Coal mine carbon emission evaluation system

Abstract

The invention relates to the technical field of carbon emission monitoring, and provides a coal mine carbon emission evaluation system which comprises a data acquisition module, a data preprocessing module, a carbon emission evaluation module, an optimization hyper-parameter module and a decision support module. The system analyzes the dynamic characteristics of carbon emission through a multi-resolution mechanism, captures carbon emission rules of different time scales, improves the weight of key characteristics in combination with an attention mechanism, and generates accurate carbon emission evaluation data. The global exploration capability of the whale optimization algorithm is optimized by introducing a dynamic dimension weight mechanism, and the local development capability is optimized by introducing an acceleration factor and a dynamic step length adjustment factor, so that the optimal configuration of the hyper-parameters of the carbon emission evaluation system is realized, and the evaluation precision and stability are improved; according to the method, the dynamic characteristics of carbon emission can be comprehensively captured, the accuracy and timeliness of an evaluation result are improved, and important support is provided for coal mine environmental protection and carbon emission reduction.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission monitoring, and in particular to a coal mine carbon emission assessment system. Background Art

[0002] With the development of technology, the monitoring and assessment of carbon emissions during coal mine production have gradually become an important research direction in the field of environmental protection; in order to achieve the sustainable development of the coal mine industry, more and more coal mines have begun to adopt carbon emission assessment systems to quantify carbon emission levels, optimize emission reduction strategies, and evaluate environmental impacts; however, in the prior art, the traditional coal mine carbon emission assessment system has the following deficiencies: First, the traditional coal mine carbon emission assessment system has a weak ability to capture the dynamic characteristics of carbon emission time series data and cannot accurately reflect the short-term, medium-term, and long-term impacts of production activities, energy consumption, and environmental factors on carbon emissions; especially for data with a high time resolution, the existing system has low sensitivity, resulting in the assessment results being unable to comprehensively reflect the fluctuation law and key influencing factors of carbon emissions; in addition, when analyzing the influencing factors of carbon emissions, the traditional system lacks accurate identification and weight allocation of key time points and cannot highlight the characteristics that have an important impact on the carbon emission assessment results, thus affecting the accuracy and practicality of the assessment; Second, the existing coal mine carbon emission assessment system is inefficient in coping with model optimization and hyperparameter configuration in complex environments and often has difficulty adapting to the processing requirements of multi-dimensional and high-frequency carbon emission data in actual coal mine scenarios, resulting in the accuracy and stability of the assessment results being difficult to meet the high requirements of carbon emission reduction and environmental management; Therefore, there is an urgent need for a coal mine carbon emission assessment system that can comprehensively capture the dynamic characteristics of time series, accurately assess the carbon emission level of coal mines, and provide high-precision assessment results to meet the needs of coal mine carbon emission management and emission reduction strategy formulation. Summary of the Invention

[0003] The present invention provides a coal mine carbon emission assessment system, aiming to solve the problems of insufficient data processing capacity, inaccurate capture of the dynamic characteristics of carbon emissions, and low accuracy of assessment results in the prior art. First, in the process of carbon emission assessment, this system adopts a multi-resolution processing mechanism to classify and analyze carbon emission data according to time resolution. By capturing the carbon emission change laws in the short, medium, and long terms, the system comprehensively extracts the impacts of different time scales in coal mine production activities on carbon emissions, thereby generating high-quality carbon emission assessment data covering the whole situation. At the same time, the system uses the multi-resolution mechanism to highlight the impact of key time points on carbon emission assessment, thereby further improving the accuracy and timeliness of the assessment. Second, the coal mine carbon emission assessment system in the present invention globally optimizes the assessment process through a dynamic dimension weight mechanism, significantly improving the comprehensiveness of data processing and the global exploration ability. In terms of local optimization, the system introduces an acceleration factor and a dynamic step size adjustment factor, enhancing the adaptability to the data characteristics of the complex coal mine environment and significantly improving the processing efficiency of high-dimensional complex data. Through this optimization method, the system can generate carbon emission assessment data with higher accuracy, providing more scientific and reliable data support for coal mine carbon emission management and emission reduction strategies.

[0004] The data acquisition module acquires relevant carbon emission data in coal mine production activities, including collecting CO2 concentration, CH4 concentration, energy consumption data, and coal mine output data through sensors, and integrating them to obtain the original carbon emission data;

[0005] The data preprocessing module processes the outliers in the original carbon emission data using the median absolute deviation method, fills the missing values in the original carbon emission data through linear interpolation, and performs normalization processing to generate preprocessed carbon emission data;

[0006] The carbon emission assessment module establishes a CNN-BiGRU model, optimizes the bidirectional gated recurrent unit through a multi-resolution mechanism to construct an enhanced bidirectional gated recurrent unit, optimizes the CNN-BiGRU model through the enhanced bidirectional gated recurrent unit to construct an enhanced CNN-BiGRU model, initializes the hyperparameters of the enhanced CNN-BiGRU model, and uses the enhanced CNN-BiGRU model to process the preprocessed carbon emission data to generate carbon emission assessment data;

[0007] The optimized hyperparameter module uses the dynamic dimension weight mechanism to optimize the global exploration of the whale optimization algorithm, introduces the acceleration factor and the dynamic step size adjustment factor to improve the Levy flight mechanism, constructs an enhanced Levy flight mechanism, optimizes the local exploitation of the whale optimization algorithm through the enhanced Levy flight mechanism, constructs an improved whale optimization algorithm, optimizes the hyperparameters of the enhanced CNN-BiGRU model through the improved whale optimization algorithm, finds the optimal hyperparameter configuration of the enhanced CNN-BiGRU model, and uses the optimal hyperparameter configuration to optimize the carbon emission assessment data to generate high-precision carbon emission assessment data;

[0008] The decision support module uses the high-precision carbon emission assessment data for coal mine carbon emission management, carbon emission reduction strategy formulation, and environmental impact assessment.

[0009] Furthermore, in the process of generating the carbon emission assessment data by the carbon emission assessment module, the specific steps are as follows:

[0010] Step P1: Data conversion: Organize the preprocessed carbon emission data according to the time series, convert it into multi-dimensional time series feature data, and define the output space of the carbon emission assessment task;

[0011] The output space of the carbon emission assessment task includes: the total carbon emission, the coal mine carbon emission reduction strategy, and the dynamic characteristics of carbon emissions at hourly, daily, and monthly time resolutions;

[0012] Step P2: Extract local features: Use one-dimensional convolution to perform convolution operations on the multi-dimensional time series feature data, capture the local correlations of the multi-dimensional time series feature data in the time dimension, obtain the convolution result, and perform non-linear mapping on the convolution result through the ReLU activation function to generate activation feature data;

[0013] Step P3: Compress data: Perform pooling processing on the activation feature data, extract the key feature values in the local time period of the multi-dimensional time series feature data through the max pooling technique, reduce the dimension of the activation feature data and compress the computational amount, generate the pooled local time feature data, and the key feature values include the mean, variance, and peak value;

[0014] Step P4: Capture global dependencies: Input the pooled local time feature data into the enhanced bidirectional gated recurrent unit to generate BiGRU global time series feature data;

[0015] Step P5: Assign attention weights: Process the BiGRU global time series feature data through the attention mechanism to generate weighted comprehensive time series feature data;

[0016] Step P6: Map feature output: Process the weighted comprehensive time series feature data through the fully connected layer, map it to the output space of the carbon emission assessment task, and generate the carbon emission assessment data.

[0017] Furthermore, step P4 specifically includes the following steps:

[0018] Step P41: Split the pooled local time feature data according to hourly, daily, and monthly time resolutions to form multiple groups of feature data; among them, the hourly resolution is used to capture device operation data and short-term carbon emission change patterns; the daily resolution is used to capture the medium-term impact of production activities and energy consumption on carbon emissions; the monthly resolution captures the long-term trend impacts of policy changes and equipment aging;

[0019] Step P42: Input the multiple groups of feature data into the sub-network of the enhanced bidirectional gated recurrent unit to extract hourly global time series features, daily global time series features, and monthly global time series features; the forward GRU and backward GRU are used inside the sub-network to capture the dynamic dependencies at different time steps respectively;

[0020] Step P43: Fuse the hourly global time series features, daily global time series features, and monthly global time series features into BiGRU global time series feature data through a weighted fusion mechanism.

[0021] Furthermore, the process of optimizing the hyperparameter module and optimizing the hyperparameters of the enhanced CNN-BiGRU model specifically includes the following steps:

[0022] Step B1: Randomly generate the beluga individuals in the population of the whale optimization algorithm. Each beluga individual represents a set of hyperparameter configurations of the enhanced CNN-BiGRU model. Define the search space. The hyperparameter configurations include the convolutional kernel size, the number of convolutional kernels, the number of BiGRU hidden units, the type of Attention mechanism, the learning rate, and the batch size. Generate the initial beluga population according to the search space, set the fitness function, calculate the initial fitness values of the initial beluga population through the fitness function, and select the current global optimal solution according to the initial fitness values;

[0023] Step B2: Conduct global exploration on the beluga individuals in the initial beluga population. Simulate the swimming behavior of belugas and combine the dynamic dimension weight mechanism. Randomly select the target whale individuals. Each beluga individual updates its own hyperparameter configuration through the random jump mechanism, combining the target whale individuals and the current global optimal solution, and expand the search space to generate the global beluga population. The global beluga population is divided into a high-performance population and a low-performance population;

[0024] Step B3: Conduct local optimization on the high-performance population. Use the enhanced Levy flight mechanism to adjust the step sizes of the beluga individuals in the high-performance population and optimize the hyperparameter configurations of the beluga individuals in the high-performance population;

[0025] Step B4: Process the low-performance population through the whale fall mechanism, randomly reset the hyperparameter configurations of the beluga individuals in the low-performance population to prevent falling into local optima;

[0026] Step B5: Update the global beluga whale population through local development and whale fall processing to generate an optimized global beluga whale population, calculate the optimized fitness value of the optimized global beluga whale population through the fitness function, and update the current global optimal solution according to the optimized fitness value;

[0027] Step B6: Set the maximum number of iterations, and iterate Steps B2 - B5 until the maximum number of iterations is reached to generate the final global optimal solution and obtain the optimal hyperparameter configuration.

[0028] Adopting the above solution, the beneficial effects of the present invention are as follows:

[0029] The present invention provides a coal mine carbon emission assessment system, which significantly improves the accuracy and efficiency of coal mine carbon emission assessment through data processing and optimization means; First of all, through the multi - resolution mechanism for the analysis and processing of coal mine carbon emission data, the present invention realizes the accurate capture of the dynamic change laws of carbon emissions at different time scales, and solves the problem that the traditional coal mine carbon emission assessment system fails to comprehensively capture the short - term fluctuations, medium - term trends and long - term impact characteristics of carbon emissions; Through the analysis of hourly, daily and monthly time resolutions, the present invention can dynamically present the impacts of various factors such as coal mine production activities, equipment operation status and policy changes on carbon emissions, providing higher - quality data support for coal mine carbon emission assessment in terms of overall situation and timeliness, and enhancing the system's adaptability to complex carbon emission patterns;

[0030] Secondly, the present invention adopts a dynamic dimension weight mechanism to optimize the global exploration ability, and combines an acceleration factor and a dynamic step - size adjustment factor to precisely adjust local development, improving the optimization efficiency of hyperparameters in the process of coal mine carbon emission assessment; Through the improved optimization strategy, the system can quickly find the optimal carbon emission data assessment configuration, solving the problems of low hyperparameter configuration efficiency and difficulty in generating high - precision assessment results in the traditional assessment system in complex environments, thereby further improving the accuracy and stability of coal mine carbon emission data analysis;

[0031] Finally, the decision - making support module of the present invention uses high - precision carbon emission assessment data to provide a scientific basis for the dynamic management of coal mine carbon emissions, the formulation of carbon emission reduction strategies and environmental impact assessment; Through the efficient operation of the system of the present invention, the coal mine can achieve the full - life - cycle management of carbon emissions, formulate more targeted and effective carbon emission reduction measures, and enhance the competitiveness and sustainable development ability of the coal mine in terms of low - carbon environmental protection; In summary, the present invention makes an important contribution to the realization of refined carbon emission assessment and environmental protection goals in the coal mine industry. Description of the Drawings

[0032] Figure 1 It is a schematic diagram of the model of a coal mine carbon emission assessment system proposed by the present invention;

[0033] Figure 2 It is a schematic flow diagram of the carbon emission assessment module in Embodiment 2. Specific implementation manners

[0034] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0035] Embodiment 1, according to Figure 1 , the present invention provides a coal mine carbon emission assessment system, which includes a data acquisition module, a data preprocessing module, a carbon emission assessment module, an optimized hyperparameter module, and a decision support module;

[0036] The data acquisition module acquires relevant carbon emission data in coal mine production activities, including collecting CO2 concentration, CH4 concentration, energy consumption data, and coal mine output data through sensors, and integrating to obtain the original carbon emission data;

[0037] The data preprocessing module uses the median absolute deviation method to process the outliers in the original carbon emission data, fills the missing values in the original carbon emission data by linear interpolation, and performs normalization processing to generate preprocessed carbon emission data;

[0038] The carbon emission assessment module establishes a CNN-BiGRU model, optimizes the bidirectional gated recurrent unit through a multi-resolution mechanism, constructs an enhanced bidirectional gated recurrent unit, optimizes the CNN-BiGRU model through the enhanced bidirectional gated recurrent unit, constructs an enhanced CNN-BiGRU model, initializes the hyperparameters of the enhanced CNN-BiGRU model, and uses the enhanced CNN-BiGRU model to process the preprocessed carbon emission data to generate carbon emission assessment data;

[0039] The optimized hyperparameter module introduces a dynamic dimension weight mechanism to optimize the global exploration of the whale optimization algorithm, introduces an acceleration factor and a dynamic step size adjustment factor to improve the Levy flight mechanism, constructs an enhanced Levy flight mechanism, optimizes the local development of the whale optimization algorithm through the enhanced Levy flight mechanism, constructs an improved whale optimization algorithm, optimizes the hyperparameters of the enhanced CNN-BiGRU model through the improved whale optimization algorithm, finds the optimal hyperparameter configuration of the enhanced CNN-BiGRU model, and uses the optimal hyperparameter configuration to optimize the carbon emission assessment data to generate high-precision carbon emission assessment data;

[0040] The described decision support module uses high-precision carbon emission assessment data for coal mine carbon emission management, carbon emission reduction strategy formulation, and environmental impact assessment.

[0041] Example 2. According to Figure 2 , this example is based on Example 1. In this example, the process of the carbon emission assessment module generating carbon emission assessment data specifically includes the following steps:

[0042] Step P1: Data conversion: Organize the preprocessed carbon emission data according to the time series, convert it into multi-dimensional time series feature data, and define the output space of the carbon emission assessment task;

[0043] The output space of the carbon emission assessment task includes: total carbon emissions, coal mine carbon emission reduction strategies, and carbon emission dynamic characteristics at hourly, daily, and monthly time resolutions;

[0044] Step P2: Extract local features: Use one-dimensional convolution to perform convolution operations on the multi-dimensional time series feature data, capture the local associations of the multi-dimensional time series feature data in the time dimension, obtain the convolution result, and perform non-linear mapping on the convolution result through the ReLU activation function to generate activation feature data;

[0045] Step P3: Compress data: Perform pooling processing on the activation feature data, extract the key feature values within the local time period of the multi-dimensional time series feature data through the max pooling technique, reduce the dimension of the activation feature data and compress the computational amount, generate pooled local time feature data, and the key feature values include mean, variance, and peak value;

[0046] Step P4: Capture global dependencies: Input the pooled local time feature data into the enhanced bidirectional gated recurrent unit to generate BiGRU global time series feature data. The enhanced bidirectional gated recurrent unit includes: hourly global time series feature extraction, daily global time series feature extraction, and monthly global time series feature extraction;

[0047] Step P5: Assign attention weights: Process the BiGRU global time series feature data through the attention mechanism to generate weighted comprehensive time series feature data;

[0048] Step P6: Map feature output: Process the weighted comprehensive time series feature data through the fully connected layer and map it to the output space of the carbon emission assessment task to generate carbon emission assessment data.

[0049] Example 3. This example is based on Example 1. In this example, the process of the carbon emission assessment module generating carbon emission assessment data specifically includes the following steps:

[0050] Step T1: Data conversion: Organize the preprocessed carbon emission data according to the time series, convert it into multi-dimensional time series feature data, and define the output space of the carbon emission assessment task;

[0051] The output space of the carbon emission assessment task includes: the total carbon emissions, the coal mine carbon emission reduction strategy, and the dynamic characteristics of carbon emissions at hourly, daily, and monthly time resolutions;

[0052] Step T2: Extract local features: Perform a convolution operation on the multi-dimensional time series feature data using one-dimensional convolution to capture the local correlation of the multi-dimensional time series feature data in the time dimension, obtain the convolution result, and perform a non-linear mapping on the convolution result through the ReLU activation function to generate the activation feature data;

[0053] Step T3: Compress data: Perform pooling processing on the activation feature data, extract the key feature values within the local time period of the multi-dimensional time series feature data through the max pooling technique, reduce the dimension of the activation feature data and compress the computational amount, generate the pooled local time feature data, and the key feature values include the mean, variance, and peak value;

[0054] Step T4: Capture global dependencies: Input the pooled local time feature data into a bidirectional gated recurrent unit to generate the BiGRU global time series feature data;

[0055] Step T5: Assign attention weights: Process the BiGRU global time series feature data through the attention mechanism to generate the weighted comprehensive time series feature data;

[0056] Step T6: Map feature output: Process the weighted comprehensive time series feature data through a fully connected layer and map it to the output space of the carbon emission assessment task to generate the carbon emission assessment data.

[0057] Example 4, this example is based on Example 2. In this example, step P4 specifically includes the following steps:

[0058] Step P41: Split the pooled local time feature data according to hourly, daily, and monthly time resolutions to form multiple groups of feature data; among them, the hourly resolution is used to capture the device operation data and short-term carbon emission change patterns; the daily resolution is used to capture the medium-term impact of production activities and energy consumption on carbon emissions; the monthly resolution captures the long-term trend impact of policy changes and equipment aging;

[0059] Step P42: Input the multiple groups of feature data into the sub-network of the enhanced bidirectional gated recurrent unit to extract the hourly global time series feature, daily global time series feature, and monthly global time series feature; the forward GRU and backward GRU are used inside the sub-network to capture the dynamic dependency relationships at different time steps respectively;

[0060] Sub-network feature extraction formula:

[0061] ;

[0062] Among them, represents the hourly global time series feature, represents the bidirectional gated recurrent unit, represents the hourly time resolution feature data in multiple groups of feature data;

[0063] ;

[0064] Among them, represents the daily global time series feature, represents the daily time resolution feature data in multiple groups of feature data;

[0065] ;

[0066] Among them, represents the monthly global time series feature, represents the monthly time resolution feature data in multiple groups of feature data;

[0067] Step P43: Fuse the hourly global time series feature, the daily global time series feature, and the monthly global time series feature into the BiGRU global time series feature data through a weighted fusion mechanism.

[0068] Example 5. This example is based on Example 4. In this example, the process of optimizing the hyperparameter module and optimizing the hyperparameters of the enhanced CNN-BiGRU model specifically includes the following steps:

[0069] Step B1: Randomly generate the beluga individuals in the population of the whale optimization algorithm. Each beluga individual represents a set of hyperparameter configurations of the enhanced CNN-BiGRU model. Define the search space. The hyperparameter configurations include the convolutional kernel size, the number of convolutional kernels, the number of BiGRU hidden units, the type of Attention mechanism, the learning rate, and the batch size. Generate the initial beluga population according to the search space, set the fitness function, calculate the initial fitness value of the initial beluga population through the fitness function, and select the current global optimal solution according to the initial fitness value;

[0070] Step B2: Conduct a global exploration of the beluga individuals in the initial beluga population. Simulate the swimming behavior of belugas and combine the dynamic dimension weight mechanism. Randomly select the target whale individual. Each beluga individual updates its own hyperparameter configuration through the random jump mechanism, combines the target whale individual and the current global optimal solution, and expands the search space to generate the global beluga population. The global beluga population is divided into a high-performance population and a low-performance population. The used formula is as follows:

[0071] Dynamic update formula for the position of the beluga individual:

[0072] Even dimensions:

[0073] ;

[0074] Among them, represents the number of iterations, represents the current dimension index, represents the dynamic dimension weight, represents the index of the current beluga individual, represents the index of the target beluga individual, represents the th new position of the th beluga individual in the th dimension, represents the th current position of the and represents a random number, represents a random number sin value, represents the position of the target beluga individual in the th dimension, represents the index of a random beluga individual, represents the position of the random beluga individual in the th dimension;

[0075] Odd - numbered dimensions:

[0076] ;

[0077] Among them, represents the cosine value of the random number ;

[0078] Step B3: Perform local optimization on the high - performance population, adjust the step size of beluga individuals in the high - performance population using the enhanced Levy flight mechanism, and optimize the hyperparameter configuration of beluga individuals in the high - performance population. The formula used is as follows:

[0079] ;

[0080] Among them, represents the acceleration factor, represents the acceleration proportionality constant, represents the current beluga individual fitness value, represents the fitness value of the beluga individual at the iteration, represents the scale factor, represents the minimum fitness value in the current population;

[0081] ;

[0082] Among them, Indicates the new position of the th beluga individual after iterations, Indicates the position of the th beluga individual in the iteration, Indicates the position of a random beluga individual in the iteration, Indicates a random number, Indicates the dynamic step size adjustment factor, Indicates the Levy flight step size function,

[0083] Step B4: Process the low-performance population through the whale fall mechanism, randomly reset the hyperparameter configurations of the beluga individuals in the low-performance population to prevent getting stuck in local optima;

[0084] Step B5: Update the global beluga population through local exploitation and whale fall processing to generate an optimized global beluga population, calculate the optimized fitness value of the optimized global beluga population through the fitness function, and update the current global optimal solution according to the optimized fitness value;

[0085] Step B6: Set the maximum number of iterations, iterate Steps B2 - B5 until the maximum number of iterations is reached, generate the final global optimal solution, and obtain the optimal hyperparameter configuration.

[0086] Example Six, this example is based on Example Four. In this example, the process of optimizing the hyperparameters of the optimized enhanced CNN - BiGRU model by the hyperparameter optimization module specifically includes the following steps:

[0087] Step R1: Randomly generate beluga individuals in the population of the whale optimization algorithm. Each beluga individual represents a set of hyperparameter configurations of the enhanced CNN - BiGRU model. Define the search space. The hyperparameter configurations include the convolutional kernel size, the number of convolutional kernels, the number of BiGRU hidden units, the type of Attention mechanism, the learning rate, and the batch size. Generate the initial beluga population according to the search space, set the fitness function, calculate the initial fitness value of the initial beluga population through the fitness function, and select the current global optimal solution according to the initial fitness value;

[0088] Step R2: Conduct global exploration on the beluga individuals in the initial beluga population, simulate the swimming behavior of belugas, randomly select target whale individuals. Each beluga individual updates its own hyperparameter configuration through the random jump mechanism, combines the target whale individual and the current global optimal solution, and expands the search space to generate the global beluga population. The global beluga population is divided into a high-performance population and a low-performance population;

[0089] Step R3: Perform local optimization on the high-performance population, adjust the step size of the beluga individuals in the high-performance population using the Levy flight mechanism, and optimize the hyperparameter configuration of the beluga individuals in the high-performance population;

[0090] Step R4: Process the low-performance population through the whale-fall mechanism, randomly reset the hyperparameter configuration of the beluga individuals in the low-performance population to prevent getting stuck in local optima;

[0091] Step R5: Update the global beluga population through local exploitation and whale-fall processing to generate an optimized global beluga population, calculate the optimized fitness value of the optimized global beluga population using the fitness function, and update the current global optimal solution according to the optimized fitness value;

[0092] Step R6: Set the maximum number of iterations, iterate Steps R2 - R5 until the maximum number of iterations is reached, generate the final global optimal solution, and obtain the optimal hyperparameter configuration.

[0093] The above describes the present invention and its implementation manners. Such description is not restrictive. What is shown in the drawings is only one of the implementation manners of the present invention, and the actual structure is not limited thereto. Generally speaking, if those of ordinary skill in the art are inspired by it and design similar structural manners and embodiments without creative efforts without departing from the gist of the present invention, they shall fall within the protection scope of the present invention.

Claims

1. A coal mine carbon emission assessment system, the system includes a data preprocessing module, and the data preprocessing module generates preprocessed carbon emission data; characterized in that: The system also includes a carbon emission assessment module and a hyperparameter optimization module; The carbon emission assessment module constructs an enhanced CNN-BiGRU model, initializes the hyperparameters of the enhanced CNN-BiGRU model, uses the enhanced CNN-BiGRU model to process the preprocessed carbon emission data, and generates carbon emission assessment data; The hyperparameter optimization module constructs an improved whale optimization algorithm, and optimizes the hyperparameters of the enhanced CNN-BiGRU model through the improved whale optimization algorithm.

2. The coal mine carbon emission assessment system according to claim 1, wherein: A CNN-BiGRU model is established, and the bidirectional gated recurrent unit is optimized through a multi-resolution mechanism to construct an enhanced CNN-BiGRU model.

3. The coal mine carbon emission assessment system according to claim 1, characterized in that: The dynamic dimension weight mechanism is used to optimize the global exploration of the whale optimization algorithm, and the acceleration factor and dynamic step size adjustment factor are introduced to improve the Levy flight mechanism. An enhanced Levy flight mechanism is constructed, and the local development of the whale optimization algorithm is optimized by enhancing the Levy flight mechanism to construct an improved whale optimization algorithm.

4. A coal mine carbon emission assessment system according to claim 1, characterized in that: The process of generating carbon emission assessment data by the carbon emission assessment module specifically includes the following steps: Step P1: Convert the pre-processed carbon emission data into multi-dimensional time series feature data; Step P2: Perform convolution operation on the multi-dimensional time series feature data to generate activation feature data; Step P3: pooling the activated feature data to generate pooled local time feature data; Step P4: Input the pooled local temporal feature data into the enhanced bidirectional gated recurrent unit to generate BiGRU global temporal feature data; Step P5: Process the BiGRU global temporal feature data through the attention mechanism to generate weighted comprehensive temporal feature data; Step P6: Process the weighted comprehensive time series feature data through the fully connected layer to generate carbon emission assessment data.

5. The coal mine carbon emission assessment system according to claim 4, characterized in that: Step P4 specifically includes the following steps: Step P41: Split the pooled local time feature data according to hourly, daily, and monthly time resolutions to form multiple groups of feature data; Step P42: Input multiple sets of feature data into the sub-network of the enhanced bidirectional gated recurrent unit to extract hourly global temporal features, daily global temporal features, and monthly global temporal features; Step P43: The hourly global time series features, daily global time series features, and monthly global time series features are fused into BiGRU global time series feature data through a weighted fusion mechanism.

6. The coal mine carbon emission assessment system according to claim 1, characterized in that: The process of optimizing the hyperparameters of the enhanced CNN-BiGRU model in the hyperparameter optimization module specifically includes the following steps: Step B1: Randomly generate beluga whales from the population of the whale optimization algorithm. Each beluga whale represents a set of hyperparameter configurations for the enhanced CNN-BiGRU model. Define the search space, generate the initial beluga whale population, and select the current global optimal solution. Step B2: Perform a global exploration of the beluga whales in the initial beluga whale population, simulate the swimming behavior of beluga whales, and combine the dynamic dimension weight mechanism to randomly select target whales. Each beluga whale uses a random jumping mechanism, combines the target whale individual and the current global optimal solution, updates its own hyperparameter configuration, and expands the search space to generate a global beluga whale population. The global beluga whale population is divided into a high-performance population and a low-performance population. Step B3: Perform local optimization on the high-performance population, adjust the step size of the beluga individuals in the high-performance population using the enhanced Levy flight mechanism, and optimize the hyperparameter configuration of the beluga individuals in the high-performance population; Step B4: Process the low-performance population through the whale fall mechanism, and randomly reset the hyperparameter configuration of the beluga individuals in the low-performance population; Step B5: Update the global beluga population through local development and whale fall processing, generate an optimized global beluga population, and update the current global optimal solution; Step B6: Iterate steps B2 - B5 to optimize the hyperparameter configuration.

Images