A full life cycle carbon neutral system and method for intelligent networked electric vehicles

Abstract

The application relates to the technical field of carbon neutralization, and discloses a full-life-cycle carbon neutralization system and method of an intelligent networked electric vehicle. The system comprises: a full-life-cycle carbon emission system, which is used for calculating carbon emissions of the vehicle in five stages of a full life cycle, i.e. material supply, part and whole vehicle manufacturing, charging use, scrap recycling and intelligent networked cloud service; an ecosystem engineering BECNU negative carbon emission system, which is used for providing a globally recognized carbon removal certification carbon sink credit C RCF ; an intelligent network system, which is used for carbon emission offset neutralization within the system boundary; and a vehicle-mounted carbon neutralization intelligent instrument, which is used for digital intelligent network record, measurement and accounting, authentication and carbon label neutralization identification of carbon footprint emission and removal information.

Description

Technical Field

[0001] This application relates to the field of carbon neutrality technology, and in particular to a carbon neutrality system and method for the entire life cycle of an intelligent connected electric vehicle. Background Technology

[0002] Traditional carbon emission calculation methods often focus only on the usage phase, neglecting the carbon footprint of production, recycling, and other stages, resulting in an incomplete carbon neutrality effect. Furthermore, existing carbon neutrality schemes are mostly static management, making it difficult to adapt to the dynamic changes during the use of electric vehicles, and they lack effective incentive mechanisms for vehicle owners.

[0003] Furthermore, with the development of intelligent connected technologies, electric vehicles are no longer simply a means of transportation, but have become mobile energy nodes and data centers. However, how to organically combine these new technologies with carbon neutrality goals and fully leverage the potential of electric vehicles in smart grids and carbon trading markets remains a pressing issue. Existing carbon neutrality systems often treat electric vehicles as isolated entities, failing to fully consider their role and value within the entire ecosystem. Summary of the Invention

[0004] This application provides a carbon neutrality system and method for the entire life cycle of intelligent connected electric vehicles, which is used to realize the monitoring and analysis of carbon neutrality throughout the entire life cycle of intelligent connected electric vehicles.

[0005] In a first aspect, this application provides an intelligent connected electric carbon neutrality system based on the BECNU negative carbon emission ecosystem engineering, characterized in that it includes:

[0006] The full lifecycle carbon emission system is used to calculate the carbon emissions of a vehicle throughout its five lifecycle stages: material supply, parts and vehicle manufacturing, charging and use, end-of-life recycling, and intelligent connected cloud services.

[0007] Ecosystem engineering BECNU negative carbon emission system, used to provide globally recognized carbon removal certification carbon sink credits C RCF ;

[0008] Intelligent connected systems are used to offset carbon emissions within the system boundaries;

[0009] The vehicle-mounted carbon neutrality smart device is used for digital intelligent network recording, metering, accounting, certification, and carbon label neutralization identification of carbon footprint emission and removal information;

[0010] The technical model for calculating carbon footprint quantity satisfies the following formula:

[0011] C t +C MA +C VM +C USE +CREC +C RCF =0, C t For the carbon footprint of cloud network digital centers, C MA For the carbon footprint of material acquisition and supply, C VM For the carbon footprint of the manufacturing process of parts and complete vehicles, C USE For the carbon footprint of charging, energy storage and discharging, C REC For the carbon footprint of the end-of-life recycling process, C RCF It is an internationally recognized carbon removal certification carbon sink credit.

[0012] Secondly, this application provides a method for achieving carbon neutrality throughout the entire lifecycle of an intelligent connected electric vehicle, the method comprising:

[0013] Distributed collection and preprocessing of multi-source data from raw material production, vehicle manufacturing, usage, and end-of-life recycling yields a full lifecycle carbon emission dataset.

[0014] Multi-level, multi-scale modeling and fusion analysis were performed on the full life cycle carbon emission dataset to obtain a dynamic carbon emission prediction model;

[0015] By performing spatiotemporal data mining and multi-objective optimization calculations using the aforementioned dynamic carbon emission prediction model, a smart charging and vehicle-grid interaction strategy scheme is obtained.

[0016] Multi-sensor data fusion and degradation analysis are performed on the aforementioned intelligent charging and vehicle-grid interaction strategy and vehicle status data to obtain predictive maintenance and lifespan optimization schemes.

[0017] A multi-dimensional carbon footprint assessment and dynamic trade-off calculation are performed on the aforementioned predictive maintenance and lifespan optimization scheme to obtain a full life-cycle carbon footprint optimization strategy;

[0018] The carbon footprint optimization strategy for the entire life cycle is used for multi-scenario prediction and adaptive path planning to obtain the carbon neutrality path for intelligent connected electric vehicles.

[0019] The technical solution provided in this application achieves accurate calculation of carbon emissions throughout the entire lifecycle of an electric vehicle, from material acquisition to end-of-life recycling, by analyzing each stage. In particular, the real-time monitoring and calculation functions of the onboard carbon neutrality smart device ensure the accuracy and timeliness of carbon emission data during the usage phase. A dual-track C... RCF The system manages carbon emissions dynamically, targeting both the production and usage phases. This design makes the carbon neutrality process more flexible and precise, adapting to different usage scenarios and variations in grid carbon intensity. Through deep integration with the smart grid, the system enables V2G services and intelligent charging scheduling, not only improving energy efficiency but also creating additional carbon reduction benefits for vehicle owners. RCFAs an embedded carbon asset in vehicles, and providing a carbon asset investment platform, it enables car owners to participate in carbon market trading, achieving a win-win situation for both economic and environmental benefits. By incentivizing car owners to participate in carbon neutrality actions, it enhances the activity and sustainability of the entire ecosystem. Utilizing blockchain technology to store and verify key carbon footprint data, combined with the CNAS certification system, ensures the transparency and credibility of the carbon neutrality process, providing a reliable basis for carbon trading and policy-making. Beyond focusing on individual vehicle carbon neutrality, it also connects electric vehicles with broader ecosystem engineering through the BECNU negative carbon emission project, achieving a wider range of carbon neutrality effects. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of one embodiment of the carbon neutrality system for the entire life cycle of an intelligent connected electric vehicle in this application.

[0022] Figure 2 This is a schematic diagram of one embodiment of the carbon neutrality method for the entire life cycle of intelligent connected electric vehicles in this application. Detailed Implementation

[0023] This application provides a carbon neutrality system and method for the entire lifecycle of an intelligent connected electric vehicle. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0024] For ease of understanding, the specific process of the embodiments of this application is described below. Please refer to [link / reference]. Figure 1 One embodiment of the intelligent connected electric carbon neutrality system based on the BECNU negative carbon emission ecosystem engineering in this application includes:

[0025] The full lifecycle carbon emission system is used to calculate the carbon emissions of a vehicle throughout its five lifecycle stages: material supply, parts and vehicle manufacturing, charging and use, end-of-life recycling, and intelligent connected cloud services.

[0026] Ecosystem engineering BECNU negative carbon emission system, used to provide globally recognized carbon removal certification carbon sink credits C RCF ;

[0027] Intelligent connected systems are used to offset carbon emissions within the system boundaries;

[0028] The vehicle-mounted carbon neutrality smart device is used for digital intelligent network recording, metering, accounting, certification, and carbon label neutralization identification of carbon footprint emission and removal information;

[0029] The technical model for calculating carbon footprint quantity satisfies the following formula:

[0030] C t +C MA +C VM +C USE +C REC +C RCF =0, C t For the carbon footprint of cloud network digital centers, C MA For the carbon footprint of material acquisition and supply, C VM For the carbon footprint of the manufacturing process of parts and complete vehicles, C USE For the carbon footprint of charging, energy storage and discharging, C REC For the carbon footprint of the end-of-life recycling process, C RCF It is an internationally recognized carbon removal certification carbon sink credit.

[0031] Specifically, the intelligent connected electric carbon neutrality system in this embodiment includes the following main components: A full life-cycle carbon emission system: This system uses the carbon emission factor method to establish a carbon emission calculation model covering four stages: material acquisition, vehicle production, use, and recycling. In the material acquisition stage, the system considers the carbon emissions from metallic materials such as steel, aluminum, and copper, as well as non-metallic materials such as plastics and rubber. The vehicle production stage covers energy consumption in processes such as stamping, welding, painting, and final assembly. The use stage mainly calculates carbon emissions caused by electricity consumption and maintenance. The recycling stage considers carbon emissions and carbon reduction from processes such as metal recycling and power battery recycling. An ecosystem engineering BECNU negative carbon emission system: This system provides internationally recognized carbon removal certification carbon sink credits (C... RCFThese carbon credits come from various ecosystem engineering projects, including afforestation and reforestation, biochar, soil carbon sequestration, and direct air carbon capture. The system ensures the authenticity, measurability, and verifiability of these carbon credits. Intelligent Connected System: This system collects vehicle usage data in real time through vehicle-to-everything (V2X) technology, including mileage and energy consumption. Simultaneously, it connects to the power grid system to obtain real-time electricity carbon emission factors. The system also connects to a carbon trading platform to achieve a dynamic balance between carbon emissions and carbon sinks. Onboard Carbon Neutralization Smart Device: This is an intelligent terminal device installed in the vehicle. It monitors the vehicle's energy consumption data in real time through a sensor network and, combined with information provided by the intelligent connected system, calculates the vehicle's real-time carbon footprint. It also records carbon emission data throughout the vehicle's entire lifecycle, generating digital carbon labels. Through the collaborative work of these systems, accurate calculation and dynamic balance of the electric vehicle's carbon footprint throughout its entire lifecycle are achieved. When a vehicle generates carbon emissions during use, the system automatically calls upon corresponding carbon credits from the BECNU negative carbon emission system to offset them, ensuring that the carbon footprint calculation model always meets the C... t +C MA +C VM +C USE +C REC +C RCF The equilibrium equation is 0.

[0032] Optionally, the whole life cycle carbon emission system includes:

[0033] The material supply carbon emission subsystem is used to calculate the first unavoidable carbon emissions and its first carbon footprint during the material supply stage. The material supply carbon emission subsystem uses low-carbon emission, ultra-low-carbon emission and carbon-neutral metallic and non-metallic materials, as well as recycled and renewable materials, and performs measurement, verification and certification of the first carbon footprint of the materials in accordance with international or domestic standards to obtain the data corresponding to the first carbon footprint and its first carbon label.

[0034] The carbon emission subsystem for component and vehicle manufacturing is used to calculate the second unavoidable carbon emissions and its second carbon footprint during the manufacturing stage. The carbon emission subsystem for component and vehicle manufacturing adopts low-carbon emission, ultra-low-carbon emission and carbon-neutral energy, low-carbon and intelligent manufacturing processes, and performs measurement, verification and certification of the second carbon footprint of the manufacturing process in accordance with international or domestic standards to obtain the data corresponding to the second carbon footprint and its second carbon label.

[0035] The charging carbon emission subsystem is used to calculate the third unavoidable carbon emissions and its third carbon footprint during the charging and usage phases. The charging carbon emission subsystem uses low-carbon emission, ultra-low-carbon emission, and carbon-neutral energy electricity for charging, including wind power and photovoltaic solar power, and utilizes new energy batteries to participate in smart grid and microgrid energy storage. The subsystem measures, verifies, and certifies the third carbon footprint of the charging and usage process according to international or domestic standards, and obtains the data corresponding to the third carbon footprint and its third carbon label.

[0036] The end-of-life recycling carbon emission subsystem is used to calculate the fourth unavoidable carbon emissions and its fourth carbon footprint during the end-of-life recycling stage. The end-of-life recycling carbon emission subsystem adopts low-carbon emission, ultra-low-carbon emission and carbon-neutral energy and electricity, low-carbon emission, ultra-low-carbon emission and carbon-neutral logistics measures, and performs measurement, accounting, verification and certification of the fourth carbon footprint of the entire end-of-life recycling process in accordance with international standards or domestic standards, so as to obtain the data corresponding to the fourth carbon footprint and its fourth carbon label.

[0037] The vehicle-mounted industrial internet and vehicle-road-cloud-energy intelligent microgrid and digital center carbon emission subsystem are used to calculate the relevant fifth unavoidable carbon emissions and their fifth carbon footprint.

[0038] Specifically, the full life-cycle carbon emission system consists of five subsystems, each responsible for calculating carbon emissions and carbon footprint at a specific stage. The materials supply carbon emission subsystem employs advanced low-carbon material technologies. For example, using low-carbon aluminum produced via electrolysis reduces the carbon emission factor of aluminum from 16.4 kg (CO2) / kg to 2.5 kg (CO2) / kg. Simultaneously, using high-strength steel reduces vehicle weight, thereby reducing steel usage and its carbon emissions. This subsystem also prioritizes recycled materials, such as recycled plastics, significantly reducing the carbon footprint of plastic materials. The system uses bill of materials management to accurately track the usage and source of each material and calculates the first carbon footprint according to international standards. The parts and vehicle manufacturing carbon emission subsystem focuses on optimizing production processes. For example, using water-based paint instead of traditional solvent-based coatings in the painting workshop and using heat pump technology to recover waste heat can reduce carbon emissions from the painting process by 30%. The welding workshop uses laser welding technology to improve energy efficiency. The final assembly workshop extensively uses intelligent logistics systems and robots to reduce energy waste. The entire manufacturing process prioritizes the use of renewable energy to further reduce the carbon footprint. The charging carbon emission subsystem achieves low-carbon operation through intelligent charging management. The system connects to the smart grid, prioritizing charging during periods of high renewable energy generation. Simultaneously, it utilizes onboard batteries to participate in grid peak shaving, providing V2G services and generating carbon reduction benefits. The system also dynamically calculates the carbon footprint of the charging process based on the grid's real-time carbon emission factor. The end-of-life recycling carbon emission subsystem employs advanced recycling technologies. For vehicle body metals, intelligent sorting technology improves recycling purity and reduces remelting energy consumption. Power batteries utilize fully automated dismantling lines and water-cooled crushing technology, significantly improving recycling efficiency and material recovery rates. The system also optimizes the logistics network, using new energy logistics vehicles to reduce carbon emissions during the recycling process. The vehicle-to-industry internet of things (V2I) and vehicle-road-cloud-energy smart microgrid and digital center carbon emission subsystem reduce data transmission volume and data center energy consumption through edge computing technology. Simultaneously, it employs efficient cooling technology and AI optimization algorithms to improve the data center's PUE value and reduce operational carbon emissions. Each subsystem transmits carbon footprint data to the vehicle-mounted carbon neutrality smart device in real time through a unified data interface, enabling accurate calculation and dynamic management of carbon emissions throughout the entire life cycle.

[0039] Optionally, the vehicle-mounted industrial internet and vehicle-road-cloud-energy smart microgrid and digital center carbon emission subsystem includes the unavoidable carbon emissions from the vehicle-mounted industrial internet, the unavoidable carbon emissions from charging and using the smart microgrid, and the carbon footprint environmental benefit emission reduction from battery participation in energy storage and discharge. It also performs measurement, verification, and certification of the fifth carbon footprint of the industrial internet, smart microgrid, and digital center according to international or domestic standards to obtain the data corresponding to the fifth carbon footprint and its fifth carbon label. The on-board carbon neutrality smart instrument connects to the vehicle system and the smart microgrid cloud for communication and data transmission. Utilizing the vehicle-road-cloud-energy smart connected cloud system and the CNAS digital intelligent cloud supervision, inspection, testing, certification, and accreditation system, it achieves intelligent, digital, and transparent carbon footprint labeling. The factory certificate of the on-board carbon neutrality smart instrument and the initial data table of the instrument's carbon neutrality label clearly indicate C. t C MA C VM C USE C REC The carbon footprint value, and the C-value purchased and built into the vehicle by the vehicle manufacturer or operator. RCF Carbon removal certification, carbon sink credits and their associated ecosystem engineering, BECNU neutralizes the unavoidable carbon emissions of vehicles.

[0040] Specifically, the vehicle-to-everything (V2X) industrial internet and vehicle-road-cloud-energy intelligent microgrid and digital center carbon emission subsystem adopts a comprehensive carbon emission management strategy. This subsystem utilizes efficient edge computing technology to offload some data processing tasks to the vehicle unit, effectively reducing the computing load and energy consumption of the data center. The data center employs advanced liquid cooling technology and intelligent scheduling algorithms to optimize the PUE value to below 1.1, significantly reducing operational carbon emissions. The intelligent microgrid charging system is closely integrated with regional renewable energy power generation facilities, prioritizing the use of clean energy such as photovoltaic and wind power. The system uses intelligent algorithms to predict grid load and renewable energy generation, rationally scheduling charging periods to maximize the proportion of clean energy use. Simultaneously, the vehicle battery, as a mobile energy storage unit, participates in grid peak shaving, providing V2G services. The system accurately records each charging and discharging behavior, calculates carbon emission reductions, and forms the owner's personal carbon account. The onboard carbon neutrality smart device is the core equipment of the entire system. It uses high-precision sensors to monitor vehicle energy consumption data in real time, combining GPS positioning information and driving behavior analysis to accurately calculate carbon emissions during driving. The smart device connects to the cloud platform in real time via a 5G network, uploading carbon emission data and receiving the latest grid carbon emission factors to ensure the accuracy of carbon footprint calculations. The smart device also interfaces with a blockchain system to store key carbon footprint data on the chain, ensuring data immutability and traceability. This provides a reliable data foundation for subsequent carbon footprint certification and carbon trading. The system automatically executes carbon offsetting operations through smart contracts, ensuring the vehicle remains carbon-neutral at all times. At the time of vehicle manufacture, the initial data table of the onboard carbon neutrality smart device records detailed C... t C MA C VM C USE C REC The carbon footprint values ​​for each stage are also shown. Additionally, the preset C values ​​are also indicated. RCF Carbon credits are allocated from rigorously certified BECNU ecosystem engineering projects, such as forest and marine carbon sinks. The entire system utilizes a vehicle-road-cloud-energy intelligent connected cloud platform for unified data management and analysis. The cloud platform connects to the CNAS testing and certification system, regularly conducting third-party verification of carbon footprint calculation results and generating authoritative carbon neutrality certificates.

[0041] Optionally, the C RCF Carbon removal certification and carbon credits have the following two properties and uses:

[0042] Used to neutralize C t +C MA +C VM C RCF Carbon removal certification and carbon credits are liquidated and cancelled according to market rules when the vehicle leaves the factory;

[0043] The third unavoidable carbon emission C used to neutralize the charging process USE C RCF Carbon credits, which are carbon assets attached to carbon-neutral vehicles, are valued within the vehicle's sales price and are pre-set to offset unavoidable carbon emissions during the charging and use of the vehicle.

[0044] Specifically, C in this embodiment RCF Carbon removal certification and carbon sink credits employ a dual-track management strategy to achieve precise carbon neutrality throughout the entire lifecycle of electric vehicles. The first category of carbon credits... RCF Used to counteract C t (Cloud Network Digital Center Carbon Footprint), C MA (Carbon footprint of materials acquisition and supply) and C VM (Carbon footprint of component and vehicle manufacturing processes). This portion of carbon emissions mainly occurs during the vehicle production phase and is relatively fixed and predictable. The system uses a life cycle assessment (LCA) method to accurately calculate the carbon emissions of each vehicle during the production process. For example, for a mid-size electric SUV, its C... MA At around 7000-8000 kg CO2 equivalent, C VM Approximately 500-600 kg CO2 equivalent, while C t This will fluctuate based on specific cloud service usage. Automakers will purchase an equivalent amount of carbon from certified carbon sink projects based on the calculation results. RCF These carbon sinks come from various pathways, including afforestation projects, wetland restoration, and soil carbon sequestration. Each carbon sink... RCF Each vehicle has a unique identification code that records its origin, quantity, and expiration date. When the vehicle leaves the factory, the system automatically assigns this part of the code... RCF The carbon footprint of vehicles is matched, and transactions are recorded on the blockchain for liquidation and cancellation. This ensures that carbon emissions during the production phase are fully offset. Category 2 C RCF For C USE (Carbon footprint during charging, energy storage, and discharging) refers to the dynamic carbon emissions during the vehicle's usage phase. Based on vehicle characteristics, battery capacity, and expected lifespan, the system estimates the vehicle's total electricity consumption and corresponding carbon emissions throughout its lifecycle. For example, assuming an electric vehicle travels an average of 15,000 kilometers per year, has a lifespan of 10 years, and consumes 15 kWh per 100 kilometers, its C2C emissions can be estimated. USE This is approximately 13,500 kg of CO2 equivalent (considering the gradual cleanification of the power grid in the future). Based on this, automakers will purchase an equivalent amount of Category II CO2. RCF This value is included in the vehicle's selling price, serving as the vehicle's "carbon asset." This part of C RCFThe carbon emissions are stored digitally in the vehicle's carbon database and smart device. When the vehicle is charging, the smart device accurately calculates the carbon emissions for this charge based on the actual electricity consumption and the real-time carbon emission factor of the local power grid, and then calculates the carbon emissions from the preset carbon data. RCF The system also includes a carbon asset trading mechanism. If the actual carbon emissions from a vehicle owner's use are lower than the estimated value, the remaining C... RCF These vehicles can be traded on the platform or used for other carbon-neutral projects. This mechanism not only ensures carbon neutrality throughout the entire vehicle's use but also provides car owners with the opportunity to participate in the carbon market, incentivizing low-carbon travel behaviors.

[0045] Optionally, it also includes the BECNU negative carbon emission neutralization incentive mechanism, an ecosystem engineering initiative for carbon-neutral vehicle owners. This mechanism connects the carbon reduction market with the carbon removal market and leverages the vehicle owner's digital identity ID from the cloud network digital center system, based on the C-value purchased when the vehicle leaves the factory. RCF Internationally recognized carbon removal certification carbon sink credit assets are managed to achieve negative carbon emission neutrality and ecological value incentives through ecosystem engineering BECNU.

[0046] Specifically, each car owner is assigned a unique digital identity ID, which is linked to the vehicle's carbon neutrality smart device. This ID serves as the owner's identifier throughout the entire ecosystem, used to record and manage all their carbon neutrality-related activities. The system establishes a comprehensive carbon asset management platform. Car owners can view their carbon asset status in real time through a mobile application, including the carbon credits pre-installed at the vehicle's factory. RCF The system tracks carbon credits, as well as carbon emissions and carbon sink consumption during usage. Regarding microgrid energy storage for emission reduction, the system encourages vehicle owners to participate in V2G (vehicle-to-grid) services. When a vehicle connects to a smart charging station, the onboard battery can discharge according to grid demand, providing peak shaving and frequency regulation services to the grid. The system accurately records the electricity consumption and time of each V2G service, calculates the corresponding carbon emission reductions, and converts them into additional carbon credits as rewards to vehicle owners.

[0047] The above describes the intelligent connected electric vehicle carbon neutrality system based on the BECNU negative carbon emission ecosystem engineering in the embodiments of this application. The following describes the full life-cycle carbon neutrality method for intelligent connected electric vehicles in the embodiments of this application. Please refer to [link / reference]. Figure 2 One embodiment of the carbon neutrality method for the entire life cycle of intelligent connected electric vehicles in this application includes:

[0048] Step S101: Distributed collection and preprocessing of multi-source data from raw material production, vehicle manufacturing, usage process and scrapping and recycling to obtain a full life cycle carbon emission dataset;

[0049] It is understood that the implementing entity of this application can be a carbon neutrality system for the entire life cycle of intelligent connected electric vehicles, or it can be a terminal or a server; no specific limitation is made here. This application's embodiments use a server as an example for illustration.

[0050] Specifically, real-time data collection of energy consumption and emissions during raw material production is performed. Various sensors and monitoring systems installed within production equipment and factories record energy consumption and emissions at each stage of production. Furthermore, by analyzing material flow relationships, a supply chain network model is constructed to help the system understand the flow of each raw material within the supply chain and its specific carbon emission structure. For vehicle manufacturing, time-series data collection and anomaly identification are performed on production line data. Data acquisition devices and monitoring systems are installed at key nodes of the production line to record the real-time operating status of the production line and the energy consumption and emissions data of each manufacturing stage. Time-series analysis and anomaly identification of this data generate a carbon emission time series for the manufacturing stage, helping to understand carbon emission patterns and anomalies during the manufacturing process. Finally, multi-source fusion of driving, charging, and environmental data during vehicle use is conducted. Vehicle sensors, charging station data acquisition systems, and environmental monitoring equipment record energy consumption, emissions, charging status, and the impact of the external environment on vehicle operation during driving. This data is cleaned and standardized to generate carbon emission characteristic data for the usage stage, helping to understand the carbon emission characteristics of vehicles under different usage conditions. The dismantling and material reuse data from the end-of-life recycling process are categorized and organized, recording the carbon emissions of each end-of-life vehicle during dismantling and material reuse. This categorization generates carbon emission classification results for the end-of-life recycling stage. By aligning and synchronizing the raw material carbon emission data structure, the manufacturing stage carbon emission time series, the usage stage carbon emission characteristic data, and the end-of-life recycling stage carbon emission classification results, a spatiotemporal correlation dataset of full lifecycle carbon emissions is generated. This data, processed using distributed storage and secure encryption technologies, forms a complete full lifecycle carbon emission dataset.

[0051] Step S102: Perform multi-level, multi-scale modeling and fusion analysis on the full life cycle carbon emission dataset to obtain a dynamic carbon emission prediction model;

[0052] Specifically, the entire lifecycle carbon emission dataset is decomposed into timescales by dividing it into short-term, medium-term, and long-term carbon emission subsets to understand the patterns of carbon emission changes at different timescales. A multi-timescale carbon emission data structure is established to analyze carbon emissions at different stages. Through segmented data analysis, rapid changes in the short term, trends in the medium term, and long-term cumulative effects are identified. Based on this multi-timescale carbon emission data structure, spatial correlation analysis is performed on carbon emission data at each lifecycle stage, comprehensively considering the spatial distribution characteristics of each stage, such as the origin of raw materials, the geographical location of manufacturing plants, the usage area, and the location of disposal and recycling. By constructing a multi-spatial-scale carbon emission correlation model, the correlation relationships of carbon emissions at different spatial scales are revealed, providing a more comprehensive understanding of the spatial distribution characteristics of carbon emissions. Cross-validation and feature extraction are performed on the multi-timescale carbon emission data structure and the multi-spatial-scale carbon emission correlation model to extract multi-dimensional correlation features of carbon emissions. These features contain information in both time and space dimensions, more accurately reflecting the true situation of carbon emissions. Based on the multidimensional correlation characteristics of carbon emissions, corresponding sub-models are established for each stage of the life cycle: raw material production, vehicle manufacturing, usage, and end-of-life recycling. These sub-models are then coupled and integrated to form a comprehensive life-cycle carbon emission initial prediction model. Historical data backtesting and error analysis are performed on this initial prediction model. By comparing historical data, the error distribution characteristics between the model predictions and actual results are identified. Based on these error distribution characteristics, a model correction mechanism is designed to self-calibrate the initial prediction model, resulting in a more accurate self-calibrated carbon emission prediction model. The self-calibrated carbon emission prediction model is further optimized with a dynamic parameter update mechanism and a real-time data access interface, enabling the model to dynamically adjust based on real-time data. This ensures that the carbon emission prediction model always reflects the latest data changes, ultimately yielding a dynamic carbon emission prediction model.

[0053] Step S103: Perform spatiotemporal data mining and multi-objective optimization calculations through a carbon emission dynamic prediction model to obtain a smart charging and vehicle-grid interaction strategy.

[0054] Specifically, spatiotemporal clustering analysis is performed on the output data of the carbon emission dynamic prediction model to identify charging demand hotspots in different geographical locations and time periods, resulting in a spatiotemporal distribution map of charging demand. Based on this map, correlation analysis is conducted on grid load data and renewable energy generation prediction data to reflect the grid load and renewable energy supply at different times and locations, generating a dynamic grid state assessment result. Multi-dimensional cross-analysis is performed on the dynamic grid state assessment result and vehicle usage pattern data to predict the optimal time window for vehicle-grid interaction. This interaction time window prediction helps the system understand when and where charging or power feedback to the grid is most efficient. Based on the time window prediction results, the distribution and capacity of charging stations are optimized to obtain a smart charging infrastructure layout scheme, ensuring sufficient charging capacity in high-demand areas and time periods to meet the needs of electric vehicle users. Multi-objective optimization calculations are performed on the smart charging infrastructure layout scheme to determine the optimal charging scheduling strategy. The initial charging scheduling strategy is the result of optimization based on multiple factors such as charging demand, dynamic grid state, and renewable energy supply. Dynamic pricing and incentive mechanisms are then adjusted for the initial charging scheduling strategy. This adjustment, through dynamic electricity pricing and corresponding incentives, guides electric vehicle users to charge when grid load is low or renewable energy supply is sufficient, thereby reducing grid pressure and improving the utilization rate of renewable energy. Ultimately, this leads to a smart charging and vehicle-grid interaction strategy.

[0055] Step S104: Perform multi-sensor data fusion and degradation analysis on the smart charging and vehicle-grid interaction strategy and vehicle status data to obtain predictive maintenance and life optimization schemes.

[0056] Specifically, the intelligent charging and vehicle-to-grid interaction strategy is decomposed, and the vehicle's pattern characteristics under different usage scenarios are extracted. Feature vectors describe the vehicle's behavioral patterns during charging, discharging, and driving. Through these pattern feature vectors, multi-source information fusion is performed on the status data of key vehicle components. This data includes sensor data, on-board diagnostic system data, and environmental monitoring data. By fusing multi-source information, a comprehensive vehicle health status index is obtained, reflecting the current health status of each key component. Time-series analysis is performed on the vehicle health status index, and by analyzing the trends of these indicators over time, component degradation trend models are established. These models can capture the degradation patterns of key components and generate remaining life prediction results for key components. These prediction results help the system identify which components will fail in the future. Based on the remaining life prediction results of key components, maintenance needs are prioritized, a multi-level maintenance decision tree is constructed, and an optimized maintenance scheduling scheme is formulated based on the remaining life of components, the availability of maintenance resources, and other relevant factors to ensure that the vehicle's operational reliability and safety are maximized with limited maintenance resources. A cost-benefit analysis is then performed on the predictive maintenance scheduling scheme. By analyzing the cost and expected benefits of each maintenance operation, an initial lifespan optimization strategy is determined. This strategy considers not only the direct costs of maintenance but also the indirect benefits of extending component lifespan and preventing failures. Real-time vehicle status and environmental factors are integrated with this strategy to dynamically adjust maintenance plans to address changing vehicle conditions and environmental circumstances.

[0057] Step S105: Perform multi-dimensional carbon footprint assessment and dynamic trade-off calculation on predictive maintenance and life optimization schemes to obtain a full life cycle carbon footprint optimization strategy.

[0058] Specifically, by performing feature calculations on predictive maintenance and lifespan optimization schemes, maintenance activity characteristics and lifespan extension indicators are obtained. These characteristics and indicators specifically reflect the carbon emissions and lifespan extension benefits of each maintenance activity. The maintenance activity characteristics and lifespan extension indicators are integrated and analyzed with data from raw material production and manufacturing processes to form a comprehensive life-cycle carbon footprint assessment dataset. This dataset covers carbon emission data from all stages, from raw material production, vehicle manufacturing, use to end-of-life recycling. Based on this life-cycle carbon footprint assessment dataset, carbon emissions at each life-cycle stage are quantified, and a multi-dimensional carbon footprint assessment model is constructed. This model calculates the carbon emissions at each stage, generating initial carbon footprint assessment results. Key influencing factors are analyzed on the initial carbon footprint assessment results, and a carbon footprint sensitivity model is established. This model identifies which factors have the greatest impact on carbon emissions, and a carbon footprint influencing factor weight matrix is ​​constructed using the carbon footprint sensitivity model to clarify the importance of each factor in the carbon footprint. Based on the carbon footprint influencing factor weight matrix, predictive maintenance and lifespan optimization schemes are dynamically adjusted to generate a candidate set of optimization schemes. The alternative solutions comprehensively consider the impact of different maintenance activities and lifespan extension strategies on carbon emissions. Guided by a weight matrix, a more environmentally friendly solution is selected. Dynamic response analysis is performed on the optimized solution candidate set to form an adaptive carbon footprint optimization framework. This framework can be adjusted based on real-time data and environmental changes to ensure that the optimized solutions effectively reduce carbon footprint under various conditions. Feedback adjustment optimization is applied to the adaptive carbon footprint optimization framework. Through continuous feedback and adjustment, the carbon footprint strategy is continuously optimized to obtain a full life-cycle carbon footprint optimization strategy. This strategy can minimize carbon emissions while ensuring vehicle performance and lifespan.

[0059] Step S106: Perform multi-scenario prediction and adaptive path planning on the full life cycle carbon footprint optimization strategy to obtain the carbon neutrality path of intelligent connected electric vehicles.

[0060] Specifically, the optimization strategy for the entire life cycle carbon footprint is analyzed to extract the key decision variables and constraints required to achieve carbon neutrality. These variables and constraints include not only internal parameters, such as the charging frequency, lifespan, and maintenance cycle of electric vehicles, but also external environmental factors, such as weather conditions, energy supply, and traffic flow. Integrating the decision variables and constraints with external environmental factors generates a basic parameter set for multi-scenario prediction. Based on this parameter set, scenarios are constructed to obtain a scenario probability distribution matrix, reflecting the probability of different scenarios occurring, including various scenario combinations from best to worst. For each scenario, carbon emission trajectory simulation is performed, and a dynamic programming model is used to calculate the initial carbon neutrality path network for each decision node. The dynamic programming model can identify potential paths to achieve carbon neutrality based on carbon emission trajectories under different scenarios and form a preliminary path network. Path sensitivity analysis is performed on the preliminary path network to identify key factors and potential risk points affecting path selection. These factors include policy changes, market fluctuations, and technological advancements. Based on the influencing factors and risk points, a path evaluation index system is established to assess the feasibility and risk of each path. A feasibility scoring table is generated based on the path evaluation index system. Through multi-criteria decision analysis, different paths are comprehensively evaluated to obtain dynamically adjusted carbon-neutral path schemes. To ensure the effectiveness and feasibility of the carbon-neutral path schemes, a feedback mechanism and checkpoint configuration are implemented. Checkpoints can monitor path execution in real time and dynamically adjust according to actual conditions, ensuring the path scheme remains optimal. Ultimately, a carbon-neutral path for intelligent connected electric vehicles is obtained.

[0061] This application's embodiments cover all stages of the entire lifecycle of intelligent connected electric vehicles, including raw material production, vehicle manufacturing, usage, and end-of-life recycling, achieving comprehensive management and optimization of carbon emissions. By establishing a dynamic carbon emission prediction model, it can reflect changes in carbon emissions at each stage in real time and make dynamic adjustments and optimizations, improving the adaptability and effectiveness of carbon neutrality strategies. Utilizing multi-source data acquisition, multi-level modeling, and multi-dimensional analysis, the accuracy of carbon emission assessment is greatly improved. It organically combines multiple aspects such as intelligent charging, vehicle-grid interaction, and predictive maintenance, achieving coordinated optimization of the energy system, transportation system, and maintenance system. Through multi-scenario prediction and adaptive path planning, it can cope with various situations, thereby realizing the full lifecycle carbon neutrality monitoring and analysis of intelligent connected electric vehicles.

[0062] In one specific embodiment, the process of performing step S101 may specifically include the following steps:

[0063] (1) Collect energy consumption and emission data in real time during the raw material production process, and construct a supply chain network model based on the material flow relationship to obtain the raw material carbon emission data structure.

[0064] (2) Time-series data collection and anomaly identification of production line data during vehicle manufacturing process to obtain carbon emission time series during manufacturing stage;

[0065] (3) Multi-source fusion of driving data, charging data and environmental data during vehicle use, followed by cleaning and standardization, yields carbon emission characteristic data for the usage phase.

[0066] (4) Classify and organize the dismantling data and material reuse data in the scrap recycling process to obtain the carbon emission classification results of the scrap recycling stage;

[0067] (5) Data alignment and time synchronization are performed on the carbon emission data structure of raw materials, the carbon emission time series of the manufacturing stage, the carbon emission characteristic data of the usage stage, and the carbon emission classification results of the scrapping and recycling stage to obtain the spatiotemporal correlation data of carbon emissions throughout the entire life cycle.

[0068] (6) Distribute and securely encrypt the spatiotemporal correlation data of carbon emissions throughout the entire life cycle to obtain a carbon emission dataset throughout the entire life cycle.

[0069] Specifically, energy consumption and emissions data during raw material production are collected in real time, and a supply chain network model is constructed based on material flow relationships to obtain the raw material carbon emission data structure. In this process, energy consumption is monitored in real time and emissions data is recorded by sensors installed on raw material production equipment and transportation vehicles. These sensors include electricity metering devices, fuel usage monitoring devices, and emission measurement devices. The energy consumed and pollutants emitted during each batch of raw materials from mining to processing and transportation are recorded. For example, let E... rm P represents the total energy consumption during the raw material production process. r m represents the total emissions, as shown in the formula below:

[0070]

[0071] Among them, e i p represents the energy consumption of the i-th production stage. iLet E represent the emissions at the i-th production stage, and n represent the total number of production stages. By analyzing this data, a supply chain network model is constructed based on material flow relationships. The supply chain network model can be represented by a directed graph, where nodes represent different stages such as production, processing, and transportation, and edges represent the direction and quantity of material flow, forming a raw material carbon emission data structure that reflects the energy consumption and emissions of each stage. Time-series data acquisition and anomaly identification are performed on the production line data of the vehicle manufacturing process to obtain the carbon emission time series for the manufacturing stage. During vehicle manufacturing, data acquisition devices are installed at each workstation on each production line. These devices can record the production line's operating status in real time, including the energy consumption, production efficiency, and emissions of each workstation. By analyzing the time-series data, anomalies occurring during the production process are identified, such as sudden increases in energy consumption or excessive emissions. By identifying and handling these anomalies, the operating efficiency of the production line is improved, and unnecessary energy consumption and emissions are reduced. Let E... mfg (t) represents the energy consumption at a certain moment in the manufacturing process, P mfg (t) represents the corresponding emissions, as shown in the following formula:

[0072]

[0073] Among them, e j (t) represents the energy consumption of the j-th workstation at time t, p j(t) represents the emissions at time t of the j-th workstation, and m represents the total number of workstations. Multi-source fusion of driving data, charging data, and environmental data during vehicle use is performed, followed by cleaning and standardization to obtain carbon emission characteristic data for the usage phase. During vehicle operation, onboard sensors and the vehicle management system record vehicle speed, mileage, charging status, and environmental data in real time. This data is transmitted to a data center via a wireless network for cleaning and standardization to remove noise and outliers. For example, vehicle driving data may include speed, acceleration, and braking frequency; charging data includes charging time, charging power, and battery status; and environmental data includes temperature, humidity, and air quality. Multi-source fusion of this data yields a carbon emission characteristic dataset for the usage phase. Dismantling data and material reuse data from the end-of-life recycling process are classified and organized to obtain carbon emission classification results for the end-of-life recycling phase. During vehicle end-of-life recycling, on-site data from dismantling and material reuse plants are collected using sensors and monitoring equipment, recording the energy consumption and emissions of each dismantling and reuse stage. By classifying and organizing this data, we obtain the carbon emission classification results for the end-of-life recycling stage. For example, carbon emissions generated during dismantling can include emissions from fuel consumption, equipment operation, and waste disposal, while carbon emissions generated during reuse include emissions from material processing and remanufacturing. We align and synchronize the raw material carbon emission data structure, the manufacturing stage carbon emission time series, the usage stage carbon emission characteristic data, and the end-of-life recycling stage carbon emission classification results to obtain spatiotemporal correlation data for the entire lifecycle of carbon emissions. In this process, data from different data sources are aligned and synchronized to ensure consistency in time and space. For example, we use unified timestamps and geographic coordinates to label the data and perform interpolation and alignment based on the actual data conditions. In this way, we obtain a spatiotemporal correlation dataset for the entire lifecycle of carbon emissions, covering carbon emissions at each stage from raw material production, vehicle manufacturing, usage to end-of-life recycling. To ensure data security and reliability, the spatiotemporal correlation data for the entire lifecycle of carbon emissions is distributed and securely encrypted, resulting in a complete lifecycle carbon emission dataset. Distributed storage can improve data storage efficiency and reliability by storing data copies on multiple nodes, ensuring that data is not lost due to a single point of failure. Secure encryption protects data privacy and security by encrypting data using encryption algorithms, preventing data from being stolen or tampered with during transmission and storage.

[0074] In one specific embodiment, the process of performing step S102 may specifically include the following steps:

[0075] (1) The whole life cycle carbon emission dataset is decomposed into time scales and divided into short-term, medium-term and long-term carbon emission data subsets to obtain a multi-time scale carbon emission data structure.

[0076] (2) Based on the multi-timescale carbon emission data structure, spatial correlation analysis is performed on the carbon emission data of each life cycle stage to construct a multi-spatial-scale carbon emission correlation model.

[0077] (3) Cross-validate and extract features from the multi-timescale carbon emission data structure and the multi-spatial-scale carbon emission correlation model to obtain multi-dimensional carbon emission correlation features;

[0078] (4) Based on the multidimensional correlation characteristics of carbon emissions, corresponding sub-models are established for each life cycle stage of raw material production, vehicle manufacturing, use process and scrap recycling, and the sub-models are coupled and integrated to obtain the initial prediction model of carbon emissions for the whole life cycle.

[0079] (5) Historical data backtesting and error analysis were performed on the initial prediction model of carbon emissions throughout the life cycle to obtain the error distribution characteristics. Based on the error distribution characteristics, a model correction mechanism was designed to obtain a self-correcting carbon emission prediction model.

[0080] (6) The dynamic parameter update mechanism and real-time data access interface of the self-calibrating carbon emission prediction model are optimized to obtain the dynamic carbon emission prediction model.

[0081] Specifically, the entire lifecycle carbon emission dataset is decomposed into time scales, dividing the data into different time periods to better understand the patterns and trends of carbon emission changes. Based on the multi-timescale carbon emission data structure, spatial correlation analysis is performed on carbon emission data at each lifecycle stage, constructing a multi-spatial-scale carbon emission correlation model. Geospatial analysis is conducted on the carbon emission data to determine the carbon emission correlations between different geographical regions and different lifecycle stages. For example, using Geographic Information System (GIS) tools, carbon emission data from raw material production sites, vehicle manufacturing plants, vehicle usage areas, and scrapping and recycling sites are analyzed to identify spatial correlations between different regions and stages. Constructing a multi-spatial-scale carbon emission correlation model can help identify high-emission areas and processes, thereby enabling targeted carbon reduction measures. Cross-validation and feature extraction are performed on the multi-timescale carbon emission data structure and the multi-spatial-scale carbon emission correlation model to obtain multi-dimensional carbon emission correlation features. Cross-validation is used to verify the accuracy and reliability of the model by dividing the dataset into training and test sets to train and test the model, ensuring that the model can accurately predict carbon emissions. Feature extraction involves extracting the variables that best represent carbon emission characteristics from the data, such as energy consumption, emissions, and production efficiency. This yields a multidimensional correlation feature of carbon emissions encompassing both temporal and spatial dimensions. Based on this multidimensional correlation feature, corresponding sub-models are established for each stage of the carbon emission lifecycle: raw material production, vehicle manufacturing, usage, and end-of-life recycling. These sub-models are then coupled and integrated to obtain an initial prediction model for carbon emissions throughout the entire lifecycle. For example, the sub-model for the raw material production stage can be based on energy consumption and emissions data, using linear regression or machine learning algorithms; the sub-model for the vehicle manufacturing stage can be based on production line energy consumption and emissions data, using time-series analysis and anomaly detection algorithms; the sub-model for the vehicle usage stage can be based on driving data, charging data, and environmental data, using multi-source data fusion and standardization techniques; and the sub-model for the end-of-life recycling stage can be based on dismantling data and material reuse data, using classification and clustering algorithms. By coupling and integrating these sub-models, a comprehensive initial prediction model for carbon emissions throughout the entire lifecycle is formed. Historical data backtesting and error analysis are then performed on the initial prediction model to obtain the error distribution characteristics. Historical data backtesting involves applying the model to historical data to test its predictive ability; error analysis calculates the difference between predicted and actual values ​​to obtain the error distribution characteristics. Let y i This represents the actual carbon emissions. Let n be the model's predicted value, and n be the total number of data points. Then the error e is... i It can be represented as:

[0082]

[0083] The total error can be expressed as mean square error (MSE):

[0084]

[0085] A model correction mechanism is designed based on the error distribution characteristics to obtain a self-calibrating carbon emission prediction model. The self-calibration mechanism can correct prediction errors by updating model parameters in real time. For example, Kalman filtering or recursive least squares algorithms can be used to dynamically adjust the model to reduce prediction errors and improve model accuracy. The self-calibrating carbon emission prediction model is then optimized with a dynamic parameter update mechanism and a real-time data access interface to obtain a dynamic carbon emission prediction model. The dynamic parameter update mechanism refers to continuously monitoring and updating model parameters during model operation to respond to changes in data and the environment. Optimizing the real-time data access interface involves optimizing the data acquisition and transmission interface to ensure that data can be transmitted to the model for processing in a timely and accurate manner. For example, Internet of Things (IoT) technology can be used to collect vehicle operation data and environmental data in real time and transmit them to the cloud via wireless networks for processing and analysis. In this way, a real-time, dynamic carbon emission prediction model is obtained.

[0086] In one specific embodiment, the process of executing step S103 may specifically include the following steps:

[0087] (1) Spatiotemporal clustering analysis was performed on the output data of the dynamic prediction model of carbon emissions to obtain the spatiotemporal clustering results. Based on the geographical location and time period, the charging demand hotspots of the spatiotemporal clustering results were divided to obtain the spatiotemporal distribution map of charging demand.

[0088] (2) Based on the spatiotemporal distribution map of charging demand, conduct correlation analysis on grid load data and renewable energy power generation forecast data to generate dynamic grid status assessment results;

[0089] (3) Perform multi-dimensional cross-analysis on the dynamic power grid state assessment results and vehicle usage pattern data to obtain the vehicle-power grid interaction time window prediction.

[0090] (4) Based on the prediction of vehicle-grid interaction time window, optimize the distribution and capacity of charging stations to obtain a smart charging infrastructure layout scheme.

[0091] (5) Perform multi-objective optimization calculations on the layout scheme of smart charging infrastructure to obtain the initial charging scheduling strategy, and adjust the initial charging scheduling strategy with dynamic pricing and incentive mechanisms to obtain the smart charging and vehicle-grid interaction strategy scheme.

[0092] Specifically, spatiotemporal clustering analysis is performed on the output data of the dynamic carbon emission prediction model to identify carbon emission patterns at different times and locations. Spatiotemporal clustering analysis can use the K-means clustering algorithm or the DBSCAN algorithm to group data points according to their geographical location and timestamp. For example, let D represent the carbon emission dataset, d i This represents the i-th data point, which includes the timestamp t. i and geographical location (x i ,y i The clustering goal is to divide D into k clusters, each containing similar time and geographic location data.

[0093]

[0094] Among them, C i Let μ represent the i-th cluster. i Denotes the centroid of the cluster, ∥d-μ i ∥ represents the distance between data point d and cluster centroid μ. i The distance between them. The results of spatiotemporal clustering analysis are used to divide charging demand hotspots according to geographical location and time period, resulting in a spatiotemporal distribution map of charging demand. These hotspots reflect the intensity of charging demand in specific geographical locations within a specific time period. For example, a city's commercial area may have higher charging demand during weekdays, while residential areas are charging hotspots at night. Based on the spatiotemporal distribution map of charging demand, correlation analysis is performed on grid load data and renewable energy generation forecast data to generate a dynamic grid state assessment result. Grid load data includes the power demand of the grid in various time periods and geographical areas, while renewable energy generation forecast data includes forecasts of power generation from renewable energy sources such as solar and wind power in different future time periods. By performing correlation analysis on these data, the grid load and renewable energy supply at different times and locations are assessed. For example, let L(t) represent the grid load at time t, and R(t) represent the renewable energy generation at time t. The dynamic grid state assessment result can be expressed as:

[0095] S(t) = L(t) - R(t);

[0096] Here, S(t) represents the dynamic grid state at time t, with a positive value indicating that the grid load exceeds the renewable energy supply, and a negative value indicating that the renewable energy supply exceeds the grid load. A multi-dimensional cross-analysis is performed on the dynamic grid state assessment results and vehicle usage pattern data to obtain a predicted vehicle-grid interaction time window. Vehicle usage pattern data includes vehicle driving and charging behavior in different time periods. By cross-analyzing this data with the grid state, the optimal time window for vehicle-grid interaction is identified. For example, if renewable energy generation is high and grid load is low during a certain time period, this period is suitable for a large number of vehicles to charge or feed electricity back to the grid. Based on the predicted vehicle-grid interaction time window, the distribution and capacity of charging stations are optimized to obtain a smart charging infrastructure layout scheme. By analyzing charging demand hotspots in different regions and time periods, the geographical distribution and capacity configuration of charging stations are optimized to ensure sufficient charging services are provided during peak charging demand periods. For example, a linear programming model is used to optimize the distribution and capacity configuration of charging stations, aiming to minimize total construction and operating costs while meeting the charging needs of all spatiotemporal hotspots. Let C represent the construction and operation cost of the charging station, and D(t,x,y) represent the charging demand at time t and location (x,y). The optimization objective is:

[0097]

[0098] Where n represents the number of charging stations, C s Let Q represent the cost of the s-th charging station. s (t,x,y) represents the charging capacity of the s-th charging station at time t and location (x,y). Multi-objective optimization calculations are performed on the smart charging infrastructure layout scheme to obtain an initial charging scheduling strategy. This initial strategy is then dynamically adjusted using pricing and incentive mechanisms to ultimately arrive at a smart charging and vehicle-grid interaction strategy. The initial charging scheduling strategy optimizes vehicle charging time and charging amount to maximize the utilization of renewable energy and reduce pressure on the grid during peak load periods. The dynamic pricing mechanism can reduce charging prices when grid load is low or renewable energy supply is sufficient, incentivizing users to charge during these periods. For example, let P(t) represent the charging price at time t, and the initial charging scheduling strategy D... c (t) can be obtained by optimizing the model:

[0099]

[0100]

[0101] Where T represents the total number of time periods, and Q(t) represents the charging capacity at time t.

[0102] In one specific embodiment, the process of executing step S104 may specifically include the following steps:

[0103] (1) Decompose the smart charging and vehicle-grid interaction strategy scheme to obtain the vehicle usage mode feature vector;

[0104] (2) Based on the vehicle usage mode feature vector, multi-source information fusion is performed on the status data of key vehicle components to obtain vehicle health status indicators.

[0105] (3) Conduct time-series analysis on vehicle health status indicators, establish component degradation trend model, and generate prediction results of the remaining life of key components through component degradation trend model;

[0106] (4) Prioritize maintenance needs based on the remaining life prediction results of key components, construct a multi-level maintenance decision tree, and obtain a predictive maintenance scheduling scheme.

[0107] (5) Conduct a cost-benefit analysis on the predictive maintenance scheduling scheme to obtain the initial life optimization strategy, and integrate the real-time vehicle status and environmental factors with the initial life optimization strategy to obtain the predictive maintenance and life optimization scheme.

[0108] Specifically, the intelligent charging and vehicle-to-grid interaction strategy is decomposed to obtain a vehicle usage mode feature vector, including indicators such as driving distance d, charging frequency, charging duration, and discharging frequency. These feature vectors are used to describe the vehicle's behavior patterns under different usage scenarios. For example, let u represent the vehicle usage mode feature vector, whose components include driving distance d, charging frequency f, etc. c Charging time t c Discharge frequency f d wait:

[0109] u=[d,f c ,t c ,f d ,…];

[0110] Based on the vehicle usage pattern feature vector, multi-source information fusion is performed on the status data of key vehicle components to obtain a vehicle health status index. The status data of key vehicle components includes operational data from components such as the engine, transmission, and battery, as well as sensor data. Through multi-source information fusion technology, this data is integrated to generate an index reflecting the overall health of the vehicle. For example, let H represent the vehicle health status index, which can be obtained by weighted averaging of the status data of various key components:

[0111]

[0112] Among them, s i w represents the status data of the i-th critical component.i This represents the corresponding weight, and n represents the total number of key components. Weight w i The settings can be configured based on the importance of each component and its impact on vehicle health. Time-series analysis of vehicle health status indicators is performed to establish component degradation trend models, and these models are used to generate predictions of the remaining life of key components. Time-series analysis can employ methods such as autoregressive integral moving average models or long short-term memory networks to capture the changing trends of vehicle health status indicators over time. For example, let H(t) represent the vehicle health status indicator at time t; the time-series analysis model can then predict the health status at future times.

[0113] H(t+1)=f(H(t),H(t-1),…);

[0114] Based on the changing trends of health status, a component degradation trend model is established to predict the remaining lifespan of critical components. For example, let R(t) represent the remaining lifespan at time t, which can be predicted using the degradation trend model:

[0115] R(t) = g(H(t), t);

[0116] Here, the function g represents the degradation trend model, considering the impact of health status and time. Maintenance needs are prioritized based on the predicted remaining lifespan of critical components, and a multi-level maintenance decision tree is constructed to obtain a predictive maintenance scheduling scheme. The prioritization of maintenance needs is based on the remaining lifespan and operational importance of critical components. For example, components with shorter remaining lifespans and higher operational importance should be maintained first. Let P... i This indicates the maintenance priority of the i-th component, which can be determined based on its remaining lifespan R. i And importance weight w i calculate:

[0117]

[0118] Based on the priority ranking results, a multi-level maintenance decision tree is constructed. Nodes in the decision tree represent different maintenance operations and decision paths, while leaf nodes represent specific maintenance actions. For example, the root node could be "whether immediate maintenance is needed." Branching based on remaining lifespan and priority yields a predictive maintenance scheduling scheme. A cost-benefit analysis is performed on the predictive maintenance scheduling scheme to obtain an initial lifespan optimization strategy. Real-time vehicle status and environmental factors are then integrated with the initial lifespan optimization strategy to obtain a predictive maintenance and lifespan optimization scheme. The cost-benefit analysis needs to consider both the direct costs of maintenance operations and the indirect costs caused by downtime due to faults. Let C... m C represents maintenance costs. d The downtime cost is represented by the total cost, which can be expressed as:

[0119] C = Cm +C d ;

[0120] By optimizing the model, the total cost can be minimized while ensuring vehicle operational reliability. Integrating real-time vehicle status and environmental factors with the initial lifespan optimization strategy, and through real-time data updates and dynamic adjustments, a final predictive maintenance and lifespan optimization plan can be obtained. For example, real-time vehicle status includes current driving data, charging status, ambient temperature, etc. By monitoring this data in real time, maintenance strategies can be dynamically adjusted to ensure the timeliness and effectiveness of maintenance plans.

[0121] In one specific embodiment, the process of executing step S105 may specifically include the following steps:

[0122] (1) Perform feature calculations on predictive maintenance and life optimization schemes to obtain maintenance activity characteristics and life extension indicators, and integrate and analyze the maintenance activity characteristics and life extension indicators with raw material production and manufacturing process data to obtain a basic dataset for full life cycle carbon footprint assessment.

[0123] (2) Based on the basic dataset of the full life cycle carbon footprint assessment, the carbon emissions of each life cycle stage are quantitatively calculated, a multi-dimensional carbon footprint assessment model is constructed, and the initial carbon footprint assessment results are calculated through the multi-dimensional carbon footprint assessment model.

[0124] (3) Conduct key influencing factor analysis on the initial carbon footprint assessment results, establish a carbon footprint sensitivity model, and construct a carbon footprint influencing factor weight matrix through the carbon footprint sensitivity model;

[0125] (4) Based on the weight matrix of carbon footprint influencing factors, the predictive maintenance and life optimization schemes are dynamically adjusted to obtain a set of optimization schemes;

[0126] (5) Perform dynamic response analysis on the set of optimization schemes to obtain an adaptive carbon footprint optimization framework, and perform feedback adjustment optimization on the adaptive carbon footprint optimization framework to obtain a full life cycle carbon footprint optimization strategy.

[0127] Specifically, the characteristics of each maintenance activity are quantified, including maintenance time, frequency, required resources, and impact on the lifespan of critical components. For example, let M... i Let t represent the i-th maintenance activity. i Indicates maintenance time, f i Indicates the maintenance frequency, r i Indicates the required resources, l i This represents the amount of extension to component life. Based on these characteristics, maintenance activity characteristics and life extension indices are calculated. The maintenance activity feature vector can be represented as:

[0128] m i =[t i ,f i ,r i ];

[0129] The life extension index L can be expressed as the sum of the life extensions from each maintenance:

[0130]

[0131] Where n represents the total number of maintenance activities. Integrating maintenance activity characteristics and lifespan extension indicators with raw material production and manufacturing process data yields a foundational dataset for lifecycle carbon footprint assessment. Data from the raw material production and manufacturing processes includes energy consumption, carbon emissions, and production efficiency at each stage. For example, let E... p C represents the energy consumption during the raw material production process. p This represents the corresponding carbon emissions; the energy consumption and carbon emissions of the manufacturing process are E, respectively. m and C m By integrating data from maintenance activities and manufacturing processes, a comprehensive dataset encompassing all lifecycle stages is created. The foundational dataset for the full lifecycle carbon footprint assessment can be represented as:

[0132] LCF={(m i ,l i E p C p E m C m ,…)};

[0133] Based on a foundational dataset, carbon emissions at each stage of the life cycle are quantified, and a multi-dimensional carbon footprint assessment model is constructed. This carbon footprint assessment model uses life cycle analysis methods to calculate the carbon footprint for the entire life cycle by quantifying carbon emissions at each stage. For example, let the total carbon emissions be C... total The sum of carbon emissions at each stage:

[0134]

[0135] in, Let represent the carbon emissions from the i-th maintenance activity. After calculating the initial carbon footprint assessment results, a key influencing factor analysis is performed to establish a carbon footprint sensitivity model. The key influencing factor analysis aims to identify the factors with the greatest impact on carbon emissions, such as energy type, production process, and maintenance frequency. The degree of influence of these factors is determined through regression analysis or sensitivity analysis. The carbon footprint sensitivity model can be expressed as:

[0136]

[0137] Where S represents carbon footprint sensitivity, F j Let w represent the j-th influencing factor. j Let w represent the corresponding weights, and m be the total number of influencing factors. A carbon footprint influencing factor weight matrix is ​​constructed using a carbon footprint sensitivity model. This matrix represents the weight of each influencing factor on carbon emissions. Let W be the weight matrix, where w... i j represents the weight of the ith factor's influence on carbon emissions at the j-th life cycle stage. The weight matrix helps understand which factors contribute most to carbon emissions, allowing for targeted optimization. Based on the carbon footprint influencing factor weight matrix, predictive maintenance and life cycle optimization schemes are dynamically adjusted to obtain a set of optimization candidates. These candidates aim to reduce carbon emissions by adjusting maintenance frequency, selecting low-carbon materials, and improving manufacturing processes. For example, adjusting maintenance frequency can reduce unnecessary maintenance activities, thereby lowering carbon emissions. The optimization objective can be expressed as minimizing total carbon emissions. Dynamic response analysis is performed on the optimization candidate set to obtain an adaptive carbon footprint optimization framework. Dynamic response analysis evaluates the effectiveness of each candidate scheme by simulating carbon emissions under different conditions. The adaptive carbon footprint optimization framework can adjust based on real-time data and environmental changes, ensuring that carbon emissions are minimized under various conditions. For example, when renewable energy supply is sufficient, the frequency of maintenance activities can be increased, utilizing low-carbon energy for maintenance; conversely, the frequency can be reduced. Feedback adjustment optimization is applied to the adaptive carbon footprint optimization framework to obtain a full life cycle carbon footprint optimization strategy. Feedback-based adjustment and optimization ensures that the optimization framework is always in its optimal state by continuously monitoring and adjusting it.

[0138] In one specific embodiment, the process of executing step S106 may specifically include the following steps:

[0139] (1) Extract decision variables and constraints for the whole life cycle carbon footprint optimization strategy, obtain decision variables and constraints, and integrate decision variables and constraints with external environmental factors to generate a set of basic parameters for multi-scenario prediction;

[0140] (2) Construct scenarios based on the basic parameter set for multi-scenario prediction to obtain the scenario probability distribution matrix;

[0141] (3) Simulate the carbon emission trajectory for each scenario in the scenario probability distribution matrix, construct a dynamic programming model, and calculate the initial carbon neutrality path network for each decision node through the dynamic programming model;

[0142] (4) Conduct path sensitivity analysis on the initial carbon neutralization pathway network to obtain influencing factors and potential risk points, and establish a pathway evaluation index system based on the influencing factors and potential risk points.

[0143] (5) Generate a path feasibility scoring table based on the path evaluation index system, and conduct multi-criteria decision analysis on the path feasibility scoring table to obtain a dynamically adjusted carbon neutrality path scheme.

[0144] (6) Implement a feedback mechanism and checkpoint configuration for the dynamically adjusted carbon neutrality path scheme to obtain the carbon neutrality path of intelligent connected electric vehicles.

[0145] Specifically, this involves analyzing the processes and influencing factors at each stage of the life cycle, including raw material production, manufacturing, use, and end-of-life recycling. By analyzing these stages, key decision variables are identified, such as production processes, energy use, material selection, and maintenance frequency, along with corresponding constraints such as resource limitations, cost constraints, and regulatory requirements. For example, let x1 represent the choice of production process, x2 represent energy consumption, x3 represent material selection, and x4 represent maintenance frequency. Constraints can be represented as resource constraints R and cost constraints C.

[0146]

[0147] Where, r i Let c represent the resource consumption of the i-th decision variable. i Let represent the cost of the i-th decision variable, and n represent the total number of decision variables. The decision variables and constraints are integrated with external environmental factors to generate a basic parameter set for multi-scenario prediction. External environmental factors include market demand, policy changes, energy prices, and climate conditions. For example, let the external environmental factors be e1 (market demand), e2 (policy changes), e3 (energy prices), and e4 (climate conditions). By integrating these factors, a basic parameter set for multi-scenario prediction is generated.

[0148] P={(x1,x2,x3,x4,e1,e2,e3,e4)};

[0149] Scenario prediction is performed using a set of basic parameters to construct scenarios, resulting in a scenario probability distribution matrix. The probability of each scenario occurring is then evaluated through simulations of parameter combinations under different scenarios. For example, let S represent scenario S, and P(S...)... i ) represents scenario S i The probability of occurrence can be generated using statistical methods or Monte Carlo simulation to create a scenario probability distribution matrix:

[0150]

[0151] Here, m represents the total number of scenarios. Carbon emission trajectory simulation is performed for each scenario in the scenario probability distribution matrix, a dynamic programming model is constructed, and the initial carbon neutrality path network for each decision node is calculated using the dynamic programming model. The carbon emission trajectory simulation is based on carbon emissions under different scenarios, and the path selection for each decision node can be optimized using the dynamic programming model. For example, let C... i S represents scenario S i Given the carbon emissions, the dynamic programming objective is to minimize the total carbon emissions:

[0152]

[0153] A path sensitivity analysis was conducted on the initial carbon neutrality pathway network to identify influencing factors and potential risk points. Based on these factors, a path evaluation index system was established. Sensitivity analysis assesses the impact of each factor on path selection, identifying the most critical influencing factors and potential risk points. For example, let F... j Let R represent the j-th influencing factor. k The path evaluation index system can be expressed as follows: (This represents the k-th risk point.)

[0154] I = {F j ,R k};

[0155] A pathway feasibility scoring table is generated based on the pathway assessment index system, and multi-criteria decision analysis is performed on the scoring table to obtain dynamically adjusted carbon neutrality pathway schemes. The pathway feasibility scoring table scores different pathway schemes by comprehensively considering various assessment indicators. For example, let the pathway feasibility score be S... p Multi-criteria decision analysis can use the weighted scoring method:

[0156]

[0157] Among them, w j I represents the weight of the j-th indicator. j This represents the score for the j-th indicator. A feedback mechanism and checkpoint configuration are implemented for the dynamically adjusted carbon-neutral pathway, resulting in a carbon-neutral pathway for intelligent connected electric vehicles. The feedback mechanism ensures real-time optimization of the pathway by continuously monitoring and adjusting the pathway plan. Checkpoint configuration refers to setting key points during pathway execution to evaluate the pathway's effectiveness in real time and make necessary adjustments and optimizations. For example, in pathway planning, at each key time node or milestone, the current carbon emissions and resource usage are assessed, and adjustments are made based on the actual situation to ensure the achievement of the carbon neutrality target.

[0158] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0159] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0160] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for carbon neutralization in a full life cycle of an intelligent connected electric vehicle, characterized in that, The method comprises: Distributed collection and preprocessing of multi-source data of raw material production, vehicle manufacturing, use process and scrap recycling to obtain a full life cycle carbon emission dataset; Multi-level and multi-scale modeling and fusion analysis are performed on the full life cycle carbon emission dataset to obtain a carbon emission dynamic prediction model; specifically, the full life cycle carbon emission dataset is decomposed in time scale and divided into short-term, medium-term and long-term carbon emission data subsets to obtain a multi-time scale carbon emission data structure; according to the multi-time scale carbon emission data structure, spatial correlation analysis is performed on the carbon emission data of each life cycle stage to construct a multi-space scale carbon emission correlation model; the multi-time scale carbon emission data structure and the multi-space scale carbon emission correlation model are cross-validated and feature extracted to obtain carbon emission multi-dimensional correlation features; according to the carbon emission multi-dimensional correlation features, corresponding sub-models are established for each life cycle stage of raw material production, vehicle manufacturing, use process and scrap recycling, and the sub-models are coupled and integrated to obtain an initial full life cycle carbon emission prediction model; the initial full life cycle carbon emission prediction model is backtested with historical data and error analyzed to obtain error distribution features, and a model correction mechanism is designed according to the error distribution features to obtain a self-correcting carbon emission prediction model; the self-correcting carbon emission prediction model is subjected to dynamic parameter updating mechanism and real-time data access interface optimization to obtain a carbon emission dynamic prediction model; Through the carbon emission dynamic prediction model, spatio-temporal data mining and multi-objective optimization calculation are performed to obtain an intelligent charging and vehicle grid interaction strategy scheme; Multi-sensor data fusion and degradation analysis are performed on the intelligent charging and vehicle grid interaction strategy scheme and vehicle state data to obtain a predictive maintenance and life optimization scheme; Multi-dimensional carbon footprint evaluation and dynamic trade-off calculation are performed on the predictive maintenance and life optimization scheme to obtain a full life cycle carbon footprint optimization strategy; Multi-scenario prediction and adaptive path planning are performed on the full life cycle carbon footprint optimization strategy to obtain an intelligent networked electric vehicle carbon neutral path.

2. The method of claim 1, wherein the method is characterized by, The distributed collection and preprocessing of multi-source data of raw material production, vehicle manufacturing, use process and scrap recycling to obtain a full life cycle carbon emission dataset comprises: Real-time collection of energy consumption and emission data during raw material production, and construction of a supply chain network model according to material flow relationships to obtain a raw material carbon emission data structure; Time series collection and anomaly identification of production line data during vehicle manufacturing to obtain a manufacturing stage carbon emission time series; Multi-source fusion of driving data, charging data and environmental data during vehicle use, and cleaning and standardization processing to obtain use stage carbon emission feature data; Classification and arrangement of disassembly data and material reuse data during scrap recycling to obtain carbon emission classification results of the scrap recycling stage; The raw material carbon emission data structure, the manufacturing stage carbon emission time series, the use stage carbon emission feature data and the carbon emission classification result of the scrap recycling stage are subjected to data alignment and time synchronization to obtain full life cycle carbon emission space-time correlation data; The full life cycle carbon emission space-time correlation data is subjected to data distributed storage and security encryption to obtain a full life cycle carbon emission dataset. 3.The method of claim 1, wherein, The space-time data mining and multi-objective optimization calculation through the carbon emission dynamic prediction model obtain an intelligent charging and vehicle grid interaction strategy scheme, including: The output data of the carbon emission dynamic prediction model is subjected to space-time clustering analysis to obtain a space-time clustering result, and the charging demand hotspots of the space-time clustering result are divided according to geographical location and time period to obtain a charging demand space-time distribution map; According to the charging demand space-time distribution map, the grid load data and renewable energy power generation prediction data are subjected to correlation analysis to generate a dynamic grid state evaluation result; The dynamic grid state evaluation result and vehicle use mode data are subjected to multi-dimensional cross analysis to obtain a vehicle grid interaction time window prediction; According to the vehicle grid interaction time window prediction, the charging station distribution and capacity are optimized to obtain an intelligent charging infrastructure layout scheme; The intelligent charging infrastructure layout scheme is subjected to multi-objective optimization calculation to obtain an initial charging scheduling strategy, and the initial charging scheduling strategy is subjected to dynamic pricing and incentive mechanism adjustment to obtain an intelligent charging and vehicle grid interaction strategy scheme. 4.The method of claim 1, wherein, The intelligent charging and vehicle grid interaction strategy scheme and vehicle state data are subjected to multi-sensor data fusion and degradation analysis to obtain a predictive maintenance and life optimization scheme, including: The intelligent charging and vehicle grid interaction strategy scheme is decomposed to obtain a vehicle use mode feature vector; According to the vehicle use mode feature vector, the state data of vehicle key components are subjected to multi-source information fusion to obtain a vehicle health state index; The vehicle health state index is subjected to time series analysis to establish a component degradation trend model, and the key component residual life prediction result is generated through the component degradation trend model; According to the key component residual life prediction result, the maintenance demand priority is sorted to construct a multi-level maintenance decision tree to obtain a predictive maintenance scheduling scheme; The predictive maintenance scheduling scheme is subjected to cost-benefit analysis to obtain an initial life optimization strategy, and the real-time vehicle state and environmental factors are integrated with the initial life optimization strategy to obtain a predictive maintenance and life optimization scheme.

Images