The accurate prediction of battery pack capacity in electric vehicles(EVs)is crucial for ensuring safety and optimizing performance.Despite extensive research on predicting cell capacity using laboratory data,predicti...The accurate prediction of battery pack capacity in electric vehicles(EVs)is crucial for ensuring safety and optimizing performance.Despite extensive research on predicting cell capacity using laboratory data,predicting the capacity of onboard battery packs from field data remains challenging due to complex operating conditions and irregular EV usage in real-world settings.Most existing methods rely on extracting health feature parameters from raw data for capacity prediction of onboard battery packs,however,selecting specific parameters often results in a loss of critical information,which reduces prediction accuracy.To this end,this paper introduces a novel framework combining deep learning and data compression techniques to accurately predict battery pack capacity onboard.The proposed data compression method converts monthly EV charging data into feature maps,which preserve essential data characteristics while reducing the volume of raw data.To address missing capacity labels in field data,a capacity labeling method is proposed,which calculates monthly battery capacity by transforming the ampere-hour integration formula and applying linear regression.Subsequently,a deep learning model is proposed to build a capacity prediction model,using feature maps from historical months to predict the battery capacity of future months,thus facilitating accurate forecasts.The proposed framework,evaluated using field data from 20 EVs,achieves a mean absolute error of 0.79 Ah,a mean absolute percentage error of 0.65%,and a root mean square error of 1.02 Ah,highlighting its potential for real-world EV applications.展开更多
The trade-off between mechanistic interpretability,operational convenience,and predictive accuracy is challenging for predicting the lifetime of lithium-ion batteries.To resolve this contradiction,we propose a damage ...The trade-off between mechanistic interpretability,operational convenience,and predictive accuracy is challenging for predicting the lifetime of lithium-ion batteries.To resolve this contradiction,we propose a damage model based on fatigue damage theory and electrochemical impedance spectroscopy.The causal relationship of“fatigue damage→resistance increase→capacity fading”is revealed to describe the underlying mechanism.Charge transfer resistance is chosen as the variable to ensure the convenience of data acquisition.To verify the accuracy of the model,the electrochemical impedance spectrum and capacity of a graphene-coated silicon electrode at two charging rates are collected and analyzed.50% and 75% of the measured data are utilized as inputs to compare the prediction capabilities of the proposed damage model and the existing empirical model.The particle filter algorithm is adopted to train the parameters of both models.The maximum prediction error of the damage model is less than 3%,showing better prediction accuracy and medium-term prediction stability than the empirical model.Our work demonstrates that the proposed damage model is an effective way to resolve contradictions in lifetime prediction.展开更多
Lithium-ion batteries have become the mainstream power source for electric vehicles because of their excellent performance.However,lithium-ion batteries still experience aging and capacity attenuation during usage.It ...Lithium-ion batteries have become the mainstream power source for electric vehicles because of their excellent performance.However,lithium-ion batteries still experience aging and capacity attenuation during usage.It is therefore critical to accu-rately predict battery remaining capacity for increasing battery safety and prolonging battery life.This paper first adopts the metabolism grey algorithm and a simplified electrochemical model to predict battery capacity under different operating conditions.To improve the prediction performance where the capacity changes nonlinearly,a decoupling analysis of battery capacity loss is then conducted based on the simplified electrochemical model.Finally,an adaptive fitting method is devel-oped for capacity prediction,aiming at improving the prediction accuracy at the inflection point of battery capacity diving.The prediction results indicate that the developed adaptive fitting method can achieve high prediction accuracy under battery capacity attenuation at different discharge stages with errors lower than 2.2%.And the battery capacity decay shows linear variation,and the proposed method effectively forecast the inflection point of battery capacity diving.展开更多
Due to the increase in the types of business and equipment in telecommunications companies,the performance index data collected in the operation and maintenance process varies greatly.The diversity of index data makes...Due to the increase in the types of business and equipment in telecommunications companies,the performance index data collected in the operation and maintenance process varies greatly.The diversity of index data makes it very difficult to perform high-precision capacity prediction.In order to improve the forecasting efficiency of related indexes,this paper designs a classification method of capacity index data,which divides the capacity index data into trend type,periodic type and irregular type.Then for the prediction of trend data,it proposes a capacity index prediction model based on Recurrent Neural Network(RNN),denoted as RNN-LSTM-LSTM.This model includes a basic RNN,two Long Short-Term Memory(LSTM)networks and two Fully Connected layers.The experimental results show that,compared with the traditional Holt-Winters,Autoregressive Integrated Moving Average(ARIMA)and Back Propagation(BP)neural network prediction model,the mean square error(MSE)of the proposed RNN-LSTM-LSTM model are reduced by 11.82%and 20.34%on the order storage and data migration,which has greatly improved the efficiency of trend-type capacity index prediction.展开更多
By analyzing the flow character of a single drainage borehole in its effectingtime and the correlative theory introduced,the reason for 'inflexion' appearance in theflow character curve of the single draining ...By analyzing the flow character of a single drainage borehole in its effectingtime and the correlative theory introduced,the reason for 'inflexion' appearance in theflow character curve of the single draining borehole in a multi-borehole was studied.Takingthe theory of permeation fluid mechanics and so on as basis,the coalbed gas flowmodel was set up,and the numerical simulation analyzer was built for undermine gasproducts.With the results from the analyzer,the gas capacity could be calculated underdifferent conditions and comparisons made with the site measurement data.展开更多
Soft computing techniques are becoming even more popular and particularly amenable to model the complex behaviors of most geotechnical engineering systems since they have demonstrated superior predictive capacity,comp...Soft computing techniques are becoming even more popular and particularly amenable to model the complex behaviors of most geotechnical engineering systems since they have demonstrated superior predictive capacity,compared to the traditional methods.This paper presents an overview of some soft computing techniques as well as their applications in underground excavations.A case study is adopted to compare the predictive performances of soft computing techniques including eXtreme Gradient Boosting(XGBoost),Multivariate Adaptive Regression Splines(MARS),Artificial Neural Networks(ANN),and Support Vector Machine(SVM) in estimating the maximum lateral wall deflection induced by braced excavation.This study also discusses the merits and the limitations of some soft computing techniques,compared with the conventional approaches available.展开更多
In this study,normal values of semen analysis were set for a general infertile population of couples among which most women had normal ovulation.The predictive capacity values of sperm quality,including concentration,...In this study,normal values of semen analysis were set for a general infertile population of couples among which most women had normal ovulation.The predictive capacity values of sperm quality,including concentration,motile count,progressive motile count,and morphology,are unclear for women with polycystic ovary syndrome(PCOS).A secondary analysis was conducted based on a randomized controlled trial investigating infertility among women with PCOS experiencing ovulatory disorder between 2011 and 2016 in China.A total of 1000 women received ovulation induction(acupuncture and clomiphene).We randomized the women with PCOS in 27 hospitals in China who received one of four interventions(acupuncture plus clomiphene,sham acupuncture plus clomiphene,acupuncture plus placebo,or sham acupuncture plus placebo).Semen analysis was performed for every male partner according to the World Health Organization(WHO)criteria.The outcomes included conception,clinical pregnancy,and live birth.Logistic regression was used to evaluate the predictive value of semen analysis among ovulatory women for conception,clinical pregnancy,and live birth.Among the 1000 couples,the number of couples who attained ovulation,conception,clinical pregnancy,and live birth were 780,320,235,and 205,respectively.Semen volume and motility were applied and used as prediction parameters for conception(area under the curve(AUC)of 0.62(95%confidence interval(CI),0.55–0.69)),clinical pregnancy(AUC of 0.67(95%CI:0.61–0.73)),and live birth(AUC of 0.57(95%CI:0.50–0.64)).No poor calibration was shown for these models in Hosmer–Lemeshow tests.The predictive capacity of semen analysis for treatment outcome in PCOS women with PCOS experiencing with ovulatory dysfunction is limited.展开更多
This paper is discussing several features of the impact of AI(artificial intelligence)on society and human behavior.It includes(1)the question if the AI can outperform the intelligent and creative capacity of humans,(...This paper is discussing several features of the impact of AI(artificial intelligence)on society and human behavior.It includes(1)the question if the AI can outperform the intelligent and creative capacity of humans,(2)if AI capabilities could show criticality and causal emergence,(3)the predictive capacity of AI,(4)the costs related to the learning process and operating AI,and(5)the loss of consensual reality and the rise of deepfakes in the AI era.AI involves considerable systemic risks impacting the social,economic,cultural,and environmental systems.Our will is kept in accordance with how the things around us are presented to us and that is precisely what AI is also doing.For us circumstances define a situation or a moment.For AI the circumstances are just statistical relationships.AI does not have its own values but incorporates the values on which it is trained.The imaginative gap between humans and AI is not just big;it’s of an essential nature.We want not just technology in the online world;we want a moral attitude.展开更多
基金supported in part by the Science and Technology Department of Sichuan Province(No.2025ZNSFSC0427,No.2024ZDZX0035)the Open Project Fund of Vehicle Measurement,Control and Safety Key Laboratory of Sichuan Province(No.QCCK2024-004)the Industrial and Educational Integration Project of Yibin(No.YB-XHU-20240001)。
文摘The accurate prediction of battery pack capacity in electric vehicles(EVs)is crucial for ensuring safety and optimizing performance.Despite extensive research on predicting cell capacity using laboratory data,predicting the capacity of onboard battery packs from field data remains challenging due to complex operating conditions and irregular EV usage in real-world settings.Most existing methods rely on extracting health feature parameters from raw data for capacity prediction of onboard battery packs,however,selecting specific parameters often results in a loss of critical information,which reduces prediction accuracy.To this end,this paper introduces a novel framework combining deep learning and data compression techniques to accurately predict battery pack capacity onboard.The proposed data compression method converts monthly EV charging data into feature maps,which preserve essential data characteristics while reducing the volume of raw data.To address missing capacity labels in field data,a capacity labeling method is proposed,which calculates monthly battery capacity by transforming the ampere-hour integration formula and applying linear regression.Subsequently,a deep learning model is proposed to build a capacity prediction model,using feature maps from historical months to predict the battery capacity of future months,thus facilitating accurate forecasts.The proposed framework,evaluated using field data from 20 EVs,achieves a mean absolute error of 0.79 Ah,a mean absolute percentage error of 0.65%,and a root mean square error of 1.02 Ah,highlighting its potential for real-world EV applications.
基金supported by the National Natural Science Foundation of China(12021002,12472183,and 12041201).
文摘The trade-off between mechanistic interpretability,operational convenience,and predictive accuracy is challenging for predicting the lifetime of lithium-ion batteries.To resolve this contradiction,we propose a damage model based on fatigue damage theory and electrochemical impedance spectroscopy.The causal relationship of“fatigue damage→resistance increase→capacity fading”is revealed to describe the underlying mechanism.Charge transfer resistance is chosen as the variable to ensure the convenience of data acquisition.To verify the accuracy of the model,the electrochemical impedance spectrum and capacity of a graphene-coated silicon electrode at two charging rates are collected and analyzed.50% and 75% of the measured data are utilized as inputs to compare the prediction capabilities of the proposed damage model and the existing empirical model.The particle filter algorithm is adopted to train the parameters of both models.The maximum prediction error of the damage model is less than 3%,showing better prediction accuracy and medium-term prediction stability than the empirical model.Our work demonstrates that the proposed damage model is an effective way to resolve contradictions in lifetime prediction.
基金supported by China Postdoctoral Science Foundation(2021M690740)the Weihai Scientific Research and Innovation Funds(2019KYCXJJYB09).
文摘Lithium-ion batteries have become the mainstream power source for electric vehicles because of their excellent performance.However,lithium-ion batteries still experience aging and capacity attenuation during usage.It is therefore critical to accu-rately predict battery remaining capacity for increasing battery safety and prolonging battery life.This paper first adopts the metabolism grey algorithm and a simplified electrochemical model to predict battery capacity under different operating conditions.To improve the prediction performance where the capacity changes nonlinearly,a decoupling analysis of battery capacity loss is then conducted based on the simplified electrochemical model.Finally,an adaptive fitting method is devel-oped for capacity prediction,aiming at improving the prediction accuracy at the inflection point of battery capacity diving.The prediction results indicate that the developed adaptive fitting method can achieve high prediction accuracy under battery capacity attenuation at different discharge stages with errors lower than 2.2%.And the battery capacity decay shows linear variation,and the proposed method effectively forecast the inflection point of battery capacity diving.
基金supported by Research on Big Data Technology for New Generation Internet Operators(H04W180609)the second batch of Sichuan Science and Technology Service Industry Development Fund Projects in 2018(18KJFWSF0388).
文摘Due to the increase in the types of business and equipment in telecommunications companies,the performance index data collected in the operation and maintenance process varies greatly.The diversity of index data makes it very difficult to perform high-precision capacity prediction.In order to improve the forecasting efficiency of related indexes,this paper designs a classification method of capacity index data,which divides the capacity index data into trend type,periodic type and irregular type.Then for the prediction of trend data,it proposes a capacity index prediction model based on Recurrent Neural Network(RNN),denoted as RNN-LSTM-LSTM.This model includes a basic RNN,two Long Short-Term Memory(LSTM)networks and two Fully Connected layers.The experimental results show that,compared with the traditional Holt-Winters,Autoregressive Integrated Moving Average(ARIMA)and Back Propagation(BP)neural network prediction model,the mean square error(MSE)of the proposed RNN-LSTM-LSTM model are reduced by 11.82%and 20.34%on the order storage and data migration,which has greatly improved the efficiency of trend-type capacity index prediction.
文摘By analyzing the flow character of a single drainage borehole in its effectingtime and the correlative theory introduced,the reason for 'inflexion' appearance in theflow character curve of the single draining borehole in a multi-borehole was studied.Takingthe theory of permeation fluid mechanics and so on as basis,the coalbed gas flowmodel was set up,and the numerical simulation analyzer was built for undermine gasproducts.With the results from the analyzer,the gas capacity could be calculated underdifferent conditions and comparisons made with the site measurement data.
基金supported by High-end Foreign Expert Introduction program (No.G20190022002)Chongqing Construction Science and Technology Plan Project (2019-0045)
文摘Soft computing techniques are becoming even more popular and particularly amenable to model the complex behaviors of most geotechnical engineering systems since they have demonstrated superior predictive capacity,compared to the traditional methods.This paper presents an overview of some soft computing techniques as well as their applications in underground excavations.A case study is adopted to compare the predictive performances of soft computing techniques including eXtreme Gradient Boosting(XGBoost),Multivariate Adaptive Regression Splines(MARS),Artificial Neural Networks(ANN),and Support Vector Machine(SVM) in estimating the maximum lateral wall deflection induced by braced excavation.This study also discusses the merits and the limitations of some soft computing techniques,compared with the conventional approaches available.
基金This study was supported by the National Public Welfare Projects for Chinese Medicine(201107005)the National Key Research and Development Program of China(2019YFC1709500)+2 种基金the Project of Heilongjiang University of Chinese Medicine(2018RCQ12 and 2019BS09)the Projects of Heilongjiang Provincial Administration of Traditional Chinese medicine(ZHY2020-102)Xuzhou Clinical Medical Team Talent Introduction Project--Academician Yixun Liu Integrated Chinese and Western medicine,Maternity and Reproductive Technology Innovation Team,and Academician Yixun Liu Workstation Project.
文摘In this study,normal values of semen analysis were set for a general infertile population of couples among which most women had normal ovulation.The predictive capacity values of sperm quality,including concentration,motile count,progressive motile count,and morphology,are unclear for women with polycystic ovary syndrome(PCOS).A secondary analysis was conducted based on a randomized controlled trial investigating infertility among women with PCOS experiencing ovulatory disorder between 2011 and 2016 in China.A total of 1000 women received ovulation induction(acupuncture and clomiphene).We randomized the women with PCOS in 27 hospitals in China who received one of four interventions(acupuncture plus clomiphene,sham acupuncture plus clomiphene,acupuncture plus placebo,or sham acupuncture plus placebo).Semen analysis was performed for every male partner according to the World Health Organization(WHO)criteria.The outcomes included conception,clinical pregnancy,and live birth.Logistic regression was used to evaluate the predictive value of semen analysis among ovulatory women for conception,clinical pregnancy,and live birth.Among the 1000 couples,the number of couples who attained ovulation,conception,clinical pregnancy,and live birth were 780,320,235,and 205,respectively.Semen volume and motility were applied and used as prediction parameters for conception(area under the curve(AUC)of 0.62(95%confidence interval(CI),0.55–0.69)),clinical pregnancy(AUC of 0.67(95%CI:0.61–0.73)),and live birth(AUC of 0.57(95%CI:0.50–0.64)).No poor calibration was shown for these models in Hosmer–Lemeshow tests.The predictive capacity of semen analysis for treatment outcome in PCOS women with PCOS experiencing with ovulatory dysfunction is limited.
文摘This paper is discussing several features of the impact of AI(artificial intelligence)on society and human behavior.It includes(1)the question if the AI can outperform the intelligent and creative capacity of humans,(2)if AI capabilities could show criticality and causal emergence,(3)the predictive capacity of AI,(4)the costs related to the learning process and operating AI,and(5)the loss of consensual reality and the rise of deepfakes in the AI era.AI involves considerable systemic risks impacting the social,economic,cultural,and environmental systems.Our will is kept in accordance with how the things around us are presented to us and that is precisely what AI is also doing.For us circumstances define a situation or a moment.For AI the circumstances are just statistical relationships.AI does not have its own values but incorporates the values on which it is trained.The imaginative gap between humans and AI is not just big;it’s of an essential nature.We want not just technology in the online world;we want a moral attitude.
