"I am passionately driving the creation of innovative solutions for electromobility, energy storage, and beyond, employing machine learning and blockchain algorithms as pivotal tools."

Energy Storage | Data Science | Blockchain | Artificial Intelligence | Smart-Grids

MSc. Carlos Rufino Júnior

Associate Researcher at Center of Automotive Research on Integrated Safety Systems and Measurement Area (CARISSMA)



iBattMan - Intelligent, Connected, and Secure Battery Management System, Enhanced by Next-Generation Cloud and Edge Computing, Sensors, and Interoperable Architecture - European Project

In this project, we will design an innovative, modular, and scalable BMS for a wide range of vehicles, from small passenger cars to electric buses and trucks, offering improved performance, connectivity, security, and reliability.

This aims to enhance battery performance and reduce the total cost of ownership in electric vehicle applications and smart battery usage for grid support and second-life applications, based on a holistic design of an interoperable architecture, supported by a suite of advanced sensors, and cloud computing capabilities. 

The project has a total budget of over 6M€ and will last for 42 months. The consortium consists of 11 European partners.

PRIMA - Batteries (PRedictive Industrial Maintenance Agent for Batteries) 

The PRIMA project aims to develop a digital twin of a battery, for real-time battery control, recording the relevant battery data in a cloud solution. The solution proposed in the PRIMA project has the main objective of predicting the maintenance of batteries, it also allows monitoring and control of the battery in real-time. He has experience in developing blockchain applications, battery modeling, battery real-time control, high fidelity models, machine learning, digital twins, lithium-ion batteries, signal processing, battery simulation, and applied artificial intelligence to solve various problems.

Second-Life Batteries

Electric vehicles are a promising means of transport, as they are less polluting than conventional vehicles.  However, the high cost of batteries makes the purchase of electric vehicles less attractive financially when compared to conventional vehicles. For this reason, there is a need for research aimed at reducing the cost of batteries, as well as making their application in real scenarios possible. One of the alternatives for reducing the cost of batteries is reuse, that is, the use of batteries in a second application.  This   reuse   consists   of   reusing   the   deactivated   batteries   of   electric   vehicles   in   less demanding applications, such as in   applications connected to the grid   to increase the efficiency, stability   and   reliability   of   the   electrical   power   system.   An   energy   storage   system   must   meet environmental, safety and performance requirements. Therefore, this project proposes to raise the state of the art of the reuse of lithium batteries by means of a comparison regarding the main technologies developed, their advantages and disadvantages, the main types of energy management systems, the quantification of the environmental impacts obtained through the reuse of batteries, the costs and technical and economic feasibility of reusing batteries.




Blockchain-based battery tracking platform

The use of technologies such as Internet of Things (IoT), data processing and blockchain have allowed companies to serve their customers with better quality, efficiency, reliability and in the shortest possible time. The growing adoption of electric vehicles on the market has increased the demand for batteries that may have numerous manufacturers. The supply chain for electric vehicle batteries is very complex because it involves everything that lies between the retrieval of raw materials for batteries manufacturing to the second-life batteries marketing and logistics and to their disposal. Batteries come from different parts of the world, belonged to different citizens and companies, experienced heterogeneous operational conditions and therefore have a different life expectancy. A large number of parameters have a role on battery health and thousands of data that need to be evaluated and consulted. The present work investigates the scenario of the battery industry in order to implement a blockchain-based platform for the supply chain implementation thus allowing a better control on performance of batteries and environmental impact. Through this system, it is possible to achieve greater transparency in the entire supply chain: production, reuse, recycle, disposal. Trasparency and traceability prevent clandestine markets, misuse and release of pollutants.

Blockchain-based fuel tracking platform

The fuel production ecosystem (from the extraction of long-chain hydrocarbons to the distribution and retailing of fuels) is made up of numerous companies and intermediaries. A common problem in the transportation sector is related to the millions of liters of fuel that are stolen, as well as miscalculations and mismanagement of a valuable and scarce resource. It is extremely difficult to estimate the damage of these illicit activities to companies. The damage can be divided into four significant areas, namely: economic, political, technical and environmental. These frauds are difficult to identify and eliminate because they can involve different parties with conflicts of interest and sometimes internal employees of the company. These issues can be addressed through a distributed IoT system capable of tracking fuel efficiently. This system can encompass the entire fuel production and retail ecosystem, encouraging and increasing the product credibility of gas station networks and independent gas stations. This system will eliminate illicit activity and will inhibit the spread of this activity to various gas stations. It will also be possible to estimate, reduce and keep fuel prices constant, preventing a price from being charged for a fuel of questionable quality. Avoiding fuel adulteration is directly related to reducing greenhouse gas emissions and environmental impacts. That's because adulterated fuel tends  to  emit  more  greenhouse  gases  and particulate  matter  than  unadulterated  fuels.  Furthermore, adulterated fuel increases the need for greater oil extraction and consequently reduces a scarce and valuable resource.

Distributed IoT system for real-time monitoring and tracking of locomotives

The transport sector is one of the main contributors to a country's carbon emissions. Among the modes of transport, there is transport by locomotives, which is a source of greenhouse gas emissions, as well as emissions of atmospheric pollutants such as NOx and PM. In addition to sustainability, fuel thefts are frequent in operating locomotives. Approximately 150 225 liters of fuel are stolen from rail transport in the Swedish market. This fuel theft of the direct impacts of fuel theft, indirect impacts are reported as: (i) delay in product delivery, (ii) need to tow the locomotive, (iii) financial losses. Fuel can account for more than 25% of a railway's total operating cost. The Blockchain-based platform has a broad scope and aims to record and integrate data making it available to the engineering, quality, supply chain and operational teams. Thus, data recording on this platform will be done by operators from different sectors, from the locomotive driver to strategic levels. 

Statistical Signal Processing Applied to Smart Grids

The main objective of this proposal is to develop methodologies for the application of statistical signal processing (PES) to Smart Grids. Among the statistical signal processing tools, the Principal Component Analysis (PCA - Principal Component Analysis), Independent Component Analysis (ICA - Independent Component Analysis) and Higher-order Statistics (HOS - Higher-order) techniques will be explored in this proposal. Statistics). These tools have in common the good ability to: (i) handle large data; (ii) extracting relevant (usually hidden) information from electrical signals; (iii) decompose signals into isolated components; (iv) estimating parameters and (v) designing adaptive filters. The methodologies to be developed will focus on application in the so-called smart grids, or Smart Grids, in a context of distributed generation (GD). Smart grids must have a set of basic functions that allow the modernization of the electrical infrastructure, among which the following stand out: (1) self-reconfiguration capacity; (2) be fault tolerant, resisting hacker attacks; (3) enable the integration of all energy source and storage options; (4) allow dynamic optimization of network operation; (5) allow the active participation of consumers; and (6) improving the reliability, power quality, safety and efficiency of the power system. Some of these functions are obviously not new, as the energy infrastructure has always relied on intelligent technologies for its operation, control and protection, etc., but in this new scenario of great penetration of distributed and dispersed generation, it will be necessary to make efforts in research and in the development of new technologies to solve the problems that are already beginning to appear on the networks. In this context, the main contributions of this project are: (i) the development of a system for classifying the causes of voltage sags; (ii) development of an islanding detection system; (iii) development of a method for extracting harmonic, subharmonic and interharmonic components and (iv) the proposal of a methodology for signal compression...

Monitoring the Quality of Electric Power with Statistical Signal Processing and Computational Intelligence

This project addresses the problem of power quality (EQ) in the current scenario characterized by the strong penetration of solar and wind energy in the context of Smart Grids. In this new scenario of great penetration of distributed and dispersed generation, it will be necessary to make efforts in research and in the development of new technologies to solve the problems that are already beginning to appear in the networks. In this sense, the general objective of this project is to develop and improve advanced techniques for statistical signal processing and computational intelligence for three purposes: (1) extraction of harmonics, interharmonics and subharmonics; (2) segmentation and classification of the causes of voltage dips; and (3) detection and classification of new PQ disorders. Regarding purpose (1), the techniques known as principal component analysis (PCA) and independent component analysis (ICA) will be improved and applied in comparison with the works in the literature and the advances already made by the project team. Regarding purpose (2), the ICA technique will be applied to segment voltage sags and higher order statistics (EOS) along with neural networks will be applied to identify the causes of voltage sags. In purpose (3), techniques involving concepts such as cognition, adaptability and evolution in PQ monitoring will be applied for the purpose of detecting and classifying novelties (new PQ phenomena). The methods will be tested on simulated and real signals via MatLab. It is expected to implement them in FPGA and LabView..


Please contact me at carlos.rufino@carissma.eu to know more about the projects