Battery management systems (BMSs) play a critical role in electric vehicles (EVs), relying heavily on two essential factors: the state of charge (SOC) and state of health (SOH). However, accurately estimating the SOC and SOH in lithium-ion (Li-ion) batteries remains a challenge. To address this, many researchers have turned to machine learning (ML) techniques. This study provides a comprehensive overview of both BMSs and ML, reviewing the latest research on popular ML methods for estimating the SOC and SOH. Additionally, it highlights the challenges involved. Beyond traditional models like equivalent circuit models (ECMs) and electrochemical battery models, this review emphasizes the prevalence of a support vector machine (SVM), fuzzy logic (FL), k-nearest neighbors (KNN) algorithm, genetic algorithm (GA), and transfer learning in SOC and SOH estimation.

In response to the efficiency bottleneck in the overall design phase of artillery, this paper proposes an agile design tool for artillery based on the RecurDyn solver, IAOD. This tool achieves rapid evaluation and optimization design of artillery dynamics simulation models through parametric modeling and integration of shooting test data. The IAOD system adopts a fully parameterized driven template model, combined with machine learning, parameter identification, and multi-level optimization algorithms, significantly improving the design efficiency of large caliber self-propelled artillery. The system innovatively applied a sparse single hidden layer neural network proxy model and a simulation parameter identification method based on test data, achieving multi-objective collaborative optimization. The effectiveness and practicality of the IAOD system have been verified through the practical application of a vehicle mounted artillery design case, demonstrating its potential for application in the field of artillery design. This study has significant military and defense value in improving the efficiency and quality of artillery equipment development.

Since product development lead-time needs to be as short as possible in contemporary enterprises, it is necessary to assess and optimise the performance of the structure in conceptual design phase for avoiding the time consuming production of trial models for vehicle body. This paper proposes a conceptual design tool based on optimisation algorithms for global body frames named vehicle concept design-intelligent CAE system (VCD-ICAE). A multilevel optimisation algorithm is applied to optimise the body performance, to decide the size parameters and generate cross-sectional shapes that satisfy design engineers' required characteristics. The global body stiffness and vibration property would be optimised while decreasing the mass of body. The paper describes the implementation of the optimal algorithm, and genetic algorithms are applied to solve the optimisation problem. A case of optimisation for a real car is given to verify the validity of the algorithm.