A system for intelligent fault detection and energy management in fuel cell hybrid electric vehicles (FCHEVs)

Abstract

A system (100) for intelligent fault detection and energy management in fuel cell hybrid electric vehicles (FCHEVs), comprising: a data acquisition unit (102) comprising sensors (102a) configured to acquire real-time operational data from vehicle components; an energy management unit (104) comprising a fuel cell unit configured to generate electricity from hydrogen and a battery unit configured to store and supply electrical energy; a regenerative braking system (106) in conjunction with an energy management unit (104) configured to recover and store energy during vehicle deceleration; a centralized processing unit (108) configured to perform functions of the system (100) based on data acquired by the sensors (102a), wherein the centralized processing unit (108) comprises the following: a neural network processor (108a) configured to analyze real-time operational data for fault prediction; an energy optimization processor (108b) configured to dynamically manage power distribution; a maintenance prediction processor (108c) configured to identify potential component failures; a communication interface (110) configured to enable data exchange between vehicle and infrastructure (V2I) and between vehicles (V2V); a driver interface (112) configured to display system status and receive user input; and a control unit (114) configured to perform corrective actions based on neural network analysis and energy optimization calculations.

Description

FIELD OF THE INVENTION

[0001] The present disclosure relates to the field of electric vehicles, particularly to improved energy management and fault diagnosis. More specifically, the present invention relates to a system for intelligent fault detection and energy management in fuel cell hybrid electric vehicles (FCHEVs). BACKGROUND OF THE INVENTION

[0002] Fuel cell hybrid electric vehicles (FCHEVs) combine fuel cell and electric propulsion technologies, offering sustainable mobility with extended range. However, due to their complex integrated systems, these vehicles face significant challenges in fault diagnosis and energy management.

[0003] Conventional FCHEV systems use reactive approaches to fault detection and only react when problems occur, resulting in performance degradation, increased energy consumption, and vehicle downtime. Furthermore, current energy management systems struggle to optimally adapt to dynamic driving conditions and environmental factors, resulting in suboptimal performance and premature component degradation.

[0004] While existing patents such as US9501917B2 and US9610672B2 have attempted to address these challenges, they focus on isolated aspects of vehicle management without providing comprehensive solutions that integrate both fault detection and energy management. The limitations of these approaches underscore the need for a more sophisticated system that can proactively control vehicle operation.

[0005] This invention addresses these limitations by implementing an AI-driven system that combines IoT sensors with advanced machine learning algorithms. The system enables proactive failure prediction and intelligent energy management, going beyond the reactive approach of conventional systems. By continuously analyzing real-time data from various vehicle components, the system can predict potential failures before they affect performance and optimize energy distribution throughout the hybrid powertrain, improving vehicle efficiency, reliability, and sustainability. SUMMARY OF THE INVENTION

[0006] The present disclosure relates to a system for intelligent fault detection and energy management in fuel cell hybrid electric vehicles (FCHEVs). The invention integrates fault detection and energy management using Internet of Things (IoT)-based data acquisition, coupled with sophisticated analytics within a higher-level controller. This system intelligently manages vehicle operation in various hybrid modes and uses state-of-the-art algorithms for energy management strategies to significantly improve vehicle efficiency, reliability, and safety. This revision sharpens the focus on the advanced AI, IoT, and energy management aspects of the invention while clearly articulating the system's purpose of improving the performance of FCHEVs.

[0007] The present disclosure aims to provide a system for intelligent fault detection and energy management in fuel cell hybrid electric vehicles (FCHEVs). The system includes: a data acquisition unit with sensors configured to acquire real-time operating data from vehicle components; an energy management unit with a fuel cell unit configured to generate electricity from hydrogen and a battery unit configured to store and deliver electrical energy; a regenerative braking system in conjunction with an energy management unit configured to recover and store energy during vehicle deceleration;a central processing unit configured to perform system functions based on the data acquired by the sensors, the central processing unit comprising a neural network processor configured to analyze the real-time operating data for failure prediction, an energy optimization processor configured to dynamically manage energy distribution, and a maintenance prediction processor configured to detect potential component failures; a communication interface configured to enable vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) data exchange; a driver interface configured to display system status and receive user inputs;and a control unit configured to execute corrective actions based on the neural network analysis and the energy optimization calculations.;

[0008] An objective of the present disclosure is to provide a system for intelligent fault detection and energy management in fuel cell hybrid electric vehicles (FCHEVs).

[0009] Another objective of the present disclosure is to provide an advanced AI-based system that integrates fault detection, predictive maintenance, and energy management to optimize the operation of fuel cell hybrid electric vehicles.

[0010] Another objective of the present disclosure is to improve vehicle safety by predicting potential failures before they occur and automatically initiating corrective actions, thereby reducing the likelihood of unexpected failures and improving overall vehicle reliability.

[0011] A further objective of the present disclosure is to optimize the energy distribution between the fuel cell and the battery to ensure that the vehicle operates with maximum efficiency under different driving conditions, thereby increasing the driving range and reducing the environmental impact.

[0012] Another objective of the present disclosure is to provide predictive maintenance capabilities that enable proactive scheduling of maintenance tasks, reduce vehicle downtime, and improve the overall driver experience.

[0013] Another objective of the present disclosure is to incorporate deep learning algorithms and real-time data processing to enable data-driven decision making that improves both the safety and efficiency of FCHEVs.

[0014] Another objective of this disclosure is to provide real-time feedback to the driver. The system aims to provide users with information that can help them make informed decisions regarding their driving behavior, thus further optimizing the vehicle's performance and efficiency.

[0015] Another objective of the present disclosure is to improve predictive capabilities by integrating external data via V2I and V2V communication to enable more accurate predictions and better-informed decision-making in real-time driving scenarios.

[0016] To further clarify the advantages and features of the present disclosure, a more detailed description of the invention will be given with reference to specific embodiments thereof illustrated in the accompanying drawings. It should be noted that these drawings represent only typical embodiments of the invention and are therefore not to be considered limiting its scope. The invention will be described and explained in additional detail and in greater detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE CHARACTERS

[0017] These and other features, aspects, and advantages of the present disclosure will be better understood when the following detailed description is read with reference to the accompanying drawings, in which like characters represent like parts throughout. Fig. 1 shows a block diagram of a system for intelligent fault detection and energy management in fuel cell hybrid electric vehicles (FCHEVs) according to an embodiment of the present disclosure; Fig. 2 shows a block diagram of the IoT-based data acquisition architecture for condition monitoring and energy management strategy in fuel cell hybrid electric vehicles (FCHEVs) according to an embodiment of the present disclosure; Fig. 3 is a block diagram illustrating the communication structure between various controllers within FCHEVs, highlighting the hierarchical control system from top to bottom level, according to one embodiment of the present disclosure; Fig. 4 shows a block diagram illustrating the operation of machine learning and AI algorithms in FCHEVs, with a focus on fault classification and energy management, according to an embodiment of the present disclosure; Fig. 5 shows a block diagram of the failure prediction system using artificial neural networks (ANN) in FCHEVs according to an embodiment of the present disclosure; Fig. 6 shows a block diagram of the energy management and control mechanism in FCHEVs according to an embodiment of the present disclosure; and Fig. 7 shows a block diagram illustrating the operation of the ANN-based learning processing unit used to manage FCHEV energy distribution and fault prediction according to an embodiment of the present disclosure.

[0018] Furthermore, those skilled in the art will appreciate that elements in the drawings are shown for convenience and may not necessarily be drawn to scale. For example, the flowcharts illustrate the method by key steps to enhance understanding of aspects of the present disclosure. Moreover, with respect to device construction, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details relevant to understanding embodiments of the present disclosure in order not to clutter the drawings with details that would be readily apparent to those skilled in the art who would benefit from the description herein. DETAILED DESCRIPTION:

[0019] To facilitate an understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the drawings and described in specific language. It is to be understood, however, that this is not intended to limit the scope of the invention, as such changes and further modifications to the illustrated system and such further applications of the principles of the invention as illustrated therein are contemplated as would normally occur to one skilled in the art to which the invention pertains.

[0020] It will be understood by one skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not intended to be limiting thereof.

[0021] References in this specification to "one aspect," "another aspect," or similar language mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Therefore, occurrences of the phrase "in one embodiment," "in another embodiment," and similar language throughout this specification may or may not all refer to the same embodiment.

[0022] The terms "comprises," "comprising," or other variations thereof are intended to cover non-exclusive inclusion, such that a process or method comprising a list of steps not only includes those steps, but may also include other steps not expressly listed or inherent in such process or method. Likewise, one or more devices or subsystems or elements or structures or components preceded by "comprises...a" does not preclude, without further limitation, the existence of other devices or other subsystems or other elements or other structures or other components or additional devices or additional subsystems or additional elements or additional structures or additional components.

[0023] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The system, methods, and examples provided herein are for illustrative purposes only and should not be considered limiting.

[0024] Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0025] The functional units described in this specification have been referred to as devices. A device may be implemented in programmable hardware devices such as processors, digital signal processors, central processing units, field-programmable gate arrays, programmable array logic, programmable logic devices, cloud processing systems, or the like. The devices may also be implemented in software for execution by various types of processors. An identified device may contain executable code and may, for example, comprise one or more physical or logical blocks of computer instructions, which may be organized, for example, as an object, procedure, function, or other construct.However, the executable file of an identified device need not be physically located together, but may comprise different instructions stored in different locations which, when logically linked together, constitute the device and fulfill the stated purpose of the device.

[0026] Indeed, executable code of a device or module may be a single instruction or multiple instructions, and may even be distributed across several different code segments, among different applications, and across multiple storage devices. Similarly, operational data may be identified and represented within the device and embodied in any suitable form and organized in any suitable type of data structure. The operational data may be captured as a single set of data or distributed across different locations, including different storage devices, and may exist, at least in part, as electronic signals in a system or network.

[0027] References in this specification to "a selected embodiment," "an embodiment," or "an embodiment" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the disclosed subject matter. Therefore, the appearances of the phrases "a selected embodiment," "in an embodiment," or "in an embodiment" in various places in this specification do not necessarily refer to the same embodiment.

[0028] Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to provide a thorough understanding of embodiments of the disclosed subject matter. However, one of ordinary skill in the art will recognize that the disclosed subject matter may be practiced without one or more of the specific details, or with different methods, components, materials, etc. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of the disclosed subject matter.

[0029] According to the example embodiments, the disclosed computer programs or modules may be executed in many example ways, for example, as an application stored in the memory of a device or as a hosted application running on a server and communicating with the device application or browser using a variety of standard protocols such as TCP / IP, HTTP, XML, SOAP, REST, JSON, and other suitable protocols. The disclosed computer programs may be written in example programming languages ​​that execute from memory on the device or from a hosted server, for example, BASIC, COBOL, C, C++, Java, Pascal, or scripting languages ​​such as JavaScript, Python, Ruby, PHP, Perl, or other suitable programming languages.

[0030] Some of the disclosed embodiments comprise or otherwise involve data transmission over a network, such as communicating various inputs or files over the network. The network may comprise, for example, one or more of the following: the Internet, wide area networks (WANs), local area networks (LANs), analog or digital wired and wireless telephone networks (e.g., a PSTN, Integrated Services Digital Network (ISDN), a cellular network, and Digital Subscriber Line (xDSL)), radio, television, cable, satellite, and / or any other delivery or tunneling mechanism for transmitting data. The network may comprise multiple networks or subnetworks, each of which may comprise, for example, a wired or wireless data path. The network may comprise a circuit-switched voice network, a packet-switched data network, or any other network capable of transmitting electronic communications.For example, the network may include networks based on Internet Protocol (IP) or Asynchronous Transfer Mode (ATM), and may support voice using, for example, VoIP, Voice over ATM, or other comparable protocols used for voice data communications. In one implementation, the network includes a cellular network configured for the exchange of text or SMS messages.

[0031] Examples of the network include, but are not limited to, a Personal Area Network (PAN), a Storage Area Network (SAN), a Home Area Network (HAN), a Campus Area Network (CAN), a Local Area Network (LAN), a Wide Area Network (WAN), a Metropolitan Area Network (MAN), a Virtual Private Network (VPN), an Enterprise Private Network (EPN), the Internet, a Global Area Network (GAN), and so on.

[0032] Fig. 1 shows a block diagram of a system (100) for intelligent fault detection and energy management in fuel cell hybrid electric vehicles (FCHEVs) according to an embodiment of the present disclosure.

[0033] With reference to Fig. 1, the system (100) comprises a data acquisition unit (102) with sensors (102a) configured to acquire real-time operating data from vehicle components; an energy management unit (104) comprising a fuel cell unit for generating electricity from hydrogen and a battery unit for storing and delivering electrical energy; a regenerative braking system (106) in communication with the energy management unit (104) configured to recover and store energy during vehicle deceleration;a central processing unit (108) configured to perform functions of the system (100) based on the data acquired by the sensors (102a), the central processing unit (108) comprising: a neural network processor (108a) configured to analyze the real-time operating data for failure prediction, an energy optimization processor (108b) configured to dynamically manage energy distribution, and a maintenance prediction processor (108c) configured to identify potential component failures; a communication interface (110) configured to enable data exchange between vehicle and infrastructure (V2I) and between vehicles (V2V); a driver interface (112) configured to display system status and receive user inputs;and a control unit (114) configured to execute corrective actions based on the neural network analysis and the energy optimization calculations;

[0034] In one embodiment, the data acquisition unit (102) is further configured to: acquire battery parameters, including state of charge (SOC) and state of health (SOH); acquire engine parameters, including temperature, current, and voltage; acquire fuel cell parameters, including pressure, temperature, and efficiency metrics; and acquire environmental parameters, including ambient temperature and humidity.

[0035] In one embodiment, the neural network processor (108a) is further configured to implement deep learning algorithms for pattern recognition in operational data, detect anomalies indicating potential component failures, create predictive maintenance plans, and continuously update prognostic models based on historical failure data.

[0036] In one embodiment, the energy optimization processor (108b) is further configured to analyze energy demand patterns in real time, calculate the optimal power distribution between the fuel cell unit and the battery unit, implement dynamic load balancing algorithms, and adjust the power distribution based on the predicted energy demand.

[0037] In one embodiment, the maintenance prediction processor (108c) is further configured to generate automated maintenance orders, calculate component wear patterns, predict optimal maintenance intervals, and provide specific maintenance recommendations.

[0038] In one embodiment, the regenerative braking system (106) is further configured to measure vehicle deceleration parameters, calculate recoverable energy during braking, optimize energy recovery efficiency, and direct recovered energy to the battery unit.

[0039] In one embodiment, the communication interface (110) is further configured to receive real-time traffic information, retrieve updates on weather conditions, exchange road gradient data, and integrate external data into the neural network analysis.

[0040] In one embodiment, the driver interface (112) is further configured to display real-time energy efficiency metrics, provide driving behavior recommendations, alert users to predicted faults, and enable configuration of energy management parameters.

[0041] In one embodiment, the control unit (114) is further configured to implement automated error mitigation strategies, adjust vehicle operating parameters, execute emergency safety protocols, and optimize driving modes based on current conditions.

[0042] In one embodiment, the system (100) further comprises a feedback loop system (116) in communication with the centralized processing unit (108), the feedback loop system configured to analyze the effectiveness of fault predictions, evaluate energy management decisions, refine neural network models, and optimize system performance based on historical data.

[0043] In one embodiment, the data acquisition unit (102), the energy management unit (104), the regenerative management unit (106), the central processing unit (108), the communication interface (110), the driver interface (112), the control unit (114), and the feedback loop system (116) may be implemented in programmable hardware devices such as processors, digital signal processors, central processing units, field-programmable gate arrays, programmable array logic, programmable logic devices, cloud processing systems, or the like. The devices may also be implemented in software for execution by various types of processors.

[0044] The present invention presents an AI-based system specifically designed to overcome the limitations of existing technologies in the field of fuel cell hybrid electric vehicles (FCHEVs). This system uses advanced deep learning algorithms to enable real-time fault prediction and energy management, thus significantly improving the overall performance, safety, and reliability of FCHEVs. The core of this invention is the integration of an AI-driven supervisory control system that continuously monitors sensor data collected from various vehicle components. These sensors provide real-time information on critical parameters such as battery health, fuel cell status, engine performance, and environmental conditions. By processing this data, the AI ​​system is able to detect patterns and anomalies that may indicate potential faults.Unlike conventional systems that react to faults after they occur, this AI-based approach predicts faults before they occur, allowing the system to autonomously initiate corrective actions. These actions can include adjusting operating parameters or advising the driver to perform preventative maintenance, thus minimizing the risk of vehicle downtime and ensuring continuous, safe operation. In addition to fault prediction, the invention also features a sophisticated energy management system that optimizes energy distribution between the fuel cell and battery. The AI ​​algorithms dynamically adjust the energy flow to driving conditions in real time, ensuring that the vehicle operates at maximum efficiency under various scenarios.This intelligent energy management not only improves fuel efficiency but also extends the service life of critical components such as the battery and fuel cell by reducing unnecessary stress and wear. The integration of AI into both fault prediction and energy management represents a significant advance over the state of the art. Conventional systems are often based on predefined rules and static models that are not suited to the complexity of modern FCHEVs. In contrast, the deep learning algorithms used in this invention continuously evolve and adapt based on new data, providing a more robust and flexible solution that can anticipate and respond to a wide range of challenges. The benefits of this AI-driven system are numerous.By proactively managing potential failures and optimizing energy consumption, the system increases vehicle safety, reduces operating costs by minimizing downtime and maintenance, and maximizes overall efficiency. This comprehensive approach ensures that FCHEVs can operate reliably and sustainably even in dynamic and demanding environments and positions the present invention as a groundbreaking technology in the field of hybrid electric vehicles.

[0045] Fig. 2 shows a block diagram of the IoT-based data acquisition architecture for condition monitoring and energy management strategy in fuel cell hybrid electric vehicles (FCHEVs) according to an embodiment of the present disclosure.

[0046] The details of the arrangement of the sensors in the vehicle are described in Fig. 2. The sensors continuously collect real-time data on various operating parameters and feed this information into the monitoring control system for further analysis. The system is designed to collect and process data from various sensors distributed throughout the vehicle to ensure optimal operation. Each component in this system plays a critical role in maintaining the vehicle's performance, safety, and efficiency. The description of the components in Fig. below shows how the integration of advanced sensors, AI / ML algorithms, and cloud connectivity work together to improve the vehicle's overall efficiency, reliability, and safety. 100 - Battery

[0047] The battery serves as the primary energy storage unit in the FCHEV and is responsible for providing the necessary electrical energy for vehicle propulsion. It supplies power directly to the drive motor during battery operation and stores energy generated during regenerative braking and fuel cell operation. Battery performance is monitored in real time, collecting data on parameters such as voltage, current, and temperature to ensure optimal operation and longevity. 101 - Fuel Cell

[0048] The fuel cell generates electricity through a chemical reaction between stored hydrogen and oxygen from the ambient air. This component converts hydrogen into electrical energy, which, in conjunction with the battery, powers the vehicle. The efficiency and performance of the fuel cell are continuously monitored, with real-time data acquisition enabling precise control of the energy balance between the fuel cell and the battery. 102 - DC connection

[0049] The DC link is a critical link between the battery and the inverter. It facilitates the transfer of electrical energy and ensures that the direct current (DC) from the battery is properly converted into alternating current (AC) for the drive motor. The DC link is monitored for voltage and current levels to prevent inconsistencies or power losses during conversion. 102 - Battery Management System (BMS)

[0050] The battery management system (BMS) is critical for maintaining the health and performance of the battery. It manages the state of charge (SOC) and state of health (SOH), ensuring that the battery operates within safe and efficient parameters. The BMS collects data on the battery's status and communicates with the monitoring control unit to optimize energy consumption and prevent potential failures. 103 - Inverters (DC / AC)

[0051] The inverter plays a crucial role in converting the direct current (DC) from the battery into the alternating current (AC) required to power the traction motor. This component is essential for controlling the motor's speed and torque, and its performance is closely monitored to ensure smooth and efficient vehicle operation. Inverter efficiency is a key factor in overall energy management, with its operation driven by real-time data. 104 - Drive motor

[0052] The drive motor is the vehicle's primary propulsion system and utilizes energy from both the battery and the fuel cell. It converts electrical energy into mechanical energy to propel the vehicle. Data from the motor, including speed, torque, and temperature, is continuously collected to optimize performance and prevent potential problems such as overheating or excessive wear. 105 - Mechanical differential and rear axle transmission unit

[0053] This unit is responsible for distributing the engine's power to the wheels, adjusting torque and speed according to the vehicle's load requirements. It ensures that the vehicle operates efficiently under varying conditions, and real-time data acquisition from this unit enables precise control of power distribution to improve vehicle stability and performance. 106 - Data acquisition sensors

[0054] Sensors are strategically distributed throughout the vehicle to monitor critical parameters such as voltage, current, temperature, and speed. These sensors form the backbone of the IoT-based data acquisition system and provide the necessary inputs for real-time condition monitoring and energy management. The data collected by these sensors is processed by AI / ML algorithms to predict faults and optimize vehicle operation.

[0055] The data collected from the battery includes the status of voltage, current, and temperature. The data collected from the motor includes voltage, current, temperature, speed, and vibration, with the gate driver and sensor unit mounted on the motor. 107 - Monitoring Control Unit

[0056] The Supervisory Control Unit acts as the central control center of the FCHEV and coordinates all vehicle operations. It manages the transition between battery and fuel cell modes based on real-time data and ensures that the vehicle runs in the most efficient mode under all conditions. The unit also monitors fault detection and correction and uses data from various sensors to maintain vehicle safety and reliability. 108 - Gate driver and motor control unit (MCU)

[0057] The motor control unit (MCU) is responsible for operating the drive motor in various modes and generates the required pulse-width modulation (PWM) signals based on control actions determined by the supervisory control unit. These PWM signals are then amplified by the gate driver to drive the metal-oxide-semiconductor field-effect transistors (MOSFETs) in the inverter and control the current flow to the motor. 109 - Display interface

[0058] The display interface provides the driver with real-time feedback and displays information on vehicle status, energy consumption, and detected errors. It communicates with the monitoring control unit via I2C or SPI protocols, ensuring the driver is always informed about the vehicle's operating status. 110 - IoT Connectivity WLAN Module with CAN Protocol Interface

[0059] The IoT connectivity module, based on an ESP32 controller, enables real-time data transfer between the vehicle and cloud storage. The Controller Area Network (CAN) protocol ensures seamless communication between various electronic control units (ECUs) in the vehicle, while the Wi-Fi module facilitates external connectivity, enabling remote monitoring and data analysis. 111 - Cloud Storage

[0060] All collected data is transferred to cloud storage for long-term analysis and model training. This data repository enables continuous improvement of AI / ML algorithms, allowing the system to learn from past performance and optimize future operations. 112 - AI / ML algorithms

[0061] AI / ML algorithms form the core of the system's predictive capabilities. These advanced algorithms process sensor data in real time to predict potential failures and optimize energy management. By leveraging deep learning techniques, the algorithms can identify patterns and trends that conventional systems might miss, providing a significant advantage in vehicle operation and maintenance. 113 - Interface for mobile devices and PCs

[0062] The mobile or PC interface serves as a human-machine interface (HMI) for users, allowing them to access and interact with the data collected by the vehicle's sensor units. This interface provides a user-friendly platform for monitoring vehicle performance, reviewing historical data, and making informed decisions based on the system's real-time analytics.

[0063] Fig. 3 shows a block diagram illustrating the communication structure between various controllers within FCHEVs and highlighting the hierarchical control system from the top to the bottom level according to an embodiment of the present disclosure.

[0064] Fig. Figure 3 shows how data flows and decisions are coordinated across multiple control levels, from high-level strategic decisions to low-level execution in the vehicle components. The communication structure between the various controllers in a fuel cell hybrid electric vehicle (FCHEV) is described below, highlighting the hierarchical control system that extends from the top-level monitoring units to the lower-level operating units. This architecture ensures seamless coordination between the vehicle's critical components, thus improving overall performance, reliability, and efficiency. Fig. shows how data flows and decisions are made across different control levels to ensure optimal vehicle operation. 200 - Battery

[0065] The battery serves as a critical energy storage component, providing the electrical energy needed to propel the vehicle. It supplies the drive motor with energy during battery operation and stores the energy recovered during regenerative braking and fuel cell operation. The battery is continuously monitored and managed by the battery management system (BMS) to ensure safe and efficient operation. 201 - Drive motor

[0066] The drive motor is responsible for propelling the vehicle by converting electrical energy from the battery and fuel cell into mechanical motion. The engine control unit (MCU) monitors its operation and adjusts speed and torque according to driving conditions. The engine's performance is critical to the vehicle's efficiency, and it continuously communicates with other control units to maintain optimal operation. 202 - Gear unit

[0067] The transmission unit distributes the engine's power to the vehicle's wheels, adjusting torque and speed to the vehicle's load requirements. The transmission control unit (TCU) controls gear shifting and ensures that the transmission operates efficiently under varying conditions. This unit plays a crucial role in maintaining the vehicle's drivability and performance. 203 - Fuel cell

[0068] The fuel cell generates electricity through a chemical reaction between stored hydrogen and oxygen from the ambient air. It works in conjunction with the battery to power the vehicle, with its operation controlled by the fuel cell control unit (FCU). The FCU ensures optimal hydrogen consumption and power output, balancing the vehicle's energy requirements. 204 - Battery Management System (BMS)

[0069] The BMS is a critical component that monitors and manages battery parameters such as state of charge (SOC), state of health (SOH), and temperature. It ensures that the battery operates within safe limits and communicates with the monitoring control unit and other controllers to optimize energy consumption and prevent faults. 205 - Engine Control Unit (MCU)

[0070] The MCU controls the operation of the drive motor, regulating its speed and torque to meet the vehicle's requirements. It receives inputs from the supervisory control unit and other sensors and makes adjustments in real time to ensure smooth and efficient vehicle propulsion. 206 - Transmission Control Unit (TCU)

[0071] The TCU is responsible for controlling the vehicle's transmission system, including gear shifting and power distribution. It ensures that the transmission works harmoniously with the engine and other powertrain components, providing the required torque and speed for different driving conditions. 207 - Fuel cell control unit (FCU)

[0072] The FCU regulates the operation of the fuel cell, ensuring that hydrogen is consumed efficiently and that the fuel cell generates the required electrical power. It coordinates the energy flow between the fuel cell and the battery with the BMS and other controllers, thus optimizing the overall efficiency of the vehicle. 208 - CAN protocol data exchange

[0073] The CAN (Controller Area Network) protocol is used for standardized communication between the various electronic control units (ECUs) in a vehicle. This protocol ensures reliable and fast data exchange, allowing the ECUs to make informed decisions based on real-time information. 209 - Bidirectional intelligent control unit

[0074] This unit facilitates communication and decision-making between the higher-level supervisory control and the lower-level operating units. It ensures that data and commands flow smoothly between different control units, enabling coordinated vehicle operation and rapid response to changing conditions. 210 - Data set

[0075] The Dataset component generates the required datasets based on the collected sensor information. This data forms the basis for further analysis, including feature extraction and classification, allowing the system to learn and adapt to new conditions. 211 - Feature extraction

[0076] Feature extraction processes the raw sensor data to identify the most relevant and useful information for further analysis. This step is crucial for controller training, as it helps isolate the most important parameters that affect vehicle performance and health. 212 - Classification

[0077] Classification involves dividing the extracted data into categories based on the identified features. This process is critical for proper data management, improving the accuracy of predictive models, and improving future predictions related to fault diagnosis and energy management. 213 - Deep Learning Algorithms

[0078] Deep learning algorithms are used for pattern recognition and fault prediction, leveraging historical and real-time data. These algorithms analyze complex data sets to identify trends and potential problems. This allows the system to predict and correct faults before they affect vehicle performance. 214 - Edition

[0079] The output component represents the real-time algorithms that diagnose and correct faults in the vehicle. It provides actionable information for energy management and fault diagnosis, ensuring that the vehicle operates safely and efficiently. 215 - Display interface

[0080] The display interface provides the driver with feedback on the vehicle's condition, detected faults, and energy management decisions. This real-time information helps the driver stay informed about the vehicle's status and make necessary adjustments as needed. 216 - Interface for mobile devices and PCs

[0081] The mobile or PC interface allows users to connect to the proposed system via a human-machine interface (HMI). This connectivity enables remote monitoring, data access, and control, providing users with the ability to interact with the vehicle systems and review performance data from any location.

[0082] The communication structure between different controllers in an FCHEV described above shows how a hierarchical control system using advanced communication protocols and AI-driven decision-making ensures coordinated operation, fault management, and energy optimization.

[0083] Fig. Figure 4 shows a block diagram illustrating the operation of machine learning and AI algorithms in FCHEVs, with a focus on fault classification and energy management, according to one embodiment of the present disclosure.

[0084] In Fig. The overall function of machine learning (ML) and artificial intelligence (AI) algorithms in controlling the operation of a fuel cell hybrid electric vehicle (FCHEV) is demonstrated. The system is designed to improve vehicle performance by dynamically adapting to real-time driving conditions and optimizing energy management. The various components required for operation are described in detail below: 300 - Vehicle powertrain components

[0085] This component represents the FCHEV's powertrain and includes critical elements such as the battery, fuel cell, inverter, motor, and transmission. These components work together to power the vehicle, with their operation continuously monitored and controlled by the ML / AI system. The seamless integration of these components is critical for efficient energy consumption and overall vehicle performance. 301 - Sensor data acquisition unit

[0086] The sensor data acquisition unit is responsible for collecting real-time data from various sensors distributed throughout the vehicle. These sensors monitor a range of parameters, including voltage, current, temperature, speed, and more. The collected data forms the basis for the subsequent analysis and decision-making processes performed by the ML / AI algorithms. 302 - Dataset preparation

[0087] This unit separates the collected sensor data into the required sample and variable units, making it available for further processing. By organizing the data into structured datasets, this step ensures that the information is ready for accurate and efficient analysis by ML / AI models. 303 - Data preprocessing unit

[0088] The data preprocessing unit cleans and formats the raw sensor data to make it usable for ML / AI models. This unit applies various techniques, including data storage, model training, and validation through appropriate testing. Preprocessing is a crucial step that improves the quality and reliability of the data and ensures that the ML / AI models can work effectively. 304 - Performance evaluation and mode selection by ML algorithms

[0089] This unit is responsible for evaluating the vehicle's performance in real time and selecting the most appropriate operating mode based on predictions from the ML algorithms. By analyzing current driving conditions and vehicle status, the system ensures that the correct operating sequence is followed, optimizing energy consumption and vehicle efficiency. 305 - Data analysis tool

[0090] The data analytics tool performs in-depth analysis of the processed data and uses it for historical analysis and model training. This tool identifies patterns, trends, and anomalies in the data, allowing the system to refine its predictive models and improve future performance. 306 - Data Analysis Tools Subunit

[0091] The data analysis tool's subunit stores the preprocessed data and analyzes it using various techniques, including pattern recognition, classification, regression, anomaly analysis, predictive analysis, and monitoring. It also plays a crucial role in planning the energy management strategy and ensuring that the vehicle operates efficiently under all conditions. 307 - Final output control processes

[0092] This component includes several important functions that contribute to the overall operation and optimization of the FCHEV: • Training and validation unit for estimating the quality and service life of various powertrain components: This unit trains the ML models using historical data and validates their accuracy for real-time use. It estimates the quality and remaining service life of powertrain components, enabling predictive maintenance and reducing the risk of unexpected failures. • Performance Evaluation Unit: This unit evaluates the effectiveness of ML models in real-time fault detection and energy management. By predicting potential problems before they occur, the system can take preventative measures to maintain vehicle performance and safety. • Operational localization through a pattern analysis unit: This unit identifies trends and anomalies in sensor data that could indicate potential errors or inefficiencies. It localizes these patterns within specific components or systems, enabling targeted interventions and optimizations. • Fault identification and classification algorithms using a fault diagnostic tool: Special algorithms in this unit classify and diagnose faults in critical vehicle components such as the battery, motor, and fuel cell. By accurately identifying faults, the system can initiate corrective actions to prevent further damage and ensure continuous vehicle operation. • Energy Management Strategy Module: This module develops and implements strategies for optimal energy distribution between the fuel cell and battery. By regulating energy flow based on real-time conditions, the system maximizes vehicle efficiency and extends the lifespan of critical components.

[0093] This description of the operation of ML / AI algorithms in FCHEVs demonstrates how advanced data processing and predictive modeling can significantly improve vehicle performance, fault detection, and energy management. The integration of these technologies provides a robust framework for intelligent vehicle operation, ensuring safety, efficiency, and reliability under dynamic driving conditions.

[0094] Fig. 5 shows a block diagram of the failure prediction system using artificial neural networks (ANN) in FCHEVs according to an embodiment of the present disclosure.

[0095] Fig. Figure 5 shows the functionality of a failure prediction system using artificial neural networks. This system is designed to predict potential failures before they occur. This enables proactive maintenance and improves vehicle safety and reliability. The components involved in this system are described in detail below: 400 - Vehicle sensor unit

[0096] The vehicle sensor unit is responsible for collecting real-time data from various sensors distributed throughout the vehicle. These sensors monitor critical parameters such as voltage, temperature, pressure, current, and mechanical stress. The data collected by this unit is crucial for subsequent steps of failure prediction and system optimization. 401 - Signal Preprocessing

[0097] The signal preprocessing unit applies initial processing techniques to the acquired sensor data. These include methods such as the fast Fourier transform (FFT), the short-time Fourier transform (STFT), wavelet analysis, and other signal processing tools. These techniques help refine the raw data and make it more suitable for analysis by the neural network. Preprocessing is a crucial step that improves the accuracy and reliability of the fault prediction models. 402 - Cloud Storage

[0098] The cloud storage component is used to store and process the acquired sensor data. This system integrates real-time data with pre-trained datasets, enabling continuous training and refinement of the models. By leveraging cloud-based resources, the system can efficiently process large amounts of data and ensure that the ANN models are always up to date. 403 - Pre-record unit

[0099] The pre-dataset unit contains standardized datasets used for the initial training of the ANN models. These datasets represent a comprehensive collection of historical data, including various failure scenarios, vehicle operating conditions, and environmental factors. The pre-dataset unit is essential for developing the baseline models, which are further refined using real-time data. 404 - Artificial Neural Network (ANN) Block

[0100] The ANN block is the core component of the fault prediction system and consists of the following subunits: • 404A - Input Layer: The input layer receives processed sensor data on various vehicle parameters, including voltage, temperature, pressure, and other relevant measurements. This layer serves as the entry point for data into the neural network. • 404B - Hidden Layers: Hidden layers consist of multiple interconnected neurons that process the input data. These layers identify complex patterns and relationships within the data that are associated with potential errors. Hidden layers play a crucial role in the neural network's predictive capabilities, allowing for the detection of subtle anomalies that may indicate impending failures. • 404C - Output Layer: The output layer creates failure predictions based on the patterns identified by the hidden layers. It indicates the specific vehicle component likely to fail and provides detailed information about the type and severity of the predicted failure. 405 - Error detection system

[0101] The fault detection system classifies and identifies various types of faults that can occur in various vehicle components such as the engine, battery, inverter, fuel cell, and transmission unit. This system uses the following architecture for its operations: • Training dataset: Historical data used to train the neural network for accurate failure prediction. This dataset contains records of past failures, operating conditions, and corrective actions taken. • Real-time data integration unit: This unit combines real-time sensor data with the predictions of the ANN model, enabling on-the-fly decision-making. It ensures that the system can quickly respond to occurring faults and adjust its predictions based on current vehicle conditions. • Fault Warning System: The fault warning system generates alerts to the driver or the central control system when a potential fault is detected. These alerts trigger corrective actions, such as adjusting vehicle operation or scheduling maintenance, to prevent the fault from escalating. • Maintenance planning unit: Based on predicted failures, this unit automatically schedules maintenance tasks. By proactively addressing potential problems, the maintenance planning unit reduces vehicle downtime and improves overall reliability. 406 - Vehicle display unit

[0102] The vehicle display unit provides real-time feedback to the driver and displays information on detected faults and vehicle status. It categorizes and lists faults in various vehicle components, including: • Motor faults: Electrical faults (e.g. short circuits, overcharging, cell imbalance) and mechanical faults (e.g. wear, tooth breakage, lubrication problems). • Battery failure: Problems such as thermal runaway, capacity degradation, increase in internal resistance and gate driver failure. • Inverter faults: overheating, short circuit, open circuit and control logic errors. • Fuel cell failures: membrane degradation, fuel starvation, water management problems, temperature control problems, and gas leak failures. • Transmission failure: Problems such as wear, misalignment, overheating and noise.

[0103] The above description of the fault prediction system using ANN highlights the advanced capabilities of the proposed innovation and demonstrates that, through the use of machine learning techniques, specifically ANN, the system can accurately predict and diagnose faults in real time, ensuring the continuous operation, safety, and efficiency of the vehicle. The integration of cloud storage, preprocessed data, and a robust fault detection system further improves the overall effectiveness of the FCHEV and represents a significant advance over traditional fault management approaches.

[0104] Fig. 6 shows a block diagram of the energy management and control mechanism in FCHEVs according to an embodiment of the present disclosure.

[0105] In Fig. Figure 6 illustrates the operation of the energy management and control mechanism in a fuel cell hybrid electric vehicle (FCHEV). The system is designed to optimize energy distribution between the battery and fuel cell in real time, ensuring maximum efficiency and vehicle performance. The key components involved in this mechanism are described in detail below: 500 - Fuel cell power control using a fuel cell DC / DC converter

[0106] The fuel cell's power control unit, equipped with a DC / DC converter, regulates the power generated by the fuel cell to supplement the battery's power. It ensures that the vehicle's energy needs are met by adjusting the fuel cell's power to different load conditions. This unit plays a crucial role in balancing the power supply between the battery and the fuel cell, especially during periods of high demand. 501 - Battery with DC / DC converter

[0107] The battery pack, in conjunction with a DC / DC converter, helps regulate the battery's power output to maintain the desired voltage levels. This regulation is important to ensure the battery can consistently supply power to the vehicle's systems, especially when transitioning between different operating modes (e.g., acceleration, driving, braking). The converter also enables the efficient storage of energy recovered during regenerative braking. 502 - DC-AC inverter

[0108] The DC / AC inverter converts the direct current (DC) from the battery and fuel cell into the alternating current (AC) required to power the drive motor. This component is critical for the efficient operation of the motor and providing the necessary torque and speed to propel the vehicle. The performance of the inverter is directly linked to the overall efficiency and responsiveness of the vehicle's powertrain. 503 - Engine

[0109] The motor is responsible for propelling the vehicle based on the power provided by the battery and fuel cell. It converts electrical energy into mechanical energy, enabling the vehicle to move. The motor's operation is closely monitored and controlled by the energy management system to ensure optimal performance under various driving conditions. 504 - Mechanical differential and rear axle transmission unit

[0110] The rear axle's mechanical differential and transmission distribute the engine's power to the wheels at the desired torque and speed, thus meeting the vehicle's load requirements. This component ensures that power is transferred efficiently to the wheels, improving the vehicle's stability and handling, especially when cornering and over uneven road conditions. 505 - Gearshift

[0111] While most electric vehicles (EVs) have single-speed transmissions, this system features an advanced multi-speed transmission with an automatic gearshift mechanism. The gearshift mechanism adjusts the gear ratio to optimize engine efficiency and vehicle performance, especially during changing driving conditions such as uphill driving or rapid acceleration. 506 - Sensors and data acquisition via the CAN protocol

[0112] Sensors distributed throughout the vehicle collect important data on various operating parameters such as speed, temperature, voltage, and current. This data is transmitted via the CAN (Controller Area Network) protocol, which ensures reliable communication between various electronic control units (ECUs) in the vehicle. The collected data is critical for real-time monitoring and control of the vehicle's energy management system. 507 - Cloud data storage

[0113] The cloud data storage unit securely stores large data sets, including both real-time sensor data and historical data used for model training. This storage is critical for improving the accuracy of energy management models over time, as it allows the system to learn from past performance and make more informed decisions. Cloud storage also facilitates long-term data analysis and model refinement. 508 - Higher-level processing unit with ANN block (artificial neural network)

[0114] The higher-level processing unit uses advanced artificial neural networks (ANNs) to process sensor data and make predictions about vehicle operation. The ANN block consists of the following subunits: • 508A - Input Layer: The input layer receives sensor data on various vehicle parameters such as voltage, temperature, and pressure. This data is then fed into the neural network for further processing. • 508B - Hidden Layers: Hidden layers consist of multiple neurons that process the input data by detecting patterns and correlations. These layers are responsible for detecting potential problems, optimizing energy management strategies, and predicting failures. • 508C - Output Layer: The output layer provides actionable insights based on the processed data, including fault predictions, energy distribution recommendations, and other control signals. This information is used to adjust vehicle operation in real time. 509 - Vehicle monitoring control units

[0115] The vehicle monitoring controller consists of several subunits that coordinate the overall operation of the vehicle's energy management system. These subunits include: • Preprocessed data from clouds and ANN units: This subunit receives and processes data from the cloud storage and the ANN block and integrates it into the vehicle's control strategies. • Electric range and total distance estimation: This sub-unit calculates the estimated range and total distance the vehicle can travel based on the battery state of charge (SOC), state of health (SOH), fuel cell condition, and hydrogen fuel level. • Navigation information / vehicle data / V21 V2V traffic information / weather conditions: This sub-unit processes external data on navigation, traffic and weather conditions and uses them to control the vehicle's operating modes and control strategies. • Energy optimization with real-time data from the engine, fuel cell and battery: This subunit dynamically adjusts the energy distribution between the motor, fuel cell and battery based on real-time data to maximize efficiency. • Gearshift mechanism control: This sub-unit manages gearshift operations and ensures that the transmission functions optimally in different driving scenarios. • Selection of driving patterns based on the automatic cruise control cluster unit: This sub-unit selects appropriate driving patterns based on vehicle speed, road conditions and driver inputs, thus optimizing the overall performance of the vehicle. Energy demand forecasting module

[0116] The energy demand prediction module predicts the vehicle's energy demand based on current driving conditions, vehicle status, and external factors such as terrain and traffic. This module allows the system to anticipate energy demand and adjust the energy distribution between the battery and fuel cell accordingly. Real-time energy distribution unit

[0117] This device dynamically distributes energy between the battery and fuel cell to meet the vehicle's predicted energy needs. By continuously adjusting the energy flow, the system ensures that both energy sources are used efficiently, minimizing energy waste and extending the vehicle's range. Battery SOC management

[0118] The Battery SOC Management subunit monitors and controls the battery's state of charge (SOC) to maintain optimal energy levels. This management is critical to ensuring the battery remains within safe operating limits and preventing over-discharge or overcharging, which could lead to reduced battery life or potential safety risks. Regenerative braking system

[0119] The regenerative braking system recovers energy during braking and feeds it back into the battery. This process improves the vehicle's overall efficiency by converting kinetic energy into electrical energy that can be reused in subsequent driving phases. Load balancing unit

[0120] The load balancing unit distributes the power load between the battery and the fuel cell, ensuring that neither power source is overloaded. By balancing the load, the system increases the service life of the vehicle's components and ensures stable vehicle performance under varying operating conditions. Driver feedback interface

[0121] The driver feedback interface provides real-time information on energy consumption, vehicle efficiency, and recommended driving behavior. This interface helps the driver optimize their driving behavior to improve vehicle performance and range. It also provides insights into the current vehicle status, including SOC, fuel cell health, and any potential faults detected by the system.

[0122] The description of the energy management and control mechanism highlights the sophisticated approach to optimizing the FCHEV's performance and efficiency. By employing advanced control strategies, real-time data processing, and machine learning algorithms, the system ensures that the vehicle operates at maximum efficiency while maintaining safety and reliability.

[0123] Fig. 7 shows a block diagram illustrating the operation of the ANN-based learning processing unit used to manage FCHEV energy distribution and fault prediction according to an embodiment of the present disclosure.

[0124] In Fig. Figure 7 demonstrates the operation of the artificial neural network (ANN)-based learning processing unit responsible for managing energy distribution and fault prediction in fuel cell hybrid electric vehicles (FCHEVs). This system continuously learns from historical and real-time data, thus improving the vehicle's performance over time. The various components of this unit are described in detail below: 600 - Data entry interface

[0125] The data input interface serves as a gateway for capturing a wide range of real-time and historical data on vehicle performance and environmental conditions. This interface processes information collected from multiple sensors distributed throughout the vehicle, including: • Battery parameters: voltage, current, state of charge (SOC), state of health (SOH), temperature, power and efficiency. • Motor parameters: voltage, current, torque, speed, efficiency and temperature. • Fuel cell parameters: voltage, current, power, efficiency, temperature and hydrogen pressure (H2). • Inverter parameters: voltage, current and temperature. • Transmission and differential: gear ratio and differential torque. • Driver inputs: accelerator pedal position, brake pedal position, driving mode selection (e.g. Eco, Sport, Normal). • Driving condition parameters: vehicle speed, acceleration, road gradient, ambient temperature, traffic conditions and location data (e.g. Google Maps).

[0126] These diverse inputs are fed into the neural network, where they undergo initial processing to prepare them for further analysis and decision-making. 601 - Learning Algorithm Unit

[0127] The learning algorithm unit uses advanced neural networks to analyze the collected data, identify patterns, and continuously refine predictions and energy management strategies. Key subcomponents include: • Feature extraction layers: These layers extract relevant features and relationships from the input data and capture both linear and nonlinear interactions between different parameters. The extracted features are critical for understanding complex dynamics within the vehicle's operating environment. • Decision layer: This layer processes the extracted features to make key energy management decisions. It determines the optimal power distribution between the fuel cell and battery, evaluates efficiency and performance metrics, and ensures that the vehicle runs at peak performance. 602 - Output levels

[0128] The output layers are responsible for generating actionable outputs based on the processed data. These outputs include: • Power Split Decision: Determines the power distribution between the fuel cell and the battery, ensuring that the vehicle’s energy needs are met efficiently. • Operating mode selection: Selects the appropriate operating mode (e.g. Eco, Sport, Normal) based on driving conditions and energy availability. • Control signals and power distribution: Provides control signals to various vehicle subsystems, including thermal management and safety systems, to ensure their proper functioning. • Fault diagnostic capabilities: Generates alerts and recommendations for maintenance or corrective actions based on detected errors or inefficiencies. 603 - Real-time prediction interface

[0129] The real-time prediction interface plays a critical role in enabling dynamic adjustments to the vehicle's control systems. By providing real-time predictions regarding energy distribution, potential faults, and system performance, this interface enables the vehicle to respond quickly to changing conditions, thus optimizing performance and safety. 604 - Optimization module

[0130] The optimization module continuously refines the vehicle's energy management strategies based on real-time predictions. By comparing predicted values ​​with actual performance results, this module iteratively improves the accuracy and effectiveness of the energy distribution strategies. The module utilizes feedback mechanisms to improve the system's responsiveness to different driving scenarios. 605 & 606 - Feedback loop with loss function and loss evaluation

[0131] The feedback loop is a critical component that incorporates performance feedback into the neural network's learning process. It operates through forward and backward propagation, with the system continuously updating weights and biases within the neural network. This iterative process, governed by a loss function and an associated loss value, helps minimize prediction errors and improve the overall accuracy of the system. The feedback loop ensures that the neural network adapts to new data and conditions, improving its predictive capabilities over time. 607 - Optimizer block unit

[0132] The Optimizers Block Unit is responsible for updating the error values ​​within the neural network using advanced optimization algorithms. These algorithms adjust the neural network parameters (weights and biases) to reduce the loss function, thus improving prediction accuracy and overall system performance. This block ensures that the neural network converges to optimal solutions for energy management and error prediction. 608 - Weights and Prejudices

[0133] Weights and biases are fundamental components of the neural network that determine how the network processes input data. These parameters are continuously adjusted during the learning process to improve the network's accuracy. In the context of FCHEVs, properly tuned weights and biases are essential for accurate predictions and effective energy management strategies, leading to improved vehicle performance and efficiency.

[0134] The description of the neural network-based learning processing unit highlights the sophisticated approach to optimizing energy distribution and fault prediction in FCHEVs. By leveraging real-time data, advanced neural networks, and iterative learning processes, this system ensures that the vehicle operates at maximum efficiency while continuously improving its performance over time.

[0135] The proposed system offers several innovative benefits that improve the functionality, safety, and efficiency of fuel cell hybrid electric vehicles (FCHEVs). By integrating AI-driven fault detection and correction, the system leverages artificial neural networks (ANNs) combined with real-time sensor data to proactively predict and resolve potential faults. This capability ensures vehicle safety and reliability by preventing failures before they occur. Furthermore, the system incorporates a dynamic energy management module that optimizes energy distribution between the fuel cell and battery in real time, adapting to the vehicle's energy needs while reducing component wear and thus extending the service life of the powertrain.

[0136] The system's predictive maintenance capabilities are equally advanced. They utilize ANN-based analysis of historical data to anticipate faults and continuously improve detection accuracy through a feedback loop. This minimizes unexpected downtime and ensures consistent vehicle performance. To further improve operational efficiency, the system incorporates an energy demand prediction mechanism and a load balancing mechanism that prevents overloading of any single power source. This balanced energy distribution optimizes vehicle performance and extends the service life of the energy storage and generation components.

[0137] Drivers benefit from a real-time feedback interface that provides insights into energy consumption, efficiency, and recommended driving behavior, enabling them to make informed decisions that improve fuel economy and range. Safety is significantly enhanced through the use of deep learning algorithms that analyze both real-time and historical data to identify risks and automatically adjust vehicle operation to mitigate them. Finally, the integration of vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) communications further enhances the system's predictive capabilities by incorporating external environmental and traffic data, enabling safer and more efficient vehicle operation under varying conditions.

[0138] The drawings and the foregoing description provide examples of embodiments. Those skilled in the art will recognize that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be separated into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of the processes described herein may be changed and are not limited to the manner described herein. Furthermore, the actions of any flowchart need not be implemented in the order shown; nor do all actions necessarily need to be performed. Also, those actions that are not dependent on other actions may be performed in parallel with the other actions. The scope of the embodiments is in no way limited by these specific examples.Numerous variations, whether explicitly stated in the specification or not, such as differences in structure, dimensions, and use of materials, are possible. The scope of the embodiments is at least as broad as indicated in the following claims.

[0139] Advantages, other benefits, and solutions to problems have been described above with reference to specific embodiments. However, the advantages, benefits, solutions to problems, and any components that may cause an advantage or solution to occur or become more apparent are not to be construed as a critical, required, or essential feature or component of any or all of the claims. REFERENCES 100 A system for intelligent fault detection and energy management in fuel cell hybrid electric vehicles (FCHEVs). 102 Data acquisition unit 102a Sensors 104 Energy management unit 106 Regenerative braking system 108 Central Processing Unit 108a Neural network processor 108b Energy Optimization Processor 108c Maintenance Prediction Processor 110 Communication interface 112 Driver interface 114 Control unit 116 Feedback loop system 302 sensor data 304 Lower Level Control Operation 306 Higher-level control operation 510 PWM 1 control signal 512 PWM 2 control signal 514 PWM 4 control signal 516 PWM 3 control signal 518 May 702 Forward propagation 704 Backward propagation QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] US 9501917B2

[0004] US 9610672B2

[0004]

Claims

[1] A system (100) for intelligent fault detection and energy management in fuel cell hybrid electric vehicles (FCHEVs), comprising: a data acquisition unit (102) comprising sensors (102a) configured to acquire real-time operating data from vehicle components; an energy management unit (104) comprising a fuel cell unit configured to generate electricity from hydrogen and a battery unit configured to store and deliver electrical energy; a regenerative braking system (106) in communication with an energy management unit (104) configured to recover and store energy during vehicle deceleration; a centralized processing unit (108) configured to perform functions of the system (100) based on the data acquired by the sensors (102a), the centralized processing unit (108) comprising: a neural network processor (108a) configured to analyze the real-time operating data for fault prediction; a power optimization processor (108b) configured to dynamically manage power distribution; a maintenance prediction processor (108c) configured to identify potential component failures; a communication interface (110) configured to enable data exchange between vehicle and infrastructure (V2I) and between vehicles (V2V); a driver interface (112) configured to display system status and receive user input; and a control unit (114) configured to execute corrective actions based on the neural network analysis and the energy optimization calculations. [2] The system of claim 1, wherein the data acquisition unit (102) is further configured to acquire battery parameters, including state of charge (SOC) and state of health (SOH); acquire engine parameters, including temperature, current, and voltage; acquire fuel cell parameters, including pressure, temperature, and efficiency readings; and acquire environmental parameters, including ambient temperature and humidity. [3] The system of claim 1, wherein the neural network processor (108a) is further configured to implement deep learning algorithms for pattern recognition in operational data, detect anomalies indicating potential component failures, create predictive maintenance plans, and continuously update prognostic models based on historical failure data. [4] The system of claim 1, wherein the energy optimization processor (108b) is further configured to analyze energy demand patterns in real time, calculate the optimal power distribution between the fuel cell unit and the battery unit, implement dynamic load balancing algorithms, and adjust the power distribution based on the predicted energy demand. [5] The system of claim 1, wherein the maintenance prediction processor (108c) is further configured to create automatic maintenance orders, calculate component wear patterns, predict optimal maintenance intervals, and provide specific maintenance recommendations. [6] The system of claim 1, wherein the regenerative braking system (106) is further configured to measure vehicle deceleration parameters, calculate recoverable energy during braking, optimize energy recovery efficiency, and direct recovered energy to the battery unit. [7] The system of claim 1, wherein the communication interface (110) is further configured to receive real-time traffic information, retrieve weather condition updates, exchange road gradient data, and integrate external data into the neural network analysis. [8] The system of claim 1, wherein the driver interface (112) is further configured to display real-time energy efficiency metrics, provide driving behavior recommendations, alert users to predicted faults, and enable configuration of energy management parameters. [9] The system of claim 1, wherein the controller (114) is further configured to implement automated error mitigation strategies, adjust vehicle operating parameters, execute emergency safety protocols, and optimize driving modes based on current conditions. [10] The system of claim 1, further comprising a feedback loop system (116) in communication with the centralized processing unit (108), the feedback loop system configured to analyze the effectiveness of fault predictions, evaluate energy management decisions, refine neural network models, and optimize system performance based on historical data.

Images