min x is the minimum value of the data. max This represents the maximum value of the data.

[0060] The dynamic spray dust suppression method based on machine learning algorithms provided in this embodiment constructs an atomization parameter determination model that can accurately predict ideal atomization parameters based on on-site dust concentration, wind speed, water supply pressure, air supply pressure, nozzle flow rate, nozzle angle, and surfactant concentration. Based on the ideal atomization parameters output by this model, the system automatically adjusts the on-site spray dust suppression system to perform atomization. This achieves automatic adjustment of the spray dust suppression system according to actual on-site conditions, enabling the system to perform dust suppression under conditions close to ideal atomization parameters. This solves the problems of inability to adapt to dynamic changes in dust concentration, poor system performance, water waste, and high dust suppression costs. It also reduces the workload of dust control personnel, saves dust control costs, and achieves automated and precise dust suppression.

[0061] Example 2

[0062] A computer device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of a dynamic spray dust suppression method based on a machine learning algorithm as described in Embodiment 1.

[0063] Example 3

[0064] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a dynamic spray dust suppression method based on a machine learning algorithm as described in Embodiment 1.

[0065] Example 4

[0066] A computer program product includes a computer program that, when executed by a processor, implements the steps of a dynamic spray dust suppression method based on a machine learning algorithm as described in Embodiment 1.

[0067] Example 5

[0068] A computer device, which may be a database, may have an internal structure diagram as shown below. Figure 4 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores pending transactions. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a dynamic spray dust suppression method based on a machine learning algorithm as described in Embodiment 1.

[0069] It should be noted that the object information (including but not limited to object device information, object personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this invention are all information and data authorized by the object or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0070] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided by this invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided by this invention may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided by this invention may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0071] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0072] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A dynamic spray dust suppression method based on machine learning algorithms, characterized in that, include: Acquire on-site dust suppression spray data; the on-site dust suppression spray data includes dust concentration, wind speed, water supply pressure, air supply pressure, nozzle flow rate, nozzle angle, and surfactant concentration; The on-site dust suppression spray data is input into the atomization parameter determination model to obtain ideal atomization parameters; the atomization parameter determination model is a model constructed based on machine learning algorithms; Based on the ideal atomization parameters, control the on-site spray dust suppression system so that the actual atomization parameters of the spray dust suppression system are close to the ideal atomization parameters; After a preset time interval, the model parameters of the atomization parameter determination model are updated based on the on-site dust suppression data and actual atomization parameters for the preset time interval before the current moment. The atomization parameter determination model is obtained through the following steps: A simulated dust suppression spray environment is constructed; the dust movement in the simulated dust suppression spray environment simulates the dust movement on-site. A dust suppression simulation experiment was conducted in the simulated dust suppression environment, and a dust suppression experiment dataset was collected. The dust suppression experiment dataset includes simulated dust suppression data and simulated atomization parameters from the dust suppression simulation experiment. The simulated dust suppression data includes environmental dust concentration, environmental temperature, environmental humidity, environmental wind speed, water supply pressure, air supply pressure, nozzle flow rate, nozzle angle, surfactant concentration, surface tension, contact angle, and settling rate. The simulated atomization parameters include D10, D50, D90, VAD, SMD, and NAD. D10, D50, and D90 represent the percentage of particles with a different diameter than the current particle in the current mist. D10 indicates that the percentage of particles with a different diameter than the current particle in the current mist is 10%. D90 indicates that the percentage of particles with a different diameter than the current particle in the current mist is 90%. SMD is the surface area-weighted average particle size, NAD is the number-weighted average particle size, and VAD is the volume-weighted average particle size. Based on the strong correlation analysis of the simulated spray dust suppression data and the simulated atomization parameters, the simulated spray dust suppression data that have little impact on the simulated atomization parameters in the spray dust suppression test dataset are removed to obtain the spray dust suppression training dataset; Based on the simulated spray dust suppression data and the simulated atomization parameters in the spray dust suppression training dataset, a model for determining atomization parameters is constructed using a machine learning algorithm.

2. The dynamic spray dust suppression method based on machine learning algorithm according to claim 1, characterized in that, After collecting the data set from the spray dust suppression experiment, the following is also included: Based on Min-Max standardization, the data in the spray dust suppression test dataset are standardized.

3. The dynamic spray dust suppression method based on machine learning algorithm according to claim 2, characterized in that, The data is standardized according to the following formula: ； in, x For the original data, x new For standardized data, x min The minimum value of the data. x max This represents the maximum value of the data.

4. The dynamic spray dust suppression method based on machine learning algorithm according to claim 1, characterized in that, Based on a strong correlation analysis of the simulated spray dust suppression data and the simulated atomization parameters, simulated spray dust suppression data that have little impact on the simulated atomization parameters are removed from the spray dust suppression test dataset to obtain the spray dust suppression training dataset, which specifically includes: Based on the simulated spray dust suppression data and the simulated atomization parameters, multiple correlation models are constructed using the random forest algorithm. Based on multiple correlation models, determine the degree of influence of each data point in the simulated spray dust suppression data on the simulated atomization parameters; Based on the degree of influence of each data point in the simulated spray dust suppression data on the simulated atomization parameters, simulated spray dust suppression data that have little influence on the simulated atomization parameters are removed from the spray dust suppression test dataset to obtain the spray dust suppression training dataset.

5. The dynamic spray dust suppression method based on machine learning algorithm according to claim 1, characterized in that, Based on the ideal atomization parameters, the on-site spray dust suppression system is controlled, specifically including: Based on the ideal atomization parameters and the actual atomization parameters of the spray dust suppression system, adjust the water supply pressure, air supply pressure, nozzle flow rate, nozzle angle, and surfactant concentration of the spray dust suppression system so that the actual atomization parameters of the spray dust suppression system are close to the ideal atomization parameters.

6. A computer device, comprising: The memory and processor contain a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the dynamic spray dust suppression method based on a machine learning algorithm according to any one of claims 1-5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the dynamic spray dust suppression method based on a machine learning algorithm as described in any one of claims 1-5.

8. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the dynamic spray dust suppression method based on a machine learning algorithm as described in any one of claims 1-5.

Images