OBD-II integrated regenerative braking optimization system based on SOC and driving conditions

Abstract

An OBD-II integrated regenerative braking optimization system based on the state of charge (SOC) and driving conditions, consisting of: an OBD-II interface configured to collect real-time vehicle data, including battery charge level, vehicle speed, acceleration and deceleration rates, engine load, road gradient, and ambient temperature; a processing unit operatively connected to the OBD-II interface, the processing unit configured to: to perform a SoC analysis to determine permissible limits for regenerative braking, analyze driving conditions to evaluate road and vehicle dynamics, and execute an optimization algorithm to calculate ideal regenerative braking parameters based on the acquired data; a control module operatively connected to the processing unit and the electronic control unit (ECU) of a vehicle, the control module configured to adjust the regenerative braking force based on the calculated parameters to ensure energy recovery without exceeding battery limits or compromising vehicle stability; a user interface configured to provide real-time feedback to the driver, including current regenerative braking performance, recovered energy, battery charge level, and recommended driving behavior to improve energy efficiency.

Description

[0001] The present invention relates to the field of automotive braking systems, particularly regenerative braking technologies in electric and hybrid vehicles. More specifically, it is an optimization system that integrates on-board diagnostics (OBD-II) data with real-time vehicle parameters such as state of charge (SoC), speed, acceleration, and road gradient to dynamically control and optimize regenerative braking performance.

[0002] Electric and hybrid vehicles often use regenerative braking systems to recover kinetic energy during deceleration and convert it into electrical energy, which is stored in the vehicle's battery. While these systems offer significant energy savings, their performance is significantly affected by variables such as the vehicle's state of charge (SoC), driving behavior, road gradient, and traffic conditions. Conventional regenerative braking systems typically operate with fixed control algorithms and cannot adapt in real time to changing environmental and operating conditions. This results in suboptimal energy recovery, reduced battery life, and limited braking performance. For example, a high state of charge can lead to overcharging risks, while steep road gradients require adaptive modulation of braking force, which conventional systems cannot provide.

[0003] Existing solutions have not yet fully integrated real-time diagnostic data from the vehicle's On-Board Diagnostic II (OBD-II) interface to dynamically adjust regenerative braking performance. While several systems and patents describe regenerative braking technologies, most are based on static logic or driver-based manual controls, limiting their responsiveness and energy optimization potential. There remains a need for an intelligent, real-time regenerative braking optimization system that leverages OBD-II data to continuously adjust braking parameters. This includes considering the current battery state of charge, vehicle dynamics, and environmental feedback to improve braking performance, maximize energy recovery, and maintain battery health.

[0004] To solve this problem, the present invention provides an OBD-II integrated system for optimizing regenerative braking based on the state of charge (SOC) and driving conditions.

[0005] The system dynamically adjusts braking parameters in real time based on the current state of charge (SoC) and driving conditions.

[0006] The system aims to improve the energy efficiency of electric and hybrid vehicles by calculating and applying optimal regenerative braking force based on real-time vehicle telemetry data such as speed, acceleration, gradient and battery status.

[0007] The system ensures the condition and longevity of the battery by preventing overcharging or deep discharge during regenerative braking through intelligent control logic based on charge level monitoring.

[0008] The system includes a processing unit that can analyze OBD-II data using rule-based logic or machine learning algorithms to calculate and apply context-specific braking parameters.

[0009] The system also enables adaptive braking control that takes into account different road and traffic conditions, thereby improving driver safety, vehicle stability and energy efficiency.

[0010] The system also includes a user interface configured to provide the driver with real-time feedback on regenerative braking performance, energy recovery, and recommended driving behavior for optimal energy utilization.

[0011] The system supports industrial applicability as it is compatible with a wide range of electric and hybrid vehicles and is scalable for integration into future autonomous driving platforms.

[0012] The system supports industrial applicability as it is compatible with a wide range of electric and hybrid vehicles and is scalable for integration into future autonomous driving platforms.

[0013] In one embodiment, the present invention provides an OBD-II integrated regenerative braking optimization system based on state of charge (SOC) and driving conditions. The present invention provides a regenerative braking optimization system that seamlessly integrates with a vehicle's on-board diagnostics (OBD-II) interface to dynamically adjust regenerative braking force based on battery state of charge (SoC) and real-time driving conditions. The system is designed to enhance energy recovery, preserve battery health, and maintain vehicle stability in varying terrain and traffic conditions.

[0014] The system includes an OBD-II interface for collecting live vehicle data such as state of charge (SoC), speed, acceleration, road gradient, and ambient temperature. A processing unit is configured to analyze the collected data and calculate optimal regenerative braking parameters using rule-based logic or machine learning models. The system further includes a control module connected to the vehicle's electronic control unit (ECU) to dynamically apply the calculated braking force. Additionally, a user interface is provided to display real-time system status, energy recovery statistics, battery charge level, and driver suggestions for maximizing energy efficiency.During operation, the system continuously monitors driving data and battery parameters, adjusts regenerative braking force accordingly, and ensures that braking performance remains efficient, safe, and responsive. By preventing battery overcharging at high SoC levels and maximizing energy recovery during deceleration, the system provides an intelligent, adaptive solution for next-generation electric and hybrid vehicles. The invention is compatible with various vehicle architectures and can be used in both manually controlled and autonomous vehicles. It represents a significant evolution over conventional fixed-response regenerative braking systems by introducing an intelligent, SoC-aware, real-time adaptive braking control mechanism.

[0015] The invention is explained again below with reference to the figures. They show: Fig. : a schematic representation of a regenerative braking system. Fig. : the system architecture diagram of the proposed regenerative braking optimization. Fig. : a representation of the workflow of the brake optimization model

[0016] Fig. shows a schematic representation of a regenerative braking system (100). In this configuration, the vehicle's kinetic energy is captured during braking by a traction motor operating in generator mode. The rotational movement of the wheels drives the electric motor, which converts the kinetic energy into electrical energy. This energy is then transferred through an inverter (acting as an AC-to-DC converter) and stored in the battery pack for later use. The control unit coordinates the operation of the motor, inverter, and battery to ensure optimal energy recovery, taking into account the braking force demand and battery capacity. The schematic also includes mechanical braking components that work in conjunction with regenerative braking to meet the total braking demand.

[0017] Fig. illustrates the system architecture diagram (101) of the proposed regenerative braking optimization. It begins with an OBD-II interface connected to the vehicle's diagnostic port, which collects real-time vehicle data such as SoC, speed, acceleration, and road gradient. An ELM 327 scanner or similar OBD-II interpreter transmits this data to a processing module, where it is analyzed by a predictive artificial intelligence model. The AI ​​model calculates optimal regenerative braking parameters based on predefined rules or learned behaviors. These parameters are then sent to the regenerative braking control system, which is connected to the vehicle's electronic control unit (ECU), to modulate the actual braking force.This architecture enables continuous feedback and adjustment of braking parameters in response to driving conditions in real time.

[0018] Fig.shows a representation of the braking optimization model's workflow (103). The model begins by collecting inputs such as the current driving scenario and the battery's state of charge (SoC). Based on these inputs, it calculates the optimal regenerative braking force. The braking system then applies this calculated force, and the result—such as the recovered energy or the deviation from the desired performance—is evaluated. This evaluation is used as feedback to reoptimize the model parameters, enabling learning and continuous improvement. The feedback loop ensures that the braking system can dynamically adapt to changing road conditions, vehicle status, and battery health, optimizing energy recovery while maintaining vehicle stability and braking performance.

[0019] The present invention discloses a regenerative braking optimization system integrated with the vehicle's on-board diagnostic interface II (OBD-II) to enhance energy recovery and optimize braking performance in electric and hybrid vehicles. The system is designed to dynamically modify regenerative braking force based on the vehicle's real-time state of charge (SoC) and current driving conditions, thereby eliminating the inefficiencies of conventional fixed logic. The regenerative braking optimization system includes four core components that work together to provide adaptive, real-time control of braking force based on vehicle conditions. The heart of the system is the OBD-II interface, which is connected to the vehicle's on-board diagnostic port.This interface serves as the primary data acquisition unit and continuously records key operating parameters such as battery state of charge (SoC), vehicle speed and acceleration, engine load, throttle position, ambient temperature, deceleration rate, and road gradient, which are determined via GPS or onboard sensors.

[0020] The system is connected to the vehicle's On-Board Diagnostics II (OBD-II) port to access real-time operating data critical for optimizing regenerative braking. Key parameters collected include the battery's state of charge (SoC), vehicle speed, acceleration and deceleration rates, engine load, road gradient—derived from GPS or onboard sensors—and ambient temperature. This continuous data stream forms the basis for intelligent braking control. Once received, the data is processed by a dedicated processing unit that serves as the system's computing core. The processing unit performs several key analytical functions. First, it performs SoC analysis to determine the current battery capacity and calculate the maximum allowable regenerative braking force to prevent overcharging.It then performs a driving condition analysis and dynamically adjusts the braking force based on variables such as road gradient, traffic patterns, and vehicle dynamics. Finally, an optimization algorithm—which can be rule-based or implemented using machine learning techniques—calculates the ideal regenerative braking force that maximizes energy recovery while maintaining vehicle stability and battery health. The calculated parameters are then transferred to a control module directly connected to the vehicle's electronic control unit (ECU). The control module makes the necessary adjustments to the regenerative braking system, ensuring that the braking force is optimized according to the vehicle's operating conditions and system limitations.To enhance user interaction and provide actionable feedback, the system features a user interface that can be delivered via the vehicle's dashboard display or a mobile application. This interface provides the driver with real-time information, including the current performance of regenerative braking, the amount of energy recovered during braking, the battery charge level, and driving behavior recommendations to further optimize energy efficiency. The integration of this feedback loop not only enhances the driving experience but also contributes to the system's continuous learning and performance optimization. List of reference symbols 100 systems

Claims

[1] An OBD-II integrated regenerative braking optimization system based on the state of charge (SOC) and driving conditions, consisting of: an OBD-II interface configured to collect real-time vehicle data, including battery charge level, vehicle speed, acceleration and deceleration rates, engine load, road gradient, and ambient temperature; a processing unit operatively connected to the OBD-II interface, the processing unit configured to: to perform a SoC analysis to determine permissible limits for regenerative braking, analyze driving conditions to evaluate road and vehicle dynamics, and execute an optimization algorithm to calculate ideal regenerative braking parameters based on the acquired data; a control module operatively connected to the processing unit and the electronic control unit (ECU) of a vehicle, the control module configured to adjust the regenerative braking force based on the calculated parameters to ensure energy recovery without exceeding battery limits or compromising vehicle stability; a user interface configured to provide real-time feedback to the driver, including current regenerative braking performance, recovered energy, battery charge level, and recommended driving behavior to improve energy efficiency. [2] The system of claim 1, wherein the optimization algorithm in the processing unit comprises a machine learning model trained using historical driving data and real-time telemetry data to adaptively calculate braking parameters. [3] The system of claim 1, wherein the processing unit is configured to prevent overcharging of the battery by reducing the regenerative braking force when the state of charge (SoC) of the battery exceeds a predefined threshold. [4] The system of claim 1, wherein the control module is configured to communicate with the vehicle's electronic control unit (ECU) to transmit braking torque commands to the electric motor controller and the inverter. [5] The system of claim 1, wherein the user interface comprises a graphical dashboard display or a mobile application for presenting regenerative braking metrics and driver instructions. [6] The system of claim 1, wherein the optimization algorithm includes predictive braking control logic configured to predict changes in road gradient and adjust braking force accordingly. [7] The system of claim 1, wherein the road gradient is derived from GPS data and on-board inertial measurement sensors integrated into the vehicle control system. [8] The system of claim 1, wherein the user interface is further configured to provide real-time warnings or suggestions for optimal acceleration and deceleration to maximize energy recovery.

Images