Jiahuan Lu

Nanjing University of Posts and Telecommunications

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Rui Xiong

Fuzhou University

Jinpeng Tian

Hong Kong Polytechnic University

Weixiang Shen

Swinburne University of Technology

Fengchun Sun

Beijing Institute of Technology

Zeyu Chen

Northeastern University

Chenxu Wang

Washington State University

Zhao Yang

Institute of Art

Rong Tang

Nanjing University of Information Science and Technology

Ying Yang

Australian Catholic University

Yimu Ji

Nanjing University of Posts and Telecommunications

Cooperative Institutions

Beijing Institute of Technology

Northeastern University

Nanjing University of Aeronautics and Astronautics

Chinese Academy of Sciences

Huazhong University of Science and Technology

Peking University

Beijing University of Posts and Telecommunications

Nanjing University of Posts and Telecommunications

Southeast University

University of Shanghai for Science and Technology

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Battery degradation prediction against uncertain future conditions with recurrent neural network enabled deep learning

Energy storage materials (2022)

Jiahuan Lu Rui Xiong Jinpeng Tian Chenxu Wang Chia‐Wei Hsu

Degradation

10.1016/j.ensm.2022.05.007

Cite

Citations (140)

Data‐driven battery degradation prediction: Forecasting voltage‐capacity curves using one‐cycle data

EcoMat (2022)

Jinpeng Tian Rui Xiong Weixiang Shen Jiahuan Lu

Abstract With the wide deployment of rechargeable batteries, battery degradation prediction has emerged as a challenging issue. However, battery life defined by capacity loss provides limited information regarding battery degradation. In this article, we explore the prediction of voltage‐capacity curves over battery lifetime based on a sequence to sequence (seq2seq) model. We demonstrate that the data of one present voltage‐capacity curve can be used as the input of the seq2seq model to accurately predict the voltage‐capacity curves at 100, 200, and 300 cycles ahead. This offers an opportunity to update battery management strategies in response to the predicted consequences. Besides, the model avoids feature engineering and is flexible to incorporate different numbers of input and output cycles. Therefore, it can be easily transplanted to other battery systems or electrochemical components. Furthermore, the model features data generation, that is, we can use the data of only one cycle to generate a large spectrum of aging data at the future cycles for developing other battery diagnosis or prognosis methods. In this way, the time and energy consuming battery degradation tests can be sharply reduced. image

Battery capacity

Degradation

Charge cycle

Capacity loss

10.1002/eom2.12213

Cite

Citations (32)

Online Estimation of State of Power for Lithium-Ion Batteries in Electric Vehicles Using Genetic Algorithm

IEEE Access (2018)

Jiahuan Lu Zeyu Chen Ying Yang Ming L.V.

Online estimation of the state of power (SoP) of lithium-ion batteries is crucial for both battery management system and energy management system in electric vehicles. In this paper, the approach of online estimating the SoP is investigated with a concern of the impact of the imprecise state of charge (SoC). First, the characteristics of lithium batteries under different state of health (SoH) conditions are experimented based on a typical vehicle driving cycle; then the SOP estimation algorithm using genetic algorithm (GA) is proposed to deal with the long time-scale estimation for power management application, on top of that, the sensitivity coefficient (δ) of the SoP estimation to the SoC precision is analyzed and the correlations of δ with the varying SoH, estimation time-scale are established. Finally, the presented algorithm is evaluated by a simulation study. The proposed GA-based estimation method can improve the SoP estimation accuracy by up to 7.2% in certain cases compared with the traditional Taylor method.

State of charge

State of health

10.1109/access.2018.2824559

Cite

Citations (57)

A Deep-Learning-Based CPR Action Standardization Method

Sensors (2024)

Yongyuan Li Ming‐Jie Yin Wenxiang Wu Jiahuan Lu Shangdong Liu

In emergency situations, ensuring standardized cardiopulmonary resuscitation (CPR) actions is crucial. However, current automated external defibrillators (AEDs) lack methods to determine whether CPR actions are performed correctly, leading to inconsistent CPR quality. To address this issue, we introduce a novel method called deep-learning-based CPR action standardization (DLCAS). This method involves three parts. First, it detects correct posture using OpenPose to recognize skeletal points. Second, it identifies a marker wristband with our CPR-Detection algorithm and measures compression depth, count, and frequency using a depth algorithm. Finally, we optimize the algorithm for edge devices to enhance real-time processing speed. Extensive experiments on our custom dataset have shown that the CPR-Detection algorithm achieves a mAP0.5 of 97.04%, while reducing parameters to 0.20 M and FLOPs to 132.15 K. In a complete CPR operation procedure, the depth measurement solution achieves an accuracy of 90% with a margin of error less than 1 cm, while the count and frequency measurements achieve 98% accuracy with a margin of error less than two counts. Our method meets the real-time requirements in medical scenarios, and the processing speed on edge devices has increased from 8 fps to 25 fps.

Margin (machine learning)

10.3390/s24154813

Cite

Citations (0)

Battery state-of-charge estimation amid dynamic usage with physics-informed deep learning

Energy storage materials (2022)

Jinpeng Tian Rui Xiong Jiahuan Lu Cheng Chen Weixiang Shen

State of charge

Fuse (electrical)

10.1016/j.ensm.2022.06.007

Cite

Citations (149)

Deep neural network battery impedance spectra prediction by only using constant-current curve

Energy storage materials (2021)

Yanzhou Duan Jinpeng Tian Jiahuan Lu Chenxu Wang Weixiang Shen

Constant current

Constant (computer programming)

10.1016/j.ensm.2021.05.047

Cite

Citations (59)

Methods for Mango and Ripeness Detection Using Improved YOLOv8

2021 IEEE International Conference on Unmanned Systems (ICUS) (2024)

Jiahuan Lu Xiangye Lin Chenglin Li Shan Zeng Xiwen Luo

Ripeness

10.1109/icus61736.2024.10839762

Cite

Citations (0)

Sentiment Classification of E-Commerce Product Quality Reviews by FL-SVM Approaches

Yi Liu Jiahuan Lu Sabina Shahbazzade

In order to improve the accuracy of sentiment classification for e-commerce products quality reviews, this paper proposed the FL-SVM approaches which use the fuzzy theory measure the level of emotional polarity of sentiment words to construct the fuzzy sentiment dictionary based on the How Net, the support vector machine (SVM) is adopted to construct the classifier model for evaluating the sentiment tendency of e-commerce product quality reviews. Compared to the NB, kNN and SVM algorithm, the experiments on different data sets show that the FL SVM approaches can achieve the better sentiment classification accuracy increased by 1% ~ 3%, which verifies the effectiveness and robustness of the proposed approaches.

Sentiment Analysis

Robustness

10.1109/icci-cc.2018.8482058

Cite

Citations (2)

Real-time Trajectory Prediction of Unmanned Aircraft Vehicles Based on Gated Recurrent Unit

Lecture notes in electrical engineering (2021)

Rong Tang Zhao Yang Jiahuan Lu Hao Liu Honghai Zhang

Longitude

10.1007/978-981-16-5429-9_45

Cite

Citations (4)

The product quality risk assessment of e-commerce by machine learning algorithm on spark in big data environment

Journal of Intelligent & Fuzzy Systems (2019)

Yi Liu Jiahuan Lu Feng Mao Kaidi Tong

In order to pre-warning the product quality risk of the e-commerce platform, this paper studies the machine learning algorithm for the products quality risk assessment, which propose the Fuzzy C-Means clustering algorithm for the feature extraction and the Cost Sensitive Leaning (CSL)-Naive Bayesia n algorithm to construct the assessment model for E-commerce product quality risk form the massive and unbalanced data. The experimental results show that the Machine Learning algorithm based on Spark has better scalability and superiority in the large-scale data environment, which can accurately identify e-commerce product quality risk.

SPARK (programming language)

10.3233/jifs-179305

Cite

Citations (27)