Real-Time Integrated Energy Management Strategy Applied to Fuel Cell Hybrid Systems

Abstract

Integrating hydrogen fuel cell systems (FCS) remains challenging in the expanding electric vehicle market. One of the levers to meet this challenge is the relevance of energy supervisors. This paper proposes an innovative energy management strategy (EMS) based on the integrated EMS (iEMS) concept. It uses a nested approach combining the best of the three EMS categories (optimization-based (OBS), rules-based (RBS), and learning-based (LBS) strategies) to overcome the real-time operating condition limitations of the fuel cell hybrid electric vehicle (FCHEV). Through a fuel cell/battery hybrid architecture, the purpose is to improve hydrogen consumption and manage the battery state of charge (SOC) under real-time driving conditions. The proposed iEMS approach is based on an OBS with optimal control to make the energy-optimal decision. However, it requires the adaptations of real-time operating conditions and a dynamic SOC horizon management. These requirements are supported by combining an RBS based on expert and fuzzy rules to compute the SOC target on each sliding window and an LBS based on fuzzy C-mean clustering to enhance the cooperative environment data processing and adapt it to the FHCEV topology. Our approach obtained simple and realistic system behaviors while having an acceptable computing time suitable for real time constraint. It was then designed and validated using a 27-hour real-time measured database. The results show the effectiveness of the proposed iEMS concept with an excellent performance close to the optimal offline strategy (an under 2% consumption gap).

Review of Energy Management Methods for Fuel Cell Vehicles: From the Perspective of Driving Cycle Information

“…In addition, some papers propose combined EMMs to further improve fuel economy while ensuring FC durability, such as DP-ECMS [107], the rule-based fuzzy control method [108], adaptive neuro-fuzzy inference system-ECMS (ANFIS-ECMS) [109], and MPC-PMP [110]. As a new research hotspot in the field of artificial intelligence (AI) and internet of vehicles (IOV), learning-based and cycle information-based EMMs have been applied to achieve the optimal fuel economy of FCVs in real time [63,111]. Progress, challenges, and potential solutions of learning-based EMMs for FCVs have been reviewed in detail in [112][113][114] and will not be further elaborated here.…”

“…Progress, challenges, and potential solutions of learning-based EMMs for FCVs have been reviewed in detail in [112][113][114] and will not be further elaborated here. More importantly, considering the importance of driving cycle information in the design and development of EMMs for FCVs, the following summarizes the existing papers from two perspectives: driving pattern As a new research hotspot in the field of artificial intelligence (AI) and internet of vehicles (IOV), learning-based and cycle information-based EMMs have been applied to achieve the optimal fuel economy of FCVs in real time [63,111]. Progress, challenges, and potential solutions of learning-based EMMs for FCVs have been reviewed in detail in [112][113][114] and will not be further elaborated here.…”

“…In addition, the DPR effect of the fuzzy controller relies heavily on engineering intuition, and it frequently fails to achieve satisfactory results. In [63], Matignon et al developed the online DPR using the fuzzy C-means clustering technique. The developed driving pattern recognizer could be mainly summarized into four steps: (i) database preprocessing, (ii) data standardization, (iii) classification, and (iv) online DPR modeling, as shown in Figure 3a.…”

“…The developed driving pattern recognizer could be mainly summarized into four steps: (i) database preprocessing, (ii) data standardization, (iii) classification, and (iv) online DPR modeling, as shown in Figure 3a. The DPR method proposed in [63] adopts standardized velocity and acceleration as the input and provides the driving pattern as the output (see Figure 3b). In other studies of this area, supervised algorithms are adopted to recognize the vehicle driving pattern [64], such as support vector machines (SVM) [65], learning vector quantization (LVQ) [66], and artificial neural networks (ANN) [67].…”

Energy Management in Hybrid Electric and Hybrid Energy Storage System Vehicles: A Fuzzy Logic Controller Review

“…The proposed Fuzzy-Reinforce utilizes Policy Gradient Reinforcement Learning (PGRL), demonstrating stability, speed, and lower hydrogen consumption compared to traditional RL in Hardware-in-the-Loop (HIL) simulations. Matignom et al synthesize learning-based, rule-based, and optimization-based EMS strategies into an integrated EMS[118]. Utilizing Fuzzy C-means for driving pattern recognition, fuzzy rule-based methods, and online PMP optimization, the proposed strategy achieves performance close to optimal offline strategies.…”