Unmanned driving-based sustainable electrified traffic optimization method and system

Abstract

The invention relates to a sustainable electrified traffic optimization method and system based on unmanned driving, and the method comprises the steps: obtaining an SDG target related to sustainable electrified traffic in a traffic scheme, obtaining a correlation score of an index factor related to unmanned driving, and constructing a correlation score interval; a weighted scoring interval is obtained according to the correlation scoring interval and the scoring confidence coefficient weight, a judgment matrix is constructed and solved to obtain an initial weight vector interval of an index factor related to unmanned driving, and a final weight vector is obtained according to the initial weight vector interval; obtaining a weighted correlation score according to the final weight vector and the weighted scoring interval, and then carrying out grade division to obtain a correlation evaluation result; and optimizing the current sustainable electrified traffic scheme through a multi-objective optimization model according to a correlation evaluation result. Compared with the prior art, the method has the advantages that the accuracy of sustainable evaluation of the sustainable electrified traffic is improved, and decision support is provided for the sustainable electrified traffic.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of electrified transportation, in particular to a sustainable electrified transportation optimization method and system based on unmanned driving. BACKGROUND

[0002] In recent years, the number of new energy passenger cars has grown rapidly, greatly promoting the electrification of the transportation sector. However, this rapid development has brought many challenges, such as a shortage of parking space resources, low utilization rate of charging piles, and insufficient convenience for users to charge, among other issues. This is not only a key obstacle to the development of global sustainable electrified transportation (SET), but also brings an innovative opportunity for the deep integration of autonomous driving and electrified transportation.

[0003] The current IEC / SyC SET has identified unmanned driving and sustainable electrified transportation as important technical directions for the future "smart + new energy" transportation collaborative development and "vehicle-energy-road-cloud" industry deep integration. The core is to realize the automatic driving of transportation tools through intelligent technology and combine it with sustainable electrified transportation to improve the efficiency, safety, and environmental friendliness of the transportation system.

[0004] In the field of electrification and unmanned driving, governments and enterprises urgently need to identify a development path that is highly compatible with sustainability. Some existing research attempts to combine autonomous driving technology with automatic charging technology in the field of electrified transportation to improve the utilization rate of charging facilities and the charging experience of users. For example, patent application CN118024923A discloses an electric vehicle automatic charging system and method. The method realizes the automatic docking of the charging interface through the cooperation of the navigation sensor and the positioning pin, and provides automatic charging services for electric vehicles. This method can only complete the automatic docking and gun insertion of the charging interface, and only focuses on the technical implementation level, lacking a systematic design from the perspective of sustainable development strategy. However, the United Nations Sustainable Development Goals (SDGs) include 17 goals and 169 targets, with a wide range of content and complex levels, making it difficult for decision-makers and researchers to determine which goals are most relevant to emerging transportation technologies. Resources are easily scattered and focused. The existing technology lacks systematic correlation analysis, quantitative evaluation, and key target identification between unmanned driving and electrified transportation systems in urban planning and sustainable development goals (SDG), and has not established a system model that can effectively map and comprehensively evaluate the United Nations Sustainable Development Goals and the development goals of unmanned driving and sustainable electrified transportation. SUMMARY

[0005] The purpose of the present application is to overcome the deficiencies of the existing technology and provide a sustainable electrified transportation optimization method and system based on unmanned driving, which improves the accuracy of sustainable assessment of sustainable electrified transportation and provides scientific and operational decision support for sustainable electrified transportation.

[0006] The object of the present application can be achieved by the following technical solutions: A sustainable electrification traffic optimization method based on unmanned driving, comprising the following steps: Obtain the SDG targets related to sustainable electrification traffic in the current sustainable electrification traffic scheme, and obtain the correlation score of the index factor related to unmanned driving in the SDG target, and build a correlation score interval; According to the correlation score interval and the score confidence weight, the weighted score interval of each SDG target is calculated; According to the weighted score interval, a judgment matrix is constructed, and the initial weight vector interval of the index factor related to unmanned driving is obtained by solving the judgment matrix; The initial weight vector interval of the index factor related to unmanned driving is fused through Hadamard product, and the final weight vector of each SDG target is obtained after normalization; According to the final weight vector of the SDG target and the weighted score interval, the weighted correlation score of each SDG target is calculated, and the weighted correlation score of each SDG target is graded to obtain the correlation evaluation result; According to the correlation evaluation result, the current sustainable electrification traffic scheme is optimized through a multi-objective optimization model.

[0007] Further, the SDG targets related to sustainable electrification traffic include multiple of SDG3, SDG7, SDG9, SDG11, SDG12 and SDG13, and the index factors related to unmanned driving include multiple of safety index, energy efficiency, carbon emission intensity, urban traffic efficiency, technology maturity and scientific research achievement output.

[0008] Further, the correlation score interval is constructed by using 1-9 scale method according to the correlation score of the index factor related to unmanned driving in the SDG target, and the correlation score interval is: In the formula, is the correlation score interval of the i-th index factor related to unmanned driving in the j-th SDG target, is the lower bound of the correlation score of the i-th index factor related to unmanned driving in the j-th SDG target, is the upper bound of the correlation score of the i-th index factor related to unmanned driving in the j-th SDG target. ​​​​​​

[0009] Further, the weighted score interval of the SDG target is: wherein, is the weighted score interval of the i-th SDG target, is the lower bound of the weighted score of the i-th SDG target, is the upper bound of the weighted score of the i-th SDG target, is the lower bound of the weighted score of the i-th SDG target, is the upper bound of the weighted score of the i-th SDG target, is the lower bound of the weighted score of the i-th SDG target, is the upper bound of the weighted score of the i-th SDG target, is the confidence weight of the j-th index factor related to unmanned driving in the i-th SDG target, is the confidence weight of the j-th index factor related to unmanned driving in the i-th SDG target.

[0010] Further, the interval characteristic vector method is used to solve the judgment matrix to obtain the initial weight vector interval of the index factor related to unmanned driving, and the initial weight vector interval is: wherein, is the initial weight vector interval of the j-th index factor related to unmanned driving in the i-th SDG target, is the lower bound of the initial weight vector interval of the j-th index factor related to unmanned driving in the i-th SDG target, is the upper bound of the initial weight vector interval of the j-th index factor related to unmanned driving in the i-th SDG target, is the upper bound of the maximum eigenvalue interval, is the lower bound of the maximum eigenvalue interval, is the lower bound of the importance ratio interval of the i-th SDG target relative to the j-th SDG target in the judgment matrix, is the lower bound of the reference weight vector interval of the j-th index factor related to unmanned driving, is the upper bound of the importance ratio interval of the i-th SDG target relative to the j-th SDG target in the judgment matrix, is the upper bound of the reference weight vector interval of the j-th index factor related to unmanned driving. j ​​​​​​​​​​​​

[0011] Furthermore, the final weight vector of the SDG objectives is: In the formula, For the first The final weight vector of each SDG objective. For the first The upper bound of the final weight vector of each SDG objective. For the first The lower bound of the final weight vector of each SDG objective.

[0012] Furthermore, the weighted relevance score of the SDG objectives is: In the formula, For the first Weighted relevance scores of each SDG objective. For the first The upper bound of the weighted score for each SDG objective. It is a non-linear adjustment parameter. For the first The lower bound of the weighted score for each SDG objective.

[0013] Furthermore, fuzzy C-means clustering is used to classify the weighted relevance scores of SDG objectives into relevance levels, including high relevance, medium relevance, and low relevance.

[0014] Furthermore, the objective function of the multi-objective optimization model is: In the formula, The objective function of the multi-objective optimization model is... For the decision variable vector, For the first The priority weight of the first SDG objective, and the priority weight of the second SDG objective. The relevance levels of the SDG objectives are matched. For the first The upper bound of the final weight vector of each SDG objective. For the first The lower bound of the final weight vector for each SDG objective. For the first The upper bound of the weighted score for each SDG objective. It is a non-linear adjustment parameter. For the first The lower bound of the weighted score for each SDG objective. the implementation degree function of the mth SDG target under the decision variable vector the upper bound of the implementation degree function of the mth SDG target under the decision variable vector the lower bound of the implementation degree function of the mth SDG target under the decision variable vector the number of index factors contained in the mth SDG target the contribution weight of the mth index factor in the mth SDG target the implementation degree of the mth index factor in the mth SDG target under the decision variable vector a set of sustainable electrified transportation schemes.

[0015] According to another aspect of the present application, a sustainable electrified transportation optimization system based on unmanned driving is provided, characterized in that it comprises: a correlation score interval construction module, configured to obtain SDG targets related to sustainable electrified transportation in a current sustainable electrified transportation scheme, and obtain correlation scores of index factors related to unmanned driving in the SDG targets, and construct a correlation score interval; a weighted score interval calculation module, configured to calculate a weighted score interval of each SDG target according to the correlation score interval and a score confidence weight; an initial weight interval vector acquisition module, configured to construct a judgment matrix according to the weighted score interval, and solve the judgment matrix to obtain an initial weight vector interval of index factors related to unmanned driving; a final weight vector acquisition module, configured to fuse the initial weight vector interval of the index factors related to unmanned driving through Hadamard product, and obtain a final weight vector of each SDG target after normalization; a correlation evaluation module, configured to calculate a weighted correlation score of each SDG target according to the final weight vector of the SDG target and the weighted score interval, and grade the weighted correlation score of each SDG target to obtain a correlation evaluation result; a scheme optimization module, configured to optimize the current sustainable electrified transportation scheme through a multi-objective optimization model according to the correlation evaluation result.

[0016] ​​​​​​​​​​​​Compared with the prior art, the present application has the following beneficial effects: 1. The present application scores the SDG targets related to sustainable electrified transportation in the sustainable electrified transportation scheme by interval scoring, uses fuzzy C-means clustering method to fuse and evaluate the SDG targets, combines interval scoring and fuzzy C-means clustering to construct a complete evaluation framework of "SDG target-index factor-relevance analysis", and provides a quantifiable and comparable evaluation system, thereby providing scientific and operable decision support for sustainable electrified transportation.

[0017] 2. The present application obtains the SDG targets related to sustainable electrified transportation in the current sustainable electrified transportation scheme, obtains the relevance score of the index factors related to unmanned driving in the SDG targets, and constructs a relevance score interval, thereby establishing a multi-dimensional and multi-level mapping mechanism between the SDG targets and the index factors related to unmanned driving, and improving the accuracy of the sustainability evaluation of sustainable electrified transportation. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A flowchart of a sustainable electrified transportation optimization method based on unmanned driving according to the present application is shown in the figure. Figure 2 A flowchart of a sustainable electrified transportation optimization method based on unmanned driving according to the present application is shown in the figure. DETAILED DESCRIPTION

[0019] The present application will be described in detail below in combination with the drawings and specific embodiments. The present embodiment is implemented on the basis of the technical scheme of the present application, and detailed implementation and specific operation processes are given, but the protection scope of the present application is not limited to the following embodiments.

[0020] English abbreviations involved: Sustainable Development Goal: SDG Fuzzy C-means Clustering: FCM Interval Analytic Hierarchy Process: IAHP Vehicle-to-Grid: V2G Nondominated Sorting Genetic Algorithm II: NSGA-II Embodiment 1 The present embodiment provides a sustainable electrified transportation optimization method based on unmanned driving, as shown inFigure 1 As shown, the method comprises the following steps: S1, obtaining the SDG targets related to sustainable electrified transportation in the current sustainable electrified transportation scheme, and obtaining the correlation scores of the index factors related to unmanned driving in the SDG targets, and constructing the correlation score interval.

[0021] Sustainable electrified transportation scheme refers to a transportation scheme designed in four dimensions of clean energy driving, electric vehicles, intelligent infrastructure, and low-carbon efficient operation.

[0022] The SDG targets related to sustainable electrified transportation include multiple targets in SDG3, SDG7, SDG9, SDG11, SDG12 and SDG13, and their specific associations are as follows: 1) SDG3: Good health and well-being Electric transportation helps improve air quality by reducing the use of fuel vehicles and reducing exhaust emissions, reducing respiratory system diseases and cardiovascular diseases caused by air pollution, thereby improving the overall health level of urban residents.

[0023] 2) SDG7: Affordable and clean energy The core of electric transportation is to use electric power to drive vehicles, and its sustainability depends on clean and renewable energy supply. This goal emphasizes the popularization of clean energy and promotes the transformation of energy structure to provide green power support for electric transportation.

[0024] 3) SDG9: Industry, innovation and infrastructure The development of electric transportation requires the construction of charging infrastructure, smart grid and new transportation systems, which is highly consistent with the "building of disaster-resistant infrastructure and promoting inclusive and sustainable industrialization" in SDG9.

[0025] 4) SDG11: Sustainable cities and communities Electric transportation is an important means to achieve sustainable urban transportation system, which can reduce traffic congestion, reduce noise and pollution, improve urban life quality, and support the goal of "providing safe, affordable and sustainable transportation systems to all".

[0026] 5) SDG12: Responsible consumption and production Electric transportation promotes the transformation of the transportation industry from traditional fossil energy to clean energy, reduces dependence on non-renewable resources, and promotes the popularization of green consumption and clean production methods, in line with the concept of sustainable consumption and production.

[0027] 6) SDG13: Climate action Transportation is one of the important sources of global greenhouse gas emissions. Electrified transportation directly supports the goal of SDG 13, "Taking urgent action to combat climate change and its impacts", by reducing carbon emissions, and is a key link to achieve carbon neutralization.

[0028] The index factors related to unmanned driving include safety, energy efficiency, carbon intensity, urban transportation efficiency, technology maturity, and research output.

[0029] Based on the SDG goals and corresponding subdivision specific SDG goals, the correlation analysis of unmanned driving and electric transportation is carried out. Considering that the subjective evaluation of experts often has uncertainty and fuzziness, it is difficult to fully reflect the true judgment by using a single numerical value, therefore, interval scoring form is adopted. According to the correlation score of the index factors related to unmanned driving in the SDG goals, the correlation score interval is constructed, and the correlation score interval is: In the formula, represents the number of evaluated SDG goals, represents that there are index factors related to unmanned driving in the SDG goals, is the th SDG goal, is the th index factor related to unmanned driving in the th SDG goal, is the lower bound of the correlation score interval of the th index factor related to unmanned driving in the th SDG goal, is the upper bound of the correlation score interval of the th index factor related to unmanned driving in the

[0030] th SDG goal.

[0031] The correlation score interval adopts 1-9 scale method, and the scale table is shown in Table 1. S2, according to the correlation score interval and the score confidence weight, the weighted score interval of each SDG goal is calculated.

[0032] The construction of score confidence weight is based on the following four dimensions: data support degree , field consensus degree , technology visibility and time verifiability . The data support degree is used to measure whether there is sufficient statistical data, research report or empirical support, the field consensus degree To ensure consistency in the correlation assessments of multiple experts regarding this indicator, technical visibility is crucial. This is used to measure whether the impact of autonomous driving technology on this indicator is intuitive, observable, and verifiable over time. Whether the current time conditions are suitable for verifying this impact.

[0033] For each indicator factor in the SDG objectives, calculate its score confidence weight, whereby the score confidence is: In the formula, For the first The first of the SDG objectives The confidence weights of the scores for each indicator factor related to autonomous driving. For the first Weight coefficients for each dimension This is the dimension for constructing the confidence weights of the ratings.

[0034] The weighted scoring range for SDG objectives is: In the formula, For the first The weighted scoring range for each SDG objective. For the first The lower bound of the weighted score for each SDG objective. For the first The upper bound of the weighted score for each SDG objective. For the first The first of the SDG objectives The confidence weights of the scores for each indicator factor related to autonomous driving.

[0035] S3. Construct a judgment matrix based on the weighted scoring interval, and solve the judgment matrix to obtain the initial weight vector interval of the indicator factors related to autonomous driving.

[0036] The Interval Hierarchical Analysis (IAHP) method is used to construct the structure. Judgment matrix : In the formula, To determine the first element in the matrix The SDG target is relative to the first The importance ratio range of each SDG target The judgment matrix is ​​solved using the interval eigenvector method to obtain the initial weight vector interval of the index factors related to autonomous driving. The initial weight vector interval is as follows: In the formula, For the first The first of the SDG goals The initial weight vector range of several indicators related to autonomous driving. For the first The first of the SDG goals The lower bound of the initial weight vector interval for each indicator factor related to autonomous driving. For the first The first of the SDG goals The upper bound of the initial weight vector interval for each indicator factor related to autonomous driving. This is the upper bound of the interval containing the largest eigenvalue. This is the lower bound of the interval containing the largest eigenvalue. To determine the first element in the matrix The SDG target is relative to the first j The lower bound of the importance ratio interval for each SDG objective. For the first The lower bound of the baseline weight vector interval for a number of indicators related to autonomous driving. To determine the first element in the matrix The SDG target is relative to the first The upper bound of the importance ratio interval for each SDG objective. For the first The upper bound of the baseline weight vector interval of a number of indicators related to autonomous driving.

[0037] S4. The initial weight vector intervals of the indicators related to autonomous driving are fused by the Adama product and normalized to obtain the final weight vector of each SDG target.

[0038] To effectively integrate the initial weight vector intervals of indicators related to autonomous driving and avoid the sensitivity of traditional arithmetic averages to extreme values, a geometric mean operator is used to integrate the weight vector intervals based on the Hadamard product concept. This reflects the synergistic effect and nonlinear compensation characteristics among the indicators. This process not only preserves the integrity of the weight vector intervals but also weakens the impact of individual data anomalies with large deviations, improving the robustness of weight allocation.

[0039] The final weight vector of the SDG objectives is: In the formula, For the first The final weight vector of each SDG objective. For the first The upper bound of the final weight vector of each SDG objective. For the first The lower bound of the final weight vector of each SDG objective.

[0040] S5. Calculate the weighted relevance score of each SDG objective based on the final weight vector and weighted scoring interval of the SDG objectives, and classify the weighted relevance score of each SDG objective into levels to obtain the relevance assessment results.

[0041] To capture both the best-case and worst-case scenarios simultaneously, and to allow policymakers to adjust the emphasis on the "upper limit" or "lower limit" based on their risk appetite, the weighted relevance score for SDG objectives is as follows: In the formula, For the first Weighted relevance scores of each SDG objective. For the first The upper bound of the weighted score for each SDG objective. For the first The lower bound of the weighted score for each SDG objective. This is a non-linear adjustment parameter with an adjustment range of 0-1. Its value reflects the contribution of the upper and lower bounds of the interval to the score. If... 5 indicates an optimistic bias, emphasizing the potential for integrated development; Taking a conservative approach, considering risks and uncertainties; if It is assumed that the contribution levels of the upper and lower bounds are equal.

[0042] Summary m The weighted scores of each objective constitute a vector set. Fuzzy C-means clustering was used to classify the relevance levels of the weighted relevance scores of the aggregated SDG objectives. The optimization objective is: In the formula, To optimize the objective, The number of clusters is the number of groups. For the first The first objective is for the... Membership degree of a category For fuzzy parameters, For the first The cluster centers of a class represent the typical relevance level of that class. In practical implementation, let... The correlation levels are divided into three categories: high correlation, medium correlation, and low correlation. The empirical value is 2.

[0043] The membership degree constraint is: In the formula, For the first The first objective is for the... Membership degree of a category.

[0044] The classification of relevance levels is shown in Table 2: Table 2. Correlation Level Classification S6. Based on the correlation assessment results, optimize the current sustainable electrification transportation scheme using a multi-objective optimization model.

[0045] The objective function of the multi-objective optimization model is: In the formula, The objective function of the multi-objective optimization model is... For the decision variable vector, For the first The priority weight of the first SDG objective, and the priority weight of the second SDG objective. The relevance levels of the SDG objectives are matched. For the first The upper bound of the final weight vector of each SDG objective. For the first The lower bound of the final weight vector for each SDG objective. For the first The upper bound of the weighted score for each SDG objective. It is a non-linear adjustment parameter. For the first The lower bound of the weighted score for each SDG objective. For the first SDG objectives in the decision variable vector The degree of implementation function below, For the first SDG objectives in the decision variable vector The upper bound of the degree of realization function, No. SDG objectives in the decision variable vector The lower bound of the implementation degree function, For the first The number of indicator factors included in each SDG objective. For the first The first of the SDG objectives The contribution weight of each indicator factor, For the first The first of the SDG objectives Each indicator factor in the decision variable vector The degree of implementation below, A collection of sustainable electrified transportation solutions.

[0046] The constraints of the multi-objective optimization model are: In the formula, For the first One constraint condition. For the first The upper limit of each constraint condition. Constraint conditions include multiple factors such as budget constraints, infrastructure capacity, technical security thresholds, and energy supply.

[0047] Sustainable electrified transportation solutions refer to transportation schemes designed from four dimensions: clean energy drive, electrified vehicles, intelligent infrastructure, and low-carbon, efficient operation. This four-dimensional transportation solution is mapped to a vector of decision variables. The clean energy-driven dimension includes the proportion of clean electricity and the proportion of V2G adjustable capacity; the electrified transportation dimension includes the penetration rate of driverless electric vehicles and the specific energy level of batteries; the intelligent infrastructure dimension includes the density of charging piles and the coverage of intelligent connected roads; and the low-carbon and efficient operation dimension includes the activation rate of ecological driving algorithms and the average passenger load factor.

[0048] Decision variable vector It can be represented as: In the formula, For the decision variable vector, The percentage of electricity used for cleaning. V2G adjustable capacity ratio, To increase the penetration rate of driverless electric vehicles, This refers to the battery's specific energy level. For charging pile density, To increase the coverage of intelligent connected roads, To increase the activation rate of eco-driving algorithms, This represents the average passenger load factor.

[0049] The indicators related to autonomous driving include multiple factors such as safety, energy efficiency, carbon emission intensity, urban traffic efficiency, technology maturity, and research output. A decision variable vector will be obtained through four-dimensional transportation scheme mapping. By bridging to the indicators and factors related to autonomous driving, we can obtain... Safety indicators in the decision variable vector The degree of implementation is as follows: In the formula, For safety indicators in the decision variable vector The degree of implementation below, A vector of decision variables The accident rate of driverless electric vehicles. The baseline accident rate.

[0050] Energy efficiency in the decision variable vector The degree of implementation is as follows: In the formula, For energy efficiency in the decision variable vector The degree of implementation below, A vector of decision variables The actual energy efficiency of driverless electric vehicles under the current conditions. For the theoretical maximum energy utilization efficiency, This serves as the benchmark energy efficiency for driverless electric vehicles.

[0051] Carbon emission intensity in the decision variable vector The degree of implementation is as follows: In the formula, Carbon emission intensity in the decision variable vector The degree of implementation below, For decision variable vectors Carbon emissions per unit of traffic volume. This is the baseline carbon emission level.

[0052] Urban traffic efficiency in the decision variable vector The degree of implementation is as follows: In the formula, For urban traffic efficiency in the decision variable vector The degree of implementation below, For decision variable vectors Average vehicle speed in urban traffic The maximum expected speed under ideal urban traffic conditions. This serves as the benchmark speed for urban traffic.

[0053] Technology maturity in the decision variable vector The degree of implementation is as follows: In the formula, For technology maturity in the decision variable vector The degree of implementation below, For decision variable vectors The actual number of driverless electric vehicles deployed. The target number of self-driving electric vehicles to be deployed. This refers to the total number of driverless electric vehicles.

[0054] Scientific research output in the decision variable vector The degree of implementation is as follows: In the formula, For the output of scientific research results in the decision variable vector The degree of implementation below, For decision variable vectors The number of related scientific research achievements. To the expected number of scientific research results, To ensure that the coverage of intelligent connected roads is 0 and the battery specific energy remains at a baseline value of 250Wh / kg. -1 The number of research achievements related to autonomous electrified transportation that can be naturally generated when the proportion of clean electricity is 0 and no new technological investment is considered. The expected incremental increase in scientific research output for every 1 percentage point increase in the coverage of intelligent connected roads. For every 1Wh / kg increase in average battery specific energy -1 The expected incremental increase in additional scientific research results The expected increase in scientific research output for every 1 percentage point increase in the proportion of clean electricity.

[0055] The process of optimizing decision parameters for autonomous driving-based sustainable electrification transportation solutions is as follows: Figure 2 As shown, it includes the following steps: Collect decision data on current sustainable electrification solutions in real time and perform normalization processing; Projecting onto any dimension that violates the constraints, we perform feasibility repair using the following formula: In the formula, This is the decision variable vector after feasibility repair. The normalized decision variable vector, The projection step size, For the first The constraints are in the decision variable vector. The gradient vector.

[0056] For the objective function The gradient of the differentiable part is calculated, and the candidate control strategy is further confirmed by white-box gradient boosting. The candidate control strategy is as follows: In the formula, For candidate control strategies, For the increment of decision variables, The step size coefficient is obtained through Armijo line search. This is the gradient vector of the decision variable vector after feasibility repair.

[0057] Candidate control strategies They are sent to subsequent NSGA-II populations as initial elite individuals for iterative updates to obtain the optimal control strategy.

[0058] Based on the correlation assessment results, the current sustainable electrification transportation scheme is optimized through the optimal control strategy to support the sustainable planning of urban transportation.

[0059] Example 2 This embodiment provides a sustainable electrified transportation optimization system based on autonomous driving, including: The correlation scoring interval construction module is used to obtain the SDG targets related to sustainable electrification transportation in the current sustainable electrification transportation scheme, and to obtain the correlation scores of the indicator factors related to autonomous driving in the SDG targets, and construct the correlation scoring interval. The weighted scoring interval calculation module is used to calculate the weighted scoring interval for each SDG objective based on the relevance scoring interval and the scoring confidence weight. The initial weight interval vector acquisition module is used to construct a judgment matrix based on the weighted scoring interval, and solve the judgment matrix to obtain the initial weight vector interval of the indicator factors related to autonomous driving. The final weight vector acquisition module is used to fuse the initial weight vector intervals of the indicators related to autonomous driving through the Adama product, and then normalize them to obtain the final weight vector of each SDG target. The relevance assessment module is used to calculate the weighted relevance score of each SDG objective based on the final weight vector and weighted score interval of the SDG objectives, and to classify the weighted relevance score of each SDG objective into levels to obtain the relevance assessment results. The scheme optimization module is used to optimize the current sustainable electrification transportation schemes based on the relevance assessment results using a multi-objective optimization model.

[0060] The rest is the same as in Example 1.

[0061] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A sustainable electrified transportation optimization method based on autonomous driving, characterized in that, Includes the following steps: Obtain the SDG targets related to sustainable electrification transportation in the current sustainable electrification transportation scheme, and obtain the correlation scores of the indicator factors related to autonomous driving in the SDG targets, and construct the correlation score range; The weighted score interval for each SDG objective is calculated based on the relevance score interval and the score confidence weight. Construct a judgment matrix based on the weighted scoring interval, and solve the judgment matrix to obtain the initial weight vector interval of the indicator factors related to autonomous driving; The initial weight vector intervals of the indicators related to autonomous driving are fused by the Adama product and normalized to obtain the final weight vector of each of the SDG targets. The weighted relevance score of each SDG objective is calculated based on the final weight vector and weighted scoring interval of the SDG objectives. The weighted relevance score of each SDG objective is then classified into levels to obtain the relevance assessment result. Based on the correlation assessment results, the current sustainable electrification transportation scheme is optimized using a multi-objective optimization model.

2. The method for optimizing sustainable electrified transportation based on autonomous driving according to claim 1, characterized in that, The SDG objectives related to sustainable electrified transportation include multiple targets from SDG3, SDG7, SDG9, SDG11, SDG12, and SDG13. The indicators related to autonomous driving include multiple targets from safety indicators, energy efficiency, carbon emission intensity, urban traffic efficiency, technology maturity, and scientific research output.

3. The method for optimizing sustainable electrified transportation based on autonomous driving according to claim 1, characterized in that, Based on the correlation scores of the indicators related to autonomous driving in the SDG objectives, a correlation score interval is constructed using the 1-9 scaling method. The correlation score interval is as follows: In the formula, For the first The first of the SDG objectives The correlation score range of the indicators and factors related to autonomous driving. For the first The first of the SDG objectives Lower bound of correlation scores for several indicators related to autonomous driving. For the first The first of the SDG objectives Upper bound of the correlation score of the indicators and factors related to autonomous driving.

4. The method for optimizing sustainable electrified transportation based on autonomous driving according to claim 3, characterized in that, The weighted scoring range for the SDG objectives is: In the formula, For the first The weighted scoring range for each SDG objective. For the first The lower bound of the weighted score for each SDG objective. For the first The upper bound of the weighted score for each SDG objective. For the first The first of the SDG objectives The confidence weights of the scores for each indicator factor related to autonomous driving.

5. The method for optimizing sustainable electrified transportation based on autonomous driving according to claim 1, characterized in that, The judgment matrix is ​​solved using the interval eigenvector method to obtain the initial weight vector interval of the index factors related to autonomous driving. The initial weight vector interval is as follows: In the formula, For the first The first of the SDG goals The initial weight vector range of several indicators related to autonomous driving. For the first The first of the SDG goals The lower bound of the initial weight vector interval for each indicator factor related to autonomous driving. For the first The first of the SDG goals The upper bound of the initial weight vector interval for each indicator factor related to autonomous driving. This is the upper bound of the interval containing the largest eigenvalue. This is the lower bound of the interval containing the largest eigenvalue. To determine the first element in the matrix The SDG target is relative to the first j The lower bound of the importance ratio interval for each SDG objective. For the first The lower bound of the baseline weight vector interval for a number of indicators related to autonomous driving. To determine the first element in the matrix The SDG target is relative to the first The upper bound of the importance ratio interval for each SDG objective. For the first The upper bound of the baseline weight vector interval of a number of indicators related to autonomous driving.

6. The method for optimizing sustainable electrified transportation based on autonomous driving according to claim 5, characterized in that, The final weight vector of the SDG objectives is: In the formula, For the first The final weight vector of each SDG objective. For the first The upper bound of the final weight vector of each SDG objective. For the first The lower bound of the final weight vector of each SDG objective.

7. The method for optimizing sustainable electrified transportation based on autonomous driving according to claim 1, characterized in that, The weighted relevance score of the SDG objectives is as follows: In the formula, For the first Weighted relevance scores of each SDG objective. For the first The upper bound of the weighted score for each SDG objective. It is a non-linear adjustment parameter. For the first The lower bound of the weighted score for each SDG objective.

8. The method for optimizing sustainable electrified transportation based on autonomous driving according to claim 1, characterized in that, The fuzzy C-means clustering method is used to classify the weighted relevance scores of SDG objectives into relevance levels, which include high relevance, medium relevance and low relevance.

9. The method for optimizing sustainable electrified transportation based on autonomous driving according to claim 8, characterized in that, The objective function of the multi-objective optimization model is: In the formula, The objective function of the multi-objective optimization model is... For the decision variable vector, For the first The priority weight of the first SDG objective, and the priority weight of the second SDG objective. The relevance levels of the SDG objectives are matched. For the first The upper bound of the final weight vector of each SDG objective. For the first The lower bound of the final weight vector for each SDG objective. For the first The upper bound of the weighted score for each SDG objective. It is a non-linear adjustment parameter. For the first The lower bound of the weighted score for each SDG objective. For the first SDG objectives in the decision variable vector The degree of implementation function below, For the first SDG objectives in the decision variable vector The upper bound of the degree of realization function, No. SDG objectives in the decision variable vector The lower bound of the implementation degree function, For the first The number of indicator factors included in each SDG objective. For the first The first of the SDG objectives The contribution weight of each indicator factor, For the first The first of the SDG objectives Each indicator factor in the decision variable vector The degree of implementation below, A collection of sustainable electrified transportation solutions.

10. A sustainable electrified transportation optimization system based on autonomous driving, characterized in that, include: The correlation scoring interval construction module is used to obtain the SDG targets related to sustainable electrification transportation in the current sustainable electrification transportation scheme, and to obtain the correlation scores of the indicator factors related to autonomous driving in the SDG targets, and construct the correlation scoring interval. The weighted scoring interval calculation module is used to calculate the weighted scoring interval for each SDG objective based on the relevance scoring interval and the scoring confidence weight. The initial weight interval vector acquisition module is used to construct a judgment matrix based on the weighted scoring interval, and solve the judgment matrix to obtain the initial weight vector interval of the indicator factors related to autonomous driving. The final weight vector acquisition module is used to fuse the initial weight vector intervals of the autonomous driving-related index factors through the Adama product, and then normalize them to obtain the final weight vector of each of the SDG targets. The relevance assessment module is used to calculate the weighted relevance score of each SDG target based on the final weight vector and weighted scoring interval of the SDG targets, and to classify the weighted relevance score of each SDG target into levels to obtain the relevance assessment result. The scheme optimization module is used to optimize the current sustainable electrification transportation scheme based on the correlation assessment results using a multi-objective optimization model.

Images