A global operating variable monitoring and optimized control system and method for an electric vehicle

Abstract

The application relates to the field of new energy vehicles and intelligent control technology, in particular to a global operation variable monitoring and optimization control system and method for an electric vehicle, which comprises a sensor unit, a data acquisition module, an electronic control unit, a control execution unit and a communication module; the sensor unit is used for collecting operation variables of the electric vehicle; the data acquisition module is used for preprocessing the operation variables; the electronic control unit is used for calling an artificial intelligence model for analysis and prediction, and generating a prediction result and a control optimization instruction; the control execution unit is used for dynamically adjusting each execution mechanism; and the communication module is used for realizing data interaction with a remote server or a vehicle networking platform, so as to support remote monitoring, diagnosis and fleet-level management. The application can prevent risks such as overcharging and overdischarging of a battery, motor overheating and brake abnormality in advance, realize global monitoring and dynamic optimization of the running state of the vehicle, and improve the safety, energy efficiency and intelligent level of the electric vehicle.

Description

Technical Field

[0001] This application relates to the fields of new energy vehicles and intelligent control technology, and in particular to a global operating variable monitoring and optimization control system and method for electric vehicles. Background Technology

[0002] With the increasing popularity of new energy vehicles, the safety and energy efficiency of electric vehicles are receiving more and more attention. Electric vehicles involve a large number of key operating parameters (i.e., operational variables) during operation, including battery pack voltage, current, state of charge (SOC), state of health (SOH), motor torque, vehicle speed, braking pressure, and temperature.

[0003] Traditional electric vehicle monitoring systems typically have the following shortcomings:

[0004] 1) Limited monitoring scope: For example, the battery management system (BMS) mainly focuses on battery voltage and SOC, while the power control unit focuses on motor torque and vehicle speed. There is a lack of information sharing between the systems, making it impossible to achieve global optimization.

[0005] 2) Lack of predictive capability: Existing systems are mostly real-time monitoring systems, which are difficult to predict potential risks such as battery overcharging / over-discharging, motor overheating, and abnormal braking in a timely manner, resulting in a lag.

[0006] 3) Insufficient energy management: The allocation between mechanical braking and regenerative braking is often fixed or relies on simple logic, failing to make dynamic adjustments based on battery status and road conditions, resulting in low energy utilization and even the risk of overcharging.

[0007] 4) Lack of remote and intelligent support: Although some models have vehicle networking functions, they often only realize data uploading and lack AI-based intelligent analysis and predictive maintenance functions.

[0008] Therefore, there is an urgent need for a system that can achieve unified monitoring, intelligent prediction, and dynamic optimization control of key operating variables of the entire vehicle in order to improve the safety, energy efficiency, and operational reliability of electric vehicles. Summary of the Invention

[0009] This application provides a global operational variable monitoring and optimization control system and method for electric vehicles, which can prevent risks such as battery overcharging and over-discharging, motor overheating, and abnormal braking in advance, realize global monitoring and dynamic optimization of vehicle operating status, and improve the safety, energy efficiency and intelligence level of electric vehicles.

[0010] To address the aforementioned technical problems, in a first aspect, embodiments of this application provide a global operational variable monitoring and optimization control system for electric vehicles, comprising: a sensor unit, a data acquisition module, an electronic control unit (ECU), a control execution unit, and a communication module connected in sequence; wherein, the sensor unit is used to collect the operational variables of the electric vehicle; the data acquisition module is used to preprocess the operational variables to obtain preprocessed data; the ECU is used to call an artificial intelligence model to analyze and predict based on the preprocessed data, and generate prediction results and control optimization instructions; the control execution unit is used to dynamically adjust each actuator according to the control optimization instructions output by the ECU; the actuators include a battery management system, a motor control system, and a braking system; the communication module is used to realize data interaction with a remote server or vehicle networking platform to support remote monitoring, diagnosis, and fleet-level management.

[0011] In some exemplary embodiments, the operating variables are operational variables involving multiple key parameters during the operation of an electric vehicle; the key parameters include: battery variables, motor variables, vehicle operating variables, and environmental variables.

[0012] In some exemplary embodiments, battery variables include battery pack voltage, current, state of charge (SOC), state of health (SOH), and individual cell temperature; motor variables include motor output torque, speed, winding temperature, and efficiency; vehicle operating variables include vehicle speed, braking pressure, and acceleration; and environmental variables include external temperature, road gradient, and air humidity.

[0013] In some exemplary embodiments, the runtime variables are preprocessed, including filtering, denoising, normalizing, time synchronizing and data fusion of the runtime variables in sequence to obtain feature vectors.

[0014] In some exemplary embodiments, the preprocessed data is input into an artificial intelligence model, which analyzes and predicts the data, and outputs the risk prediction results of the operational variables and the corresponding control optimization instructions.

[0015] In some exemplary embodiments, the control optimization instructions include motor power adjustment instructions, energy recovery ratio adjustment instructions, braking pressure distribution instructions, and battery energy management strategies.

[0016] In some exemplary embodiments, the control execution unit is used to perform the following operations based on the prediction results and control optimization instructions output by the electronic control unit: dynamically adjusting the motor output power and torque limit to prevent the motor from overheating or decreasing in efficiency; adjusting the ratio of mechanical braking and energy recovery braking of the braking system to achieve an optimal balance between braking safety and energy utilization; and triggering a battery protection mechanism when the battery temperature is abnormal, including reducing charging power, equalizing charging and discharging, and thermal management control.

[0017] In some exemplary embodiments, the communication module supports data interaction with a remote server to enable remote real-time monitoring of vehicle operating status, predictive maintenance and diagnosis of vehicle health status, centralized management and energy scheduling at the fleet level, and linkage with a cloud database to support remote updates and iterative optimization of artificial intelligence models.

[0018] Secondly, this application also provides a method for global operational variable monitoring and optimization control of electric vehicles. This method is based on the global operational variable monitoring and optimization control system for electric vehicles described in the above embodiments, and includes the following steps: First, the operating variables of the electric vehicle are collected; then, the operating variables are preprocessed to obtain preprocessed data; next, based on the preprocessed data, an artificial intelligence model is called for analysis and prediction, and prediction results and control optimization instructions are generated; finally, based on the control optimization instructions, each actuator is dynamically adjusted; the actuators include a battery management system, a motor control system, and a braking system; the data is uploaded to the cloud to realize data interaction with a remote server or vehicle networking platform to support remote monitoring, diagnosis, and fleet-level management.

[0019] In some exemplary embodiments, when any operating variable reaches a preset critical threshold, an electronic control unit generates a corresponding active control strategy; the active control strategy includes motor power regulation, energy recovery ratio adjustment, braking pressure distribution, and battery protection measures.

[0020] The technical solution provided in this application has at least the following advantages:

[0021] This application provides a global operating variable monitoring and optimization control system and method for electric vehicles. The system includes: a sensor unit, a data acquisition module, an electronic control unit, a control execution unit, and a communication module connected in sequence. The sensor unit collects the operating variables of the electric vehicle. The data acquisition module preprocesses the operating variables to obtain preprocessed data. The electronic control unit uses the preprocessed data to call an artificial intelligence model for analysis and prediction, and generates prediction results and control optimization instructions. The control execution unit dynamically adjusts each actuator according to the control optimization instructions output by the electronic control unit. The actuators include a battery management system, a motor control system, and a braking system. The communication module enables data interaction with a remote server or vehicle networking platform to support remote monitoring, diagnostics, and fleet-level management.

[0022] The global operating variable monitoring and optimization control system and method for electric vehicles provided in this application have the following beneficial effects:

[0023] (1) Achieve global monitoring by uniformly collecting and monitoring key operating variables of the entire vehicle, such as battery, motor, brake and environment, to avoid system fragmentation.

[0024] (2) Enhance prediction capabilities by using artificial intelligence models to predict time series data and identify risks such as battery overcharging, over-discharging, motor overheating, or abnormal braking in advance.

[0025] (3) Optimize energy management, dynamically adjust the ratio of mechanical braking to regenerative braking, improve energy recovery efficiency and reduce the risk of battery overcharging.

[0026] (4) Improve safety and comfort by issuing control commands in advance before variables reach the critical point, thereby reducing discomfort caused by emergency intervention.

[0027] (5) Supports vehicle networking expansion, interacts with remote servers through communication modules, and supports predictive maintenance and fleet-level management.

[0028] (6) Good engineering adaptability: the system is compatible with existing ECU architecture and can be implemented through software upgrades, reducing integration costs. Attached Figure Description

[0029] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations do not constitute a limitation on the embodiments, and unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0030] Figure 1 This is a schematic diagram of the structure of the global operating variable monitoring and optimization control system for electric vehicles provided in the embodiments of this application.

[0031] Figure 2 This is a flowchart of the runtime variable data acquisition and processing provided in the embodiments of this application.

[0032] Figure 3 This is a schematic diagram of the prediction and optimization control of operating variables provided in the embodiments of this application. Detailed Implementation

[0033] As can be seen from the background technology, traditional electric vehicle monitoring systems suffer from technical problems such as limited monitoring range, lack of predictive capabilities, insufficient energy management, and lack of remote and intelligent support.

[0034] To address the aforementioned technical problems, this application provides a global operational variable monitoring and optimization control system and method for electric vehicles. The system includes: a sensor unit, a data acquisition module, an electronic control unit, a control execution unit, and a communication module connected in sequence. The sensor unit collects the operational variables of the electric vehicle; the data acquisition module preprocesses the operational variables to obtain preprocessed data; the electronic control unit uses the preprocessed data to call an artificial intelligence model for analysis and prediction, generating prediction results and control optimization instructions; the control execution unit dynamically adjusts each actuator according to the control optimization instructions output by the electronic control unit; the actuators include a battery management system, a motor control system, and a braking system; the communication module enables data interaction with a remote server or vehicle networking platform to support remote monitoring, diagnostics, and fleet-level management. This application can proactively prevent risks such as battery overcharging and over-discharging, motor overheating, and abnormal braking, achieving global monitoring and dynamic optimization of the vehicle's operating status, and improving the safety, energy efficiency, and intelligence level of electric vehicles.

[0035] The embodiments of this application will now be described in detail with reference to the accompanying drawings. However, those skilled in the art will understand that many technical details have been provided in the embodiments of this application to facilitate a better understanding of the application. However, the technical solutions claimed in this application can be implemented even without these technical details and various variations and modifications based on the following embodiments.

[0036] See Figure 1 This application provides a global operational variable monitoring and optimization control system for electric vehicles, comprising: a sensor unit, a data acquisition module, an electronic control unit, a control execution unit, and a communication module connected in sequence; wherein, the sensor unit is used to collect the operational variables of the electric vehicle; the data acquisition module is used to preprocess the operational variables to obtain preprocessed data; the electronic control unit is used to call an artificial intelligence model to analyze and predict based on the preprocessed data, and generate prediction results and control optimization instructions; the control execution unit is used to dynamically adjust each actuator according to the control optimization instructions output by the electronic control unit; the actuators include a battery management system, a motor control system, and a braking system; the communication module is used to realize data interaction with a remote server or vehicle networking platform to support remote monitoring, diagnosis, and fleet-level management.

[0037] In some embodiments, the operating variables are operational variables involving multiple key parameters during the operation of an electric vehicle; the key parameters include: battery variables, motor variables, vehicle operating variables, and environmental variables.

[0038] In some embodiments, battery variables include battery pack voltage, current, state of charge, state of health, and individual cell temperature; motor variables include motor output torque, speed, winding temperature, and efficiency; vehicle operating variables include vehicle speed, braking pressure, and acceleration; and environmental variables include external temperature, road gradient, and air humidity.

[0039] Specifically, the global operating variable monitoring and optimization control system for electric vehicles provided in this application collects key operating variables such as battery pack voltage, current, state of charge (SOC), state of health (SOH), motor torque, vehicle speed, braking pressure, and temperature in real time, and uses the artificial intelligence (AI) model embedded in the electronic control unit for fusion analysis and prediction, thereby generating dynamic control commands.

[0040] In some embodiments, the preprocessing of the running variables includes: sequentially filtering, denoising, normalizing, time synchronizing and data fusion of the running variables to obtain a feature vector.

[0041] Specifically, the data acquisition module sequentially filters, denoises, calibrates, and normalizes the multi-source signals acquired by the sensor unit, and finally performs data fusion processing to obtain feature vectors, which are then transmitted to the ECU. The ECU runs an artificial intelligence model to predict trends in the feature vectors and outputs risk prediction results and control optimization instructions.

[0042] In some embodiments, the preprocessed data is input into an artificial intelligence model, which analyzes and predicts the data, and outputs the risk prediction results of the operational variables and the corresponding control optimization instructions.

[0043] Specifically, the inputs to the AI ​​model include multi-source parameters from the battery, motor, vehicle, and environment, while its outputs include risk prediction results for the manipulated variables and control optimization instructions. The AI ​​model predicts future variable trends based on time series analysis methods (such as recurrent neural networks, long short-term memory networks, or attention-based models).

[0044] The control execution unit is used to dynamically adjust the motor output power, braking distribution ratio, and battery thermal management measures according to control optimization instructions.

[0045] In some embodiments, the control optimization instructions include motor power adjustment instructions, energy recovery ratio adjustment instructions, braking pressure distribution instructions, and battery energy management strategies.

[0046] In some embodiments, the control execution unit is configured to perform the following operations based on the prediction results and control optimization instructions output by the electronic control unit: dynamically adjust the motor output power and torque limits to prevent the motor from overheating or decreasing in efficiency; adjust the ratio of mechanical braking and energy recovery braking in the braking system to achieve an optimal balance between braking safety and energy utilization; and trigger a battery protection mechanism when the battery temperature is abnormal, including reducing charging power, equalizing charging and discharging, and thermal management control.

[0047] Specifically, abnormal battery temperature refers to situations where the battery temperature is too high or too low; when the temperature of a single cell / battery pack is ≥45℃, the battery temperature is determined to be too high; when the temperature of a single cell / battery pack is ≤0℃, the battery temperature is determined to be too low.

[0048] In some embodiments, the communication module supports data interaction with a remote server to enable remote real-time monitoring of vehicle operating status, predictive maintenance and diagnosis of vehicle health status, centralized management and energy scheduling at the fleet level, and linkage with a cloud database to support remote updates and iterative optimization of artificial intelligence models.

[0049] This application also provides a method for global operational variable monitoring and optimization control of electric vehicles. This method is based on the global operational variable monitoring and optimization control system for electric vehicles described in the above embodiments, and includes the following steps: First, collecting the operational variables of the electric vehicle; then, preprocessing the operational variables to obtain preprocessed data; next, based on the preprocessed data, calling an artificial intelligence model for analysis and prediction, and generating prediction results and control optimization instructions; finally, based on the control optimization instructions, dynamically adjusting each actuator; the actuators include a battery management system, a motor control system, and a braking system; and uploading the data to the cloud to achieve data interaction with a remote server or vehicle networking platform to support remote monitoring, diagnosis, and fleet-level management.

[0050] In some embodiments, when any operating variable reaches a preset critical threshold, an electronic control unit generates a corresponding active control strategy. The critical thresholds for different operating variables are shown in Table 1.

[0051] Table 1. Categories of runtime variables and their corresponding critical thresholds

[0052]

[0053] Active control strategies include motor power regulation, energy recovery ratio adjustment, braking pressure distribution, and battery protection measures.

[0054] Specifically, proactive control strategies include:

[0055] 1) Limit the peak torque output of the motor to avoid motor overload or overheating.

[0056] 2) Dynamically adjust the distribution ratio of mechanical braking and regenerative braking to prevent overcharging during energy recovery.

[0057] 3) Activate the battery thermal management device (such as liquid cooling or air cooling) to reduce the temperature.

[0058] 4) When the risk is high, provide advance warning to the driver or upload a remote alarm signal.

[0059] The global operating variable monitoring and optimization control system and method for electric vehicles provided in this application will be described in detail below through specific embodiments.

[0060] like Figure 1 As shown, the electric vehicle operation variable monitoring system provided in this application mainly includes:

[0061] The sensor unit includes a voltage sensor, a current sensor, a temperature sensor, a vehicle speed sensor, a brake pressure sensor, and an environmental information acquisition device, used to collect vehicle operating parameters in real time. These operating parameters specifically include: battery voltage, battery current, state of charge (SOC), state of health (SOH), battery temperature, motor torque, speed, and winding temperature, vehicle speed, brake pressure, and external variables such as ambient temperature and road gradient. The sensor unit transmits data to the data acquisition module via an onboard communication bus (such as a CAN bus or Ethernet).

[0062] The data acquisition module, connected to the sensor unit, is used to preprocess multi-source sensor data. Preprocessing includes filtering and noise reduction, zero-point / range calibration, time synchronization, and data fusion. The processed feature data is transmitted to the electronic control unit (ECU) via an internal bus. The feature data includes: real-time battery power, motor power factor, temperature rise rate, SOC / SOH change rate, regenerative braking ratio, and environmental load factor.

[0063] The Electronic Control Unit (ECU), including a central processing unit and memory, integrates an artificial intelligence model. The ECU receives feature data from a data acquisition module, and the AI ​​model, based on time series prediction and pattern recognition algorithms, outputs the following two types of information:

[0064] 1) Predicted values ​​of key variables in a future preset time domain (10~30 seconds), such as predicted battery SOC trend, motor temperature curve, braking pressure fluctuation, etc.

[0065] 2) Corresponding risk assessment results and control optimization instructions. The risk assessment results are quantified using risk level values, and the control optimization instructions include: motor power limiting instructions, brake distribution ratio adjustment instructions, battery thermal management start / stop instructions, etc.

[0066] The control execution unit communicates bidirectionally with the ECU to receive optimized control commands output by the ECU and send execution feedback back to the ECU. This unit includes: a motor controller (MCU), a brake control module (BCU), a battery management system (BMS), and a thermal management execution module. The MCU receives motor power limiting commands and dynamically adjusts the motor torque output; the BCU receives brake distribution commands and adjusts the ratio of mechanical braking to energy recovery; the BMS and thermal management module execute battery cooling / heating operations according to the commands.

[0067] The communication module, connected to the ECU, uploads key operating variables, predicted trends, risk levels, and control strategies to a remote server or cloud platform. It also supports receiving fleet-level management commands from the cloud. The uploaded data packets include: unique vehicle identifier, timestamp, raw data of operating variables, AI model prediction results, and control execution status. This module supports 4G / 5G, V2X, or Ethernet communication. Through this module, the system can achieve remote monitoring, remote diagnostics, and centralized fleet dispatch.

[0068] Figure 2 A flowchart of the operational variable data acquisition and processing is shown. Specifically, the electric vehicle operational variable data acquisition provided in this application embodiment mainly includes the following steps:

[0069] Step S1: Data Acquisition. The sensor unit collects vehicle operating parameters in real time, including battery voltage, current, SOC, SOH, temperature, motor torque, speed, temperature, vehicle speed, braking pressure, and external ambient temperature and road gradient. The data is output at a millisecond-level sampling frequency and transmitted to the data acquisition module via CAN bus or Ethernet.

[0070] Step S2: The data acquisition module preprocesses the raw signals from the sensor unit, including:

[0071] Step S201, Filtering and Denoising: Use low-pass filtering or Kalman filtering to remove acquisition noise.

[0072] Step S202, Calibration and Normalization: Zero-point correction and amplitude normalization are performed on signals such as voltage, current, and speed.

[0073] Step S203, Time Synchronization: Timestamps are aligned on data output from different sensors to ensure consistency in analysis.

[0074] Step S204, Data Fusion: Fusion of multi-sensor data into a unified feature vector, including SOC change rate, motor power factor, braking energy recovery efficiency, etc.

[0075] Figure 3 A flowchart of the predictive and optimized control process for operating variables is shown. Specifically, the electric vehicle operation processing flow provided in this application embodiment mainly includes the following steps:

[0076] Step S1: Feature Extraction. Inside the data acquisition module, the preprocessed data is further subjected to fusion feature extraction, which is then transmitted to the ECU as a high-dimensional input vector.

[0077] 1) Battery-related characteristics: instantaneous power, voltage change rate, and temperature rise rate.

[0078] 2) Motor-related characteristics: torque fluctuation amplitude, temperature gradient, efficiency factor.

[0079] 3) Vehicle-related characteristics: vehicle speed curve, brake pressure change rate.

[0080] 4) Environmental characteristics: external temperature trend, slope factor.

[0081] Step S2: AI Model Prediction and Risk Assessment. The Electronic Control Unit (ECU) calls its internal artificial intelligence model to perform time-series analysis and trend prediction on the input feature vector, obtaining predicted values ​​for operational variables over a future period (e.g., 30-120 seconds). For example, it predicts the battery SOC trend under long downhill energy recovery conditions and the motor temperature rise curve under high-speed conditions. Simultaneously, the ECU calculates the risk level based on the prediction results and generates risk labels such as "Normal," "Warning," and "High Risk." Risk assessment criteria are implemented based on threshold models or probability functions.

[0082] Step S3: Control optimization strategy generation. When a certain operating variable is detected to be about to exceed a preset critical value, the ECU automatically generates control optimization instructions, which include the following aspects:

[0083] 1) Battery-related strategies.

[0084] When it is predicted that the battery's SOC (State of Charge) is about to reach its upper limit (e.g., >95%), the system generates the following control command.

[0085] a. Reduce the energy recovery ratio to avoid overcharging.

[0086] b. Prioritize the use of mechanical braking to replace regenerative braking.

[0087] c. Activate the battery cooling system to reduce the rate of battery temperature rise.

[0088] When the system predicts that the battery SOC is about to be too low (e.g., <10%), it performs the following operations.

[0089] a. Limit power output to extend driving range.

[0090] b. Send a low battery alert to the driver.

[0091] c. Adjust the power distribution of auxiliary electrical equipment.

[0092] When a rapid increase in battery temperature is predicted, the system performs the following operations.

[0093] a. Start the cooling fan or liquid cooling system.

[0094] b. Limit peak charging and discharging current to reduce heat generation.

[0095] 2) Motor-related strategies.

[0096] When the predicted motor winding temperature exceeds the safety threshold, the system performs the following operations.

[0097] a. Limit the peak torque output of the motor.

[0098] b. Start the motor cooling device.

[0099] c. Optimize the motor's operating point to the high-efficiency range to reduce heat generation.

[0100] When a declining trend in motor efficiency is detected, the system performs the following operations.

[0101] a. Adjust the torque distribution between the motor and the reducer.

[0102] b. Optimize shift logic (applicable to multi-speed electric drive systems).

[0103] 3) Braking system related strategies.

[0104] When the predicted braking pressure exceeds the set upper limit or abnormal fluctuations occur, the system performs the following operations.

[0105] a. Optimize the front and rear axle braking force distribution ratio (K f / K r ).

[0106] b. Reduce the proportion of regenerative braking and increase the proportion of mechanical braking.

[0107] c. Trigger the braking system's self-diagnostic function and upload abnormal information.

[0108] When it is predicted that energy recovery braking under long downhill conditions may lead to battery overcharging, the system performs the following operations.

[0109] a. The system prioritizes mechanical braking to balance energy recovery and safety.

[0110] b. Dynamically limit the regenerative braking current.

[0111] 4) Vehicle energy management strategy.

[0112] When the system predicts that the vehicle's energy consumption will be too high under long-distance highway conditions, it will perform the following operations.

[0113] a. Limit the power consumption of high-energy-consuming components such as air conditioners.

[0114] b. Optimize the motor output curve to reduce energy consumption.

[0115] When the predicted range is insufficient to complete the preset trip, the system performs the following operations.

[0116] a. Indicate the location of the nearest charging station to the driver.

[0117] b. Automatically switch to energy-saving mode (Eco mode).

[0118] 5) Environmental adaptation strategies.

[0119] When the predicted external temperature is too low, the system performs the following operations.

[0120] a. Preheat the battery to ensure discharge capacity at low temperatures.

[0121] b. Adjust the battery management strategy to limit instantaneous high current output.

[0122] When a road gradient is predicted to be large, the system performs the following operations.

[0123] a. Optimize motor output power and braking distribution to ensure climbing stability.

[0124] b. During downhill driving, dynamically adjust the energy recovery ratio to avoid overcharging the battery.

[0125] 6) Driver interaction and remote upload.

[0126] While generating control optimization commands, the ECU provides the driver with warning prompts (such as battery high temperature, motor power limitation, and brake distribution adjustment) through the human-machine interface module (HMI).

[0127] Meanwhile, the system uploads predicted trends, risk levels, and control commands to a remote server via a communication module, enabling vehicle-to-everything (V2X) monitoring and fleet-level management.

[0128] Based on the above technical solutions, this application provides a global operating variable monitoring and optimization control system and method for electric vehicles. The system includes: a sensor unit, a data acquisition module, an electronic control unit, a control execution unit, and a communication module connected in sequence. The sensor unit collects the operating variables of the electric vehicle; the data acquisition module preprocesses the operating variables to obtain preprocessed data; the electronic control unit uses the preprocessed data to call an artificial intelligence model for analysis and prediction, and generates prediction results and control optimization instructions; the control execution unit dynamically adjusts each actuator according to the control optimization instructions output by the electronic control unit; the actuators include a battery management system, a motor control system, and a braking system; the communication module enables data interaction with a remote server or vehicle networking platform to support remote monitoring, diagnostics, and fleet-level management.

[0129] The global operating variable monitoring and optimization control system and method for electric vehicles provided in this application have the following beneficial effects:

[0130] (1) Achieve global monitoring by uniformly collecting and monitoring key operating variables of the entire vehicle, such as battery, motor, brake and environment, to avoid system fragmentation.

[0131] (2) Enhance prediction capabilities by using artificial intelligence models to predict time series data and identify risks such as battery overcharging, over-discharging, motor overheating, or abnormal braking in advance.

[0132] (3) Optimize energy management, dynamically adjust the ratio of mechanical braking to regenerative braking, improve energy recovery efficiency and reduce the risk of battery overcharging.

[0133] (4) Improve safety and comfort by issuing control commands in advance before variables reach the critical point, thereby reducing discomfort caused by emergency intervention.

[0134] (5) Supports vehicle networking expansion, interacts with remote servers through communication modules, and supports predictive maintenance and fleet-level management.

[0135] (6) Good engineering adaptability: the system is compatible with existing ECU architecture and can be implemented through software upgrades, reducing integration costs.

[0136] Those skilled in the art will understand that the above-described embodiments are specific examples of implementing this application, and in practical applications, various changes in form and detail may be made without departing from the spirit and scope of this application. Any person skilled in the art can make their own modifications and alterations without departing from the spirit and scope of this application; therefore, the scope of protection of this application should be determined by the scope defined in the claims.

Claims

1. A global operating variable monitoring and optimized control system for an electric vehicle, characterized by, Comprise: sequentially connected sensor unit, data acquisition module, electronic control unit, control execution unit and communication module; wherein, The sensor unit is used to collect the operating variables of the electric vehicle; the operating variables include battery variables, motor variables, vehicle operating variables and environmental variables; The data acquisition module is used to preprocess the operating variables, which includes sequentially filtering, denoising, normalizing, time synchronizing and data fusion on the operating variables, to obtain preprocessed data; the preprocessed data is a feature vector for inputting an artificial intelligence model; The electronic control unit is used to call an artificial intelligence model for analysis and prediction according to the preprocessed data, and output risk prediction results and corresponding control optimization instructions of operating variables; the artificial intelligence model predicts future variable trends based on time series analysis method; The control execution unit is used to dynamically adjust each execution mechanism according to the control optimization instructions output by the electronic control unit; the execution mechanism includes battery management system, motor control system and brake system; the control optimization instructions include motor power adjustment instructions, energy recovery ratio adjustment instructions, brake pressure distribution instructions and battery energy management strategy; The communication module is used to upload operating variables, risk prediction results and control optimization instructions to a remote server or a vehicle networking platform; the risk prediction results include key variable prediction values and risk assessment results in a future preset time domain; the key variable prediction values include the change trend of the predicted battery SOC under long downhill energy recovery working condition, the rising curve of the predicted motor temperature under high speed working condition and brake pressure fluctuation; the uploaded data packet includes vehicle unique identifier, time stamp, operating variable original data, AI model prediction result and control execution state, realizing data interaction with the remote server or the vehicle networking platform, for realizing remote real-time monitoring of vehicle operating state, predictive maintenance and diagnosis of vehicle health state, centralized management and energy scheduling of vehicle fleet level and linkage with cloud database; The communication module is also used to receive the updated artificial intelligence model from the cloud, supporting remote updating and iterative optimization of the artificial intelligence model.

2. The global operational variables monitoring and optimized control system for electric vehicles of claim 1, wherein, The operating variables are operating variables involving various key parameters during the operation of the electric vehicle.

3. The global operational variables monitoring and optimized control system for electric vehicles of claim 2, wherein, The battery variables include battery pack voltage, current, state of charge, health status and single battery temperature; The motor variables include motor output torque, speed, winding temperature and efficiency; The vehicle operating variables include vehicle speed, brake pressure and acceleration; The environmental variables include external temperature, road slope and air humidity.

4. The global operational variables monitoring and optimized control system for electric vehicles of claim 1, wherein, The control execution unit is used to perform the following operations according to the prediction results and control optimization instructions output by the electronic control unit: Dynamically adjust the motor output power and torque limit value to prevent motor overheating or efficiency decline; Adjust the mechanical braking and energy recovery braking ratio of the brake system to achieve optimal balance between braking safety and energy utilization rate; Trigger the battery protection mechanism when the battery temperature is abnormal, including reducing the charging power, balancing charging and discharging, and thermal management control.

5. A method for global operating variable monitoring and optimal control of an electric vehicle, the method being implemented based on the global operating variable monitoring and optimal control system of any one of claims 1 to 4, characterized in that, Comprise the following steps: Collecting operation variables of an electric vehicle; Preprocessing the operation variables to obtain preprocessed data; Based on the preprocessed data, calling an artificial intelligence model for analysis and prediction, and generating a prediction result and a control optimization instruction; Based on the control optimization instruction, dynamically adjusting each actuator, including a battery management system, a motor control system, and a braking system; Uploading data to the cloud to realize data interaction with a remote server or a vehicle networking platform to support remote monitoring, diagnosis, and fleet-level management.

6. The global operational variables monitoring and optimization control method of an electric vehicle of claim 5, wherein, When any operation variable reaches a preset critical threshold, an electronic control unit generates a corresponding active control strategy; The active control strategy includes motor power regulation, energy recovery ratio adjustment, brake pressure distribution, and battery protection measures.

Images