Batteries are essential for electric vehicles and other forms of green energy-powered transportation, such as hydrogen-fuelled vehicles. Batteries are rechargeable and provide fast energy delivery to compensate for the slow response of fuel cells in hydrogen fuelled vehicles. The Battery Management System (BMS) manages the battery to maximise performance, which depends on environmental conditions, and thus reduce battery degradation and lengthen the lifetime. A key element of the BMS is to estimate the critical variables of the battery, such as state-of-charge and state-of-health.
Using physical equations to model systems is desirable when possible but variables such as wear and degradation are notoriously difficult to estimate, which is where a BMS can benefit from the availability of data. The use of data in the estimation of such wear and degradation variables can improve both the reliability and accuracy of estimates. The data can be used not only for the initial offline development of the estimator, but also for continuous online improvement.
ISC has been developing its skills in artificial intelligence (AI) and machine learning (ML) over the last decade, mostly in the automotive and process industries. Although AI has had success in industrial applications to assist management planning and future initiatives, the engineering applications of ML have been more limited.
Our recent work in the area included applications of the the AI/ML technology to improve the reliability and accuracy of estimating critial variables encountered in BMS, such as state-of-charge and state-of-health.
We have also produced an easy-to-use BMS data analysis and design tool in MATLAB Simulink. Contact us for more info.
ISC provides independent, high quality control engineering consultancy and R & D services and training courses to the automotive industry, including the control of autonomous vehicles.
We provide standard, industry specific and bespoke courses on a range of fundamental and advanced control engineering topics.
ISC is working with NXP and have explored ways to mitigate the wear and damage to batteries using for example rainfall counting algorithms to provide an index for assessment.
In this Scottish Enterprise funded project, ISC addressed the problem of optimising energy use whilst reducing the degradation of expensive components, particularly fuel cells and batteries, in zero-emission heavy-duty vehicles powered by a combination of hydrogen fuel cells and batteries which is needed to provide a faster response and to enable energy to be captured through regenerative breaking. A new energy management control system was produced and tested using simulation. Various control solutions were tested and the results were analysed and retuned/optimised.
This Scottish Enterprise funded project focuses on optimising the performance and control of batteries in various transport applications from heavy goods vehicles to marine systems. The work exploits recent advances in AI to improve the quality of the estimators needed for determining critical variables of the battery, such as state-of-charge and state-of-health. The new data-driven, AI/ML-based estimation algorithm improves the estimation performance by exploiting advanced statistical theory and data-driven techniques. The resulting design tool reduces the development effort and cost.