资源类型

期刊论文 216

年份

2023 24

2022 23

2021 17

2020 12

2019 7

2018 8

2017 14

2016 12

2015 8

2014 5

2013 11

2012 5

2011 5

2010 7

2009 16

2008 7

2007 10

2006 3

2005 3

2004 2

展开 ︾

关键词

地震预测 5

机器学习 3

预测 3

人工智能 2

储层预测 2

发展 2

地震 2

地震预报 2

寿命预测 2

汶川地震 2

汶川大震 2

深度学习 2

神经网络 2

1)模型 1

Anderson 模型 1

CO2 捕集 1

COVID-19 1

GM(1 1

GPS轨迹 1

展开 ︾

检索范围:

排序: 展示方式:

Two-phase early prediction method for remaining useful life of lithium-ion batteries based on a neural

《能源前沿(英文)》 doi: 10.1007/s11708-023-0906-4

摘要: Lithium-ion batteries (LIBs) are widely used in transportation, energy storage, and other fields. The prediction of the remaining useful life (RUL) of lithium batteries not only provides a reference for health management but also serves as a basis for assessing the residual value of the battery. In order to improve the prediction accuracy of the RUL of LIBs, a two-phase RUL early prediction method combining neural network and Gaussian process regression (GPR) is proposed. In the initial phase, the features related to the capacity degradation of LIBs are utilized to train the neural network model, which is used to predict the initial cycle lifetime of 124 LIBs. The Pearson coefficient’s two most significant characteristic factors and the predicted normalized lifetime form a 3D space. The Euclidean distance between the test dataset and each cell in the training dataset and validation dataset is calculated, and the shortest distance is considered to have a similar degradation pattern, which is used to determine the initial Dual Exponential Model (DEM). In the second phase, GPR uses the DEM as the initial parameter to predict each test set’s early RUL (ERUL). By testing four batteries under different working conditions, the RMSE of all capacity estimation is less than 1.2%, and the accuracy percentage (AP) of remaining life prediction is more than 98%. Experiments show that the method does not need human intervention and has high prediction accuracy.

关键词: lithium-ion batteries     RUL prediction     double exponential model     neural network     Gaussian process regression (GPR)    

Spatial prediction of soil contamination based on machine learning: a review

《环境科学与工程前沿(英文)》 2023年 第17卷 第8期 doi: 10.1007/s11783-023-1693-1

摘要:

● A review of machine learning (ML) for spatial prediction of soil contamination.

关键词: Soil contamination     Machine learning     Prediction     Spatial distribution    

Hybrid deep learning model for risk prediction of fracture in patients with diabetes and osteoporosis

《医学前沿(英文)》 2022年 第16卷 第3期   页码 496-506 doi: 10.1007/s11684-021-0828-7

摘要: The fracture risk of patients with diabetes is higher than those of patients without diabetes due to hyperglycemia, usage of diabetes drugs, changes in insulin levels, and excretion, and this risk begins as early as adolescence. Many factors including demographic data (such as age, height, weight, and gender), medical history (such as smoking, drinking, and menopause), and examination (such as bone mineral density, blood routine, and urine routine) may be related to bone metabolism in patients with diabetes. However, most of the existing methods are qualitative assessments and do not consider the interactions of the physiological factors of humans. In addition, the fracture risk of patients with diabetes and osteoporosis has not been further studied previously. In this paper, a hybrid model combining XGBoost with deep neural network is used to predict the fracture risk of patients with diabetes and osteoporosis, and investigate the effect of patients’ physiological factors on fracture risk. A total of 147 raw input features are considered in our model. The presented model is compared with several benchmarks based on various metrics to prove its effectiveness. Moreover, the top 18 influencing factors of fracture risks of patients with diabetes are determined.

关键词: XGBoost     deep neural network     healthcare     risk prediction    

Position-varying surface roughness prediction method considering compensated acceleration in milling

《机械工程前沿(英文)》 2021年 第16卷 第4期   页码 855-867 doi: 10.1007/s11465-021-0649-z

摘要: Machined surface roughness will affect parts’ service performance. Thus, predicting it in the machining is important to avoid rejects. Surface roughness will be affected by system position dependent vibration even under constant parameter with certain toolpath processing in the finishing. Aiming at surface roughness prediction in the machining process, this paper proposes a position-varying surface roughness prediction method based on compensated acceleration by using regression analysis. To reduce the stochastic error of measuring the machined surface profile height, the surface area is repeatedly measured three times, and Pauta criterion is adopted to eliminate abnormal points. The actual vibration state at any processing position is obtained through the single-point monitoring acceleration compensation model. Seven acceleration features are extracted, and valley, which has the highest R-square proving the effectiveness of the filtering features, is selected as the input of the prediction model by mutual information coefficients. Finally, by comparing the measured and predicted surface roughness curves, they have the same trends, with the average error of 16.28% and the minimum error of 0.16%. Moreover, the prediction curve matches and agrees well with the actual surface state, which verifies the accuracy and reliability of the model.

关键词: surface roughness prediction     compensated acceleration     milling     thin-walled workpiece    

Improved prediction of pile bending moment and deflection due to adjacent braced excavation

《结构与土木工程前沿(英文)》 doi: 10.1007/s11709-023-0961-2

摘要: Deep excavations in dense urban areas have caused damage to nearby existing structures in numerous past construction cases. Proper assessment is crucial in the initial design stages. This study develops equations to predict the existing pile bending moment and deflection produced by adjacent braced excavations. Influential parameters (i.e., the excavation geometry, diaphragm wall thickness, pile geometry, strength and small-strain stiffness of the soil, and soft clay thickness) were considered and employed in the developed equations. It is practically unfeasible to obtain measurement data; hence, artificial data for the bending moment and deflection of existing piles were produced from well-calibrated numerical analyses of hypothetical cases, using the three-dimensional finite element method. The developed equations were established through a multiple linear regression analysis of the artificial data, using the transformation technique. In addition, the three-dimensional nature of the excavation work was characterized by considering the excavation corner effect, using the plane strain ratio parameter. The estimation results of the developed equations can provide satisfactory pile bending moment and deflection data and are more accurate than those found in previous studies.

关键词: pile responses     excavation     prediction     deflection     bending moments    

Reliability prediction and its validation for nuclear power units in service

Jinyuan SHI,Yong WANG

《能源前沿(英文)》 2016年 第10卷 第4期   页码 479-488 doi: 10.1007/s11708-016-0425-7

摘要: In this paper a novel method for reliability prediction and validation of nuclear power units in service is proposed. The equivalent availability factor is used to measure the reliability, and the equivalent availability factor deducting planed outage hours from period hours and maintenance factor are used for the measurement of inherent reliability. By statistical analysis of historical reliability data, the statistical maintenance factor and the undetermined parameter in its numerical model can be determined. The numerical model based on the maintenance factor predicts the equivalent availability factor deducting planed outage hours from period hours, and the planed outage factor can be obtained by using the planned maintenance days. Using these factors, the equivalent availability factor of nuclear power units in the following 3 years can be obtained. Besides, the equivalent availability factor can be predicted by using the historical statistics of planed outage factor and the predicted equivalent availability factor deducting planed outage hours from period hours. The accuracy of the reliability prediction can be evaluated according to the comparison between the predicted and statistical equivalent availability factors. Furthermore, the reliability prediction method is validated using the nuclear power units in North American Electric Reliability Council (NERC) and China. It is found that the relative errors of the predicted equivalent availability factors for nuclear power units of NERC and China are in the range of –2.16% to 5.23% and –2.15% to 3.71%, respectively. The method proposed can effectively predict the reliability index in the following 3 years, thus providing effective reliability management and maintenance optimization methods for nuclear power units.

关键词: nuclear power units in service     reliability     reliability prediction     equivalent availability factors    

Trend prediction technology of condition maintenance for large water injection units

Xiaoli XU, Sanpeng DENG

《机械工程前沿(英文)》 2010年 第5卷 第2期   页码 171-175 doi: 10.1007/s11465-009-0091-0

摘要: Trend prediction technology is the key technology to achieve condition-based maintenance of mechanical equipment. Large-sized water injection units are key equipment in oilfields. The traditional preventive maintenance is not economical and cannot completely avoid vicious accidents. To ensure the normal operation of units and save maintenance costs, trend prediction technology is studied to achieve condition-based maintenance for water injection units. The main methods of the technology are given, the trend prediction method based on neural network is put forward, and the expert system based on the knowledge is developed. The industrial site verification shows that the proposed trend prediction technology can reflect the operating condition trend change of the water injection units and provide technical means to achieve condition-based predictive maintenance.

关键词: water injection units     condition-based maintenance     trend prediction    

Dynamic prediction of moving trajectory in pipe jacking: GRU-based deep learning framework

《结构与土木工程前沿(英文)》   页码 994-1010 doi: 10.1007/s11709-023-0942-5

摘要: The moving trajectory of the pipe-jacking machine (PJM), which primarily determines the end quality of jacked tunnels, must be controlled strictly during the entire jacking process. Developing prediction models to support drivers in performing rectifications in advance can effectively avoid considerable trajectory deviations from the designed jacking axis. Hence, a gated recurrent unit (GRU)-based deep learning framework is proposed herein to dynamically predict the moving trajectory of the PJM. In this framework, operational data are first extracted from a data acquisition system; subsequently, they are preprocessed and used to establish GRU-based multivariate multistep-ahead direct prediction models. To verify the performance of the proposed framework, a case study of a large pipe-jacking project in Shanghai and comparisons with other conventional models (i.e., long short-term memory (LSTM) network and recurrent neural network (RNN)) are conducted. In addition, the effects of the activation function and input time-step length on the prediction performance of the proposed framework are investigated and discussed. The results show that the proposed framework can dynamically and precisely predict the PJM moving trajectory during the pipe-jacking process, with a minimum mean absolute error and root mean squared error (RMSE) of 0.1904 and 0.5011 mm, respectively. The RMSE of the GRU-based models is lower than those of the LSTM- and RNN-based models by 21.46% and 46.40% at the maximum, respectively. The proposed framework is expected to provide an effective decision support for moving trajectory control and serve as a foundation for the application of deep learning in the automatic control of pipe jacking.

关键词: dynamic prediction     moving trajectory     pipe jacking     GRU     deep learning    

Prediction of the shear wave velocity

Amoroso SARA

《结构与土木工程前沿(英文)》 2014年 第8卷 第1期   页码 83-92 doi: 10.1007/s11709-013-0234-6

摘要: The paper examines the correlations to obtain rough estimates of the shear wave velocity from non-seismic dilatometer tests (DMT) and cone penetration tests (CPT). While the direct measurement of is obviously preferable, these correlations may turn out useful in various circumstances. The experimental results at six international research sites suggest that the DMT predictions of from the parameters (material index), (horizontal stress index), (constrained modulus) are more reliable and consistent than the CPT predictions from (cone resistance), presumably because of the availability, by DMT, of the stress history index .

关键词: horizontal stress index     shear wave velocity     flat dilatometer test     cone penetration test    

Liquefaction prediction using support vector machine model based on cone penetration data

Pijush SAMUI

《结构与土木工程前沿(英文)》 2013年 第7卷 第1期   页码 72-82 doi: 10.1007/s11709-013-0185-y

摘要: A support vector machine (SVM) model has been developed for the prediction of liquefaction susceptibility as a classification problem, which is an imperative task in earthquake engineering. This paper examines the potential of SVM model in prediction of liquefaction using actual field cone penetration test (CPT) data from the 1999 Chi-Chi, Taiwan earthquake. The SVM, a novel learning machine based on statistical theory, uses structural risk minimization (SRM) induction principle to minimize the error. Using cone resistance ( ) and cyclic stress ratio ( ), model has been developed for prediction of liquefaction using SVM. Further an attempt has been made to simplify the model, requiring only two parameters ( and maximum horizontal acceleration ), for prediction of liquefaction. Further, developed SVM model has been applied to different case histories available globally and the results obtained confirm the capability of SVM model. For Chi-Chi earthquake, the model predicts with accuracy of 100%, and in the case of global data, SVM model predicts with accuracy of 89%. The effect of capacity factor ( ) on number of support vector and model accuracy has also been investigated. The study shows that SVM can be used as a practical tool for prediction of liquefaction potential, based on field CPT data.

关键词: earthquake     cone penetration test     liquefaction     support vector machine (SVM)     prediction    

Machine learning-based solubility prediction and methodology evaluation of active pharmaceutical ingredients

《化学科学与工程前沿(英文)》 2022年 第16卷 第4期   页码 523-535 doi: 10.1007/s11705-021-2083-5

摘要: Solubility has been widely regarded as a fundamental property of small molecule drugs and drug candidates, as it has a profound impact on the crystallization process. Solubility prediction, as an alternative to experiments which can reduce waste and improve crystallization process efficiency, has attracted increasing attention. However, there are still many urgent challenges thus far. Herein we used seven descriptors based on understanding dissolution behavior to establish two solubility prediction models by machine learning algorithms. The solubility data of 120 active pharmaceutical ingredients (APIs) in ethanol were considered in the prediction models, which were constructed by random decision forests and artificial neural network with optimized data structure and model accuracy. Furthermore, a comparison with traditional prediction methods including the modified solubility equation and the quantitative structure-property relationships model was carried out. The highest accuracy shown by the testing set proves that the ML models have the best solubility prediction ability. Multiple linear regression and stepwise regression were used to further investigate the critical factor in determining solubility value. The results revealed that the API properties and the solute-solvent interaction both provide a nonnegligible contribution to the solubility value.

关键词: solubility prediction     machine learning     artificial neural network     random decision forests    

The prediction of adsorption isotherms of ester vapors on hypercrosslinked polymeric adsorbent

Liuyan WU,Lijuan JIA,Xiaohan LIU,Chao LONG

《环境科学与工程前沿(英文)》 2016年 第10卷 第3期   页码 482-490 doi: 10.1007/s11783-015-0826-6

摘要: Adsorption isotherms of methyl acetate, ethyl acetate, propyl acetate, isopropyl acetate and ethyl propionate on hypercrosslinked polymeric resin (ND-100) were measured at 303K, 318K and 333K,respectively, and well fitted by Dubinin–Astakhov (DA) equation. The plots of the adsorbed volume ( ) versus the adsorption potential ( ) at three different temperatures all fell basically onto one single curve for every ester. A predicted model based on DA equation was obtained on the basis of adsorption equilibrium data of methyl acetate, ethyl acetate and ethyl propionate at 318K. The model equation successfully predicted the adsorption isotherms of methyl acetate, ethyl acetate and ethyl propionate on ND-100 at 303K, and 333K, and also gave accurate predictive results for adsorption isotherms of the other two ester compounds (propyl acetate and isopropyl acetate) on ND-100 at 303K, 318K and 333K. The results proved the effectiveness of DA model for predicting the adsorption isotherms of ester compounds onto ND-100. In addition, the relationship between physico-chemical properties of adsorbates and their adsorption properties was also investigated. The results showed that molecular weight, molar volume and molar polarizability had good linear correlations with the parameter (which represents adsorption characteristic energy) of DA equation.

关键词: hypercrosslinked polymeric adsorbent     adsorption isotherm     ester     prediction    

Water quality soft-sensor prediction in anaerobic process using deep neural network optimized by Tree-structured

《环境科学与工程前沿(英文)》 2023年 第17卷 第6期 doi: 10.1007/s11783-023-1667-3

摘要:

● Hybrid deep-learning model is proposed for water quality prediction.

关键词: Water quality prediction     Soft-sensor     Anaerobic process     Tree-structured Parzen Estimator    

An energy consumption prediction approach of die casting machines driven by product parameters

《机械工程前沿(英文)》 2021年 第16卷 第4期   页码 868-886 doi: 10.1007/s11465-021-0656-0

摘要: Die casting machines, which are the core equipment of the machinery manufacturing industry, consume great amounts of energy. The energy consumption prediction of die casting machines can support energy consumption quota, process parameter energy-saving optimization, energy-saving design, and energy efficiency evaluation; thus, it is of great significance for Industry 4.0 and green manufacturing. Nevertheless, due to the uncertainty and complexity of the energy consumption in die casting machines, there is still a lack of an approach for energy consumption prediction that can provide support for process parameter optimization and product design taking energy efficiency into consideration. To fill this gap, this paper proposes an energy consumption prediction approach for die casting machines driven by product parameters. Firstly, the system boundary of energy consumption prediction is defined, and subsequently, based on the energy consumption characteristics analysis, a theoretical energy consumption model is established. Consequently, a systematic energy consumption prediction approach for die casting machines, involving product, die, equipment, and process parameters, is proposed. Finally, the feasibility and reliability of the proposed energy consumption prediction approach are verified with the help of three die casting machines and six types of products. The results show that the prediction accuracy of production time and energy consumption reached 91.64% and 85.55%, respectively. Overall, the proposed approach can be used for the energy consumption prediction of different die casting machines with different products.

关键词: die casting machine     energy consumption prediction     product parameters    

A novel hybrid model for water quality prediction based on VMD and IGOA optimized for LSTM

《环境科学与工程前沿(英文)》 2023年 第17卷 第7期 doi: 10.1007/s11783-023-1688-y

摘要:

● A novel VMD-IGOA-LSTM model has proposed for the prediction of water quality.

关键词: Water quality prediction     Grasshopper optimization algorithm     Variational mode decomposition     Long short-term memory neural network    

标题 作者 时间 类型 操作

Two-phase early prediction method for remaining useful life of lithium-ion batteries based on a neural

期刊论文

Spatial prediction of soil contamination based on machine learning: a review

期刊论文

Hybrid deep learning model for risk prediction of fracture in patients with diabetes and osteoporosis

期刊论文

Position-varying surface roughness prediction method considering compensated acceleration in milling

期刊论文

Improved prediction of pile bending moment and deflection due to adjacent braced excavation

期刊论文

Reliability prediction and its validation for nuclear power units in service

Jinyuan SHI,Yong WANG

期刊论文

Trend prediction technology of condition maintenance for large water injection units

Xiaoli XU, Sanpeng DENG

期刊论文

Dynamic prediction of moving trajectory in pipe jacking: GRU-based deep learning framework

期刊论文

Prediction of the shear wave velocity

Amoroso SARA

期刊论文

Liquefaction prediction using support vector machine model based on cone penetration data

Pijush SAMUI

期刊论文

Machine learning-based solubility prediction and methodology evaluation of active pharmaceutical ingredients

期刊论文

The prediction of adsorption isotherms of ester vapors on hypercrosslinked polymeric adsorbent

Liuyan WU,Lijuan JIA,Xiaohan LIU,Chao LONG

期刊论文

Water quality soft-sensor prediction in anaerobic process using deep neural network optimized by Tree-structured

期刊论文

An energy consumption prediction approach of die casting machines driven by product parameters

期刊论文

A novel hybrid model for water quality prediction based on VMD and IGOA optimized for LSTM

期刊论文