Vehicle core control unit domain control system integrated with networking function

Abstract

The invention discloses a vehicle core control unit domain control system integrated with a networking function, which relates to the technical field of vehicle control, and comprises a networking data fusion module for establishing a multi-source data interaction channel; the domain control collaborative decision-making module is used for generating a global optimization control strategy; the dynamic control execution module is used for adjusting vehicle operation parameters in real time; the remote upgrading operation and maintenance module is used for realizing remote iterative updating of a control algorithm and functional firmware through a network connection channel and synchronously finishing system state diagnosis; and the closed-loop optimization feedback module is used for collecting vehicle operation data, user driving behaviors and environment feedback information and continuously optimizing cross-domain cooperative control logic. According to the invention, through integration of multi-module cooperative work such as network connection data fusion, domain control cooperative decision, dynamic control execution, remote upgrade operation and maintenance and closed-loop optimization feedback, high intelligence and adaptive control of each domain of the vehicle are realized, and further development of an intelligent driving technology is promoted.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and more specifically to a vehicle core control unit domain control system with integrated connectivity functions. Background Technology

[0002] As the automotive industry undergoes a profound transformation towards intelligence and connectivity, traditional vehicle control systems exhibit multi-domain decentralized control characteristics. Systems such as powertrain, chassis, cockpit, and intelligent driving operate independently, lacking cross-domain coordination mechanisms. This leads to issues such as conflicting control strategies and response delays, making them unable to adapt to the comprehensive demands of complex driving scenarios. Current vehicle data collection is limited to a single source on the vehicle itself, failing to fully integrate external data such as cloud-based traffic services and roadside collaborative perception. This results in limited data dimensions and insufficient transmission security, making it difficult to support precise control decisions. Furthermore, control algorithms and firmware upgrades rely on offline after-sales operations, leading to low efficiency, high costs, and a lack of personalized adaptation capabilities based on user driving preferences.

[0003] Furthermore, existing systems mostly employ fixed parameter configurations for control strategies, lacking a closed-loop optimization mechanism based on full lifecycle operational data. This hinders continuous improvement in control accuracy, energy efficiency, and user experience. The data interaction demands brought about by connectivity also expose vehicles to security risks such as cyberattacks and data tampering. Existing protective measures are insufficient to meet the high security requirements of vehicle control. Therefore, there is an urgent need for a vehicle core control unit domain control system that integrates connectivity functions, cross-domain collaboration, closed-loop optimization, and high security to address these technical challenges. Summary of the Invention

[0004] To address the aforementioned technical problems, a vehicle core control unit domain control system with integrated connectivity functions is provided. This technical solution solves the problems described above.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A vehicle core control unit domain control system integrating connected functions includes: a connected data fusion module, a domain control collaborative decision-making module, a dynamic control execution module, a remote upgrade and maintenance module, and a closed-loop optimization feedback module; The connected data fusion module is used to integrate vehicle-side sensor data, cloud service data, and roadside collaborative data to establish a multi-source data interaction channel; The domain control collaborative decision-making module is used to realize cross-domain collaborative control of the power domain, chassis domain, cockpit domain and intelligent driving domain based on fused data, and generate a global optimization control strategy; The dynamic control execution module is used to drive the actuators in each domain to respond precisely based on the results of collaborative decision-making, and adjust the vehicle operating parameters in real time. The remote upgrade and maintenance module is used to remotely iteratively update control algorithms and functional firmware through the network channel, and simultaneously complete system status diagnosis. The closed-loop optimization feedback module is used to collect vehicle operation data, user driving behavior and environmental feedback information to continuously optimize cross-domain collaborative control logic.

[0006] Preferably, the networked data fusion module specifically includes: Multi-source data acquisition unit: acquires real-time operating data from vehicle-mounted millimeter-wave radar, cameras, and inertial navigation; collects user driving habits and operation command behavior data; and receives cloud-based traffic conditions, weather warnings, and collaborative perception data from roadside equipment. Data verification and synchronization unit: Based on the data output from the multi-source data acquisition unit, the data timing is calibrated through a timestamp alignment algorithm, abnormal data is filtered by a CRC32 verification algorithm, and low-latency synchronization of vehicle-cloud-road data is achieved using the 5G-V2X communication protocol to generate a time-consistent valid dataset. Fusion Data Modeling Unit: Based on a time-consistent valid dataset, key parameters of power output, chassis attitude, cabin environment and road conditions are extracted. A full-state vehicle dataset is constructed through feature engineering methods to generate a high-dimensional vehicle operation feature matrix. Security Encryption Unit: Based on the high-dimensional vehicle operation feature matrix and various data during transmission, the unit uses AES-256 end-to-end encryption technology to encrypt the data and completes the data integrity verification through the blockchain distributed node verification mechanism to generate encrypted secure data transmission packets.

[0007] Preferably, the domain controller collaborative decision-making module specifically includes: Cross-domain demand arbitration unit: Based on the high-dimensional vehicle operation feature matrix, it extracts control demand parameters from the power domain, chassis domain, cabin domain and intelligent driving domain, prioritizes them through the analytic hierarchy process, balances the goals of power performance, driving safety, ride comfort and energy economy, and generates conflict-free cross-domain collaborative demand instructions. Scenario-based decision modeling unit: Based on cross-domain collaborative demand instructions and road condition data in the high-dimensional vehicle operation feature matrix, it uses convolutional neural networks to extract road condition image features, combines recurrent neural networks to capture the temporal change patterns of driving scenarios, adapts to the control requirements of different vehicle models through transfer learning methods, establishes a scenario feature library containing key parameters such as road curvature, slope, and traffic flow, and generates scenario recognition results and corresponding basic control logic for the scenario. Dynamic optimization computing unit: Based on scene recognition results, basic control logic, and cross-domain collaborative requirements, it optimizes the control strategy in real time using a model predictive control algorithm. The model formula is as follows: In the formula, To optimize the objective function, for The system state vector at any given time. To control the input vector, , , This is the weight matrix. , These are the parameters of the system state equations. , To control input constraints, , For system state constraints; Decision result output unit: Based on the optimized control strategy parameters, the control commands are classified and organized into power domain, chassis domain, cockpit domain and intelligent driving domain, and synchronously pushed to the dynamic control execution module and cloud system for filing, generating domain control classification control command set.

[0008] Preferably, the construction of decision models for different driving scenarios based on deep learning algorithms specifically includes: A convolutional neural network is used to extract features from road condition image data in a high-dimensional vehicle operation feature matrix to obtain static feature parameters of the road environment; a recurrent neural network is combined to analyze continuous time-series road condition data to capture the dynamic change patterns of driving scenarios and obtain scene time-series feature parameters. By using transfer learning, the pre-trained scene recognition model is adapted to the control parameters of the target vehicle, thereby reducing the amount of training data for the model. By integrating key parameters such as road curvature, slope, and traffic flow, a standardized scene feature library is established. Through feature matching algorithms, scene identification is achieved quickly, and scene category identifiers and corresponding basic control logic are output.

[0009] Preferably, the dynamic control execution module specifically includes: Power domain control unit: Based on the power domain control instructions in the domain control classification control instruction set, it adjusts the engine fuel injection quantity, motor output power and transmission shift logic to generate power output adjustment results; Chassis Domain Control Unit: Based on the chassis domain control commands in the domain control classification control command set, it coordinates the braking system, steering system and suspension system, and generates chassis attitude control results through electro-hydraulic brake control and electric power steering adjustment; Cockpit Domain Control Unit: Based on cockpit domain control commands in the domain control classification control command set, adjusts air conditioning temperature, seat posture and audio effects, and generates cockpit environment adaptation results; Intelligent Driving Domain Control Unit: Based on the intelligent driving domain control commands in the domain control classification control command set, it controls the actuator actions of adaptive cruise control and lane keeping functions, and generates intelligent driving function execution results.

[0010] Preferably, the dynamic control execution module further includes: Real-time feedback adjustment unit: Based on the power output adjustment results, chassis attitude control results, cabin environment adaptation results, and intelligent driving function execution results, it collects real-time response data of each actuator through sensors, compares it with the domain control classification control commands, uses PID algorithm to dynamically correct control parameters, and generates parameter correction commands; Redundant control unit: Based on domain control classification control instructions and parameter correction instructions, it monitors the operating status of the main control channel in real time through dual backup control channels. When the main control channel fails, it switches to the backup channel and generates redundant control execution instructions. Energy consumption optimization unit: Based on real-time road condition data and power domain control requirements in the high-dimensional vehicle operation feature matrix, it dynamically allocates the power output ratio of the engine and motor, and generates energy-optimized power control commands.

[0011] Preferably, the remote upgrade and maintenance module specifically includes: Upgrade Package Management Unit: Based on upgrade package data pushed from the cloud, it verifies the integrity of the upgrade package through a file verification algorithm, confirms the compatibility of the upgrade package with the current system through a version compatibility detection algorithm, supports breakpoint resume technology to resume interrupted upgrade package transmission, and generates verified upgrade package files; Differential upgrade unit: Based on the verified upgrade package file and the current system firmware file, it uses a binary differential algorithm to extract the changed code fragments, transmits differential data through the network channel, and generates incremental upgrade data packets; Remote diagnostic unit: Based on system operation status monitoring data, it automatically identifies abnormal system information through fault code recognition algorithm, establishes fault analysis model in combination with component operation parameters, generates a diagnostic report including fault location and fault cause, and pushes it to the cloud operation and maintenance platform; Upgrade Rollback Unit: Based on the status feedback data during the upgrade process, when an upgrade failure or compatibility issue is detected, the version rollback program is started to restore the previous stable version and generate an upgrade rollback completion confirmation signal.

[0012] Preferably, the closed-loop optimization feedback module specifically includes: Data acquisition unit: Based on power output adjustment results, chassis attitude control results, cabin environment adaptation results, and intelligent driving function execution results, it collects vehicle operating parameters, actuator response data, user operation feedback, and fault information, and organizes them into a complete feedback dataset in a standardized format. Feedback Analysis Unit: Based on the feedback dataset, it identifies deviation data of cross-domain collaborative response delay and energy consumption control accuracy through big data statistical analysis methods, establishes a control effect evaluation system that includes response speed, control accuracy, energy consumption level and user satisfaction, uses the analytic hierarchy process to determine the weight of each evaluation index, and uses the fuzzy comprehensive evaluation method to obtain the comprehensive score of the control strategy, generating the score results and deviation analysis report. Strategy Iteration Unit: Based on the scoring results and deviation analysis report, and combined with industry benchmark data, comparative analysis is conducted to clarify the optimization direction, update the collaborative decision-making model and control algorithm parameters, and complete a strategy iteration optimization every quarter to generate the optimized model and algorithm parameter set; User preference learning unit: Based on user operation feedback data, it records the user's personalized adjustment parameters for vehicle control, establishes a user driving preference profile, and combines the profile data with the control strategy through a preference matching algorithm to generate personalized control adaptation parameters.

[0013] Preferably, the feedback analysis unit specifically includes: extracting raw data from four dimensions—response speed, control accuracy, energy consumption level, and user satisfaction—based on the feedback dataset; constructing a judgment matrix using the analytic hierarchy process (AHP) and calculating the weight coefficients of each evaluation indicator; transforming the raw data into a fuzzy evaluation matrix using the fuzzy comprehensive evaluation method, and calculating the comprehensive score of the control strategy by combining the weight coefficients; calculating the difference between the comprehensive score and preset industry benchmark data, identifying the control links corresponding to the score gap, generating a deviation analysis report, clarifying the optimization direction, and providing data support for strategy iteration.

[0014] Preferably, the network security protection module specifically includes: Firewall Unit: Based on network data packets interconnected with the network, it blocks unauthorized network access through port filtering rules, filters malicious attack data packets using feature matching algorithms, and generates legitimate data packet transmission permission signals; Identity Authentication Unit: Based on the device identity information accessing the system, it uses an asymmetric encryption algorithm for identity verification, and periodically changes the communication key through a dynamic key update mechanism to generate device authentication credentials; Behavior auditing unit: Based on legitimate data packet transmission records and device authentication credentials, it records the time, content, and device identification information of all network-connected interactive behaviors, forming a standardized audit log that supports traceability and querying by time range and device identification. Emergency Response Unit: Based on the attack detection data from the firewall unit and the abnormal behavior records from the behavior audit unit, it automatically cuts off dangerous communication links, activates preset security protection plans, adjusts system communication permissions, generates security emergency handling results, and ensures that vehicle control is not affected.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention proposes a system that integrates multiple modules, including connected data fusion, domain control collaborative decision-making, dynamic control execution, remote upgrade and maintenance, and closed-loop optimization feedback, to achieve highly intelligent and adaptive control across various vehicle domains. Particularly in data fusion and deep learning decision models, cross-domain collaborative optimization is achieved through multi-source data acquisition and advanced algorithms, improving vehicle performance, safety, comfort, and energy efficiency. Simultaneously, the system ensures that the vehicle maintains the optimal control strategy at all times through real-time feedback mechanisms and remote upgrade and maintenance, meeting personalized user needs and promoting the further development of intelligent driving technology. Attached Figure Description

[0016] Figure 1 This is a system framework diagram of the present invention. Detailed Implementation

[0017] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0018] Reference Figure 1 As shown, a vehicle core control unit domain control system with integrated connectivity functions includes: The module includes a network data fusion module, a domain control collaborative decision-making module, a dynamic control execution module, a remote upgrade and maintenance module, and a closed-loop optimization feedback module. The connected data fusion module is used to integrate vehicle-side sensor data, cloud service data, and roadside collaborative data to establish a multi-source data interaction channel; The domain control collaborative decision-making module is used to realize cross-domain collaborative control of the power domain, chassis domain, cockpit domain and intelligent driving domain based on fused data, and generate a global optimization control strategy; The dynamic control execution module is used to drive the actuators in each domain to respond precisely based on the results of collaborative decision-making, and adjust the vehicle operating parameters in real time. The remote upgrade and maintenance module is used to remotely iteratively update control algorithms and functional firmware through the network channel, and simultaneously complete system status diagnosis. The closed-loop optimization feedback module is used to collect vehicle operation data, user driving behavior and environmental feedback information to continuously optimize cross-domain collaborative control logic.

[0019] The network data fusion module specifically includes: Multi-source data acquisition unit: acquires real-time operating data from vehicle-mounted millimeter-wave radar, cameras, and inertial navigation; collects user driving habits and operation command behavior data; and receives cloud-based traffic conditions, weather warnings, and collaborative perception data from roadside equipment. Data verification and synchronization unit: Based on the data output from the multi-source data acquisition unit, the data timing is calibrated through a timestamp alignment algorithm, abnormal data is filtered by a CRC32 verification algorithm, and low-latency synchronization of vehicle-cloud-road data is achieved using the 5G-V2X communication protocol to generate a time-consistent valid dataset. Fusion Data Modeling Unit: Based on a time-consistent valid dataset, key parameters of power output, chassis attitude, cabin environment and road conditions are extracted. A full-state vehicle dataset is constructed through feature engineering methods to generate a high-dimensional vehicle operation feature matrix. Security Encryption Unit: Based on the high-dimensional vehicle operation feature matrix and various data during transmission, the unit uses AES-256 end-to-end encryption technology to encrypt the data, and completes the data integrity verification through the blockchain distributed node verification mechanism to generate encrypted secure data transmission packets. By using multi-source data fusion technology, real-time information from different sensors, cloud services, and roadside collaborative data is integrated, which enhances the accuracy and timeliness of the data. The CRC32 check algorithm and 5G-V2X protocol are used to ensure data synchronization and accuracy, reduce data transmission latency, and improve system responsiveness.

[0020] The domain controller collaborative decision-making module specifically includes: Cross-domain demand arbitration unit: Based on the high-dimensional vehicle operation feature matrix, it extracts control demand parameters from the power domain, chassis domain, cabin domain and intelligent driving domain, prioritizes them through the analytic hierarchy process, balances the goals of power performance, driving safety, ride comfort and energy economy, and generates conflict-free cross-domain collaborative demand instructions. Scenario-based decision modeling unit: Based on cross-domain collaborative demand instructions and road condition data in the high-dimensional vehicle operation feature matrix, it uses convolutional neural networks to extract road condition image features, combines recurrent neural networks to capture the temporal change patterns of driving scenarios, adapts to the control requirements of different vehicle models through transfer learning methods, establishes a scenario feature library containing key parameters such as road curvature, slope, and traffic flow, and generates scenario recognition results and corresponding basic control logic for the scenario. Dynamic optimization computing unit: Based on scene recognition results, basic control logic, and cross-domain collaborative requirements, it optimizes the control strategy in real time using a model predictive control algorithm. The model formula is as follows: In the formula, To optimize the objective function, for The system state vector at any given time. To control the input vector, , , This is the weight matrix. , These are the parameters of the system state equations. , To control input constraints, , For system state constraints; Decision result output unit: Based on the optimized control strategy parameters, the control commands are classified and organized into power domain, chassis domain, cockpit domain and intelligent driving domain, and synchronously pushed to the dynamic control execution module and cloud system for filing, generating a domain control classification control command set; The Analytic Hierarchy Process (AHP) is introduced to arbitrate cross-domain demands, optimizing vehicle power performance, safety, comfort, and energy efficiency from multiple dimensions. Convolutional neural networks and recurrent neural networks are used to model driving scenarios, and deep learning technology is combined to achieve scene recognition and control strategy optimization, adapting to changing driving environments.

[0021] The specific steps for constructing decision models for different driving scenarios based on deep learning algorithms include: A convolutional neural network is used to extract features from road condition image data in a high-dimensional vehicle operation feature matrix to obtain static feature parameters of the road environment; a recurrent neural network is combined to analyze continuous time-series road condition data to capture the dynamic change patterns of driving scenarios and obtain scene time-series feature parameters. By using transfer learning, the pre-trained scene recognition model is adapted to the control parameters of the target vehicle, thereby reducing the amount of training data for the model. By integrating key parameters such as road curvature, slope, and traffic flow, a standardized scene feature library is established. Through feature matching algorithms, scene identification is achieved quickly, and scene category identifiers and corresponding basic control logic are output.

[0022] The dynamic control execution module specifically includes: Power domain control unit: Based on the power domain control instructions in the domain control classification control instruction set, it adjusts the engine fuel injection quantity, motor output power and transmission shift logic to generate power output adjustment results; Chassis Domain Control Unit: Based on the chassis domain control commands in the domain control classification control command set, it coordinates the braking system, steering system and suspension system, and generates chassis attitude control results through electro-hydraulic brake control and electric power steering adjustment; Cockpit Domain Control Unit: Based on cockpit domain control commands in the domain control classification control command set, adjusts air conditioning temperature, seat posture and audio effects, and generates cockpit environment adaptation results; Intelligent Driving Domain Control Unit: Based on the intelligent driving domain control commands in the domain control classification control command set, it controls the actuator actions of adaptive cruise control and lane keeping functions, and generates intelligent driving function execution results.

[0023] The dynamic control execution module further includes: Real-time feedback adjustment unit: Based on the power output adjustment results, chassis attitude control results, cabin environment adaptation results, and intelligent driving function execution results, it collects real-time response data of each actuator through sensors, compares it with the domain control classification control commands, uses PID algorithm to dynamically correct control parameters, and generates parameter correction commands; Redundant control unit: Based on domain control classification control instructions and parameter correction instructions, it monitors the operating status of the main control channel in real time through dual backup control channels. When the main control channel fails, it switches to the backup channel and generates redundant control execution instructions. Energy consumption optimization unit: Based on real-time road condition data and power domain control requirements in the high-dimensional vehicle operation feature matrix, dynamically allocate the power output ratio of the engine and motor, and generate energy-optimized power control commands; A real-time feedback adjustment unit is introduced, which dynamically corrects the control parameters through the PID algorithm to adapt to changes in driving conditions in real time. Redundant control channels and energy consumption optimization units are used to ensure system stability, while optimizing power output and reducing energy consumption under different road conditions.

[0024] The remote upgrade and maintenance module specifically includes: Upgrade Package Management Unit: Based on upgrade package data pushed from the cloud, it verifies the integrity of the upgrade package through a file verification algorithm, confirms the compatibility of the upgrade package with the current system through a version compatibility detection algorithm, supports breakpoint resume technology to resume interrupted upgrade package transmission, and generates verified upgrade package files; Differential upgrade unit: Based on the verified upgrade package file and the current system firmware file, it uses a binary differential algorithm to extract the changed code fragments, transmits differential data through the network channel, and generates incremental upgrade data packets; Remote diagnostic unit: Based on system operation status monitoring data, it automatically identifies abnormal system information through fault code recognition algorithm, establishes fault analysis model in combination with component operation parameters, generates a diagnostic report including fault location and fault cause, and pushes it to the cloud operation and maintenance platform; Upgrade Rollback Unit: Based on the status feedback data during the upgrade process, when an upgrade failure or compatibility issue is detected, the version rollback program is started to restore the previous stable version and generate an upgrade rollback completion confirmation signal.

[0025] The closed-loop optimization feedback module specifically includes: Data acquisition unit: Based on power output adjustment results, chassis attitude control results, cabin environment adaptation results, and intelligent driving function execution results, it collects vehicle operating parameters, actuator response data, user operation feedback, and fault information, and organizes them into a complete feedback dataset in a standardized format. Feedback Analysis Unit: Based on the feedback dataset, it identifies deviation data of cross-domain collaborative response delay and energy consumption control accuracy through big data statistical analysis methods, establishes a control effect evaluation system that includes response speed, control accuracy, energy consumption level and user satisfaction, uses the analytic hierarchy process to determine the weight of each evaluation index, and uses the fuzzy comprehensive evaluation method to obtain the comprehensive score of the control strategy, generating the score results and deviation analysis report. Strategy Iteration Unit: Based on the scoring results and deviation analysis report, and combined with industry benchmark data, comparative analysis is conducted to clarify the optimization direction, update the collaborative decision-making model and control algorithm parameters, and complete a strategy iteration optimization every quarter to generate the optimized model and algorithm parameter set; User preference learning unit: Based on user operation feedback data, it records the user's personalized adjustment parameters for vehicle control, establishes a user driving preference profile, and combines the profile data with the control strategy through a preference matching algorithm to generate personalized control adaptation parameters.

[0026] The feedback analysis unit specifically includes: extracting raw data from four dimensions—response speed, control accuracy, energy consumption level, and user satisfaction—based on the feedback dataset; constructing a judgment matrix using the analytic hierarchy process (AHP) and calculating the weight coefficients of each evaluation indicator; transforming the raw data into a fuzzy evaluation matrix using the fuzzy comprehensive evaluation method, and calculating the comprehensive score of the control strategy by combining the weight coefficients; calculating the difference between the comprehensive score and preset industry benchmark data, identifying the control links corresponding to the score gap, generating a deviation analysis report, clarifying the optimization direction, and providing data support for strategy iteration.

[0027] The network security protection module specifically includes: Firewall Unit: Based on network data packets interconnected with the network, it blocks unauthorized network access through port filtering rules, filters malicious attack data packets using feature matching algorithms, and generates legitimate data packet transmission permission signals; Identity Authentication Unit: Based on the device identity information accessing the system, it uses an asymmetric encryption algorithm for identity verification, and periodically changes the communication key through a dynamic key update mechanism to generate device authentication credentials; Behavior auditing unit: Based on legitimate data packet transmission records and device authentication credentials, it records the time, content, and device identification information of all network-connected interactive behaviors, forming a standardized audit log that supports traceability and querying by time range and device identification. Emergency Response Unit: Based on the attack detection data from the firewall unit and the abnormal behavior records from the behavior audit unit, it automatically cuts off dangerous communication links, activates preset security protection plans, adjusts system communication permissions, generates security emergency handling results, and ensures that vehicle control is not affected.

[0028] In summary, the advantages of this invention are as follows: By integrating multi-source data from vehicles, cloud, and roads through the connected data fusion module, a high-dimensional vehicle operation feature matrix is ​​generated, providing comprehensive data support for domain control collaborative decision-making. The cross-domain demand arbitration unit and the scenario-based decision modeling unit combine deep learning algorithms to achieve conflict-free coordination of multi-domain control needs and accurate identification of different driving scenarios, dynamically optimize control strategies, and make the vehicle's power output, chassis stability, cabin comfort, and intelligent driving functions highly compatible, thereby improving the overall control accuracy. An independent network security protection module is set up, which adopts multiple technologies such as AES-256 end-to-end encryption, blockchain node verification, and asymmetric encryption identity authentication. It forms a full-link protection from data transmission, device access, behavior auditing to emergency response, effectively blocking unauthorized access and malicious attacks, preventing data tampering, ensuring the secure transmission of vehicle control commands and operating data, and avoiding the impact of network security issues on vehicle driving safety. The closed-loop optimization feedback module collects data throughout the entire process and conducts multi-dimensional evaluation and analysis. Combined with user driving preference learning, it regularly updates the collaborative decision-making model and control algorithm parameters to achieve continuous iteration of the control strategy. At the same time, personalized control adaptation parameters enable the system to accurately match the driving habits of different users, taking into account both energy economy and driving comfort. The user experience is gradually optimized over time. The remote upgrade and maintenance module adopts differential upgrade technology and breakpoint resume function, which greatly reduces the amount of data transmitted during upgrade and upgrade time, and realizes remote rapid iteration of control algorithms and functional firmware. Users can obtain new functions and performance optimizations without having to go to the after-sales service outlet. The remote diagnosis and fault analysis function can identify system anomalies in advance, generate accurate diagnostic reports, reduce maintenance costs, improve fault handling efficiency, and ensure stable vehicle operation. The dynamic control execution module is equipped with a real-time feedback adjustment unit and a redundant control unit. It dynamically corrects control parameters through a PID algorithm, and the dual backup design of the key control channels can quickly switch in case of failure of the main channel, ensuring accurate execution of control commands and driving safety. The energy consumption optimization unit dynamically allocates the power output ratio based on real-time road conditions, effectively reducing the vehicle's energy consumption and improving the driving range, which is in line with the trend of energy conservation and environmental protection.

[0029] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A vehicle core control unit domain control system with integrated connectivity functions, characterized in that, include: The module includes a network data fusion module, a domain control collaborative decision-making module, a dynamic control execution module, a remote upgrade and maintenance module, and a closed-loop optimization feedback module. The connected data fusion module is used to integrate vehicle-side sensor data, cloud service data, and roadside collaborative data to establish a multi-source data interaction channel; The domain control collaborative decision-making module is used to realize cross-domain collaborative control of the power domain, chassis domain, cockpit domain and intelligent driving domain based on fused data, and generate a global optimization control strategy; The dynamic control execution module is used to drive the actuators in each domain to respond precisely based on the results of collaborative decision-making, and adjust the vehicle operating parameters in real time. The remote upgrade and maintenance module is used to remotely iteratively update control algorithms and functional firmware through the network channel, and simultaneously complete system status diagnosis. The closed-loop optimization feedback module is used to collect vehicle operation data, user driving behavior and environmental feedback information to continuously optimize cross-domain collaborative control logic.

2. The vehicle core control unit domain control system with integrated connectivity function according to claim 1, characterized in that, The network-connected data fusion module specifically includes: Multi-source data acquisition unit: acquires real-time operating data from vehicle-mounted millimeter-wave radar, cameras, and inertial navigation; collects user driving habits and operation command behavior data; and receives cloud-based traffic conditions, weather warnings, and collaborative perception data from roadside equipment. Data verification and synchronization unit: Based on the data output from the multi-source data acquisition unit, the data timing is calibrated using a timestamp alignment algorithm, and abnormal data is filtered using a CRC32 verification algorithm to generate a valid dataset with consistent timing. Fusion Data Modeling Unit: Based on a time-consistent valid dataset, key parameters of power output, chassis attitude, cabin environment and road conditions are extracted. A full-state vehicle dataset is constructed through feature engineering methods to generate a high-dimensional vehicle operation feature matrix. Security Encryption Unit: Based on the high-dimensional vehicle operation feature matrix and various data during transmission, the unit uses AES-256 end-to-end encryption technology to encrypt the data and completes the data integrity verification through the blockchain distributed node verification mechanism to generate encrypted secure data transmission packets.

3. The vehicle core control unit domain control system with integrated connectivity function according to claim 1, characterized in that, The domain controller collaborative decision-making module specifically includes: Cross-domain demand arbitration unit: Based on the high-dimensional vehicle operation feature matrix, it extracts control demand parameters from the power domain, chassis domain, cabin domain and intelligent driving domain, prioritizes them through the analytic hierarchy process, balances the goals of power performance, driving safety, ride comfort and energy economy, and generates conflict-free cross-domain collaborative demand instructions. Scenario-based decision modeling unit: Based on cross-domain collaborative demand instructions and road condition data in the high-dimensional vehicle operation feature matrix, it uses convolutional neural networks to extract road condition image features, combines recurrent neural networks to capture the temporal change patterns of driving scenarios, adapts to the control requirements of different vehicle models through transfer learning methods, establishes a scenario feature library containing key parameters such as road curvature, slope, and traffic flow, and generates scenario recognition results and corresponding basic control logic for the scenario. Dynamic optimization computing unit: Based on scene recognition results, basic control logic, and cross-domain collaborative requirements, it optimizes the control strategy in real time using a model predictive control algorithm. The model formula is as follows: In the formula, To optimize the objective function, for The system state vector at any given time. To control the input vector, , , This is the weight matrix. , These are the parameters of the system state equations. , To control input constraints, , For system state constraints; Decision result output unit: Based on the optimized control strategy parameters, the control commands are classified and organized into power domain, chassis domain, cockpit domain and intelligent driving domain, and synchronously pushed to the dynamic control execution module and cloud system for filing, generating domain control classification control command set.

4. The vehicle core control unit domain control system with integrated connectivity function according to claim 3, characterized in that, The decision-making models for different driving scenarios constructed based on deep learning algorithms specifically include: A convolutional neural network is used to extract features from road condition image data in a high-dimensional vehicle operation feature matrix to obtain static feature parameters of the road environment; a recurrent neural network is combined to analyze continuous time-series road condition data to capture the dynamic change patterns of driving scenarios and obtain scene time-series feature parameters. By using transfer learning, the pre-trained scene recognition model is adapted to the control parameters of the target vehicle, thereby reducing the amount of training data for the model. By integrating key parameters such as road curvature, slope, and traffic flow, a standardized scene feature library is established. Through feature matching algorithms, scene identification is achieved quickly, and scene category identifiers and corresponding basic control logic are output.

5. The vehicle core control unit domain control system with integrated connectivity function according to claim 1, characterized in that, The dynamic control execution module specifically includes: Power domain control unit: Based on the power domain control instructions in the domain control classification control instruction set, it adjusts the engine fuel injection quantity, motor output power and transmission shift logic to generate power output adjustment results; Chassis Domain Control Unit: Based on the chassis domain control commands in the domain control classification control command set, it coordinates the braking system, steering system and suspension system, and generates chassis attitude control results through electro-hydraulic brake control and electric power steering adjustment; Cockpit Domain Control Unit: Based on cockpit domain control commands in the domain control classification control command set, adjusts air conditioning temperature, seat posture and audio effects, and generates cockpit environment adaptation results; Intelligent Driving Domain Control Unit: Based on the intelligent driving domain control commands in the domain control classification control command set, it controls the actuator actions of adaptive cruise control and lane keeping functions, and generates intelligent driving function execution results.

6. The vehicle core control unit domain control system with integrated connectivity function according to claim 5, characterized in that, The dynamic control execution module further includes: Real-time feedback adjustment unit: Based on the power output adjustment results, chassis attitude control results, cabin environment adaptation results, and intelligent driving function execution results, it collects real-time response data of each actuator through sensors, compares it with the domain control classification control commands, uses PID algorithm to dynamically correct control parameters, and generates parameter correction commands; Redundant control unit: Based on domain control classification control instructions and parameter correction instructions, it monitors the operating status of the main control channel in real time through dual backup control channels. When the main control channel fails, it switches to the backup channel and generates redundant control execution instructions. Energy consumption optimization unit: Based on real-time road condition data and power domain control requirements in the high-dimensional vehicle operation feature matrix, it dynamically allocates the power output ratio of the engine and motor, and generates energy-optimized power control commands.

7. The vehicle core control unit domain control system with integrated connectivity function according to claim 1, characterized in that, The remote upgrade and maintenance module specifically includes: Upgrade Package Management Unit: Based on upgrade package data pushed from the cloud, it verifies the integrity of the upgrade package through a file verification algorithm, confirms the compatibility of the upgrade package with the current system through a version compatibility detection algorithm, and generates a verified upgrade package file; Differential upgrade unit: Based on the verified upgrade package file and the current system firmware file, it uses a binary differential algorithm to extract the changed code fragments, transmits differential data through the network channel, and generates incremental upgrade data packets; Remote diagnostic unit: Based on system operation status monitoring data, it automatically identifies abnormal system information through fault code recognition algorithms and pushes it to the cloud operation and maintenance platform; Upgrade Rollback Unit: Based on the status feedback data during the upgrade process, when an upgrade failure is detected, the version rollback procedure is initiated.

8. The vehicle core control unit domain control system with integrated connectivity function according to claim 1, characterized in that, The closed-loop optimization feedback module specifically includes: Data acquisition unit: Based on power output adjustment results, chassis attitude control results, cabin environment adaptation results, and intelligent driving function execution results, it collects vehicle operating parameters, actuator response data, user operation feedback, and fault information, and organizes them into a complete feedback dataset in a standardized format. Feedback Analysis Unit: Based on the feedback dataset, it identifies deviation data of cross-domain collaborative response delay and energy consumption control accuracy through big data statistical analysis methods, establishes a control effect evaluation system that includes response speed, control accuracy, energy consumption level and user satisfaction, uses the analytic hierarchy process to determine the weight of each evaluation index, and uses the fuzzy comprehensive evaluation method to obtain the comprehensive score of the control strategy, generating the score results and deviation analysis report. Strategy Iteration Unit: Based on the scoring results and deviation analysis report, and combined with industry benchmark data, comparative analysis is conducted to clarify the optimization direction, update the collaborative decision-making model and control algorithm parameters, and complete a strategy iteration optimization every quarter to generate the optimized model and algorithm parameter set; User preference learning unit: Based on user operation feedback data, it records the user's personalized adjustment parameters for vehicle control, establishes a user driving preference profile, and combines the profile data with the control strategy through a preference matching algorithm to generate personalized control adaptation parameters.

9. The vehicle core control unit domain control system with integrated connectivity function according to claim 8, characterized in that, The feedback analysis unit specifically includes: extracting raw data from four dimensions—response speed, control accuracy, energy consumption level, and user satisfaction—based on the feedback dataset; constructing a judgment matrix using the analytic hierarchy process (AHP); calculating the weight coefficients of each evaluation indicator; transforming the raw data into a fuzzy evaluation matrix using the fuzzy comprehensive evaluation method; calculating the comprehensive score of the control strategy by combining the weight coefficients; calculating the difference between the comprehensive score and preset industry benchmark data; identifying the control links corresponding to the score gap; and generating a deviation analysis report.

10. The vehicle core control unit domain control system with integrated connectivity function according to claim 1, characterized in that, The network security protection module specifically includes: Firewall Unit: Based on network data packets interconnected with the network, it blocks unauthorized network access through port filtering rules and filters malicious attack data packets using feature matching algorithms; Identity Authentication Unit: Based on the device identity information accessing the system, it uses an asymmetric encryption algorithm for identity verification, and periodically changes the communication key through a dynamic key update mechanism to generate device authentication credentials; Behavior auditing unit: Based on legitimate data packet transmission records and device authentication credentials, it records the time, content, and device identification information of all network-connected interactive behaviors; Emergency Response Unit: Based on the attack detection data from the firewall unit and the abnormal behavior records from the behavior audit unit, it automatically cuts off dangerous communication links, activates preset security protection plans, adjusts system communication permissions, and generates security emergency handling results.

Images