Mine water tail end water quality regulation and control system

Abstract

The invention discloses a mine water end water quality regulation and control system which comprises a data acquisition module used for acquiring water quality parameters of mine water; the model construction module is connected with the data acquisition module and is used for constructing a water quality prediction model based on the recurrent neural network and the historical water quality data; the water quality prediction module is connected with the model construction module and is used for analyzing the water quality parameters through a water quality prediction model to obtain a water quality change trend; and the regulation and control module is connected with the water quality prediction module and used for regulating and controlling water quality based on the water quality change trend. According to the invention, data acquisition, model prediction and automatic regulation and control are integrated, automation and intellectualization of water quality regulation and control at the tail end of mine water are realized, and the need of manual intervention is reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of mine water treatment, and in particular relates to a mine water terminal water quality control system. Background Art

[0002] If mine water is discharged directly without treatment, it may cause serious pollution to the surrounding environment. Therefore, effective water quality control not only helps to protect the environment, but also ensures the rational use of water resources and the sustainable development of mining areas. The chemical composition of mine water is complex and contains a variety of harmful substances, such as heavy metals and mineral salts. The changes in their concentration need to be monitored in real time and the treatment strategy needs to be adjusted in time.

[0003] Therefore, mine water treatment is an important link in mining production. However, traditional water quality control methods have problems such as low efficiency and insufficient control accuracy. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a mine water terminal water quality control system to solve the problems existing in the above prior art.

[0005] To achieve the above object, the present invention provides a mine water terminal water quality control system, comprising:

[0006] Data acquisition module, used to collect water quality parameters of mine water;

[0007] A model building module, connected to the data acquisition module, for building a water quality prediction model based on a recurrent neural network and historical water quality data;

[0008] A water quality prediction module, connected to the model building module, is used to analyze water quality parameters through a water quality prediction model to obtain a water quality change trend;

[0009] The control module is connected to the water quality prediction module and is used to control the water quality based on the water quality change trend.

[0010] Preferably, the data acquisition module includes a detection unit and a preprocessing unit;

[0011] The detection unit is used to detect water quality parameters, which include pH value, dissolved oxygen, chemical oxygen demand, ammonia nitrogen and heavy metal ion concentration;

[0012] The preprocessing unit is used to preprocess the water quality parameters to obtain preprocessing parameters.

[0013] Preferably, the preprocessing unit includes a denoising subunit and a normalization subunit;

[0014] The denoising subunit is used to remove noise in water quality parameters to obtain denoised data;

[0015] The normalization subunit is used to perform normalization processing on the denoised data to obtain normalized data.

[0016] Preferably, the model construction module includes a network construction submodule, a training submodule and a verification submodule;

[0017] The network construction submodule is used to construct a recurrent neural network group by adjusting the recurrent neural network loss function;

[0018] The training submodule is used to iteratively train the recurrent neural network group through historical water quality data and genetic algorithm to obtain an initial water quality prediction model;

[0019] The verification submodule is used to verify the initial water quality prediction model through a ten-fold verification method to obtain a water quality prediction model.

[0020] Preferably, the training submodule includes a network structure encoding unit, a function construction unit, a conversion unit and a genetic optimization unit;

[0021] The network structure encoding unit is used to encode the structural parameters of the recurrent neural network group into chromosomes of the genetic algorithm to obtain a network chromosome structure;

[0022] The function construction unit is used to construct a fitness function based on the detection rate, the false detection rate and the positioning accuracy;

[0023] The conversion unit is used to randomly generate a set of initial recurrent neural network chromosome structures through the network chromosome structure;

[0024] The genetic optimization unit is used to iterate the initial recurrent neural network chromosome structure based on the fitness function, select the recurrent neural network structure corresponding to the individual with the highest fitness in the last generation of iteration and decode it to obtain the initial water quality prediction model.

[0025] Preferably, the genetic optimization unit includes a selection subunit, a crossover subunit, a mutation subunit, an iteration subunit and a decoding subunit;

[0026] The selection subunit is used to select the initial recurrent neural network chromosome structure through the fitness function to obtain the selected parent recurrent neural network chromosome structure;

[0027] The crossover subunit is used to perform a crossover operation on the selected parent recurrent neural network chromosome structure to generate a new individual;

[0028] The mutation subunit is used to introduce randomness, mutate the new individual, and obtain a mutant individual;

[0029] The iterative subunit is used to perform multiple iterations and evolutions on the recurrent neural network chromosome structure through the selection subunit, the crossover subunit and the mutation subunit, and select the individual with the highest fitness;

[0030] The decoding subunit is used to decode the individual with the highest fitness to obtain the initial water quality prediction model.

[0031] Preferably, the control module includes a classification unit, a control method generation unit and an execution unit;

[0032] The classification unit is used to classify water quality grades according to water quality;

[0033] The control method generation unit is used to formulate a control strategy according to the water quality grade and water quality change trend;

[0034] The execution unit is used to perform regulation according to the regulation strategy.

[0035] Preferably, the control method generation unit includes a single factor determination subunit and a water quality grade control subunit;

[0036] The single factor determination subunit is used to control the single influencing factor when one of the water quality influencing factors exceeds the standard;

[0037] The water quality level control subunit is used to formulate an overall control strategy when the water quality level reaches the control level.

[0038] Compared with the prior art, the present invention has the following advantages and technical effects:

[0039] The present invention discloses a mine water terminal water quality control system, including: a data acquisition module, used to collect water quality parameters of mine water; a model construction module, connected to the data acquisition module, used to build a water quality prediction model based on a recurrent neural network and historical water quality data; a water quality prediction module, connected to the model construction module, used to analyze water quality parameters through the water quality prediction model to obtain water quality change trends; a control module, connected to the water quality prediction module, used to control water quality based on water quality change trends. The present invention integrates data acquisition, model prediction and automatic control. Through the recurrent neural network model, the system can more accurately learn and understand the change law of mine water quality parameters over time, so as to reliably predict the future water quality conditions. The automation and intelligence of mine water terminal water quality control is realized, the need for manual intervention is reduced, and the control accuracy is enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0041] Figure 1 4 is a system functional structure diagram of an embodiment of the present invention. DETAILED DESCRIPTION

[0042] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0043] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0044] Embodiment 1

[0045] like Figure 1 As shown, this embodiment provides a mine water terminal water quality control system, including a data acquisition module, a model building module, a water quality prediction module and a control module.

[0046] The data acquisition module is responsible for collecting water quality parameters of mine water, such as pH value, dissolved oxygen, chemical oxygen demand, ammonia nitrogen and heavy metal ion concentration. These parameters are crucial to understanding the water quality of mine water. In order to ensure the accuracy and reliability of the data, the data acquisition module also includes a detection unit and a pre-processing unit. The detection unit is used to detect water quality parameters, while the pre-processing unit pre-processes the detected water quality parameters to obtain more accurate data.

[0047] The model building module is connected to the data acquisition module and builds a water quality prediction model based on the recurrent neural network and historical water quality data. The model building module includes a network building submodule, a training submodule, and a verification submodule. The network building submodule builds a recurrent neural network group by adjusting the recurrent neural network loss function. The training submodule uses historical water quality data and genetic algorithms to iteratively train the recurrent neural network group to obtain an initial water quality prediction model. The verification submodule verifies the initial water quality prediction model through the ten-fold verification method to ensure its accuracy and reliability.

[0048] The water quality prediction module is connected to the model building module, and analyzes the water quality parameters through the water quality prediction model. It can obtain the trend of water quality changes and provide a basis for subsequent water quality regulation. By analyzing the water quality parameters, the water quality of the mine water in the future can be predicted, so that corresponding measures can be taken in advance for regulation.

[0049] The control module is connected to the water quality prediction module to control water quality according to the trend of water quality changes. The control module includes a grading unit, a control method generation unit and an execution unit. The grading unit divides water quality grades according to water quality so as to adopt corresponding control strategies for different grades of water quality. The control method generation unit formulates a control strategy based on the water quality grade and the trend of water quality changes. When one of the water quality influencing factors exceeds the standard, the single factor determination subunit will control the single influencing factor; when the water quality grade reaches the control grade, the water quality grade control subunit will formulate an overall control strategy. The execution unit is responsible for performing actual control operations according to the control strategy.

[0050] In this embodiment, the preprocessing unit of the data acquisition module further includes a denoising subunit and a normalization subunit. The denoising subunit is used to remove noise in the water quality parameters to obtain more accurate data. The normalization subunit normalizes the denoised data to make it meet the requirements of subsequent processing.

[0051] The training submodule of the model construction module further includes a network structure encoding unit, a function construction unit, a conversion unit and a genetic optimization unit. The network structure encoding unit encodes the structural parameters of the recurrent neural network group into the chromosome of the genetic algorithm to obtain the network chromosome structure. The function construction unit constructs a fitness function based on the detection rate, false detection rate and positioning accuracy. The conversion unit randomly generates a set of initial recurrent neural network chromosome structures through the network chromosome structure. The genetic optimization unit iterates the initial recurrent neural network chromosome structure based on the fitness function, and selects the recurrent neural network structure corresponding to the individual with the highest fitness in the last generation of iteration for decoding to obtain the initial water quality prediction model.

[0052] The genetic optimization unit further includes a selection subunit, a crossover subunit, a mutation subunit, an iteration subunit and a decoding subunit. The selection subunit selects the initial recurrent neural network chromosome structure through the fitness function to obtain the selected parent recurrent neural network chromosome structure. The crossover subunit performs a crossover operation on the selected parent recurrent neural network chromosome structure to generate a new individual. The mutation subunit introduces randomness, mutates the new individual, and obtains a mutant individual. The iteration subunit iterates and evolves the recurrent neural network chromosome structure multiple times through the selection subunit, the crossover subunit and the mutation subunit, and selects the individual with the highest fitness. The decoding subunit decodes the individual with the highest fitness to obtain an initial water quality prediction model.

[0053] The control method generation unit of the control module further includes a single factor determination subunit and a water quality level control subunit. The single factor determination subunit is used to control the single influencing factor when one of the water quality influencing factors exceeds the standard. The water quality level control subunit is used to formulate an overall control strategy when the water quality level reaches the control level. Such a design enables the system to take corresponding control measures according to different water quality conditions, thereby improving the effect and efficiency of water quality control.

[0054] In summary, the mine water terminal water quality control system of the present invention realizes effective control of mine water quality through the coordinated work of the data acquisition module, the model building module, the water quality prediction module and the control module. The data acquisition module ensures the accuracy and reliability of the data; the model building module builds an accurate water quality prediction model based on the recurrent neural network and historical water quality data; the water quality prediction module obtains the water quality change trend by analyzing the water quality parameters; the control module formulates corresponding control strategies according to the water quality change trend and performs control operations. The design and implementation of this system provides an efficient and accurate method for monitoring and controlling the water quality of mine water.

[0055] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A mine water terminal water quality control system, characterized in that: include: Data acquisition module, used to collect water quality parameters of mine water; A model building module, connected to the data acquisition module, for building a water quality prediction model based on a recurrent neural network and historical water quality data; A water quality prediction module, connected to the model building module, is used to analyze water quality parameters through a water quality prediction model to obtain a water quality change trend; The control module is connected to the water quality prediction module and is used to control the water quality based on the water quality change trend.

2. The mine water terminal water quality control system according to claim 1, characterized in that: The data acquisition module includes a detection unit and a preprocessing unit; The detection unit is used to detect water quality parameters, which include pH value, dissolved oxygen, chemical oxygen demand, ammonia nitrogen and heavy metal ion concentration; The preprocessing unit is used to preprocess the water quality parameters to obtain preprocessing parameters.

3. The mine water terminal water quality control system according to claim 2 is characterized in that: The preprocessing unit includes a denoising subunit and a normalization subunit; The denoising subunit is used to remove noise in water quality parameters to obtain denoised data; The normalization subunit is used to perform normalization processing on the denoised data to obtain normalized data.

4. The mine water terminal water quality control system according to claim 1, characterized in that: The model construction module includes a network construction submodule, a training submodule and a verification submodule; The network construction submodule is used to construct a recurrent neural network group by adjusting the recurrent neural network loss function; The training submodule is used to iteratively train the recurrent neural network group through historical water quality data and genetic algorithm to obtain an initial water quality prediction model; The verification submodule is used to verify the initial water quality prediction model through a ten-fold verification method to obtain a water quality prediction model.

5. The mine water terminal water quality control system according to claim 4, characterized in that: The training submodule includes a network structure encoding unit, a function construction unit, a conversion unit and a genetic optimization unit; The network structure encoding unit is used to encode the structural parameters of the recurrent neural network group into chromosomes of the genetic algorithm to obtain a network chromosome structure; The function construction unit is used to construct a fitness function based on the detection rate, the false detection rate and the positioning accuracy; The conversion unit is used to randomly generate a set of initial recurrent neural network chromosome structures through the network chromosome structure; The genetic optimization unit is used to iterate the initial recurrent neural network chromosome structure based on the fitness function, select the recurrent neural network structure corresponding to the individual with the highest fitness in the last generation of iteration and decode it to obtain the initial water quality prediction model.

6. The mine water terminal water quality control system according to claim 5, characterized in that: The genetic optimization unit includes a selection subunit, a crossover subunit, a mutation subunit, an iteration subunit and a decoding subunit; The selection subunit is used to select the initial recurrent neural network chromosome structure through the fitness function to obtain the selected parent recurrent neural network chromosome structure; The crossover subunit is used to perform a crossover operation on the selected parent recurrent neural network chromosome structure to generate a new individual; The mutation subunit is used to introduce randomness, mutate the new individual, and obtain a mutant individual; The iterative subunit is used to perform multiple iterations and evolutions on the recurrent neural network chromosome structure through the selection subunit, the crossover subunit and the mutation subunit, and select the individual with the highest fitness; The decoding subunit is used to decode the individual with the highest fitness to obtain the initial water quality prediction model.

7. The mine water terminal water quality control system according to claim 1, characterized in that: The control module includes a classification unit, a control method generation unit and an execution unit; The classification unit is used to classify water quality grades according to water quality; The control method generation unit is used to formulate a control strategy according to the water quality grade and water quality change trend; The execution unit is used to perform regulation according to the regulation strategy.

8. The mine water terminal water quality control system according to claim 7, characterized in that: The control method generation unit includes a single factor determination subunit and a water quality grade control subunit; The single factor determination subunit is used to control the single influencing factor when one of the water quality influencing factors exceeds the standard; The water quality level control subunit is used to formulate an overall control strategy when the water quality level reaches the control level.

Images