Spray dust suppression method and system based on multi-field multi-phase model and deep learning algorithm

Abstract

The invention relates to the technical field of industrial spray dust fall and the technical field of computers, and discloses a spray dust fall method and system based on a multi-field multi-phase model and a deep learning algorithm. The method comprises the following steps: acquiring dust data and environment data of a region to be subjected to dust fall; according to the dust particle size data, the dust density data, the wind speed data and the air density data, the dust migration speed under the multi-field and multi-phase theory is calculated; carrying out characterization processing on the dust data and the dust migration speed; according to the processing result and the trained spray solution parameter prediction model, generating a spray solution type and dosage prediction result; and according to the prediction result, dust falling of the area to be subjected to dust falling is realized. According to the method, the dust migration speed calculated based on the multi-field and multi-phase model and the spray solution parameter prediction model based on the deep learning algorithm are utilized to calculate, predict and update the dust data of the area to be subjected to dust falling, so that more accurate spray solution types and doses can be obtained, and the dust falling effect of the area to be subjected to dust falling is remarkably improved.

Description

Technical Field

[0001] The present disclosure relates to the fields of spray dust suppression technology and computer technology, and in particular to a spray dust suppression method and system based on a multi-field multi-phase model and a deep learning algorithm. Background Art

[0002] In the production activities of modern industry, agriculture and other fields, the generation and spread of dust is an environmental problem that needs to be solved urgently. Whether it is underground coal mines, open-pit coal mines, or screening workshops in washing plants, a large amount of dust will be generated during their respective production processes. These dusts will not only endanger the health of workers, but also cause serious pollution to the surrounding environment. At present, spray dust suppression technology has gradually become one of the important means of controlling dust. An effective spray dust suppression system is crucial to controlling dust pollution.

[0003] In traditional spray dust suppression systems, the selection of spray solution type and dosage often relies on experience, lacking scientific and systematic theoretical guidance. This approach may lead to the selection of inaccurate spray solution type and dosage, which in turn affects the final dust suppression effect. Therefore, it is urgent to provide an improved technical solution for the above technical deficiencies. Summary of the invention

[0004] In view of the above situation, the embodiments of the present disclosure provide a spray dust reduction method and system based on a multi-field multi-phase model and a deep learning algorithm, aiming to solve the above problems or at least partially solve the above problems.

[0005] In a first aspect, an embodiment of the present disclosure provides a spray dust suppression method based on a multi-field multi-phase model and a deep learning algorithm, the method comprising: Obtain dust data and environmental data of the area to be dusted; wherein the dust data includes dust concentration data, dust particle size data, dust density data and dust particle mineral component data, and the environmental data includes wind speed data and air density data; Calculating the dust migration velocity under the multi-field multi-phase theory according to the dust particle size data, the dust density data, the wind speed data and the air density data; Performing characterization processing on the dust data and the dust migration speed to obtain processed dust data and processed dust migration speed respectively; Generate a spray solution type prediction result and a spray solution dosage prediction result according to the treated dust data, the treated dust migration speed and the trained spray solution parameter prediction model; According to the prediction results of the type of spray solution and the prediction results of the dosage of the spray solution, the target spray dust reduction system is controlled to achieve dust reduction in the area to be dust reduced.

[0006] In a second aspect, the embodiment of the present disclosure further provides a spray dust suppression device based on a multi-field multi-phase model and a deep learning algorithm, the device comprising: An acquisition module is used to acquire dust data and environmental data of the area to be dusted; wherein the dust data includes dust concentration data, dust particle size data, dust density data and dust particle mineral component data, and the environmental data includes wind speed data and air density data; A calculation module, used for calculating the dust migration speed under the multi-field multi-phase theory according to the dust particle size data, the dust density data, the wind speed data and the air density data; A characterization module, used for performing characterization processing on the dust data and the dust migration speed to obtain processed dust data and processed dust migration speed respectively; A prediction module, for generating a spray solution type prediction result and a spray solution dosage prediction result according to the treated dust data, the treated dust migration speed and a trained spray solution parameter prediction model; The dust reduction module is used to control the target spray dust reduction system according to the prediction result of the spray solution type and the prediction result of the spray solution dosage, so as to achieve dust reduction in the area to be dusted.

[0007] In a third aspect, the disclosed embodiment further provides a spray dust suppression system based on a multi-field multi-phase model and a deep learning algorithm, the system comprising: a data acquisition device, a spray solution parameter prediction unit, a dry fog dust suppression host, and an atomizing nozzle; The data acquisition device is used to collect dust data and environmental data of the area to be dusted, and send the dust data and environmental data to the spray solution parameter prediction unit; The spray solution parameter prediction unit is used to perform the steps of the method described in the first aspect; The dry fog dust suppression host is used to control the output power of the atomizing nozzle and the type of solution sprayed according to the received prediction result of the type of spray solution and the prediction result of the dosage of the spray solution.

[0008] In a fourth aspect, an embodiment of the present disclosure further provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions, which, when executed, cause the processor to perform the steps of the above-mentioned spray dust reduction method based on a multi-field multi-phase model and a deep learning algorithm.

[0009] In a fifth aspect, an embodiment of the present disclosure also provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes the steps of the above-mentioned spray dust reduction method based on the multi-field multi-phase model and deep learning algorithm.

[0010] By means of the above technical scheme, the spray dust reduction method and system based on the multi-field multi-phase model and deep learning algorithm provided by the embodiment of the present disclosure does not rely on human subjective experience. By obtaining the dust data and environmental data of the area to be dusted, the dust migration speed under the multi-field multi-phase model is calculated based on the dust data and environmental data and the spatiotemporal laws of dust diffusion, migration and aggregation. The dust data can more accurately reflect the overall dust situation in the area to be dusted, and the dust migration speed can accurately simulate the movement of dust in the actual environment. The dust data and the dust migration speed are characterized, and according to the processed dust data and the processed dust migration speed, a spray solution parameter prediction model based on a deep learning algorithm can be used to predict more accurate and reasonable types and dosages of spray solutions. Finally, according to the prediction results of the type and dosage of the spray solution, the target spray dust reduction system is controlled, which can significantly improve the dust reduction effect on the area to be dusted.

[0011] The above description is only an overview of the technical solution of the present disclosure. In order to more clearly understand the technical means of the present disclosure, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the specific implementation methods of the present disclosure are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure. In the drawings: Figure 1 A schematic flow chart of a spray dust suppression method based on a multi-field multi-phase model and a deep learning algorithm provided in an embodiment of the present disclosure is shown; Figure 2 A schematic diagram of the structure of a spray dust suppression device based on a multi-field multi-phase model and a deep learning algorithm provided in an embodiment of the present disclosure is shown; Figure 3 A schematic diagram of the structure of a spray dust suppression system based on a multi-field multi-phase model and a deep learning algorithm provided in an embodiment of the present disclosure is shown; Figure 4 A schematic diagram of the structure of another spray dust suppression system based on a multi-field multi-phase model and a deep learning algorithm provided by an embodiment of the present disclosure is shown; Figure 5A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the technical solutions of the present disclosure will be clearly and completely described below in combination with the specific embodiments of the present disclosure and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0014] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0015] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such usage is interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the term "including" and its variants are to be interpreted as open-ended terms meaning "including but not limited to".

[0016] As mentioned above, in traditional spray dust suppression systems, the selection of spray solution type and dosage often relies on experience and lacks scientific and systematic theoretical guidance. This approach may lead to the selection of inaccurate spray solution type and dosage, which in turn affects the final dust suppression effect. Based on this, the present invention proposes a spray dust suppression method and system based on a multi-field multi-phase model and a deep learning algorithm. The present disclosure is described in detail below through specific embodiments.

[0017] To facilitate understanding of this embodiment, a spray dust reduction method based on a multi-field multi-phase model and a deep learning algorithm disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the spray dust reduction method based on a multi-field multi-phase model and a deep learning algorithm provided in the embodiment of the present disclosure is generally a computer device with a certain computing power, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, etc. In some implementations, the spray dust reduction method based on a multi-field multi-phase model and a deep learning algorithm can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0018] Figure 1 The schematic diagram of the process of the spray dust suppression method based on the multi-field multi-phase model and the deep learning algorithm provided by the embodiment of the present disclosure is shown. Figure 1 It can be seen that the embodiment of the present disclosure at least includes steps S101-S105: S101: Obtain dust data and environmental data of the area to be dusted; wherein the dust data includes dust concentration data, dust particle size data, dust density data and dust particle mineral component data, and the environmental data includes wind speed data and air density data.

[0019] Here, the area to be dusted is any area where production operations are carried out, dust particles are generated and spread, and dust reduction is required. The specific area can be selected according to actual needs.

[0020] Dust concentration refers to the mass of dust contained in a unit volume of air. Dust concentration can directly reflect the density of dust in the area to be dusted. The higher the concentration, the greater the amount of spray solution required for dust reduction, and it also affects the choice of spray solution type. For example, high-concentration dust may require a spray solution with a stronger dust reduction effect. Dust particle size refers to the average particle size of dust particles. Dust of different particle sizes has different suspension characteristics and sedimentation speeds in the air. Dust with smaller particle sizes is easier to suspend and difficult to settle. It may require finer spray particles and specific types of spray solutions to effectively capture and settle. Dust density refers to the ratio of the mass of dust particles to their volume. The higher the dust density, the greater the dust mass per unit volume. The amount of spray solution required for dust reduction may need to be increased accordingly to ensure adequate coverage and sedimentation of dust. At the same time, high dust density may also prompt the selection of spray solutions with stronger adhesion or targeting to cope with denser dust particles. The mineral composition of dust particles refers to the mineral source of dust formation. The mineral composition of dust particles can help understand the chemical and physical properties of dust. Different mineral components may have different reactions and adsorption effects on the spray solution. Some minerals may be more easily combined with specific chemical reagents and thus precipitated. For example, the dust concentration data, dust particle size data, and dust particle mineral component data may be the average dust concentration, average dust particle size, and the largest proportion of the mineral component in the dust removal area over a period of time.

[0021] The method for the subject of the method to obtain dust data and environmental data depends on the needs of the actual scenario, and this disclosure does not specifically limit this. For example, dust data and environmental data can be obtained by using detection devices such as dust particle counters and laser component online analyzers, anemometers, and gas densitometers, or by directly receiving dust data and environmental data manually input by users through the front-end page.

[0022] S102: Calculate the dust migration velocity under the multi-field multi-phase theory according to the dust particle size data, the dust density data, the wind speed data and the air density data.

[0023] S103: performing characterization processing on the dust data and the dust migration speed to obtain processed dust data and processed dust migration speed respectively.

[0024] S104: Generate a spray solution type prediction result and a spray solution dosage prediction result according to the treated dust data, the treated dust migration speed and the trained spray solution parameter prediction model.

[0025] Here, the trained spray solution parameter prediction model is constructed based on an iteratively optimized deep neural network model. During implementation, for example, the sample set can be used to train the multi-layer perceptron (MLP) neural network model through forward propagation, and the trained spray solution parameter prediction model can be obtained by continuously optimizing it through error back propagation. The trained spray solution parameter prediction model includes an input layer, a hidden layer, and an output layer. Among them, the input data of the input layer includes but is not limited to the processed dust data and the processed dust migration speed. The hidden layer can use activation functions such as rectified linear units (ReLU) to activate neurons, and use cross entropy loss functions to evaluate the prediction error of the model. The output data of the output layer is the type and dosage of the spray solution in the next period of time.

[0026] S105: According to the prediction result of the type of spray solution and the prediction result of the dosage of the spray solution, the target spray dust reduction system is controlled to achieve dust reduction in the area to be dust reduced.

[0027] It can be seen that compared with the prior art, the embodiment of the present disclosure does not rely on people's subjective experience. It obtains dust data and environmental data of the area to be dusted, and calculates the dust migration speed under the multi-field multi-phase theory based on the dust data and environmental data and the spatiotemporal laws of dust diffusion, migration and aggregation. The dust data can more accurately reflect the overall dust situation in the area to be dusted, and the dust migration speed can accurately simulate the movement of dust in the actual environment. The dust data and the dust migration speed are characterized, and according to the processed dust data and the processed dust migration speed, a spray solution parameter prediction model based on a deep learning algorithm can be used to predict a more accurate and reasonable type and dosage of the spray solution. Finally, according to the prediction results of the type and dosage of the spray solution, the target spray dust reduction system is controlled, which can significantly improve the dust reduction effect on the area to be dusted.

[0028] Furthermore, in order to better illustrate the process of the above-mentioned spray dust reduction method based on the multi-field multi-phase model and the deep learning algorithm, as a refinement and extension of the above-mentioned embodiment, the embodiment of the present invention provides several embodiments, but is not limited thereto, as follows.

[0029] During implementation, the step is to calculate the dust migration velocity under the multi-field multi-phase theory based on the dust particle size data, dust density data, wind speed data and air density data. Specifically, the generation and movement of dust essentially belong to the category of gas-solid two-phase flow in the multi-field multi-phase theory. In this category, mechanical fields and fluid fields are mainly involved. In the process of dust diffusion and migration, the air fluid can be regarded as a continuous medium, and the dust particles can be regarded as discrete phases. In some application scenarios, the movement of dust in the air can be decomposed into two modes: horizontal movement with the airflow and vertical sedimentation with the action of gravity. In the horizontal direction, the dust will gradually accelerate under the drag force of the airflow until its speed is equal to the airflow speed. From Newton's second law, we can get: ; In the formula, —Horizontal component of dust migration velocity, m / s; —Gas movement speed, i.e. wind speed; —Air density, kg / m 3 ; —dust particle size, mm; —Rock density, i.e. dust particle density, kg / m 3 ; —Gas resistance coefficient, m / s. During implementation, the gas resistance coefficient can be obtained by referring to relevant professional literature and manuals; t—time, s.

[0030] Set wind speed is a certain value ( ≠0), and , after substituting into the above formula and performing indefinite integration, we get: ; Let t = 0, =0 is substituted into the above formula, and C=1 is calculated. Then the horizontal component of the dust migration velocity is: ; In the vertical direction, the forces acting on dust are mainly gravity and air resistance, which determine the movement time of dust in space and indirectly affect the trajectory of its diffusion movement. For dust moving in horizontal airflow, if the airflow velocity in the vertical direction is zero, the force equation of dust in the vertical direction is: ; In the formula, —Vertical component of dust transport velocity, m / s; g—gravitational acceleration, m / s².

[0031] set up ,but , transform the above force equation to obtain: ; Integrating both sides of the above transformed equation, we can get: ; Let t = 0, =0, we can calculate C=0, and substitute it into the above formula to get: ; Assumptions ,but , , so the vertical component of dust migration velocity is: ; In some embodiments of the present disclosure, the trained spray solution parameter prediction model is a first parameter prediction model; generating a spray solution type prediction result and a spray solution dosage prediction result based on the treated dust data, the treated dust migration speed and the trained spray solution parameter prediction model includes: inputting the treated dust data and the treated dust migration speed into the first parameter prediction model to obtain the spray solution type prediction result and the spray solution dosage prediction result.

[0032] For the first parameter prediction model, in some embodiments, the first parameter prediction model is obtained according to the following method: obtaining a first data set; the characteristics of the samples in the first data set include dust characteristic data and dust migration speed characteristic data, and the labels of the samples include spray solution type and spray solution dosage data; using the first data set to train the first initial parameter prediction model to obtain the first parameter prediction model.

[0033] During implementation, the first data set can be constructed first. Specifically, based on industrial big data technology, information retrieval can be performed with spray dust reduction systems in typical industrial fields such as coking, coal, and mining as index conditions to obtain historical dust removal data of various spray dust reduction systems. During implementation, the historical dust removal data of the spray dust reduction system that controls an area similar to the area to be dusted can also be directly obtained, so as to train a first parameter prediction model that is more suitable for the area to be dusted based on these historical dust removal data. Then, information extraction is performed on the historical dust removal data, and the obtained dust data, environmental data, and spray solution parameter data are used as the basis to construct the first data set.

[0034] It can be understood that the end time of the time interval corresponding to the model input data is earlier than the start time of the time interval corresponding to the model output data, so that the model can effectively predict the future spray solution parameters based on the historical dust conditions and environmental conditions.

[0035] For example, a sample in the first data set includes: an average dust particle size value of 5 microns, an average dust concentration value of 100 mg / m3, an average dust density value of 0.01 kg / m3, and dust particle mineral components of "quartz 30%, feldspar 20%, clay 50%" in the past 24 hours, and an average dust migration speed value of 1 m / s. The sample is characterized to obtain corresponding characteristic values, which are used as the characteristics of the sample. The sample labels include: the type of spray solution in the next 12 hours is sodium chloride solution, and the average dosage data is 5 liters.

[0036] After obtaining the first data set, the first initial parameter prediction model can be trained with the first data set. During implementation, the first data set can be divided into a training set and a validation set according to a preset data partitioning rule. Among them, the preset data partitioning rule can be set by a technician in this field according to the actual amount of training data. For example, the proportion of the training set to the first data set can be set to 80%, and the proportion of the validation set to the first data set can be set to 20%. Then, the first initial parameter prediction model is supervised and validated using the training set and the validation set. During specific training, first, a group of training data is randomly selected from the training set to start supervised training. Among them, each group of training data includes its corresponding dust characteristic data and dust migration velocity characteristic data; the labels obtained by the training are compared with the original labels in the group of training data. When the two are consistent, supervised training of the next group of training data is performed; when the two are inconsistent, the error is redistributed according to the error back propagation method, and the weights and bias parameters in the hidden layer activation function of the first initial parameter prediction model are continuously optimized, and then supervised training of the next group of training data is continued. By continuously iterative supervised training, the output result of the first initial parameter prediction model tends to be stable. The validation set is then used to perform validation training on the first initial parameter prediction model at this time, and when the accuracy of the output result of the model is higher than or equal to the expected target value, the trained first parameter prediction model is obtained. The expected target value can be set according to actual needs, and the embodiments of the present disclosure are not limited to this.

[0037] Research has found that in some scenarios, environmental factors play an important role in the physical characteristics of dust generation, movement trend, movement trajectory, etc. For example, the higher the ambient temperature, the lower the humidity, and the greater the wind speed, the greater the amount of dust generated. For another example, in open-pit coal mines and coal yards, the wind speed is high, and the dust is easier to spread. These physical characteristics of dust directly affect the determination of the type and dosage of the spray solution. It can be seen that in these scenarios, environmental factors largely determine the prediction results of the type and dosage of the spray solution. Based on this, in some embodiments of the present disclosure, the environmental data also includes at least one of temperature data, humidity data, and wind direction data; if the trained spray solution parameter prediction model is a second parameter prediction model; the method also includes: characterizing the environmental data to obtain processed environmental data; generating spray solution type prediction results and spray solution dosage prediction results based on the processed dust data, the processed dust migration speed and the trained spray solution parameter prediction model, including: inputting the processed dust data, the processed dust migration speed and the processed environmental data into the second parameter prediction model to obtain the spray solution type prediction results and the spray solution dosage prediction results.

[0038] Here, wind direction refers to the direction from which the wind blows. In implementation, for example, 8 directions (east, south, west, north, southeast, northeast, southwest, northwest) or 16 directions can be used to describe the wind direction. This embodiment does not limit the characterization processing method for environmental data. Exemplarily, for ambient temperature data, ambient humidity data, wind speed data, and air density data, they can be normalized to obtain corresponding eigenvalues; for wind direction, the wind direction can be characterized using unique hot encoding to obtain corresponding eigenvalues.

[0039] In some embodiments, the second parameter prediction model is obtained according to the following method: obtaining a second data set; the characteristics of the samples in the second data set include dust characteristic data, environmental characteristic data and dust migration speed characteristic data, and the labels of the samples include spray solution type and spray solution dosage data; using the second data set to train the second initial parameter prediction model to obtain the second parameter prediction model.

[0040] During implementation, first construct the second data set. The specific construction process is similar to that of the first data set, and will not be repeated here. For example, a sample in the second data set includes: the average dust particle size value of 4 microns, the average dust concentration value of 120 mg / m3, the average dust density value of 0.01 kg / m3, the dust particle mineral composition of "quartz 30%, feldspar 20%, clay 50%", the average wind speed of 10 m / s, the average air density value of 2 kg / m3, and the average dust migration speed value of 1 m / s. The sample is characterized to obtain the corresponding characteristic values, and these characteristic values ​​are used as the characteristics of the sample. The label of the sample includes: the type of spray solution in the next 0.5 hours is sodium chloride solution, and the average dosage data is 1 liter.

[0041] After obtaining the second data set, the second initial parameter prediction model is trained with the second data set to obtain the second parameter prediction model. The specific training process is similar to the training process of the first initial parameter prediction model, and will not be repeated here.

[0042] This embodiment takes into account the environmental factors that affect the dust reduction effect, and inputs the treated environmental data of the dust reduction area, the treated dust migration speed and the treated dust data into the second parameter prediction model together, so that the spray solution type and dosage prediction results generated by the model are more accurate and reasonable, thereby further improving the dust reduction effect.

[0043] The embodiment of the present disclosure also provides a spray dust reduction method based on a multi-field multi-phase model and a deep learning algorithm, comprising the following steps: Step S1: Obtain dust data and environmental data of the area to be dusted, the dust data includes dust concentration data, dust particle size data, dust density data, and dust particle mineral composition data, and the environmental data includes temperature data, humidity data, wind speed data, wind direction data, and air density data.

[0044] Step S2: Calculate the dust migration velocity under the multi-field multi-phase theory according to the dust particle size data, dust density data, wind speed data and air density data.

[0045] Step S3: Characterize the dust data, environmental data and dust migration speed to obtain processed dust data, processed environmental data and processed dust migration speed.

[0046] Step S4: input the treated dust data, the treated environment data and the treated dust migration speed into the third parameter prediction model to obtain the spray solution type prediction result and the spray solution dosage prediction result.

[0047] During implementation, the third parameter prediction model is obtained according to the following method: A third data set is obtained; the characteristics of the samples in the third data set include dust characteristic data, environmental characteristic data, and dust migration speed characteristic data, and the labels of the samples include spray solution type and spray solution dosage data; the third initial parameter prediction model is trained using the third data set to obtain a third parameter prediction model. The third initial parameter prediction model is obtained based on a deep learning algorithm.

[0048] Step S5: According to the prediction results of the type of spray solution and the dosage of spray solution, the target spray dust reduction system is controlled to achieve dust reduction in the area to be dusted.

[0049] This embodiment first comprehensively obtains dust data of the area to be dusted, including information such as dust concentration, particle size, density and mineral composition, as well as environmental data such as temperature, humidity, wind speed, wind direction and air density. Then, based on data such as dust particle size, density, wind speed and air density, the dust migration speed is calculated through multi-field multi-phase theory, which reflects the movement of dust in the environment. Then, the collected dust data, environmental data and calculated dust migration speed are characterized, and the processed data are input into the third parameter prediction model obtained based on the deep learning algorithm. The model can accurately predict the type and dosage of the spray solution added according to the environment and dust distribution and operation conditions of the area to be dusted. Finally, the target spray dust reduction system is controlled based on the predicted results of the type and dosage of the spray solution. This solution can greatly improve the efficiency of spray dust reduction, reduce resource waste, and enable the spray dust reduction system to have stronger adaptability and flexibility when facing complex and changeable dust reduction scenes.

[0050] Those skilled in the art will appreciate that, in the above method of the specific implementation manner, the writing order of the steps does not mean a strict execution order, but does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0051] It should be noted that in practical applications, all the above possible implementation methods can be combined in any way to form possible embodiments of the present disclosure, and they will not be described one by one here. The information (including but not limited to device information, user information, etc.) and data (including but not limited to data used for analysis, storage and display, etc.) involved in the present disclosure are all information and data authorized by the user or fully authorized by all parties.

[0052] Based on the same concept, an embodiment of the present disclosure also provides a spray dust reduction device based on a multi-field multi-phase model and a deep learning algorithm. The spray dust reduction device based on a multi-field multi-phase model and a deep learning algorithm corresponds one-to-one to the spray dust reduction method based on a multi-field multi-phase model and a deep learning algorithm in the above-mentioned embodiment. Figure 2The schematic diagram of the structure of the spray dust suppression device based on the multi-field multi-phase model and the deep learning algorithm provided by the embodiment of the present disclosure is shown in FIG. Figure 2 As shown, the spray dust suppression device 200 based on the multi-field multi-phase model and the deep learning algorithm provided by the embodiment of the present disclosure includes: The acquisition module 201 is used to acquire dust data and environmental data of the dust reduction area; wherein the dust data includes dust concentration data, dust particle size data, dust density data and dust particle mineral component data, and the environmental data includes wind speed data and air density data; A calculation module 202 is used to calculate the dust migration speed under the multi-field multi-phase theory according to the dust particle size data, the dust density data, the wind speed data and the air density data; A characterization module 203 is used to perform characterization processing on the dust data and the dust migration speed to obtain processed dust data and processed dust migration speed respectively; A prediction module 204, for generating a spray solution type prediction result and a spray solution dosage prediction result according to the treated dust data, the treated dust migration speed and the trained spray solution parameter prediction model; The dust reduction module 205 is used to control the target spray dust reduction system according to the prediction result of the spray solution type and the prediction result of the spray solution dosage, so as to achieve dust reduction in the area to be dusted.

[0053] In some embodiments, in the above device, the horizontal component of the dust migration velocity is calculated according to the following formula: ; in, represents the horizontal component of the dust migration velocity, represents the wind speed data, Indicates the dust particle size data, Indicates the dust density data, represents the air density data, Indicates the preset gas resistance coefficient, Indicates time; the vertical component of the dust migration velocity is calculated according to the following formula: ; ; in, represents the vertical component of the dust transport velocity, Represents the acceleration due to gravity.

[0054] In some embodiments, the trained spray solution parameter prediction model is a first parameter prediction model; the prediction module is used to input the treated dust data and the treated dust migration speed into the first parameter prediction model to obtain the spray solution type prediction result and the spray solution dosage prediction result.

[0055] In some embodiments, the device also includes a first training module for acquiring a first data set; the characteristics of the samples in the first data set include dust characteristic data and dust migration speed characteristic data, and the labels of the samples include spray solution type and spray solution dosage data; the first initial parameter prediction model is trained using the first data set to obtain the first parameter prediction model.

[0056] In some embodiments, the environmental data also includes at least one of temperature data, humidity data, and wind direction data; if the trained spray solution parameter prediction model is a second parameter prediction model; the characterization module 203 is also used to perform characterization processing on the environmental data to obtain processed environmental data; the prediction model is used to input the processed dust data, the processed dust migration speed and the processed environmental data into the second parameter prediction model to obtain the spray solution type prediction result and the spray solution dosage prediction result.

[0057] In some embodiments, the device also includes a second training module for acquiring a second data set; the characteristics of the samples in the second data set include dust characteristic data, environmental characteristic data and dust migration speed characteristic data, and the labels of the samples include spray solution type and spray solution dosage data; the second initial parameter prediction model is trained using the second data set to obtain the second parameter prediction model.

[0058] The present invention provides a spray dust suppression device based on a multi-field multi-phase model and a deep learning algorithm. The device obtains dust data and environmental data of the area to be dusted, and calculates the dust migration speed under the multi-field multi-phase theory based on the dust data and environmental data and the spatiotemporal laws of dust diffusion, migration and aggregation. The dust data can more accurately reflect the overall dust situation in the area to be dusted, and the dust migration speed can accurately simulate the movement of dust in the actual environment. The dust data and the dust migration speed are characterized, and according to the processed dust data and the processed dust migration speed, a spray solution parameter prediction model based on a deep learning algorithm can be used to predict a more accurate and reasonable type and dosage of the spray solution. Finally, according to the prediction results of the type and dosage of the spray solution, the target spray dust suppression system is controlled, which can significantly improve the dust suppression effect on the area to be dusted.

[0059] Based on the same concept, the embodiment of the present disclosure also provides a spray dust suppression system based on a multi-field multi-phase model and a deep learning algorithm. Figure 3 The schematic diagram of the structure of the spray dust suppression system based on the multi-field multi-phase model and deep learning algorithm provided by the embodiment of the present disclosure is shown. Figure 3 It can be seen that the spray dust suppression system 300 based on the multi-field multi-phase model and deep learning algorithm provided by the embodiment of the present disclosure includes a data acquisition device 301, a spray solution parameter prediction unit 302, a dry fog dust suppression host 303, and an atomizing nozzle 304, wherein: the data acquisition device 301 is used to collect dust data and environmental data of the area to be dusted, and send the dust data and the environmental data to the spray solution parameter prediction unit; the spray solution parameter prediction unit 302 is used to execute the steps of any of the aforementioned methods; the dry fog dust suppression host 303 is used to control the output power of the atomizing nozzle 304 and the type of sprayed solution according to the received spray solution type prediction result and the spray solution dosage prediction result.

[0060] During implementation, the data acquisition device is arranged in the area to be dusted. In some embodiments, the data acquisition device includes but is not limited to: a dust particle counter (for example, a laser dust particle counter), a laser component online analyzer, a dust true density analyzer, an anemometer, a temperature sensor, a humidity sensor and a gas density meter, which are used to collect dust data and environmental data in the area to be dusted, and send them to the spray solution parameter prediction unit; the spray solution parameter prediction unit is also used to execute the steps of any of the aforementioned spray dust reduction methods based on multi-field multi-phase models and deep learning algorithms. The spray solution parameter prediction unit can be deployed on the execution body of any of the aforementioned spray dust reduction methods based on multi-field multi-phase models and deep learning algorithms. The dry fog dust suppression host can control the output power of the atomizing nozzle and the type of solution sprayed according to the received spray solution type prediction results and spray solution dosage prediction results, so as to achieve dust reduction in the area to be dusted.

[0061] Figure 4 FIG. 2 shows a schematic diagram of the structure of another spray dust suppression system based on a multi-field multi-phase model and a deep learning algorithm provided by an embodiment of the present disclosure. Figure 4As shown, the spray dust suppression system based on the multi-field multi-phase model and deep learning algorithm is used for dust suppression in multiple dust suppression areas, including multiple data acquisition devices 301, wireless transceivers, spray solution parameter prediction units 302, dry fog dust suppression hosts 303 and multiple atomizing nozzles 304. Among them, the wireless transceivers include wireless sensors 1, wireless sensors 2, wireless sensors 3 and wireless transceiver stations, and the dry fog dust suppression hosts include a master controller, a frequency converter, an air pump, a solution storage device and a liquid pump. Each data acquisition device collects dust data and environmental data of the corresponding area and sends them to the corresponding wireless sensor. The wireless transceiver station receives the dust data and environmental data sent by each wireless sensor and sends them to the spray solution prediction unit. The spray solution prediction unit generates the spray solution type and dosage prediction results based on the received dust data and environmental data and the trained spray solution parameter prediction model, and sends them to the dry fog dust suppression host. The master controller in the dry fog dust suppression host receives the spray solution parameter prediction results of each area and sends instructions to the solvent storage device and the frequency converter respectively. The solution storage device can be used to store various types of spray solutions used in spray dust suppression in various industrial fields according to the actual needs of technicians in the field, so as to meet different spray dust suppression needs. The solvent storage device outputs the corresponding spray solution type and dosage to the liquid pump according to the instructions, and the frequency converter adjusts the output power of the air pump and the liquid pump to the atomizing nozzle according to the instructions to meet the dust suppression needs of each partition in a targeted manner. The frequency converter can control the output power of the liquid pump and the air pump according to the dosage of the spray solution in each area to achieve efficient spray dust suppression effect. The liquid pump and the air pump control a certain amount of gas and spray solution to enter the atomizing nozzle according to the instructions of the frequency converter. The atomizing nozzle sprays the spray solution formed into droplets under the action of air pressure at a certain power with high pressure, so that it merges with the fine dust suspended in the air, absorbs the dust particles in the air, and achieves the purpose of dust suppression.

[0062] Figure 5 FIG. 1 shows a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Figure 5 As shown, at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage, etc. Of course, the electronic device may also include hardware required for other services.

[0063] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0064] The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0065] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a spray dust suppression device based on a multi-field multi-phase model and a deep learning algorithm at the logical level. The processor executes the program stored in the memory and is specifically used to execute the above method.

[0066] The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present disclosure may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present disclosure may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in a decoding processor. The software module may be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0067] The electronic device can execute the spray dust suppression method based on the multi-field multi-phase model and the deep learning algorithm provided by the multiple embodiments of the present disclosure, and realize the spray dust suppression device based on the multi-field multi-phase model and the deep learning algorithm. Figure 2 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present disclosure.

[0068] The embodiments of the present disclosure also propose a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple application programs, the electronic device can execute the spray dust reduction method based on the multi-field multi-phase model and deep learning algorithm provided by multiple embodiments of the present disclosure.

[0069] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0071] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0073] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0074] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0075] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0076] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity or device including the element.

[0077] It should be understood by those skilled in the art that the embodiments of the present disclosure may be provided as methods, systems or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0078] The above are only embodiments of the present disclosure and are not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the scope of the claims of the present disclosure.

Claims

1. A spray dust suppression method based on a multi-field multi-phase model and a deep learning algorithm, characterized in that: The method comprises: Obtain dust data and environmental data of the area to be dusted; wherein the dust data includes dust concentration data, dust particle size data, dust density data and dust particle mineral component data, and the environmental data includes wind speed data and air density data; Calculating the dust migration velocity under the multi-field multi-phase theory according to the dust particle size data, the dust density data, the wind speed data and the air density data; Performing characterization processing on the dust data and the dust migration speed to obtain processed dust data and processed dust migration speed respectively; Generate a spray solution type prediction result and a spray solution dosage prediction result according to the treated dust data, the treated dust migration speed and the trained spray solution parameter prediction model; According to the prediction results of the type of spray solution and the prediction results of the dosage of the spray solution, the target spray dust reduction system is controlled to achieve dust reduction in the area to be dust reduced.

2. The method according to claim 1, characterized in that The horizontal component of the dust migration velocity is calculated according to the following formula: ； in, represents the horizontal component of the dust migration velocity, represents the wind speed data, Indicates the dust particle size data, Indicates the dust density data, represents the air density data, Indicates the preset gas resistance coefficient, Indicates time; The vertical component of the dust migration velocity is calculated according to the following formula: ； ； in, represents the vertical component of the dust transport velocity, Represents the acceleration due to gravity.

3. The method according to claim 1 or 2, characterized in that: The trained spray solution parameter prediction model is a first parameter prediction model; the generation of a spray solution type prediction result and a spray solution dosage prediction result according to the treated dust data, the treated dust migration speed and the trained spray solution parameter prediction model includes: The treated dust data and the treated dust migration speed are input into the first parameter prediction model to obtain the spray solution type prediction result and the spray solution dosage prediction result.

4. The method according to claim 3, characterized in that The first parameter prediction model is obtained according to the following method: Acquire a first data set; the characteristics of the samples in the first data set include dust characteristic data and dust migration speed characteristic data, and the labels of the samples include spray solution type and spray solution dosage data; The first initial parameter prediction model is trained using the first data set to obtain the first parameter prediction model.

5. The method according to claim 1, characterized in that The environmental data also includes at least one of temperature data, humidity data, and wind direction data; if the trained spray solution parameter prediction model is a second parameter prediction model; the method also includes: Performing characterization processing on the environmental data to obtain processed environmental data; The method generates a spray solution type prediction result and a spray solution dosage prediction result according to the treated dust data, the treated dust migration speed and the trained spray solution parameter prediction model, including: The treated dust data, the treated dust migration speed and the treated environment data are input into the second parameter prediction model to obtain the spray solution type prediction result and the spray solution dosage prediction result.

6. The method according to claim 5, characterized in that The second parameter prediction model is obtained according to the following method: Acquire a second data set; the characteristics of the samples in the second data set include dust characteristic data, environmental characteristic data and dust migration speed characteristic data, and the labels of the samples include spray solution type and spray solution dosage data; The second initial parameter prediction model is trained using the second data set to obtain the second parameter prediction model.

7. A spray dust suppression device based on a multi-field multi-phase model and a deep learning algorithm, characterized in that: The device comprises: An acquisition module is used to acquire dust data and environmental data of the area to be dusted; wherein the dust data includes dust concentration data, dust particle size data, dust density data and dust particle mineral component data, and the environmental data includes wind speed data and air density data; A calculation module, used for calculating the dust migration speed under the multi-field multi-phase theory according to the dust particle size data, the dust density data, the wind speed data and the air density data; A characterization module, used for performing characterization processing on the dust data and the dust migration speed to obtain processed dust data and processed dust migration speed respectively; A prediction module, for generating a spray solution type prediction result and a spray solution dosage prediction result according to the treated dust data, the treated dust migration speed and a trained spray solution parameter prediction model; The dust reduction module is used to control the target spray dust reduction system according to the prediction result of the spray solution type and the prediction result of the spray solution dosage, so as to achieve dust reduction in the area to be dusted.

8. A spray dust suppression system based on a multi-field multi-phase model and a deep learning algorithm, characterized in that: The system comprises: a data acquisition device, a spray solution parameter prediction unit, a dry fog dust suppression host, and an atomizing nozzle; The data acquisition device is used to collect dust data and environmental data of the area to be dusted, and send the dust data and environmental data to the spray solution parameter prediction unit; The spray solution parameter prediction unit is used to perform the steps of any method according to claims 1 to 6; The dry fog dust suppression host is used to control the output power of the atomizing nozzle and the type of solution sprayed according to the received prediction result of the type of spray solution and the prediction result of the dosage of the spray solution.

9. An electronic device, comprising: processor; and a memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to perform the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium storing one or more programs, characterized in that: When the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device executes the steps of the method as claimed in any one of claims 1 to 6.

Images