A low-carbon construction evaluation method based on data processing

Abstract

The present invention discloses a low-carbon construction evaluation method based on data processing, which belongs to the field of low-carbon assessment technology and includes the following steps: S1, inputting the historical carbon emission data set of the construction site into the expected detection model to obtain the expected error coefficient at each moment; S2, generating the amplitude adjustment value of the nonlinear mapping based on the expected error coefficient at each moment, and using several power coefficients of the nonlinear mapping to obtain the carbon emission mapping value at each moment; S3, constructing an adaptive penalty equation based on the carbon emission mapping values ​​at all moments to obtain the optimal penalty weight of the historical carbon emission data set; S4, determining the carbon emission evaluation of the construction site based on the optimal penalty weight of the historical carbon emission data set. The present invention uses the calculation result of the historical peak value and the optimal penalty weight as the evaluation threshold to construct a double safety margin to ensure whether the possibility of extreme emission scenarios can be grasped, so that the evaluation results are accurate and comprehensive.

Description

Technical Field

[0001] The present invention belongs to the technical field of low-carbon assessment, and in particular relates to a low-carbon construction evaluation method based on data processing. Background Art

[0002] In energy conservation and emission reduction, CO2, CH4 and N2O, as the main components of greenhouse gases, are the key research objects of energy conservation and emission reduction. Since CO2 accounts for the largest proportion of greenhouse gases, about 60%, the term carbon emissions is often used as a general term for greenhouse gases. When calculating carbon emissions, other greenhouse gases are converted into equivalent CO2 in order to calculate the total amount of greenhouse gas emissions and then judge the intensity of the greenhouse effect.

[0003] The carbon emissions continuously generated during the construction process have become a management issue that cannot be ignored in urban development. However, the carbon emission data at the construction site often have the characteristics of time-varying, nonlinearity and uncertainty, which makes it difficult for traditional linear evaluation methods to accurately reflect the carbon emission status of the construction site. Summary of the Invention

[0004] In order to solve the above problems, the present invention proposes a low-carbon construction evaluation method based on data processing.

[0005] The technical solution of the present invention is: a low-carbon construction evaluation method based on data processing comprises the following steps:

[0006] S1. Input the historical carbon emission dataset of the construction site into the expected detection model to obtain the expected error coefficient at each moment;

[0007] S2. Generate an amplitude adjustment value of the nonlinear mapping based on the expected error coefficient at each moment, and use several power coefficients of the nonlinear mapping to obtain the carbon emission mapping value at each moment;

[0008] S3. Based on the carbon emission mapping values ​​at all times, an adaptive penalty equation is constructed to obtain the optimal penalty weight for the historical carbon emission dataset;

[0009] S4. Determine the carbon emission evaluation of the construction site based on the optimal penalty weight of the historical carbon emission dataset.

[0010] Furthermore, in S1, the expected detection model is used to extract the maximum and minimum values ​​between the carbon emission value at each moment and the expected carbon emission value, and the ratio between the minimum value and the maximum value is subtracted from 1 to generate the expected error coefficient at each moment.

[0011] The beneficial effects of this further solution are as follows: The normalized calculation method used in this invention maps the error coefficient to the interval [0, 1], eliminating dimensionality effects and facilitating direct comparison and comprehensive analysis of errors across time periods. The maximum and minimum value selection mechanism naturally focuses on extreme data values, effectively identifying sudden and abnormal fluctuations in carbon emissions.

[0012] Furthermore, S2 includes the following sub-steps:

[0013] S21, using the expected error coefficient at each moment as the amplitude adjustment value of the nonlinear mapping;

[0014] S22. Perform an exponential operation on the carbon emission value at each moment with the natural constant e as the base, and use this as the first power coefficient of the nonlinear mapping; perform an exponential operation on the inverse of the ratio between the carbon emission value at each moment and the average carbon emission value at all moments with the natural constant e as the base, and use this as the second power coefficient of the nonlinear mapping;

[0015] S23 . Perform nonlinear mapping on the carbon emission value at each moment according to the amplitude adjustment value, the first power coefficient, and the second power coefficient of the nonlinear mapping to obtain the carbon emission mapping value at each moment.

[0016] The beneficial effect of this further solution is that, in this invention, the expected error coefficient generated by S1 is directly used as the amplitude adjustment value A, establishing an error-driven mapping intensity adjustment mechanism. Carbon emission data at moments with greater errors will receive more significant nonlinear transformation amplitudes, enabling automatic focusing on abnormal emission patterns. Through moment-specific amplitude adjustment values, a correlation mapping between temporal error characteristics and spatial emission intensity is established.

[0017] The first power function performs a natural exponential operation on the original carbon emission value to enhance the discrimination of high emission values. The second power function constructs a standardized deviation index through the ratio operation of the carbon emission value to the global mean, eliminates the dimensional effect, and suppresses the excessive interference of extreme outliers on the mapping process, while retaining key morphological features.

[0018] Furthermore, in S23, the expression for performing nonlinear mapping is:

[0019] ;

[0020] Where, represents the carbon emission mapping value, represents the amplitude adjustment value of the nonlinear mapping, represents the first power coefficient of the nonlinear mapping, represents the second power coefficient of the nonlinear mapping, Indicates the carbon emission value, represents the activation function, Indicates the average carbon emissions at the total time, Represents the base-2 logarithm function.

[0021] The beneficial effect of the above further solution is: in the present invention, in the first part, the first power function is used to form a self-regulating gating unit to prevent the exponential channel from being oversaturated. In the second part, Periodic modulation is introduced, and the hyperbolic tangent constrained tanh function compresses the carbon emission mapping values ​​into the (-1, 1) interval, ensuring controllable oscillation amplitudes and avoiding the vanishing gradient problem. In the third part, the linear component of the original emission value is retained as a residual supplement to the nonlinear mapping to prevent information loss.

[0022] Furthermore, S3 includes the following sub-steps:

[0023] S31. Using the standard deviation of the carbon emission mapping values ​​at all times as the initial weight of the equation;

[0024] S32, constructing an adaptive penalty equation using the initial weights;

[0025] S33. Solve the adaptive penalty equation to obtain the optimal penalty weight of the historical carbon emission data set.

[0026] The beneficial effect of this further solution is that, in this invention, the standard deviation of the carbon emission mapping value is used as the initial weight, incorporating the inherent volatility of the data into the initialization process of the adaptive penalty equation. Solving the adaptive penalty equation can be decomposed into the parallel optimization of the weights at each moment, and the resulting optimal penalty weight more comprehensively considers the changes in carbon emissions over the entire time period.

[0027] Furthermore, in S33, the adaptive penalty equation The expression is:

[0028] ;

[0029] Where, Indicates the Carbon emissions at the moment, Indicates the The weight of the moment, Indicates the Expected carbon emissions, represents the initial weight of the adaptive penalty equation, represents the regularization coefficient, Indicates the final result that needs to be solved for the adaptive penalty equation. Indicates the total time, Indicates the expected carbon emission value. Represents a function that finds the input value that minimizes the function.

[0030] The beneficial effect of the above further solution is: in the present invention, A measure of the deviation between the predicted and expected values ​​was constructed to ensure the accurate fitting of the model to the historical emission patterns using the least squares form. Regularization can be introduced to prevent overfitting. Adjusting the γ value allows for a flexible balance between prediction error and model complexity. Continuous optimization of the final weights captures the optimal penalty weight.

[0031] Furthermore, S4 includes the following sub-steps:

[0032] S41. Obtain the expected carbon emission value of the construction site at a future time;

[0033] S42. Determine whether the product of the maximum carbon emission value of the historical carbon emission data set and the optimal penalty weight is greater than the expected carbon emission value. If so, the carbon emission evaluation of the construction site is failed; otherwise, it is passed.

[0034] The beneficial effect of the above further solution is that in the present invention, the historical maximum carbon emission value is used as a benchmark, rather than the mean or median, to construct a "worst case" assessment concept, ensuring that the construction site can grasp the possibility of sudden emissions.

[0035] The beneficial effects of the present invention are: the present invention extracts the expected error coefficient at each moment through the expected detection model, reflecting the deviation analysis of carbon emissions, and the expected error coefficient is dynamically generated based on historical data to avoid the hysteresis of the fixed threshold; the present invention uses the expected error coefficient to perform multi-channel processing such as logarithmic compression, hyperbolic tangent oscillation and adaptive linearity on the carbon emission value to identify the optimal penalty weight that plays a decisive role in carbon emission prediction; the calculation result of the historical peak value and the optimal penalty weight is used as the evaluation threshold to construct a double safety margin to ensure whether the possibility of extreme emission scenarios can be grasped, so that the evaluation results are accurate and comprehensive. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 Flowchart of the low-carbon construction evaluation method based on data processing. DETAILED DESCRIPTION

[0037] The embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0038] like Figure 1 As shown, the present invention provides a low-carbon construction evaluation method based on data processing, comprising the following steps:

[0039] S1. Input the historical carbon emission dataset of the construction site into the expected detection model to obtain the expected error coefficient at each moment;

[0040] S2. Generate an amplitude adjustment value of the nonlinear mapping based on the expected error coefficient at each moment, and use several power coefficients of the nonlinear mapping to obtain the carbon emission mapping value at each moment;

[0041] S3. Based on the carbon emission mapping values ​​at all times, an adaptive penalty equation is constructed to obtain the optimal penalty weight for the historical carbon emission dataset;

[0042] S4. Determine the carbon emission evaluation of the construction site based on the optimal penalty weight of the historical carbon emission dataset.

[0043] In an embodiment of the present invention, in S1, the expected detection model is used to extract the maximum and minimum values ​​between the carbon emission value at each moment and the expected carbon emission value, and the ratio between the minimum value and the maximum value is subtracted from 1 to generate the expected error coefficient at each moment.

[0044] This paper uses a normalized calculation method to map the error coefficient to the interval [0, 1], eliminating dimensionality and facilitating direct comparison and comprehensive analysis of errors across time periods. The maximum and minimum value selection mechanism naturally focuses on extreme data values, effectively identifying sudden, abnormal fluctuations in carbon emissions.

[0045] In this embodiment of the present invention, S2 includes the following sub-steps:

[0046] S21, using the expected error coefficient at each moment as the amplitude adjustment value of the nonlinear mapping;

[0047] S22. Perform an exponential operation on the carbon emission value at each moment with the natural constant e as the base, and use this as the first power coefficient of the nonlinear mapping; perform an exponential operation on the inverse of the ratio between the carbon emission value at each moment and the average carbon emission value at all moments with the natural constant e as the base, and use this as the second power coefficient of the nonlinear mapping;

[0048] S23 . Perform nonlinear mapping on the carbon emission value at each moment according to the amplitude adjustment value, the first power coefficient, and the second power coefficient of the nonlinear mapping to obtain the carbon emission mapping value at each moment.

[0049] In this paper, the expected error coefficient generated by S1 is directly used as the amplitude adjustment value A, establishing an error-driven mapping intensity adjustment mechanism. Carbon emission data at moments with greater errors will receive more significant nonlinear transformation amplitudes, enabling automatic focusing on abnormal emission patterns. This moment-specific amplitude adjustment value establishes a correlation mapping between temporal error characteristics and spatial emission intensity.

[0050] The first power function performs a natural exponential operation on the original carbon emission value to enhance the discrimination of high emission values. The second power function constructs a standardized deviation index through the ratio operation of the carbon emission value to the global mean, eliminates the dimensional effect, and suppresses the excessive interference of extreme outliers on the mapping process, while retaining key morphological features.

[0051] In the embodiment of the present invention, in S23, the expression for performing nonlinear mapping is:

[0052] ;

[0053] Where, represents the carbon emission mapping value, represents the amplitude adjustment value of the nonlinear mapping, represents the first power coefficient of the nonlinear mapping, represents the second power coefficient of the nonlinear mapping, Indicates the carbon emission value, represents the activation function, Indicates the average carbon emissions at the total time, Represents the base-2 logarithm function.

[0054] In the present invention, in the first part, the first power function is used to form a self-regulating gating unit to prevent the exponential channel from being oversaturated. In the second part, Periodic modulation is introduced, and the hyperbolic tangent constrained tanh function compresses the carbon emission mapping values ​​into the (-1, 1) interval, ensuring controllable oscillation amplitudes and avoiding the vanishing gradient problem. In the third part, the linear component of the original emission value is retained as a residual supplement to the nonlinear mapping to prevent information loss.

[0055] In this embodiment of the present invention, S3 includes the following sub-steps:

[0056] S31. Using the standard deviation of the carbon emission mapping values ​​at all times as the initial weight of the equation;

[0057] S32, constructing an adaptive penalty equation using the initial weights;

[0058] S33. Solve the adaptive penalty equation to obtain the optimal penalty weight of the historical carbon emission data set.

[0059] In this paper, the standard deviation of the carbon emission mapping value is used as the initial weight, incorporating the inherent volatility of the data into the initialization process of the adaptive penalty equation. Solving the adaptive penalty equation can be decomposed into the parallel optimization of the weights at each moment, and the resulting optimal penalty weight more comprehensively considers the changes in carbon emissions over the entire time period.

[0060] In the embodiment of the present invention, in S33, the adaptive penalty equation The expression is:

[0061] ;

[0062] Where, Indicates the Carbon emissions at the moment, Indicates the The weight of the moment, Indicates the Expected carbon emissions, represents the initial weight of the adaptive penalty equation, represents the regularization coefficient, Indicates the final result that needs to be solved for the adaptive penalty equation. Indicates the total time, Indicates the expected carbon emission value. Represents a function that finds the input value that minimizes the function.

[0063] In the present invention, A measure of the deviation between the predicted and expected values ​​was constructed to ensure the accurate fitting of the model to the historical emission patterns using the least squares form. Regularization can be introduced to prevent overfitting. Adjusting the γ value allows for a flexible balance between prediction error and model complexity. Continuous optimization of the final weights captures the optimal penalty weight.

[0064] In this embodiment of the present invention, S4 includes the following sub-steps:

[0065] S41. Obtain the expected carbon emission value of the construction site at a future time;

[0066] S42. Determine whether the product of the maximum carbon emission value of the historical carbon emission data set and the optimal penalty weight is greater than the expected carbon emission value. If so, the carbon emission evaluation of the construction site is failed; otherwise, it is passed.

[0067] In the present invention, the historical maximum carbon emission value is used as a benchmark, rather than the mean or median, to construct a "worst-case scenario" assessment concept to ensure that the construction site can grasp the possibility of sudden emissions.

[0068] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and it should be understood that the scope of protection of the present invention is not limited to such specific descriptions and embodiments. Those skilled in the art can make various other specific variations and combinations based on the technical teachings disclosed in the present invention without departing from the essence of the present invention, and such variations and combinations are still within the scope of protection of the present invention.

Claims

1. A low-carbon construction evaluation method based on data processing, characterized in that: The following steps are involved: S1. Input the historical carbon emission dataset of the construction site into the expected detection model to obtain the expected error coefficient at each moment; S2. Generate an amplitude adjustment value of the nonlinear mapping based on the expected error coefficient at each moment, and use several power coefficients of the nonlinear mapping to obtain the carbon emission mapping value at each moment; S3. Based on the carbon emission mapping values ​​at all times, an adaptive penalty equation is constructed to obtain the optimal penalty weight for the historical carbon emission dataset; S4. Determine the carbon emission evaluation of the construction site based on the optimal penalty weight of the historical carbon emission dataset; In S1, the expected detection model is used to extract the maximum and minimum values ​​between the carbon emission value at each moment and the expected carbon emission value, and the ratio between the minimum value and the maximum value is subtracted from 1 to generate the expected error coefficient at each moment; The S2 includes the following sub-steps: S21, using the expected error coefficient at each moment as the amplitude adjustment value of the nonlinear mapping; S22. Perform an exponential operation on the carbon emission value at each moment with the natural constant e as the base, and use this as the first power coefficient of the nonlinear mapping; perform an exponential operation on the inverse of the ratio between the carbon emission value at each moment and the average carbon emission value at all moments with the natural constant e as the base, and use this as the second power coefficient of the nonlinear mapping; S23. Perform nonlinear mapping on the carbon emission value at each moment according to the amplitude adjustment value, the first power coefficient, and the second power coefficient of the nonlinear mapping to obtain a carbon emission mapping value at each moment; The S3 includes the following sub-steps: S31. Using the standard deviation of the carbon emission mapping values ​​at all times as the initial weight of the equation; S32, constructing an adaptive penalty equation using the initial weights; S33, solving the adaptive penalty equation to obtain the optimal penalty weight for the historical carbon emission dataset; The S4 includes the following sub-steps: S41. Obtain the expected carbon emission value of the construction site at a future time; S42. Determine whether the product of the maximum carbon emission value of the historical carbon emission data set and the optimal penalty weight is greater than the expected carbon emission value. If so, the carbon emission evaluation of the construction site is failed; otherwise, it is passed.

2. The low-carbon construction evaluation method based on data processing according to claim 1 is characterized in that: In S23, the expression for performing nonlinear mapping is: ； Where, represents the carbon emission mapping value, represents the amplitude adjustment value of the nonlinear mapping, represents the first power coefficient of the nonlinear mapping, represents the second power coefficient of the nonlinear mapping, Indicates the carbon emission value, represents the activation function, Indicates the average carbon emissions at the total time, Represents the base-2 logarithm function.

3. The low-carbon construction evaluation method based on data processing according to claim 1 is characterized in that: In S33, the adaptive penalty equation The expression is: ； Where, Indicates the Carbon emissions at the moment, Indicates the The weight of the moment, Indicates the Expected carbon emissions, represents the initial weight of the adaptive penalty equation, represents the regularization coefficient, Indicates the final result that needs to be solved for the adaptive penalty equation. represents the total time, J represents the expected carbon emission value, Represents a function that finds the input value that minimizes the function.

Images