Carbon emission prediction method based on immersed tube joint quality

Abstract

The invention relates to a carbon emission prediction method based on immersed tube joint quality, and belongs to the technical field of immersed tube tunnel construction. The carbon emission prediction method comprises the following steps: obtaining the carbon emission, the pipe joint quality and the pipe joint type of each pipe joint in the construction process in the completed immersed tunnel project; establishing a rectangular plane coordinate system by taking the pipe joint mass as a horizontal coordinate and the carbon emission as a vertical coordinate to obtain a plurality of data points distributed in the rectangular plane coordinate system; fitting the data points by adopting a least square method to obtain a first prediction model; obtaining abnormal points of the plurality of data points relative to the first prediction model; the pipe joint quality and the pipe joint type corresponding to the abnormal point are obtained, and the pipe joint type compensation amount is determined; correcting the first prediction model based on the pipe joint quality corresponding to the abnormal point and the pipe joint type compensation amount to obtain a second prediction model; and on the basis of the pipe joint quality of the to-be-constructed pipe joint, a carbon emission prediction value of the to-be-constructed pipe joint is calculated through the second prediction model.

Description

Technical Field

[0001] This invention belongs to the field of immersed tunnel construction technology, and in particular relates to a method for predicting carbon emissions based on the quality of immersed tunnel segments. Background Technology

[0002] With increasing global attention to climate change, green construction has become an inevitable trend in infrastructure development. Immersed tunnels, as a crucial form of cross-river and sea transportation hubs, involve large-scale construction and consume significant amounts of energy and materials, emitting greenhouse gases during the construction phase. Therefore, effectively managing carbon emissions during immersed tunnel construction is a vital path to achieving green and low-carbon development in tunnel engineering, and the scientific assessment of carbon emissions is a core element of this process.

[0003] Currently, carbon emissions are mostly calculated using life cycle assessment methods, which cover the entire process from material production and construction to operation and maintenance, and can comprehensively reflect the carbon emissions of a project. However, the construction process of immersed tunnels is complex and involves many procedures. In the early design stage of the project, due to the lack of detailed construction data, existing methods are unable to quickly and accurately predict carbon emissions, thus limiting the effective implementation of carbon management during the construction phase.

[0004] Therefore, designing a method that can predict carbon emissions during the construction of immersed tunnels in advance is of great significance for the green construction of immersed tunnels. Summary of the Invention

[0005] To address the shortcomings of related technologies, this invention provides a carbon emission prediction method based on the quality of immersed tunnel segments. A carbon emission prediction model is established using historical data on segment quality and carbon emissions from completed immersed tunnel projects. The prediction model is then corrected based on anomalies in the historical data, including segment quality and segment type, to effectively predict the carbon emissions of the segments to be constructed. This allows for optimization of the segment construction process based on the carbon emission prediction results, ensuring green construction of the immersed tunnel.

[0006] This invention provides a method for predicting carbon emissions based on the mass of immersed tunnel sections, comprising the following steps: Obtain information on the carbon emissions, mass, and type of each tunnel segment during the construction process of a completed immersed tunnel project. A Cartesian coordinate system is established with pipe section mass as the abscissa and carbon emissions as the ordinate, and several data points are distributed in the Cartesian coordinate system. The first prediction model is obtained by fitting the data points using the least squares method; Obtain outliers from several data points relative to the first prediction model; acquire the pipe section quality and pipe section type corresponding to the outliers, and determine the pipe section type compensation amount; The first prediction model is corrected based on the pipe section quality and pipe section type compensation amount corresponding to the anomaly point to obtain the second prediction model. The predicted carbon emissions of the pipe section to be constructed are calculated using a second prediction model based on the quality of the pipe section to be constructed.

[0007] The technical solution establishes a carbon emission prediction model using historical data on the quality, carbon emissions, and types of pipe sections from completed immersed tunnel projects. This model is used to predict the carbon emissions of the pipe sections to be constructed, thereby optimizing the construction process based on the predicted carbon emissions and ensuring green construction of the immersed tunnel.

[0008] In some embodiments of this application, the first prediction model is y=k1x+b; where y is the predicted value of carbon emissions; k1 and b are constants, and x is the mass of the pipe section.

[0009] In some embodiments of this application, the structural feature compensation amount is determined based on the proportion of steel in the pipe section; the first prediction model is further modified based on the structural feature compensation amount of the pipe section corresponding to the anomaly point to obtain the second prediction model.

[0010] In some embodiments of this application, the second prediction model is finally corrected based on the compensation amount of the pipe section type and the compensation amount of the structural characteristics of the pipe section to be constructed, so as to obtain the final prediction model; the final prediction model is y=k2x+k3m+[b+ug(i)]+Z, where k2, k3, and b are constants and k2≠k3, m is max(xn,0), n is the pipe section mass of the outlier point; ug(i) is the compensation amount of the pipe section type of the pipe section to be constructed; and Z is the compensation amount of the structural characteristics of the pipe section to be constructed.

[0011] In some embodiments of this application, the pipe section type includes at least a standard section, a transition section, and an interface section; the pipe section type compensation is based on the carbon emissions of the standard section during the sinking stage. The calculation method for the pipe section type compensation is as follows: Select the transition section, standard section, and interface section from the completed immersed tunnel project. The difference between the actual carbon emissions of the transition section and the actual carbon emissions of the standard section during the immersion stage is the pipe section type compensation for the transition section. The difference between the actual carbon emissions of the interface section and the actual carbon emissions of the standard section during the immersion stage is the pipe section type compensation for the interface section.

[0012] In some embodiments of this application, the structural feature compensation amount is based on the steel ratio. The carbon emissions of the pipe sections during the prefabrication stage are used as a benchmark for compensation; The calculation method for structural feature compensation is as follows: Select pipe sections with the same mass but different steel proportions from completed immersed tunnel projects, and use the steel proportion as... The actual carbon emissions of each pipe section during the prefabrication stage are used as the baseline carbon emissions; the difference between the actual carbon emissions of each pipe section during the prefabrication stage and the baseline carbon emissions is the structural feature compensation amount corresponding to the proportion of each steel material.

[0013] In some embodiments of this application, after obtaining the second prediction model, the effectiveness of the second prediction model is verified; if the second prediction model is effective, the carbon emissions of the pipe section to be constructed are predicted using the second prediction model; if the second prediction model is ineffective, the second prediction model is further modified. The effectiveness of the second prediction model was verified using at least one of the following: residual, mean square error, adjusted coefficient of determination, Durbin-Watson statistic, and mean absolute percentage error.

[0014] In some embodiments of this application, the predicted value of carbon emissions corresponding to the pipe section mass in each data point is calculated according to the first prediction model, and the absolute value between the actual value of carbon emissions and the predicted value of carbon emissions is calculated. If the absolute value exceeds the first preset threshold, the data point where the pipe section mass is located is a high anomaly point. If the ratio of the number of high outliers to the total number of data points exceeds the second preset threshold, then the first prediction model is refitted.

[0015] In some embodiments of this application, when refitting the first prediction model, the weights of outliers are first calculated, and then the data points are refitted using an iterative reweighting method to obtain a new first prediction model; and the new first prediction model is corrected based on the pipe section quality and pipe section type compensation amount corresponding to the outliers to obtain a new second prediction model.

[0016] In some embodiments of this application, the pipe section includes at least concrete, steel, and waterproofing material; the mass of the pipe section is at least the sum of the mass of the concrete, the mass of the steel, and the mass of the waterproofing material. And / or, the carbon emissions of the pipe section are at least the sum of the carbon emissions during the pipe section prefabrication stage, the pipe section transportation stage, and the pipe section placement stage.

[0017] Based on the above technical solution, the carbon emission prediction method based on the quality of immersed tunnel segments in this embodiment of the invention establishes a carbon emission prediction model based on historical data such as the quality and carbon emission of tunnel segments in completed immersed tunnel projects, and corrects the prediction model based on the quality and type of tunnel segments at anomalies in the historical data, so as to effectively predict the carbon emission of the tunnel segments to be constructed. Thus, the tunnel segment construction process can be optimized based on the carbon emission prediction results to ensure green construction of immersed tunnels. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings: Figure 1 This is a schematic diagram illustrating the source of carbon emissions from a pipe section in one embodiment of the carbon emission prediction method based on the mass of an immersed tunnel section according to the present invention. Figure 2 This is a flowchart of an embodiment of the carbon emission prediction method based on the mass of immersed tunnel sections according to the present invention; Figure 3 This is a distribution diagram of data points in a rectangular coordinate system in one embodiment of the carbon emission prediction method based on the mass of immersed tunnel sections of the present invention. Figure 4 This is a schematic diagram of the first prediction model fitting data points in one embodiment of the carbon emission prediction method based on the mass of immersed tunnel sections of the present invention. Figure 5 This is a schematic diagram of the second prediction model fitting data points in one embodiment of the carbon emission prediction method based on the mass of immersed tunnel sections of the present invention. Detailed Implementation

[0019] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0020] In the description of this invention, it should be understood that the terms "center", "lateral", "longitudinal", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0021] The terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first," "second," or "third" may explicitly or implicitly include one or more of that feature.

[0022] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0023] An immersed tunnel consists of multiple segments. After prefabrication, these segments are transported to the construction site and submerged in an underwater trench. They are then precisely connected to the existing segments to form a tunnel that runs through both sides of the water body. Since each segment is prefabricated, transported, and submerged independently, each segment is constructed separately, and each segment has its own corresponding carbon emissions during construction.

[0024] The sources of carbon emissions from pipe sections mainly include building material production during the prefabrication stage, transport vehicles during the transportation stage, and construction machinery during the placement stage. It can be considered that the carbon emissions during pipe section construction are the sum of the carbon emissions generated during pipe section prefabrication, the carbon emissions generated during pipe section transportation by transport vehicles, and the carbon emissions generated during pipe section placement by construction machinery. In short, the carbon emissions from a single pipe section are at least the sum of the carbon emissions from the prefabrication, transportation, and placement stages.

[0025] Depending on their location, pipe sections can be categorized into various types, including at least standard sections, transition sections, and interface sections. Because of these different types, the installation processes and other aspects may vary. Therefore, even pipe sections of the same quality may have different carbon emissions depending on their type.

[0026] The pipe section includes at least concrete, steel, and waterproofing materials; the mass of the pipe section is at least the sum of the mass of the concrete, the mass of the steel, and the mass of the waterproofing materials; different proportions of steel will lead to different carbon emissions during the prefabrication process of the pipe section, thus resulting in different carbon emissions of the pipe section. Therefore, even if the mass of the pipe section is the same, the carbon emissions of the pipe section may be different due to different proportions of steel.

[0027] As attached Figure 1 As shown in an illustrative embodiment of the carbon emission prediction method based on the mass of immersed tunnel sections of the present invention, the carbon emission prediction method based on the mass of immersed tunnel sections includes the following steps: Obtain information on the carbon emissions, mass, and type of each tunnel segment during the construction process of a completed immersed tunnel project. A Cartesian coordinate system is established with pipe section mass as the abscissa and carbon emissions as the ordinate, and several data points are distributed in the Cartesian coordinate system. The first prediction model is obtained by fitting the data points using the least squares method; Obtain outliers from several data points relative to the first prediction model; obtain the pipe section quality and pipe section type corresponding to the outliers, and determine the pipe section type compensation amount based on the pipe section type of the outliers; The first prediction model is corrected based on the pipe section quality and pipe section type compensation amount corresponding to the anomaly point to obtain the second prediction model. The predicted carbon emissions of the pipe section to be constructed are calculated using a second prediction model based on the quality of the pipe section to be constructed.

[0028] The aforementioned carbon emission prediction method based on the quality of immersed tunnel segments establishes a carbon emission prediction model by using historical data such as the quality and carbon emissions of tunnel segments in completed immersed tunnel projects, and then corrects the prediction model to effectively predict the carbon emissions of the tunnel segments to be constructed. This allows for optimization of the tunnel segment construction process based on the carbon emission prediction results, ensuring green construction of immersed tunnels.

[0029] It should be noted that, since the calculation of carbon emissions during pipe section construction may produce errors, the data points are preprocessed to remove outliers before using the least squares method to fit the first prediction model. Then, the least squares method is used to fit the preprocessed data points to ensure the effectiveness of the first prediction model.

[0030] Generally, the larger the mass of a pipe section, the greater its carbon emissions. Pipe section mass is directly proportional to its carbon emissions. Therefore, the first prediction model is a linear function, which is y=k1x+b; where y is the predicted value of carbon emissions; k1 and b are constants, and x is the mass of the pipe section.

[0031] Although larger pipe sections generally produce more carbon emissions, the relationship between pipe section mass and carbon emissions changes once the pipe section mass reaches a certain value. Therefore, outliers may be the turning point in the relationship between pipe section mass and carbon emissions.

[0032] Because different types of pipe sections may have different installation processes, even if the pipe sections are of the same quality, their carbon emissions may differ depending on their type. Therefore, anomalies may also be caused by the type of pipe section.

[0033] It should be noted that outliers are specific to a particular prediction model. The same data point may be an outlier relative to the current prediction model, but may be a normal point relative to another prediction model.

[0034] In this application, outliers of data points relative to the first prediction model are obtained, and the first prediction model is corrected according to the pipe section quality and pipe section type corresponding to the outliers to obtain the second prediction model. The carbon emissions of the pipe section to be constructed are predicted using the second prediction model to increase the accuracy of the prediction results.

[0035] Different types of pipe sections undergo different immersion processes during the immersion phase, resulting in varying carbon emissions even for sections of the same mass. Under the same mass, transition sections typically emit less carbon than standard sections, while interface sections emit more. In this application, carbon emission compensation for other types of pipe sections is performed based on the standard section. If the current pipe section is a standard section, the pipe section type compensation is 0; if the current pipe section is a transition section, the pipe section type compensation is negative; and if the current pipe section is an interface section, the pipe section type compensation is positive.

[0036] The calculation method for the pipe section type compensation is as follows: Select the transition section, standard section, and interface section from the completed immersed tunnel project. The difference between the actual carbon emissions of the transition section and the actual carbon emissions of the standard section during the immersion stage is the pipe section type compensation for the transition section. The difference between the actual carbon emissions of the interface section and the actual carbon emissions of the standard section during the immersion stage is the pipe section type compensation for the interface section.

[0037] It should be noted that the carbon emissions from the pipe section mass during the pipe section laying stage have a relatively small impact and can be ignored.

[0038] It should also be noted that, due to the differences in the tunnel segment placement process in different immersed tunnel constructions, the compensation amount for the same type of tunnel segment will also be different in different immersed tunnel constructions.

[0039] In addition, it should be noted that in this application, under the premise that the construction process is determined, the compensation amount for pipe section type is usually a specific value.

[0040] Since the proportion of steel in the pipe section is also an important factor affecting the carbon emissions of the pipe section, the anomaly may also be caused by the proportion of steel in the pipe section.

[0041] In this application, the structural feature compensation amount of the pipe section is determined based on the proportion of steel in the pipe section, and the first prediction model is further modified based on the structural feature compensation amount of the pipe section corresponding to the anomaly point to obtain the second prediction model.

[0042] The steel content refers to the ratio of steel to the total weight of the pipe section. Using the steel content as... Using the carbon emissions of a single pipe section as a benchmark, and assuming the same pipe section mass, if the steel content is higher than [a certain percentage], [the following scenario applies]. If the prefabrication of pipe sections consumes more high-carbon-emission materials, the carbon emissions will be higher than the baseline level; similarly, if the proportion of steel is lower than... This reduces the amount of high-carbon emission materials used during pipe section prefabrication, resulting in carbon emissions below the baseline level.

[0043] Therefore, the structural feature compensation amount is based on the proportion of steel. The carbon emissions of the pipe sections during the prefabrication stage are used as a benchmark for compensation. When the steel proportion is... When the structural feature compensation is 0, and when the steel accounts for a higher percentage than 100%, the compensation amount is 0. When the structural feature compensation is positive, the compensation amount is negative; when the proportion of steel is less than 10%, the compensation amount is positive. At this time, the structural feature compensation amount is negative. It should be noted that the structural feature compensation amount is different for different proportions of steel.

[0044] In some embodiments, the steel content in a standard pipe section is 0.096%. It is 0.096.

[0045] The calculation method for structural feature compensation is as follows: Select pipe sections with the same mass but different steel proportions from completed immersed tunnel projects, and use the steel proportion as... The actual carbon emissions of each pipe section during the prefabrication stage are used as the baseline carbon emissions; the difference between the actual carbon emissions of each pipe section during the prefabrication stage and the baseline carbon emissions is the structural feature compensation amount corresponding to the proportion of each steel material.

[0046] It should be noted that the proportion of steel in different types of pipe sections may not be exactly the same, but structural feature compensation compensates for this. Therefore, the pipe section type compensation mainly compensates for the differences in carbon emissions caused by different immersion processes. Specifically, different pipe section types have their own corresponding pipe section type compensation amounts, and different steel proportions also have their own corresponding structural feature compensation amounts.

[0047] The second prediction model obtained after correcting the first prediction model based on the pipe section type compensation amount and structural feature compensation amount of the anomaly point is y=k2x+k3m+b, where k2, k3, and b are constants and k2≠k3, m is max(xn,0), and n is the pipe section mass of the anomaly point.

[0048] In some embodiments, standardized residuals are used to identify outliers from a number of data points. The calculation method of the standardized residual method is as follows: the predicted value of carbon emissions corresponding to the mass of each pipe section in the data point is calculated according to the first prediction model; the absolute value between the actual value of carbon emissions corresponding to the mass of the pipe section and the predicted value of carbon emissions is calculated; if the absolute value exceeds a set value, the data point is determined to be an outlier.

[0049] Since the second prediction model is obtained by correcting the first prediction model using parameters such as pipe section quality and pipe section type at outliers, the effectiveness of the second prediction model will also decrease if the fitting error of the first prediction model is large.

[0050] In some embodiments of this application, when using the standardized residual method to determine outliers of the first prediction model, if the absolute value between the actual value of carbon emissions corresponding to the pipe section mass and the predicted value of carbon emissions exceeds a first preset threshold, then the data point where the pipe section mass is located is a high outlier; if the ratio of the number of high outliers to the total number of data points exceeds a second preset threshold, it indicates that the fitting error of the first prediction model is large and the first prediction model needs to be refitted.

[0051] When refitting the first prediction model, the weights of outliers are calculated separately, and then the data points are fitted using an iterative reweighting method to obtain the refitted first prediction model.

[0052] It should be noted that outliers and high outliers can also be obtained using methods such as leverage value and Cook distance. Identifying outliers and high outliers from a number of data points is a conventional technique in this field and will not be elaborated here.

[0053] Outliers may not be unique. When there are multiple outliers, the pipe section quality corresponding to the outlier that minimizes the overall residual is selected as n, that is, the outlier with the largest residual contribution is selected as n.

[0054] It should be noted that the residual contribution refers to the relative impact of the difference between the observed value and the model prediction on the overall result. The calculation of the residual contribution is a conventional technique in this field and will not be elaborated here.

[0055] It should be noted that after compensating for the pipe section type and structural feature compensation at the anomaly point, the pipe section compensation corresponding to the anomaly point can be considered as the standard section, and the steel proportion of the pipe section corresponding to the anomaly point is... This is equivalent to treating outliers as normal points. For example, suppose a pipe section is identified as an outlier because it is a transition section or interface section. However, after compensation by the pipe section type compensation amount, the pipe section is used as a standard section for data fitting. But outliers are not erroneous data points; they are also necessary data points. Carbon emission prediction is also required for transition sections and interface sections. According to the second prediction model, the predicted carbon emissions of the transition section, the predicted carbon emissions of the interface section, and the predicted carbon emissions of the standard section are all the same. Therefore, it can be seen that the second prediction model still has a large prediction error in the carbon emissions of pipe sections.

[0056] Therefore, in this application, the second prediction model is finally modified according to the compensation amount of the pipe section type and the compensation amount of the structural characteristics of the pipe section to be constructed, so as to obtain the final prediction model; the final prediction model is y=k2x+k3m+[b+ug(i)]+Z, where k2, k3, and b are constants and k2≠k3, m is max(xn,0), n is the pipe section mass of the outlier point; ug(i) is the compensation amount of the pipe section type of the pipe section to be constructed; Z is the compensation amount of the structural characteristics of the pipe section to be constructed.

[0057] In some embodiments of this application, after obtaining the final prediction model, the effectiveness of the final prediction model is verified to ensure that the final prediction model can effectively predict the carbon emissions of the pipe section. If the final prediction model is verified to be effective, it can be used to predict the carbon emissions of the pipe section to be constructed. If the final prediction model is verified to be invalid, the predicted value of the carbon emissions of the pipe section to be constructed calculated using the final prediction model will have a large error.

[0058] The validity of the final prediction model can be verified by using at least one of the following methods: residual, mean squared error, adjusted coefficient of determination, Durbin-Watson statistic, and mean absolute percentage error.

[0059] When using the adjusted coefficient of determination to verify the effectiveness of the final prediction model, if the adjusted coefficient of determination is greater than or equal to 0.80, the final prediction model is considered effective.

[0060] When using the Durbin-Watson statistic to verify the effectiveness of the final prediction model, if the Durbin-Watson statistic is between 1.5 and 2.5, the final prediction model is considered effective.

[0061] When using the mean absolute percentage error (MASE) to verify the effectiveness of the final prediction model, if the MASE does not exceed 10%, the final prediction model is considered effective.

[0062] In some embodiments, the effectiveness of the final prediction model can also be verified using a significance level. When verifying the effectiveness of the final prediction model using a significance level, if the overall significance of the final prediction model is less than 0.05, the final prediction model is deemed effective.

[0063] If the final prediction model is found to be invalid, it needs to be further revised. Outliers relative to the final prediction model are selected from the data points, and the compensation amount for the pipe section type is re-determined. Based on the pipe section quality, type, and steel ratio of the outliers, the final prediction model is revised to obtain a third prediction model. The effectiveness of this third prediction model is then verified until the revised prediction model is validated. It should be noted that the revision of the prediction model simply involves repeating the above steps, which will not be elaborated upon here.

[0064] The following section details the carbon emission prediction method based on the quality of immersed tunnel segments, using actual construction data from some large-scale cross-sea immersed tunnel projects in my country.

[0065] S1. Collect as-built data for 35 prefabricated tunnel segments. Data items include the mass of each segment and the total life-cycle carbon emissions accurately calculated using traditional life-cycle assessment methods. The segment mass includes the total mass of major building materials such as concrete, steel, and waterproofing materials. It should be noted that, for simplicity, Table 1 only shows a portion of the data; the complete dataset contains 35 samples.

[0066] Table 1. Pipe section mass and carbon emissions data (partial)

[0067] S2. Establish a Cartesian coordinate system with pipe section mass as the abscissa and carbon emissions as the ordinate to obtain several data points distributed in the Cartesian coordinate system; preprocess the data to remove obvious error points; finally, 30 data points are obtained.

[0068] S3. The first prediction model is obtained by fitting the preprocessed data points using the least squares method. The first prediction model is y=541.219x-8069273.974. S4. Calculate the predicted carbon emissions corresponding to the mass of each pipe section in the data point according to the first prediction model. Calculate the absolute value between the actual carbon emissions corresponding to the pipe section mass and the predicted carbon emissions. If the absolute value exceeds 2, the data point is judged as an anomaly; if the absolute value exceeds 3, the data point is judged as a high anomaly. Obtain the pipe section mass and pipe section type corresponding to the anomaly point, and determine the pipe section type compensation amount. Determine whether the number of anomalies exceeds 10% of the valid data points. If it exceeds, the first prediction model is invalid; if it does not exceed, the first prediction model is valid. In this embodiment, there is an anomaly point A. The pipe section mass corresponding to anomaly point A is 57417.17t, the carbon emissions are 22462080.07CO2eq, and the pipe section type is an interface segment. S5. Determine the structural feature compensation amount based on the proportion of steel in the pipe section corresponding to anomaly point A; S6. Based on the pipe section quality and pipe section type compensation amount corresponding to the anomaly point, the first prediction model is corrected to obtain the second prediction model y=535.28x+550.276(x-57417.17)-8069273.974. The second prediction model is then finally corrected to obtain the final prediction model y=535.28x+550.276(x-57417.17)-[8069273.974-ug(i)]+Z; where the pipe section type compensation amount for the transition section is -234,498.75CO2eq, and the pipe section type compensation amount for the interface section is 152,001.20CO2eq. Since the steel ratio involves a large number of values, the structural feature compensation amount is also large. In this embodiment, the specific values ​​of the structural feature compensation amount under different steel ratios will not be introduced.

[0069] S7. The effectiveness of the second prediction model was verified using the coefficient of determination method, the adjusted coefficient of determination method, the Durbin-Watson statistic method, and the significance level value method for variable relationships, respectively. The results showed that: Coefficient of determination: 0.899; Adjusted decision coefficient: 0.896; Dubin-Watson statistic: 1.714; The significance level (sig.) for the variable relationship is less than 0.001; The above data shows that the second prediction model has high reliability and engineering application value, and can be used to quickly and accurately predict the carbon emissions of new immersed tunnel segments.

[0070] S8. Based on the quality of the pipe section to be constructed, the predicted carbon emission value of the pipe section to be constructed is calculated by the second prediction model.

[0071] The aforementioned carbon emission prediction method based on the quality of immersed tunnel segments establishes a carbon emission prediction model by using historical data such as the quality and carbon emissions of segments from completed immersed tunnel projects. The prediction model is then corrected based on the quality and type of segments at outliers in the historical data. This allows for effective prediction of the carbon emissions of the segments to be constructed, thereby optimizing the segment construction process based on the carbon emission prediction results and ensuring green construction of immersed tunnels.

[0072] By establishing scientific and efficient predictive models, it is possible to conduct forward-looking assessments of potential carbon emissions during construction at the design stage, providing a basis for comparing and optimizing low-carbon construction schemes. This not only helps improve the level of green construction of immersed tunnels, but also has important practical significance for promoting the low-carbon transformation of transportation infrastructure and achieving coordinated development between engineering construction and environmental protection.

[0073] Finally, it should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0074] The above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them; although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications can still be made to the specific implementation of the present invention or equivalent substitutions can be made to some technical features without departing from the spirit of the technical solutions of the present invention, and all such modifications and substitutions should be covered within the scope of the technical solutions claimed in the present invention.

Claims

1. A method for predicting carbon emissions based on the mass of immersed tunnel sections, characterized in that, Includes the following steps: Obtain information on the carbon emissions, mass, and type of each tunnel segment during the construction process of a completed immersed tunnel project. A Cartesian coordinate system is established with the mass of the pipe section as the abscissa and the carbon emissions as the ordinate, and several data points distributed in the Cartesian coordinate system are obtained. The first prediction model is obtained by fitting the data points using the least squares method; Several data points are obtained as outliers relative to the first prediction model; Obtain the pipe section quality and pipe section type corresponding to the anomaly point, and determine the pipe section type compensation amount; The first prediction model is corrected based on the pipe section quality and pipe section type compensation amount corresponding to the anomaly point to obtain the second prediction model. The predicted carbon emissions of the pipe section to be constructed are calculated using the second prediction model based on the quality of the pipe section to be constructed.

2. The carbon emission prediction method based on the mass of immersed tunnel sections according to claim 1, characterized in that, The first prediction model is y=k1x+b; where y is the predicted value of carbon emissions; k1 and b are constants, and x is the mass of the pipe section.

3. The carbon emission prediction method based on the mass of immersed tunnel sections according to claim 1, characterized in that, The structural feature compensation amount is determined based on the proportion of steel in the pipe section; the first prediction model is further modified based on the structural feature compensation amount of the pipe section corresponding to the anomaly point to obtain the second prediction model.

4. The carbon emission prediction method based on the mass of the immersed tunnel section according to claim 3, characterized in that, The second prediction model is finally corrected based on the compensation amount of the pipe section type and the compensation amount of the structural characteristics of the pipe section to be constructed, so as to obtain the final prediction model; the final prediction model is y=k2x+k3m+[b+ug(i)]+Z, where k2, k3, and b are constants and k2≠k3, m is max(xn,0), n is the pipe section mass of the outlier point; ug(i) is the compensation amount of the pipe section type of the pipe section to be constructed; Z is the compensation amount of the structural characteristics of the pipe section to be constructed.

5. The carbon emission prediction method based on the mass of the immersed tunnel section according to claim 4, characterized in that, The pipe section type includes at least a standard section, a transition section, and an interface section; the compensation amount for the pipe section type is based on the carbon emissions of the standard section during the sinking stage. The calculation method for the pipe section type compensation is as follows: Select transition section, standard section and interface section from the completed immersed tunnel project. The difference between the actual carbon emissions of the transition section during the immersion stage and the actual carbon emissions of the standard section during the immersion stage is the pipe section type compensation for the transition section. The difference between the actual carbon emissions of the interface section during the immersion stage and the actual carbon emissions of the standard section during the immersion stage is the pipe section type compensation for the interface section.

6. The carbon emission prediction method based on the mass of immersed tunnel sections according to claim 4, characterized in that, The structural feature compensation amount is based on the proportion of the steel. The carbon emissions of the pipe sections during the prefabrication stage are used as a benchmark for compensation; The calculation method for the structural feature compensation is as follows: Select pipe sections with the same mass but different steel proportions from completed immersed tunnel projects, and use the steel proportion as... The actual carbon emissions of the pipe section during the prefabrication stage are used as the baseline carbon emissions; The difference between the actual carbon emissions of each pipe section during the prefabrication stage and the benchmark carbon emissions is the structural feature compensation amount corresponding to the proportion of each steel material.

7. The carbon emission prediction method based on the mass of immersed tunnel sections according to claim 4, characterized in that, After obtaining the final prediction model, the effectiveness of the final prediction model is verified; if the final prediction model is effective, the carbon emissions of the pipe section to be constructed are predicted using the final prediction model. If the final prediction model is invalid, then the final prediction model will continue to be modified. The effectiveness of the final prediction model is verified by using at least one of the following: residual, mean square error, adjusted coefficient of determination, Durbin-Watson statistic, and mean absolute percentage error.

8. The carbon emission prediction method based on the mass of immersed tunnel sections according to claim 1, characterized in that, The predicted carbon emissions corresponding to the pipe section mass in each data point are calculated based on the first prediction model. The absolute value between the actual carbon emissions and the predicted carbon emissions is calculated. If the absolute value exceeds the first preset threshold, the data point where the pipe section mass is located is a high anomaly point. If the ratio of the number of high anomalies to the total number of data points exceeds a second preset threshold, then the first prediction model is refitted.

9. The carbon emission prediction method based on the mass of immersed tunnel sections according to claim 8, characterized in that, When refitting the first prediction model, the weights of the outliers are calculated separately, and then the data points are refitted using an iterative reweighting method to obtain a new first prediction model. The new first prediction model is then corrected based on the pipe section quality and pipe section type compensation amount corresponding to the outliers to obtain a new second prediction model.

10. The carbon emission prediction method based on the mass of immersed tunnel sections according to claim 1, characterized in that, The pipe section comprises at least concrete, steel, and waterproofing material; the mass of the pipe section is at least the sum of the mass of the concrete, the mass of the steel, and the mass of the waterproofing material. And / or, the carbon emissions of the pipe section are at least the sum of the carbon emissions during the pipe section prefabrication stage, the pipe section transportation stage, and the pipe section placement stage.

Images