In the Industry 4.0 era, integrating artificial intelligence (AI) with battery prognostics and health management (PHM) offers transformative solutions to the challenges posed by the complex nature of battery systems. These systems, known for their dynamic and nonl*-inear behavior, often exceed the capabilities of traditional PHM approaches, which struggle to account for the interplay of multiple physical domains and scales. By harnessing technologies such as big data analytics, cloud computing, the Internet of Things (IoT), and deep learning, AI provides robust, data-driven solutions for capturing and predicting battery degradation. These advancements address long-standing limitations in battery prognostics, enabling more accurate and reliable performance assessments. The convergence of AI with Industry 4.0 technologies not only resolves existing challenges but also introduces innovative approaches that enhance the adaptability and precision of battery health management. This perspective highlights recent progress in battery PHM and explores the shift from traditional methods to AI-powered, data-centric frameworks. By enabling more precise and scalable monitoring and prediction of battery health, this transition marks a significant step forward in advancing the field.

Energy storage and power boost are major problems in the development of electric vehicles (EV). Installing a super-capacitor as an auxiliary power source to improve the performance of electric vehicles is a feasible and realistic solution. In this paper, the structure of a multi-energy system and the principles of flow of the multi energy of electric vehicles were introduced first, explaining how different sources of energy work in different situations. A model of electric vehicle with a battery and a super-capacitor, based on Matlab/Simulink was built up. The model was validated by comparing the simulation results and the actual data from later field tests. The drive cycle used in the simulation was the CYC_CONST_45. Comparisons were made between the model of the vehicle with a super-capacitor and the model of a vehicle without a super-capacitor. Field tests of an electric vehicle were conduct and analyses were made. The analysis includes vehicle dynamic performance and economical performance in urban environments where the vehicle accelerated and decelerated frequently. The results showed that installing a super-capacitor improves the working conditions of the battery. The variation of the current drawn by the vehicle was smoothed due to the working of the super-capacitor, which provided better working conditions for the battery and increased the operating life of the battery. A super-capacitor can also improve the acceleration performance of the vehicle. The super-capacitor could provide large current in short time, delivering extra energy to meet the energy requirement when it is needed. A battery and a super-capacitor working together can reduce the average energy consumption. The average energy consumption of a vehicle with a super-capacitor is only 77% of that of a vehicle without a super-capacitor. The mileage in one charge of the electric vehicle will enlarged notably

Current electric vehicle power trains comprise on-board energy generation, energy storage and traction drive, where the battery used for energy storage is heavy or expensive or both and requires regular maintenance. Best practice is to use super-capacitors with batteries, reducing the deep charge-discharge cycle and battery size. According to the energy requirements of the EV bus, the control strategies of the energy management system about the dynamic battery and super-capacitor EV bus are studied. With batteries and super-capacitors electric vehicle as the main research subjects, which runs between system and parts time after time, different parts of the dynamic model was built, which include road-load model, super-capacitors model, direct current link model, power transform model and system circuit model etc. The electric vehicle simulation model with the control system of the multi-energy dynamic assembly is built, and simulated, in the ECE 15 which is an urban driving cycle and EDUC (extra urban driving cycle). Simulation results show that the dynamic performance is increased with super-capacitors in the same condition. Based on simulation, average energy consumptions with super-capacitors and without super-capacitors are calculated in typical urban driving and suburb driving cycles respectively. Calculations show that whilst average energy consumption with super-capacitors in urban driving cycle is reduced, this is not so in the suburb driving cycle. The developing low floorboard EV bus (BK6121EV) with multi-energy dynamic assembly system was used to experiment on the test road surface of Tong county in Beijing city, under the different states of the super-capacitors controller on-off. The trend of tested data curve is consistent with the simulation. With super-capacitors, dynamic performance is improved, and both traction battery current and average energy consumption are decreased. The simulation and the control system based CAN bus are both verified by experiment of the low floorboard EV bus

In this paper, a static state observer algorithm based on the static equilibrium position is proposed, which can realize accurate control of electric vehicle height adjustment with existing road excitation. The existence of road excitation can lead to deflection variation of the electronically controlled air suspension (ECAS). The use of only dynamic deflection as the reference for the electric vehicle height adjustment will produce great errors. Therefore, this paper provides an observation algorithm, which can realize the accurate control of vehicle height. Firstly, the static equilibrium position equation of suspension is derived according to the theory of hydrodynamics and characteristics of pneumatic chamber. Secondly, a vehicle dynamics model with seven degrees of freedom (7-DOF) is established and the kinetic equations are discretized. Then, the unscented Kalman filter (UKF) algorithm is used to obtain the static equilibrium position of vehicle. According to the vehicle static equilibrium position obtained by UKF, the height of the vehicle is adjusted by using a fuzzy controller. The simulation and experimental results show that this proposed algorithm can realize the control of vehicle height with an accuracy of over 96%, which ensures the excellent driving performance of vehicles under different road conditions.

This study presents a methodology to improve combined lane-keeping (LKA) and direct yaw-moment control (DYC) of distributed drive electric vehicles (EVs) running at a steady high speed, where a domain-centralized electronic and electrical ( E/E ) architecture based on software-defined networking is adopted. It is well known that domain-centralized E/E architecture has great advantages in terms of function integration, software upgrade and wiring reduction. However, the increasing E/E function components, heterogeneous network topologies, multiple different protocols and cross-domain communication behaviors would bring unknown cross-domain multi-hop information delays and negative system uncertainties, which may degrade the system performance and even deteriorate the system stability. To enjoy the advantages while dealing with the problems of the domain-centralized E/E system, a centralized software-defined networking (SDN) framework is introduced which includes strategy plane, control plane and data plane, for the design of combined LKA and DYC system. And in the control plane, a scheduling strategy based on the fractional-type basic period (FBP) method is developed to actively regulate information flow and restrain the cross-domain information delays. In the strategy plane, a hierarchical control scheme is adopted, where a delay-embedded LKA controller at upper level is designed to actively make decisions, and at lower level a H ∞-LQR controller is employed to ensure the stability of motion control system against the local within-domain information delays. The results of hardware-in-loop (HIL) test demonstrate that the loop delays have been reduced by 87.5% with the proposed SDN and the proposed methodology can effectively make the lane keeping well.

Considering the battery-failure-induced catastrophic events reported frequently, the early fault warning of batteries is essential to the safety of electric vehicles (EVs). Motivated by this, a novel data-driven method for early-stage battery-fault warning is proposed in this paper by the fusion of the short-text mining and the grey correlation. In particular, the short-text mining approach is exploited to identify the fault information recorded in the maintenance and service documents and further to analyze the categories of battery faults in EVs statistically. The grey correlation algorithm is employed to build the relevance between the vehicle states and typical battery faults, which contributes to extracting the key features of corresponding failures. A key fault-prediction model of electric buses based on big data is then established on the key feature variables. Different selections of kernel functions and hyperparameters are scrutinized to optimize the performance of warning. The proposed method is validated with real-world data acquired from electric buses in operation. Results suggest that the constructed prediction model can effectively predict the faults and carry out the desired early fault warning.