Lithium-Ion Battery Prognostics through Reinforcement Learning Based on Entropy Measures

Namdari, Alireza; Samani, Maryam Asad; Durrani, T.S.

doi:10.3390/a15110393

Cited by 28 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, reinforcement learning methods have driven impressive advances in artificial intelligence in recent years, surpassing human performance in many domains [22][23][24][25][26][27]. More recently, some researchers have begun to use reinforcement learning to model collective motion in a learning way [28][29][30][31].…”

Section: Related Workmentioning

confidence: 99%

Modeling Collective Behavior for Fish School With Deep Q-Networks

et al. 2023

View full text Add to dashboard Cite

Modeling collective behavior is a way to better understand the mechanisms that govern collective animal behaviors. Traditional rule-based modeling methods rely heavily on human prior knowledge and may not provide a proper explanation of the phenomenon of collective behaviors. This paper proposes a Deep Q-Networks (DQN)-based modeling method for fish school. Firstly, an individual's state (continuous value) is expressed by the angle between its direction and the average direction of its perceived neighbors. An individual's action is represented with discretized turning angle. Then, the reward function is constructed with the change in the number of neighbors. And finally, the neural network structure is constructed to represent the Q-value function and is trained by the DQN algorithm. The proposed approach is tested in two scenarios: single-learner and multi-learner. Results show that in both scenarios the proposed method can gradually converge and finally obtain a model that can produce collective behavior. On this basis, this paper also deeply analyzes the learned model from the perspectives of average order parameter and collective behavior patterns. It verifies that the behavior pattern generated by the learned model is a highly ordered collective behavior. In addition, we make a comparison between our proposed approach and the Q-Learning algorithm. The results show that our approach not only has a stronger ability to express policy and is better at handling continuous states but also has a more stable learning performance in training. INDEX TERMSCollective behavior, collective behavior model, Deep Q-Networks (DQN), fish school

show abstract

Section: Related Workmentioning

confidence: 99%

Modeling Collective Behavior for Fish School With Deep Q-Networks

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Machine learning techniques have emerged as powerful tools by extracting features from data [7] and [8].…”

Section: Introductionmentioning

confidence: 99%

Multi-Layer Perceptron and Radial Basis Function for Thyroid Disease Diagnosis

Samani,

Khazaee,

Ebadollahi

2024

Preprint

Self Cite

View full text Add to dashboard Cite

Thyroid disease is a common health disorder that affect millions of people worldwide. Achieving an accurate diagnosis often involves conducting multiple laboratory tests. However, recent advancements in machine learning have demonstrated promising outcomes in extracting meaningful information from these tests and medical images. By leveraging machine learning techniques, healthcare professionals can enhance their ability to analyze and interpret the data obtained from these tests, leading to more accurate and efficient diagnoses of thyroid dis- eases. This paper proposes a method to enhance thyroid disease diagnosis by combining Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) neural networks. The proposed method utilizes thyroid-related features to categorize a patient’s status into hyperthyroidism, hypothyroidism, or normal. UCI Machine Learning Repository is used as the training dataset for this study. To ensure high accuracy, data is randomly fitted to both the MLP and RBF networks. Additionally, an adaptive learning rate is applied in the backpropagation training for MLP. This helps avoid local minimums and reduces loss fluctuations and divergence. On the other hand, RBF is trained using the K-means algorithm together with the RLS algorithm. Based on the results, MLP outperforms RBF when the patient’s status is A or B. However, RBF shows better detection when the patient’s status is C. Therefore, the highest accuracy is achieved when the network switches from MLP to RBF based on the patient’s status. Overall, this paper suggests that combining MLP and RBF neural networks can improve the accuracy of thyroid disease diagnosis, especially when considering different patient statuses.

show abstract

“…Hence there are some recent research applying RL to the field of prognostics for RUL estimation. In [25], the researcher proposed an entropybased method that combines RL with DL models for the RUL estimation of lithium-ion batteries. And in [34], an RLbased approach was proposed to construct health indicator (HI) for the RUL prediction task based on multi-sensors.…”

Section: Introductionmentioning

confidence: 99%

Remaining Useful Life Estimation in Prognostics Using Deep Reinforcement Learning

Zhao

Wang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

In modern industrial systems, condition-based maintenance (CBM) has been wildly adopted as an efficient maintenance strategy. Prognostics, as a key enabler of CBM, involves the kernel task of estimating the remaining useful life (RUL) for engineered systems. Much research in recent years has focused on developing new machine learning (ML) based approaches for RUL estimation. A variety of ML algorithms have been employed in these approaches. However, there was no research on applying deep reinforcement learning (DRL) to RUL estimation. To fill this research gap, a novel DRL based prognostic approach is proposed for RUL estimation in this paper. In the proposed approach, the conventional RUL estimation task is first formulated into a Markov decision process (MDP) model. Then an advanced DRL algorithm is employed to learn the optimal RUL estimation policy from this MDP environment. The effectiveness and superiority of the proposed approach are demonstrated through a case study on turbofan engines in C-MAPSS dataset. Compared to other approaches, the proposed approach obtains superior performance on all four sub-datasets of C-MAPSS dataset. What is more, on the most complicated subdatasets FD002 and FD004, the RMSE metric is improved by 14.4% and 7.81%, and the score metric is improved by 3.7% and 48.79%, respectively.

show abstract

Lithium-Ion Battery Prognostics through Reinforcement Learning Based on Entropy Measures

Cited by 28 publications

References 35 publications

Modeling Collective Behavior for Fish School With Deep Q-Networks

Modeling Collective Behavior for Fish School With Deep Q-Networks

Multi-Layer Perceptron and Radial Basis Function for Thyroid Disease Diagnosis

Remaining Useful Life Estimation in Prognostics Using Deep Reinforcement Learning

Contact Info

Product

Resources

About