Logistics vehicle carbon emission optimization method, system and device based on multi-target cooperation and storage medium

Abstract

The invention relates to the technical field of carbon emission optimization, in particular to a logistics vehicle carbon emission optimization method, system and device based on multi-target cooperation and a storage medium. The invention discloses a logistics vehicle carbon emission optimization method based on multi-target cooperation, and the method reduces the load error through the real-time correction of multi-source data, and improves the time synchronization precision. Abnormal behaviors such as overload, high fuel consumption and false mileage are accurately identified by using an abnormal detection model; a multi-dimensional carbon effect feature model is constructed, the operation problem is effectively diagnosed, and the overload occurrence rate is reduced; an improved NSGA-II algorithm is adopted to solve the multi-objective optimization model, carbon emission per ton kilometer is reduced, and the daily average utilization rate of the vehicle is improved; a decision support mechanism is established, the scheme generation time is shortened, and the constraint violation rate is reduced. Therefore, a low-cost and quantifiable carbon efficiency improvement approach is provided for logistics enterprises in the aspects of environmental protection compliance and operation efficiency, and the enterprises are assisted to realize green and sustainable development.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission optimization, and particularly to a method, system, device and storage medium for optimizing the carbon emissions of logistics vehicles based on multi-objective collaboration. Background Art

[0002] In the context of the global active response to climate change, the logistics industry, as a major carbon emitter, its carbon efficiency management has become a key issue. Currently, logistics enterprises face many difficulties in carbon emission monitoring and management. On the one hand, the problem of data dispersion is prominent. Logistics operations involve multiple links such as transportation, warehousing, and distribution, and the data of each link is stored in different systems respectively, such as weighbridge weighing data, access control timestamp data, fuel consumption data, mileage data, etc. There is a lack of an effective integration mechanism, which makes it difficult for enterprises to obtain comprehensive and accurate data to support carbon emission accounting and analysis, resulting in poor accuracy of carbon accounting. On the other hand, the existing carbon accounting methods rely on manual collection and simple calculations, which are easily affected by data errors and human factors and cannot accurately reflect the true carbon emissions of logistics activities. These problems not only hinder the effective control of logistics enterprises over their own carbon emissions, but also limit their development in environmental protection compliance and are difficult to meet the increasingly strict environmental protection regulations.

[0003] The traditional decision-making mechanism can no longer meet the development needs of enterprises. In logistics operation decision-making, enterprises often only focus on single objectives such as transportation cost and efficiency, ignoring the collaborative relationship between carbon emissions and operation efficiency, resulting in a lack of comprehensiveness and scientificity in decision-making. For example, in the process of vehicle scheduling and task allocation, the impact of vehicle load and driving speed on carbon emissions and energy efficiency is not fully considered, resulting in frequent phenomena such as vehicle overloading and inefficient driving, which not only increase carbon emissions but also reduce the overall operation efficiency of enterprises. At the same time, due to the lack of an effective anomaly detection mechanism, logistics enterprises are difficult to detect and handle abnormal behaviors such as overloading and high fuel consumption, and false mileage in real time, further exacerbating resource waste and increasing carbon emissions. This obsolete decision-making mechanism makes it difficult for logistics enterprises to find a balance between environmental protection and economic development, and there is an urgent need for an innovative system and method to optimize decision-making and achieve multi-objective collaborative development of carbon emission reduction and operation efficiency improvement. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a method for optimizing the carbon emissions of logistics vehicles based on multi-objective collaboration, which is characterized by including the following steps: S1. Obtain the multi-source data set of logistics vehicles, the evaluation index set of logistics vehicles, and the task data set of logistics vehicles, and correct the multi-source data set of logistics vehicles through a Kalman filter model; S2. Based on the corrected multi-source dataset of logistics vehicles, construct a joint probability density model, perform anomaly detection on the corrected multi-source dataset of logistics vehicles, and obtain logistics vehicle anomaly data; S3. According to the logistics vehicle anomaly data, construct a multi-dimensional carbon efficiency feature model in combination with the logistics vehicle evaluation index set, and obtain a carbon efficiency feature matrix; S4. Based on the carbon efficiency feature matrix, construct a multi-objective carbon efficiency optimization model, and solve the multi-objective carbon efficiency optimization model through an improved NSGA-II algorithm to obtain a Pareto front solution set; S5. Based on the logistics vehicle task dataset, construct a dynamic weight scoring model to evaluate the Pareto front solution set, obtain an optimal Pareto solution set, and implement it as a logistics vehicle carbon emission optimization strategy.

[0005] Further, the multi-source dataset of logistics vehicles includes vehicle load data, vehicle access control system data, vehicle fuel consumption data, vehicle transportation mileage data, and vehicle basic operation data; The logistics vehicle evaluation index set has the same data types as the multi-source dataset of logistics vehicles and is used to evaluate the data in the multi-source dataset of logistics vehicles; The logistics vehicle task dataset includes task assignment data and business constraint data; The vehicle basic operation data includes vehicle type, vehicle maximum load, vehicle fuel type, and vehicle carbon emission coefficient; The business constraint data includes business priority, real-time road condition data, and vehicle maintenance data.

[0006] Further, the step S2 includes the following steps: S201. According to the corrected multi-source dataset of logistics vehicles, construct a multi-source data matrix of logistics vehicles, and construct a joint probability density function using the kernel density estimation algorithm; S202. Solve the joint probability density function through the local outlier factor algorithm, and calculate the local outlier factors of each data point in the multi-source data matrix of logistics vehicles; S203. According to the obtained local outlier factors, classify the data points as anomalies through the K-means clustering algorithm to obtain logistics vehicle anomaly data.

[0007] Further, the local outlier factor algorithm uses the Manhattan distance for spatial distance measurement.

[0008] Further, the step S3 includes the following steps: S301. According to the logistics vehicle anomaly data, construct a multi-dimensional carbon efficiency feature model based on the logistics vehicle evaluation index set; S302. According to the multi-dimensional carbon efficiency characteristic model, perform feature correlation analysis through the DBSCAN clustering algorithm to obtain a carbon efficiency feature matrix.

[0009] The present invention also provides a logistics vehicle carbon emission optimization system based on multi-objective collaboration. This system is implemented based on any one of the above-mentioned multi-objective collaborative logistics vehicle carbon emission optimization methods, and includes a multi-source data acquisition module, an anomaly detection module, a multi-dimensional carbon efficiency feature extraction module, a multi-objective dynamic optimization module, and a dynamic decision support module that are sequentially connected by signals; The multi-source data acquisition module is used to obtain a multi-source data set of logistics vehicles, an evaluation index set of logistics vehicles, and a task data set of logistics vehicles, and perform data correction on the multi-source data set of logistics vehicles through a Kalman filter model; The anomaly detection module is used to construct an anomaly detection model through a kernel density estimation algorithm and a local outlier factor algorithm according to the corrected multi-source data set of logistics vehicles, perform anomaly detection on the corrected multi-source data set of logistics vehicles, and obtain logistics vehicle anomaly data; The multi-dimensional carbon efficiency feature extraction module is used to construct a multi-dimensional carbon efficiency feature model according to the logistics vehicle anomaly data, combined with the evaluation index set of logistics vehicles, to obtain a structured carbon efficiency feature matrix; The multi-objective dynamic optimization module is used to construct a multi-objective carbon efficiency optimization model according to the structured carbon efficiency feature matrix, and solve the multi-objective carbon efficiency optimization model through an improved NSGA-II algorithm to obtain a Pareto front solution set; The dynamic decision support module is used to construct a dynamic weight scoring model according to the logistics vehicle task data set to evaluate the Pareto front solution set, obtain an optimal Pareto solution set, and implement it as a logistics vehicle carbon emission optimization strategy.

[0010] Furthermore, the system further includes a visualization module for real-time displaying the multi-source data set of logistics vehicles, the evaluation index set of logistics vehicles, and the task data set of logistics vehicles, and real-time presenting the carbon emission detection results and optimization solutions.

[0011] The present invention also provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor is characterized in that when the processor executes the computer program, it implements the above-mentioned multi-objective collaborative logistics vehicle carbon emission optimization method.

[0012] The present invention also provides a storage medium, on which a computer program is stored. The computer program is characterized in that when the computer program is executed by a processor, it implements the above-mentioned multi-objective collaborative logistics vehicle carbon emission optimization method.

[0013] The beneficial effects of the present invention are: Through real-time correction of multi-source data, the load error is reduced and the time synchronization accuracy is improved; an anomaly detection model is used to accurately identify abnormal behaviors such as overloading, high fuel consumption, and false mileage; a multi-dimensional carbon efficiency feature model is constructed to effectively diagnose operation problems and reduce the incidence of overloading; an improved NSGA-II algorithm is used to solve the multi-objective optimization model, reduce the carbon emissions per ton-kilometer, and improve the daily vehicle utilization rate; a decision support mechanism is built to shorten the solution generation time and reduce the constraint violation rate. Thus, a low-cost and quantifiable carbon efficiency improvement approach is provided for logistics enterprises in terms of environmental protection compliance and operation efficiency, helping enterprises achieve green and sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 Flowchart of a method for optimizing carbon emissions of logistics vehicles based on multi-objective collaboration according to the present invention.

[0015] Figure 2 Structure diagram of a system for optimizing carbon emissions of logistics vehicles based on multi-objective collaboration according to the present invention.

[0016] Figure 3 Carbon efficiency scatter plot of an embodiment of the present invention.

[0017] Figure 4 Distribution diagram of Pareto front solution sets of an embodiment of the present invention.

[0018] Figure 5 Structure diagram of a terminal device of a method for optimizing carbon emissions of logistics vehicles based on multi-objective collaboration proposed in an embodiment of the present invention.

[0019] Figure 6 Structure diagram of a computer-readable storage medium of a method for optimizing carbon emissions of logistics vehicles based on multi-objective collaboration proposed in an embodiment of the present invention.

[0020] In the figure, 200 - terminal device, 210 - memory, 211 - RAM, 212 - cache memory, 213 - ROM, 214 - programs / utilities, 215 - program modules, 220 - processor, 230 - bus, 240 - external device, 250 - I / O interface, 260 - network adapter, 300 - program product. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] For those skilled in the art to better understand the content of the present invention, making the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and the accompanying drawings.

[0022] The illustrative embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended as a further limitation to the present invention.

[0023] Example 1: As Figure 1 shown, an embodiment of the present invention provides a method for optimizing the carbon emissions of logistics vehicles based on multi-objective collaboration, which is characterized by including the following steps: S1. Obtain the multi-source data set of logistics vehicles, the evaluation index set of logistics vehicles, and the task data set of logistics vehicles, and correct the multi-source data set of logistics vehicles through a Kalman filter model; S2. Based on the corrected multi-source data set of logistics vehicles, construct a joint probability density model, perform anomaly detection on the corrected multi-source data set of logistics vehicles, and obtain logistics vehicle anomaly data; S3. According to the logistics vehicle anomaly data, construct a multi-dimensional carbon efficiency feature model in combination with the logistics vehicle evaluation index set to obtain a carbon efficiency feature matrix; S4. Based on the carbon efficiency feature matrix, construct a multi-objective carbon efficiency optimization model, and solve the multi-objective carbon efficiency optimization model through an improved NSGA-II algorithm to obtain a Pareto front solution set; S5. Based on the logistics vehicle task data set, construct a dynamic weight scoring model to evaluate the Pareto front solution set, obtain an optimal Pareto solution set, and implement it as a logistics vehicle carbon emission optimization strategy.

[0024] Furthermore, the multi-source data set of logistics vehicles includes vehicle load data, vehicle access control system data, vehicle fuel consumption data, vehicle transportation mileage data, and vehicle basic operation data; The logistics vehicle evaluation index set has the same data types as the multi-source data set of logistics vehicles and is used to evaluate the multi-source data set of logistics vehicles; The logistics vehicle task data set includes task assignment data and business constraint data; The vehicle basic operation data includes vehicle type, vehicle maximum load, vehicle fuel type, and vehicle carbon emission coefficient; The business constraint data includes business priority, real-time road condition data, and vehicle maintenance data.

[0025] Furthermore, step S1 includes the following sub-steps: S101. Construct a state vector, expressed as: where is the state vector at time k, is the true cargo weight at time k, is the weight change rate at time k; S102. Construct an observation equation, expressed as: where is the observed value at time k, and H is the observation matrix. is the observation noise, and the observation noise obeys a normal distribution with a mean of 0 and an observation noise variance of R. S103. Define the system dynamics equation, expressed as: where F is the state transition matrix, is the state vector at the previous time, and , and the time interval Δt = 0.2 s; , representing the system process noise, obeys a normal distribution with a mean of 0 and a process noise covariance matrix of Q. The process noise covariance matrix .

[0026] Specifically, the implementation principle flow of each sub-step in the above embodiment is as follows: First, build a data acquisition system, including weighbridge data acquisition: access the Kelai D2008 weighing system through the RS485 interface, set a high-frequency sampling frequency of 1 Hz, and obtain the original cargo weight data (unit: kg); access control data acquisition: read the vehicle entry and exit timestamps (format: YYYY-MM-DD HH:MM:SS.sss) of the Hikvision access control system through the API interface, with an accuracy of ±0.1 second. Then, build a Kalman filter model. State variables: Define , where is the state vector at time k, represents the true cargo weight at time k, represents the weight change rate at time k (kg / s), with a dynamic range of ±50 kg / s; Observation equation: , where is the observed value at time k; is the observation matrix, used to map the state vector to the observation space; represents the observation noise, and , that is, the observation noise obeys a normal distribution with a mean of 0 and an observation noise variance of R; Observation noise variance (FS = 10 tons), where FS represents the full mileage, used to represent the maximum value that the measuring instrument can measure within the measuring range; System dynamics model: , where: State transition matrix , where = 0.2 s, representing the time interval between two adjacent times. The state transition matrix is used to predict the state at the current time based on the state at the previous time; Process noise covariance matrix , which is used to quantify the influence degree of process noise on the system state; Next, perform filtering calculations, prediction step: , where is the state estimate at time k, is the state vector at the previous time, , where is the error covariance matrix at the previous time, represents the predicted error covariance matrix at the current time, is the transpose matrix of the state transition matrix; update step: , ; Then, perform parameter optimization, and determine the optimal parameters through sensitivity analysis: process noise covariance matrix (influence weight is 0.78); observation noise variance R = 22500 (influence weight is 0.22); Δt = 0.2 seconds; Finally, conduct effect verification, test objects: 30 trucks (10 trucks each of 8 tons / 15 tons / 30 tons), conduct continuous 7-day actual measurements; compare the following indicators respectively: Load error rate: before correction 15% - 20% → after correction ±0.8%; Time synchronization accuracy: before correction ±5 seconds → after correction ±1 second; The error calculation can be expressed as: , where WCZ is the error value, is the measured load, is the true load, time synchronization error: the absolute value of the difference between the access control timestamp and the weighbridge timestamp, and the verification data is shown in Table 1: Table 1 Error result table Furthermore, the step S2 includes the following steps: S201. According to the corrected multi-source data set of logistics vehicles, construct a multi-source data matrix of logistics vehicles, and use the kernel density estimation algorithm to construct a joint probability density function, and the joint probability density function is expressed as: where is the kernel density, which characterizes the multi-source data of logistics vehicles, W is the vehicle load, w is the vehicle load at the estimated joint probability density, L is the vehicle fuel consumption, l is the vehicle fuel consumption at the estimated joint probability density, S is the vehicle mileage, s is the vehicle mileage at the estimated joint probability density, h W is the bandwidth parameter corresponding to the vehicle load data dimension, h L is the bandwidth parameter corresponding to the vehicle fuel consumption data dimension, h Sis the bandwidth parameter corresponding to the vehicle mileage data dimension, K is the kernel function, n is the number of logistics vehicles, i represents the i-th sample data, and W i is the vehicle load of the i-th sample data, L i is the vehicle fuel consumption of the i-th sample data, S i is the vehicle mileage of the i-th sample data; S202. Solve the joint probability density function by using the local outlier factor algorithm to calculate the local outlier factor of each data point in the multi-source data matrix of logistics vehicles. The local outlier factor algorithm is expressed as: in, is the i-th sample data, for The local outlier factor value of for The number of neighboring points of for The jth neighbor of For distance Recent A set of data points, for The local reachable density of for The local reachable density of S203. According to the obtained local outlier factor, the data points are classified into abnormal categories through the K-means clustering algorithm to obtain the abnormal data of logistics vehicles.

[0027] Specifically, the implementation principle flow of each sub-step in the above embodiment is as follows: First, logistics vehicle data integration and preprocessing are carried out, including: 1) Vehicle load (W): obtained based on the filtered data from the scale, with a data error of ±0.8%; 2) Vehicle fuel consumption (L): The initial value is reported by the logistics vehicle driver, and the reported value is verified by the CRC algorithm. The fuel consumption data with incorrect data is eliminated and the unit is L / 100km; 3) Vehicle mileage (S): obtained based on the matching results of the access control system and the transportation documents, with a data error of ±3%; 4) Theoretical fuel consumption calculation: obtained through historical data regression, which can be expressed as: Where L ll is the theoretical fuel consumption, a and b are the obtained regression coefficients, and c is the regression error; Then, joint probability density modeling is performed through the Kernel Density Estimation theory KDE. Specifically, the KDE parameter settings are as follows: 1) Number of samples: Using 90 days of normal operation data, the number of trips n of logistics vehicles constitutes a data volume of 2,700; 2) Kernel function: The Gaussian kernel function is used, which can be expressed as: ; where K(u) is the Gaussian kernel function, e is the natural logarithm, and u is the standardized distance; 3) Bandwidth optimization: Obtained according to the Silverman rule = 50 kg, = 1.2 L / 100 km, = 8 km; 4) Construct the joint probability density function: where, is the kernel density, W is the vehicle load, w is the vehicle load at the estimated joint probability density, L is the vehicle fuel consumption, l is the vehicle fuel consumption at the estimated joint probability density, S is the vehicle mileage, s is the vehicle mileage at the estimated joint probability density, h W is the bandwidth parameter corresponding to the vehicle load data dimension, h L is the bandwidth parameter corresponding to the vehicle fuel consumption data dimension, h S is the bandwidth parameter corresponding to the vehicle mileage data dimension, K is the kernel function, n is the number of trips of logistics vehicles, i represents the i-th sample data, W i is the vehicle load of the i-th sample data, L i is the vehicle fuel consumption of the i-th sample data, S i is the vehicle mileage of the i-th sample data; Next, the Local Outlier Factor is calculated.

[0028] Parameter setting: Number of neighboring points = 15 nearest neighbors, and the Manhattan distance is used for distance measurement; Specifically, the calculation steps are as follows: Calculate distance: , is equal to the 15th smallest Euclidean distance, and the represents the distance from the sample data to its 15th nearest neighbor, which is used to measure the spatial distance between data points, is the Euclidean distance.

[0029] Calculate the reachable distance reach-distk, and its calculation formula is: For the reachable distance between and is the o - distance of which comprehensively considers the k - distance of the data point and the actual distance between

[0030] Calculate the local reachability density where is the local reachability density of which reflects the density situation around the sample data

[0031] Calculate the LOF value: , used to determine whether the data point is an outlier. If the LOF value is much greater than 1, it indicates that the density around this point is quite different from the density of its neighborhood points and it may be an abnormal point.

[0032] After that, perform anomaly determination and classification.

[0033] Anomaly level threshold: where YC is the anomaly level. Specifically: when LOF > 3.0, the anomaly level is severe anomaly; when 2.5 < LOF ≤ 3.0, the anomaly level is medium anomaly; when LOF ≤ 2.5, the anomaly level is normal.

[0034] According to the obtained anomaly level, identify the anomaly type. Specifically: the identification conditions for overloading and high fuel consumption are: W > 1.1Wmax, L > 25% of the theoretical value, where W is the vehicle load, Wmax is the maximum vehicle load, and L is the vehicle fuel consumption; the identification conditions for false mileage declaration are: S is contradictory to the access control time, and L / S is abnormally low, where S is the vehicle mileage and L / S is the ratio of vehicle fuel consumption to vehicle mileage; the identification conditions for inefficient routes are: W is normal and , where is the average value of fuel consumption per kilometer is the standard deviation of fuel consumption per kilometer; the identification conditions for abnormal idling fuel consumption are: S < 50km, but L > 30L / 100km. The identification results of abnormal behaviors are shown in Table 2: Table 2 Anomaly type identification table Theoretical fuel consumption calculation: Based on the regression of vehicle model parameters and historical data (e.g., for a 15-ton truck: , where represents the theoretical fuel consumption; Distribution of abnormal types: Severe abnormalities account for 18%, moderate abnormalities account for 24%, and normal cases account for 58%.

[0035] Step 3: Multi-dimensional carbon efficiency feature modeling and diagnosis First, integrate and preprocess the data. The specific data sources are as follows: Basic operation data, including vehicle type (8T / 15T / 30T), license plate number; Dynamic transportation data, including vehicle load W, vehicle fuel consumption L, vehicle mileage S, vehicle driving duration T; Environmental parameters, including fuel carbon emission coefficient P. In this embodiment, the fuel carbon emission coefficient corresponding to diesel is adopted, P = 2.68; Manually marked data, including historical abnormal records (such as overloading, route deviation).

[0036] Secondly, calculate the theoretical fuel consumption of the current logistics vehicle. The calculation formula is: Among them, is the theoretical fuel consumption of the vehicle, W is the vehicle load, and S is the vehicle mileage; Thirdly, calculate the carbon efficiency index of the current logistics vehicle to obtain the carbon efficiency scatter plot as shown in Figure 3 . Specifically, it includes the following data calculations: Carbon emission rate : Among them, is the carbon emission efficiency, P is the fuel carbon emission coefficient, L is the vehicle fuel consumption, and T is the vehicle driving duration; Energy efficiency index : Among them, is the energy efficiency index; Load balance: Among them is the load balance, which reflects the uniformity of load distribution in the transportation task, is the average vehicle load, is the standard deviation of the vehicle load W; Fuel consumption - load elasticity coefficient: Among them, is the fuel consumption-load elasticity coefficient, is the standard load; Timeliness deviation: Among them, is the timeliness deviation, is the standard transportation time; Based on the above calculated values, perform DBSCAN clustering analysis on the current logistics vehicle, specifically including the following steps: First, set the parameters. Specifically, it includes: standardize the neighborhood radius to obtain = 0.25 (after standardization), where is the neighborhood radius; the minimum number of samples minPts = 5; perform (Z-score standardization) on the input features: (Z-score standardization).

[0037] Then perform clustering analysis, including: data standardization: , where is the standardized input feature (including ), is the non-standardized input feature (including ), is the mean of the input feature, is the standard deviation of the input feature; density reachability judgment: core point → border point → noise point; According to the clustering analysis results, identify the abnormal patterns of the current logistics vehicle as: Overload and high consumption type: and , where is the mean of the input feature, is the standard deviation of the input feature, is the fuel consumption - load elasticity coefficient; Inefficient path type: and , where is the lower quartile of EEI, that is, the value at the 25% position, is the interquartile range of EEI (the difference between the upper and lower quartiles); Driving behavior type: and , where is the carbon emission rate fluctuation value; Obtain the abnormal type distribution as: overload and high consumption type accounts for 24%, inefficient path type accounts for 18%, and normal accounts for 58%; verification indicators: the model precision rate is 91%, and the overload incidence rate drops from 18.3% to 5.1%.

[0038] Step 4: MCMC simulation and contribution degree calculation 1. Data integration and parameter setting Input data: Vehicle attributes: The maximum load of 52 trucks (8T / 15T / 30T) , carbon emission coefficient , fuel consumption benchmark (L / 100km). i is the i-th sample data, corresponding to the vehicle number in Table 2 in Step 4 of this embodiment; Transportation tasks: 150 tasks per day, including cargo weight requirements , mileage , time window , where is the shortest vehicle transportation time, is the longest vehicle transportation time; j represents the j-th task; Abnormal marking: Vehicle classification (red / orange / yellow), corresponding marking weights for each classification are (red = 0.5, orange = 0.3, yellow = 0.1).

[0039] Key parameters: Load penalty coefficient ; Time window slack ; Marking weight .

[0040] , Mathematical model construction Decision variables: , whether vehicle i executes task c; , the average speed of vehicle i executing task c.

[0041] Objective function: The total carbon emissions are expressed as: where is the total carbon emissions target, is the vehicle fuel consumption of sample data i under the current target, is the vehicle load of sample data i under the current target, is the vehicle mileage of sample data i under the current target, is a 0-1 variable indicating whether sample data i executes task c under the current target; The comprehensive efficiency is expressed as: where, is the comprehensive efficiency, is the marking weight; The constraint conditions include; Load constraint: ; Time window: where is the transportation time of sample data i under the current target; Task coverage: ; Vehicle capacity: .

[0042] , Improved NSGA-II algorithm: Population initialization: The proportion of the initial solution of the marked vehicles is increased by 20%; Crossover operation: The retention rate of the task sequence of the red-marked vehicles is 80%; Mutation strategy: Non-uniform mutation of the speed variable (the step size decays with the number of iterations).

[0043] Optimization strategy: The number of iterations is 200, and the population size is 300; Non-dominated sorting and crowding degree calculation ensure the diversity of the solution set.

[0044] , Decision plan generation: Pareto front solution set: It contains 47 non-dominated solutions, the carbon emission range is 26,200 - 30,500 kg, and the comprehensive efficiency is 76.5 - 98.3 t·km / L·h; 5. Parameter sensitivity analysis: When, the carbon emission reduction of the red vehicles reaches 22.4%; When, the task completion rate is 97%, and the carbon emission increases by 2.1%.

[0045] , Optimization effect: The carbon emission reduction of the red-marked vehicles is the largest (16% - 24%), and the comprehensive efficiency is increased by 17% - 21%; Comparison indicators: The carbon emission per ton-kilometer is reduced from 0.148 kg to 0.122 kg, and the daily vehicle utilization rate is increased from 68% to 79%.

[0046] The verification data is shown in Table 3 Table 3 Schematic table of verification data Step 5: The Pareto front solution set generates data to integrate 300 non-dominated solutions output by the multi-objective optimization model, including: Total carbon emission target ; Comprehensive efficiency ; Constraint violation degree , where CV is the constraint violation degree, CZL is the overload, and TWPL is the time window deviation.

[0047] Some example data is shown in Table 4 Table 4 Pareto front solutions Pareto front generation Non-dominated sorting: (1)Define the dominance relationship: If and only if and , and at least one strict inequality holds, where X is any 01 matrix of , respectively represent Two arbitrary 01 matrices, , represent bringing two arbitrary 01 matrices into the total carbon emission objective function and the comprehensive efficiency function for comparison; (2) Divide the frontier levels: : Solutions not dominated by any solution; : Solutions only dominated by ; and so on.

[0048] Calculation of crowding degree: For each objective m, sort the solutions in ascending order; Set the crowding degree of boundary solutions to infinity; The crowding degree of intermediate solutions can be expressed as: where, is the crowding degree of intermediate solutions, m is the number of objectives. Here there are only two objectives, one is total carbon emission and the other is comprehensive efficiency, is the total carbon emission or comprehensive efficiency function, is the maximum value of the total carbon emission or comprehensive efficiency function, is the minimum value of the total carbon emission or comprehensive efficiency function; is the i-th sample data, is the (i + 1)-th sample data, is the (i - 1)-th sample data.

[0049] Analysis of solution set characteristics: Conduct characteristic analysis on Pareto frontier solutions to obtain the Pareto frontier solution set distribution as shown in Figure 4 ; Its specific parameter statistics are shown in Table 5: Table 5 Statistics of Pareto frontier solution set distribution Classification of typical solutions: Radical emission reduction type (sacrifice 12% efficiency for 19% carbon emission reduction): ( <26,500); Balanced type (14% carbon emission reduction + 11% efficiency increase): (27,000 < <28,000); High efficiency priority type (22% efficiency increase, only 5% carbon emission reduction): ( > 95).

[0050] Verification and optimization The convergence verification results are shown in Table 6: Table 6 Convergence acceptance results The optimization results of the marked vehicles are shown in Table 7: Table 7 Optimization Results of Marked Vehicles Distribution of solution types: 24% for radical emission reduction type, 48% for balanced type, and 28% for high-efficiency priority type; Constraint violation degree: when the population size is 300, 94% of the solutions have CV = 0.

[0051] Step 6: Implementation of the decision support mechanism 1. Data integration and parameter setting Core data Pareto solution set: 47 non-dominated solutions, including carbon emissions and comprehensive efficiency as well as vehicle-task allocation plans ; , an arbitrary 0-1 matrix indicating whether vehicle i executes task c; Business constraints: customer priority (VIP / ordinary), real-time traffic congestion index and vehicle maintenance plan.

[0052] Decision parameters include: Carbon emission weight and efficiency weight ; Urgency coefficient .

[0053] 2. Construction of decision rules Solution scoring model: where is the score of the g-th solution, is the constraint violation degree of the g-th solution. This model comprehensively considers carbon emissions, efficiency, and constraint violation situations, providing a quantitative basis for decision-making.

[0054] 3. Dynamic adjustment rules According to different business requirements, dynamic adjustment rules are formulated: When the urgency coefficient ( = 1.8), the rule applies to the time-sensitive mode: when the task time is urgent, prioritize ensuring transportation efficiency, and adjust the weight to ; When the urgency coefficient ( = 1.0), the rule applies to the emission reduction priority mode: when facing environmental protection pressure or the enterprise focuses on emission reduction, adjust the weight to and prioritize reducing carbon emissions; The special rules for marked vehicles are shown in Table 8: Table 8 Marked Vehicle Special Rules 4. Decision-making Process Initial Screening: Eliminate the solutions and vehicle plans during the maintenance period; 5. Scenario Matching According to different business scenarios, select the appropriate range of solutions, as shown in Table 9, where is the remaining time of the task: Table 9 Business Scenario Range 6. Final Decision Determine the final implementation plan by comprehensively considering the solution score and driver satisfaction: Among them, is the index of the optimal solution, is the set of all g that makes reach the maximum value, and MY is the driver satisfaction; 7. Effect Verification Decision-making efficiency: The single-solution generation time is reduced from 45 minutes to 2.3 minutes, and the number of constraint violations is reduced from 5.2 times per day to 0.7 times per day; The target achievement rate is shown in Table 10: Table 10 Target Achievement Rate The verification data is shown in Table 11: Table 11 Decision Implementation Verification Data Decision result: 97% of the solutions are generated within 2.3 minutes, and the constraint violation rate is only 3%; Driver satisfaction: Based on the historical task completion quality modeling, the value range is 0-1.

[0055] Example 2 As a preferred implementation manner of the above embodiment, as Figure 2 shown, a logistics vehicle carbon emission optimization system based on multi-objective collaboration is provided. This system is implemented based on any one of the above-mentioned logistics vehicle carbon emission optimization methods based on multi-objective collaboration, and includes a multi-source data acquisition module, an anomaly detection module, a multi-dimensional carbon efficiency feature extraction module, a multi-objective carbon efficiency optimization module, and a dynamic decision support module that are sequentially connected by signals; The multi-source data acquisition module is used to obtain the multi-source data set of logistics vehicles, the evaluation index set of logistics vehicles, and the task data set of logistics vehicles, and perform data correction on the multi-source data set of logistics vehicles through a Kalman filter model; The abnormal detection module is used to construct an abnormal detection model through the kernel density estimation algorithm and the local outlier factor algorithm based on the corrected multi-source data set of logistics vehicles, perform abnormal detection on the corrected multi-source data set of logistics vehicles, and obtain abnormal data of logistics vehicles; The multi-dimensional carbon efficiency feature extraction module is used to construct a multi-dimensional carbon efficiency feature model according to the abnormal data of logistics vehicles and in combination with the evaluation index set of logistics vehicles, and obtain a structured carbon efficiency feature matrix; The multi-objective carbon efficiency optimization module is used to construct a multi-objective carbon efficiency optimization model according to the structured carbon efficiency feature matrix, and solve the multi-objective carbon efficiency optimization model through the improved NSGA-II algorithm to obtain a Pareto front solution set; The dynamic decision-making support module is used to construct a dynamic weight scoring model to evaluate the Pareto front solution set according to the logistics vehicle task data set, obtain an optimal Pareto solution set, and implement it as a carbon emission optimization strategy for logistics vehicles.

[0056] Furthermore, the system further includes a visualization module for real-time displaying the multi-source data set of logistics vehicles, the evaluation index set of logistics vehicles, and the logistics vehicle task data set, and real-time presenting the carbon emission detection results and optimization solutions.

[0057] Embodiment 3 Such as Figure 5 , on the basis of Embodiment 1, this embodiment proposes a terminal device for optimizing the carbon emissions of logistics vehicles based on multi-objective collaboration. The terminal device 200 includes at least one memory 210, at least one processor 220, and a bus 230 connecting different platform systems.

[0058] The memory 210 may include a readable medium in the form of volatile memory, such as RAM 211 and / or cache memory 212, and may further include ROM 213.

[0059] Among them, the memory 210 also stores a computer program, and the computer program can be executed by the processor 220, so that the processor 220 executes any one of the above-mentioned methods for optimizing the carbon emissions of logistics vehicles based on multi-objective collaboration in the embodiments of the present application. Its specific implementation manner is the same as the implementation manner and the achieved technical effects recorded in the embodiments of the above method, and some contents will not be elaborated. The memory 210 may further include a program / utilities 214 having a set (at least one) of program modules 215. Such program modules include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0060] Correspondingly, the processor 220 can execute the above computer program and can execute the program / utilities 214.

[0061] The bus 230 can represent one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local area bus using any of the multiple bus structures.

[0062] The terminal device 200 can also communicate with one or more external devices 240 such as a keyboard, a pointing device, a Bluetooth device, etc., and can also communicate with one or more devices capable of interacting with the terminal device 200, and / or communicate with any device (such as a router, a modem, etc.) that enables the terminal device 200 to communicate with one or more other computing devices. Such communication can be performed through the I / O interface 250. Moreover, the terminal device 200 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 260. The network adapter 260 can communicate with other modules of the terminal device 200 through the bus 230. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the terminal device 200, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0063] Embodiment 4 As Figure 6 , on the basis of Embodiment 1, this embodiment proposes a computer-readable storage medium for an optimization method of carbon emissions of logistics vehicles based on multi-objective collaboration. Instructions are stored on the computer-readable storage medium, and when the instructions are executed by a processor, the above-mentioned optimization method of carbon emissions of logistics vehicles based on multi-objective collaboration is implemented. Its specific implementation manner is the same as the implementation manner and the achieved technical effects recorded in the embodiments of the above method, and some contents will not be elaborated.

[0064] Figure 3Fig. 0 shows a program product 300 provided by this embodiment for implementing the above method. It can be a portable compact disc read-only memory (CD-ROM) and includes program code, and can run on a terminal device, such as a personal computer. However, the program product 300 of the present invention is not limited to this. In this embodiment, the readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or component. The program product 300 can adopt any combination of one or more readable media. The readable media can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0065] The computer-readable storage medium can include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium can also be any readable medium other than the readable storage medium, and this readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, device, or component. The program code contained on the readable storage medium can be transmitted with any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the above. The program code for performing the operations of the present invention can be written in any combination of one or more programming languages. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, executed as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, by using an Internet service provider to connect through the Internet).

[0066] The foregoing has shown and described the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and what is described in the above embodiments and the specification is only to illustrate the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

[0067] The present invention is described from the viewpoints of purpose of use, efficacy, progressiveness and novelty. It has practical progressiveness and meets the functional enhancement and use requirements emphasized by the patent law. The above description and drawings of this application are only the preferred embodiments of this application, and do not limit this application thereby. Therefore, all those that are similar or identical to the structure, device, features, etc. of this application, that is, all equivalent replacements or modifications made according to the scope of the patent application of this application, shall fall within the scope of protection of the patent application of this application.

[0068] The specific embodiments described above have further elaborated on the purpose, technical solution and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A logistics vehicle carbon emission optimization method based on multi-objective collaboration, characterized in that It includes the following steps: S1. Obtain the multi-source data set of logistics vehicles, the evaluation index set of logistics vehicles, and the task data set of logistics vehicles, and perform data correction on the multi-source data set of logistics vehicles through a Kalman filter model; S2. Based on the corrected multi-source data set of logistics vehicles, construct an anomaly detection model through the kernel density estimation algorithm and the local outlier factor algorithm, perform anomaly detection on the corrected multi-source data set of logistics vehicles, and obtain the abnormal data of logistics vehicles; S3. According to the abnormal data of logistics vehicles, construct a multi-dimensional carbon efficiency feature model in combination with the evaluation index set of logistics vehicles to obtain a carbon efficiency feature matrix; S4. Based on the carbon efficiency feature matrix, construct a multi-objective carbon efficiency optimization model, and solve the multi-objective carbon efficiency optimization model through an improved NSGA-II algorithm to obtain a Pareto front solution set; S5. Based on the task data set of logistics vehicles, construct a dynamic weight scoring model to evaluate the Pareto front solution set, obtain an optimal Pareto solution set, and implement it as a carbon emission optimization strategy for logistics vehicles.

2. The method for optimizing carbon emissions of logistics vehicles based on multi-objective collaboration according to claim 1, characterized in that the multi-source data set of logistics vehicles includes vehicle load data, vehicle access control system data, vehicle fuel consumption data, vehicle transportation mileage data, and vehicle basic operation data; the evaluation index set of logistics vehicles has the same data types as the multi-source data set of logistics vehicles and is used to evaluate the multi-source data set of logistics vehicles; the task data set of logistics vehicles includes task assignment data and business constraint data; the vehicle basic operation data includes vehicle type, vehicle maximum load, vehicle fuel type, and vehicle carbon emission coefficient; the business constraint data includes business priority, real-time road condition data, and vehicle maintenance data.

3. A method for optimizing carbon emissions of logistics vehicles based on multi-objective collaboration according to claim 1, characterized in that, The step S2 includes the following steps: S201. According to the corrected multi-source data set of logistics vehicles, construct a multi-source data matrix of logistics vehicles, and construct a joint probability density function by using the kernel density estimation algorithm; S202. Solve the joint probability density function through the local outlier factor algorithm, and calculate the local outlier factor of each data point in the multi-source data matrix of logistics vehicles; S203. According to the obtained local outlier factor, perform anomaly classification on the data points through the K-means clustering algorithm to obtain the abnormal data of logistics vehicles.

4. A method for optimizing carbon emissions of logistics vehicles based on multi-objective collaboration according to claim 3, characterized in that, The local outlier factor algorithm uses the Manhattan distance for spatial distance measurement.

5. A method for optimizing carbon emissions of logistics vehicles based on multi-objective collaboration according to claim 1, characterized in that, The step S3 includes the following steps: S301. According to the abnormal data of logistics vehicles, construct a multi-dimensional carbon efficiency feature model based on the evaluation index set of logistics vehicles; S302. According to the multi-dimensional carbon efficiency feature model, perform feature correlation analysis through the DBSCAN clustering algorithm to obtain a carbon efficiency feature matrix.

6. A logistics vehicle carbon emission optimization system based on multi-objective collaboration, which is implemented based on the method for optimizing the carbon emissions of a logistics vehicle based on multi-objective collaboration described in any one of claims 1-5, characterized in that, It includes a multi-source data acquisition module, an anomaly detection module, a multi-dimensional carbon efficiency feature extraction module, a multi-objective dynamic optimization module, and a dynamic decision support module that are sequentially signal-connected; The multi-source data acquisition module is used to obtain the multi-source data set of logistics vehicles, the evaluation index set of logistics vehicles, and the task data set of logistics vehicles, and correct the multi-source data set of logistics vehicles through a Kalman filter model; The anomaly detection module is used to construct an anomaly detection model through a kernel density estimation algorithm and a local outlier factor algorithm based on the corrected multi-source data set of logistics vehicles, perform anomaly detection on the corrected multi-source data set of logistics vehicles, and obtain logistics vehicle anomaly data; The multi-dimensional carbon efficiency feature extraction module is used to construct a multi-dimensional carbon efficiency feature model based on the logistics vehicle anomaly data and in combination with the evaluation index set of logistics vehicles, and obtain a structured carbon efficiency feature matrix; The multi-objective dynamic optimization module is used to construct a multi-objective carbon efficiency optimization model based on the structured carbon efficiency feature matrix, and solve the multi-objective carbon efficiency optimization model through an improved NSGA-II algorithm to obtain a Pareto front solution set; The dynamic decision support module is used to construct a dynamic weight scoring model based on the logistics vehicle task data set to evaluate the Pareto front solution set, obtain an optimal Pareto solution set, and implement it as a logistics vehicle carbon emission optimization strategy.

7. The carbon emission optimization system for logistics vehicles based on multi-objective collaboration according to claim 6, characterized in that, The system further includes a visualization module, which is signal-connected to the dynamic decision support module to display the multi-source data set of logistics vehicles, the evaluation index set of logistics vehicles, and the task data set of logistics vehicles in real time, and display the carbon emission detection results and optimization solutions in real time.

8. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for optimizing the carbon emission of logistics vehicles based on multi-objective collaboration according to any one of claims 1 to 5.

9. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for optimizing the carbon emission of logistics vehicles based on multi-objective collaboration according to any one of claims 1 to 5.

Images