Density Prediction Model Research Articles

A Machine Learning-Based Model for Multiple Material Density Prediction Developed by Powder Bed Fusion Additive Manufacturing

A Machine Learning-Based Model for Multiple Material Density Prediction Developed by Powder Bed Fusion Additive Manufacturing

Probability density prediction for carbon allowance prices based on TS2Vec and distribution Transformer

Carbon allowance price is an important tool to reduce carbon emissions and achieve carbon neutrality. It is necessary to establish a predictive model to provide accurate and reliable information to managers and participants in the carbon trading market. Therefore, a novel probability density prediction model, called TS2Vec-based distribution Transformer (TDT), is proposed. TDT consists of two stages: contrastive unsupervised pre-training and supervised training. In the contrastive unsupervised training stage, time series to vector (TS2Vec) is used to represent the dynamic trends and unique features of the data. Then, these representations are fed into the distribution Transformer (DT) to fit the hypothetical probability distribution. Experimental results show that the prediction results of the proposed TDT are more accurate and reliable than other benchmark models. In addition, our research indicates reliable probability density predictions provide enterprises with opportunities to control carbon emission costs and increase economic returns, thereby improving the competitiveness of enterprises and promoting carbon emission reduction.

Personalized 3D Printing of Artificial Vertebrae: A Predictive Bone Density Modeling Approach for Robotic Cutting Applications

Robotic vertebral plate cutting poses significant challenges due to the complex bone structures of the lumbar spine, which consist of varying densities in cortical and cancellous regions. This study addresses these challenges by developing a predictive model for robotic vertebral plate cutting force and bone quality recognition through the fabrication of artificial vertebrae with controlled, consistent bone density. To address the variability in bone density between cortical and cancellous regions, CT data are utilized to predict target bone density, serving as a foundation for determining the optimal 3D printing process parameters. The proposed methodology integrates a Response Surface Methodology (RSM), Back Propagation (BP) neural network, and genetic algorithm (GA) to systematically evaluate the effects of key process parameters, such as the filling density, material flow rate, and layer thickness, on the printed vertebrae’s density. A one-factor experimental approach and RSM-based central composite design are applied to build an initial bone density prediction model, followed by Sobol’s sensitivity analysis to quantify the influence of each parameter. The GA-BP neural network model is then employed to rapidly and accurately identify optimal printing parameters for different bone layer densities. The resulting optimized models are used to fabricate personalized artificial lumbar vertebrae, which are subsequently validated through robotic cutting experiments. This research not only contributes to the advancement in personalized 3D printing technology but also provides a reliable framework for developing patient-specific surgical planning models in robot-assisted orthopedic surgery.

Short-Term Photovoltaic Power Probabilistic Forecasting Based on Temporal Decomposition and Vine Copula

With the large-scale development of solar power generation, highly uncertain photovoltaic (PV) power output has an increasing impact on distribution networks. PV power generation has complex correlations with various weather factors, while the time series embodies multiple temporal characteristics. To more accurately quantify the uncertainty of PV power generation, this paper proposes a short-term PV power probabilistic forecasting method based on the combination of decomposition prediction and multidimensional variable dependency modeling. First, a seasonal and trend decomposition using a Loess (STL)-based PV time series feature decomposition model is constructed to obtain periodic, trend, and residual components representing different characteristics. For different components, this paper develops a periodic component prediction model based on TimeMixer for multi-scale temporal feature mixing, a long short-term memory (LSTM)-based trend component extraction and prediction model, and a multidimensional PV residual probability density prediction model optimized by Vine Copula optimized with Q-Learning. These components’ results form a short-term PV probabilistic forecasting method that considers both temporal features and multidimensional variable correlations. Experimentation with data from the Desert Knowledge Australia Solar Center (DKASC) demonstrates that the proposed method reduced root mean square error (RMSE) and mean absolute percentage error (MAPE) by at least 14.8% and 22%, respectively, compared to recent benchmark models. In probability interval prediction, while improving accuracy by 4% at a 95% confidence interval, the interval width decreased by 19%. The results show that the proposed approach has stronger adaptability and higher accuracy, which can provide more valuable references for power grid planning and decision support.

Consistent predictive ability of prostate-specific antigen density prediction model for clinically significant prostate cancer across age strata.

Prebiopsy prostate-specific antigen density (PSAD) is a well-known predictor of clinically significant prostate cancer (csPCa). Since prostate-specific antigen(PSA) and prostate volume (PV) increase normally with aging, PSAD thresholds may vary. The purpose of the study was to determine if PSAD was predictive of csPCa in different age strata. We retrospectively reviewed our institutional database for patients who underwent multiparametricmagnetic resonance imaging (MRI) between January 2016 and December 2021. We included patients who had post-MRI prostate biopsies. Based on age, we divided our cohort into four subgroups (groups 1-4): <55, 55-64, 65-74, and ≥75 years old. PSAD accuracy was estimated by the area under the curve (AUC) as a predictive model for differentiating csPCa between the groups. CsPCa was defined as a Gleason Grade Group 2 or higher. Three different PSAD thresholds (0.1, 0.15, and 0.2) were tested across the groups for sensitivity, specificity, and positive predictive value (PPV) and negative predictive value(NPV). Chi-square and analysis of variance tests were used for bivariate analysis. All analyswere completed using R 4.3 (R Core Team, 2023). Among 1913 patients, 883 (46.1%) had prostate biopsies. In groups 1, 2, 3, and 4, there were 62 (7%), 321 (36.4%), 404 (45.8%), and 96 (10.9%) patients, respectively. Median PSA was 5.6 (interquartile range 3.4-8.1), 6.2 (4.8-9), 6.8 (5.1-9.7), and 9 (5.6-13), respectively (p < 0.01). Median PV was 42.3 (30-62), 51 (36-77), 55.5 (38-85.9), and 59.3 (42-110) mL, respectively (p < 0.01). No difference was observed in median PSAD between age groups 1-4 (0.1 [0.07-0.16], 0.11 [0.08-0.18], 0.1 [0.07-0.19], and 0.1 [0.07-0.2]), respectively (p = 0.393). CsPCa was diagnosed in 241 (27.3%) patients, of which 10 (16.1%), 65 (20.2%), 121 (30%), and 45 (46.7%) were in groups 1-4, respectively (p < 0.001). For groups 1-4, the PSAD AUC for predicting csPCa was 0.75, 0.68, 0.71, and 0.74. While testing PSAD threshold of 0.15 across the different age groups (1-4), the PPV vs.NPV was 39.1 vs. 93.2, 33.6 vs. 87, 50.9 vs. 80.8, and 66.1 vs. 64.7, respectively. PSAD prediction model was found to be similar among different age groups. In young patients, PSAD had a high NPV but low PPV. With increasing age, the opposite trend was observed, likely due to higher disease prevalence. While PSAD thresholds may be less useful in older patients to rule out higher-grade prostate cancer, the clinical consequences of these diagnoses require a case-by-case evaluation.

Field Study and Analysis of Passenger Density in the Beijing Subway Transfer Hall

Passenger density is a major factor influencing indoor climate conditions and the corresponding energy consumption in the transfer halls of metro transportation hubs. In this study, passenger flow in a subway transfer hall in Beijing was measured across three typical seasons. A differential equation model was established to account for the characteristics of passenger density. Based on this, a passenger density prediction model was developed and utilized for analysis. The results show that passenger density is primarily affected by operation time and the surrounding population composition, with a relatively weak correlation to outdoor weather conditions. Additionally, passenger density differs significantly between weekdays and weekends, with the weekday peak being 2.5 times higher than that on weekends. During the four peak hours on weekdays, both in the morning and evening, passenger density exceeds the design capacity, resulting in insufficient fresh air supply. However, for most of the weekday hours and for all hours on weekends, passenger density remains below the design capacity. This indicates a substantial potential for energy savings by adjusting the fresh air supply according to actual passenger density.

Study on wind power prediction based on improved double wavelet transform and quantile regression forest

Abstract The random fluctuation of a wind power system will bring significant challenges to its stable operation when connected to the grid[1]. To reduce the impact of microgrid wind power integration on electric power systems and in response to the certain prediction inaccuracy of BP, LSSVM, and ARIMA-based prediction models in case of rapid fluctuation of actual power, a method of decomposing the original wind power sequence into several characteristic subcomponents through the improved double wavelet transform algorithm was proposed in this study to weaken the fluctuation of the wind power sequence. Specifically, a short-term wind power probability density prediction model based on the improved double wavelet algorithm and quantile regression method was established. Then, the original wind power sequence was decomposed into a series of components with different frequencies using the double wavelet transform method. Suitable components were chosen to construct a QRF prediction model to acquire the prediction results.

Density Prediction Model of Binary or Ternary Diesel Fuel Blends with Biodiesel and Ethanol for Compression-Ignition Engine Calculations

Density Prediction Model of Binary or Ternary Diesel Fuel Blends with Biodiesel and Ethanol for Compression-Ignition Engine Calculations

The eutectic and physicochemical properties of the carboxylic-acid-based deep eutectic solvents

The excellent performance of the deep eutectic solvent (DES) is consistent with the 12 Principles of Green Chemistry. It is of importance to study the DES’s structural characteristics, thermophysical properties and physicochemical properties, especially the DES’s solid–liquid-equilibrium phase diagrams in the entire mole fraction. In this work, ten DES were prepared using tetrabutylammonium bromide as the hydrogen bond acceptor, and octanoic acid/hexanoic acid as the hydrogen bond donors. The molar ratio ranged from 1:1.25 to 1:4. Then, the solid–liquid-equilibrium phase diagrams were obtained. The eutectics and the corresponding eutectic points were discovered. The nuclear magnetic resonance spectra and the Fourier transform infrared spectra were applied to analyze the interactions in DES. The densities and viscosities of the prepared DES were measured. With the optimized Lydersen-Joback-Reid method combined with Lee-Kesler rules, the critical properties were predicted. And then the results were verified through a density prediction model. The average absolute relative deviation (AARD) is better than 1.38%. The mass-connectivity-index-based model was introduced for density prediction with AARD of less than 0.17%. For the viscosity, the Arrhenius equation was compared with an equation considering the molar mass. The AARD of them were less than 2.68 % and 0.69 %, respectively.

Analysis of dust deposition law at the micro level and its impact on the annual performance of photovoltaic modules

Solar photovoltaic (PV) power generation is a promising clean energy technology, but dust affects its performance. This study, conducted in nine Chinese cities with varying climates and geographies, analyzed the physicochemical properties of dust and its deposition patterns at different inclination angles using microanalysis. Inclination angles were classified into three categories, and a dust density prediction (DDP) model was developed for each. The study also quantified the effect of different dust densities on PV module temperature in a controlled environment and created a PV module output power prediction (POPP) model to assess dust accumulation impacts on PV efficiency. It was found that dust insulation could increase PV module output power by 1.64 %–1.79 % at dust densities of 5–10 g/m2 and radiation levels of 400–800 W/m2. Combining the DDP and POPP models, a PV efficiency loss rate model was proposed to evaluate annual average PV efficiency and power generation losses at different tilting angles. Results showed an annual average PV efficiency loss of over 7 % at a 15° inclination angle and about 4.5 % at a 90° inclination angle. This study provides a framework for evaluating PV module mounting angles and cleaning intervals, optimizing solar energy systems for improved efficiency and returns.

Improved density prediction model based on global optimization algorithm for GPR system

Density prediction models are key to pavement compaction and density estimation using ground penetrating radar (GPR). However, current models do not account for the effects of dielectric constant errors and rely on limited data for parameter fitting. This article introduces an electromagnetic (EM) mixing theory and genetic algorithm (GA) based density prediction model named EM-GA. A comprehensive density database is established from literature, laboratory and field tests. After comparing Bayesian optimization, GA, simulated annealing (SA), and particle swarm optimization (PSO), the GA, which performs the best, is selected. On the testing set, the EM-GA model outperforms traditional models, with a notable reduction of 43.6 % in Mean Absolute Percentage Error (MAPE) and 39.8 % in Root Mean Square Error (RMSE). More importantly, the EM-GA predictions are accurate in the validation of four continuous survey lines. The proposed EM-GA model effectively enhances the accuracy of GPR-based density estimation for newly constructed asphalt pavement.

Accurate Density Prediction of Sesquiterpenoid HEDFs and the Multiproperty Computing Server SesquiterPre.

Accurate and rapid evaluation of density is crucial for evaluating the packing and combustion characteristics of high-energy-density fuels (HEDFs). This parameter is pivotal in the selection of high-performance HEDFs. Our study leveraged a polycyclic compound density data set and quantum chemical (QC) descriptors to establish a correlation with the target properties using the XGBoost algorithm. We utilized a recursive feature elimination method to simplify the model and developed a concise and interpretable density prediction model incorporating only six QC descriptors. The model demonstrated robust performance, achieving coefficients of determination (R 2) of 0.967 and 0.971 for internal and external test sets, respectively, and root-mean-square errors (RMSE) of 0.031 and 0.027 g/cm3, respectively. Compared to the other two mainstream methods, the marginal discrepancy between the predicted and actual molecular densities underscores the model's superior predictive ability and more usefulness for energy density calculation. Furthermore, we developed a web server (SesquiterPre, https://sespre.cmdrg.com/#/) that can simultaneously calculate the density, enthalpy of combustion, and energy density of sesquiterpenoid HEDFs, which greatly facilitates the use of researchers and is of great significance for accelerating the design and screening of novel sesquiterpenoid HEDFs.

Separation density prediction of geldart A– dense medium in gas-solid fluidized bed coal beneficiators

Gas-solid Fluidized Bed Coal Beneficiator (GFBCB) process is a crucial dry coal beneficiation fluidization technology. The work employs the GFBCB process alongside a novel Geldart A– dense medium, consisting of Geldart A magnetite particles and Geldart C ultrafine coal, to separate small-size separated objects in the GFBCB. The effects of various operational conditions, including the volume fraction of ultrafine coal, the gas velocity, the separated objects size, and the separation time, were investigated on the GFBCB's separation performance. The results indicated that the probable error for 6∼3 mm separated objects could be controlled within 0.10 g/cm3. Compared to the traditional Geldart B/D dense medium, the Geldart A/A– dense medium exhibited better size-dependent separation performance with an overall probable error 0.04∼0.12 g/cm3. Moreover, it achieved a similar separation accuracy to the Geldart B/D dense medium fluidized bed with different external energy for the small-size object beneficiation. The work furthermore validated a separation density prediction model based on theoretical derivation, available for both Geldart B/D dense medium and Geldart A/A– dense medium at different operational conditions.

Rapid accomplishment of cost-effective and macro-defect-free LPBF-processed Ti parts based on deep data augmentation

Machine learning methods can accurately predict the density of as-built parts by laser power bed fusion (LPBF), providing a reference for optimizing process parameters. However, obtaining massive training data via experiments is time-consuming and high-cost. Herein, a novel data augmentation method based on the Wasserstein generative adversarial network and regularization strategy (LC-WGAN) was developed to generate new training data for density prediction modelling. Four machine learning (ML) algorithms, support vector regression (SVR), multilayer perceptron (MLP), random forest (RF) and gradient boosting decision tree (GBDT), were adopted to construct the density prediction models. Results show that the proposed LC-WGAN effectively enhanced the prediction performance of all four models. R2 of MLP dramatically increased by 73.06 %, while that of RF and GBDT was marginally improved by 10.07 % and 7.48 %, respectively. RF trained by augmented dataset has the highest prediction performance on test set with MAE, RMSE and R2 of 0.7589, 0.9584 and 0.9822, respectively, which is suitable for density prediction. Additionally, SHAP analysis reveals that energy density is the most important parameter with an overall positive impact on density. The proposed method can provide valuable insights for the limited sample modelling in other fields.

A prediction model of maximum dry density of over coarse-grained soil

The control of maximum dry density is an important issue for over coarse-grained soil. A theoretical formula of the maximum dry density for over coarse-grained soil was derived, which is related to the maximum dry density of the original soil, particle density, and mass fraction of giant particles in the mixed soil. Maximum dry densities of seven groups of mixed soil were calculated by the discrete element method (DEM) and theoretical formula, and the results showed that the maximum dry densities obtained from the DEM were always lower than the results calculated by theoretical formula, and the difference increased with the increase in giant particle proportion. The volume growth coefficient was proposed to describe the increase in pore volume of the mixed soil caused by the embedding of giant particles, and the maximum dry density model for over coarse-grained soil was proposed. The results showed that the model fitted well to the DEM results, validating the high rationality and reliability.

Prediction of Density in Standing Trees of Various Wood Species in Natural Forests Using Near-infrared Spectroscopy

Density plays an important role as basic information for applying wood as construction materials. Recent years, the application of near-infrared spectroscopy as non-destructive testing (NDT) has been promising. Density prediction for standing trees in huge variation trees and species of natural forest needs to be investigated using NDT as of eco-green harvesting. The combination of density information and near-infrared spectroscopy is enabled to build a prediction model. This research applied increment cores sampling for density prediction analysis using near-infrared spectroscopy method. The research combined increment cores samples from multiple wood species to be analyzed in one chemometrics analysis of cross-validation partial least squares regression (CV-PLSR) to build a prediction model of density. The research resulted coefficient of determination for cross-validation (R2CV) of 0.76 with number of latent variable (LV) 10 from the 1st derivative with 13 smoothing-point spectra and wavelength of 1200 – 1800 nm as the best prediction model. The result seemed sufficient enough with those number of LV for this small tube wood sampling of increment cores from multiple wood species. This research proved that building a prediction model for multiple wood species is possible to be done.

Development and validation of a hybrid model for prediction of viable cell density, titer and cumulative glucose consumption in a mammalian cell culture system

Among the many approaches to build predictive models for bioprocesses, hybrid models have gained increased attention due to their ability to combine data driven approaches with process knowledge. This study develops and compares hybrid models that predict the performance of a mammalian CHO cell culture producing a therapeutic product. Three machine learning algorithms, MLP, Random Forest and XGBoost regressors are compared to understand the effect of algorithm choice on the rates predicted and overall performance of the hybrid model. When combined in series with mechanistic equations, all three algorithms could predict next day Viable Cell Density, titer and the cumulative amount of glucose consumed with low error, although decision tree-based algorithm required less computational time for training. The models performed well using a dataset for a new product, without further model training. Retraining the model on a subset of data from the new product improved the prediction accuracy of VCD and titer. The potential for application and further model developments are also outlined.

The coordinated evolution of ecological environment, public service, and tourism economy along the Silk Road Economic Belt, using the Dual-Carbon Targets

Carbon peak and carbon neutrality (dual-carbon) are important targets for the international response to climate change. The Silk Road Economic Belt is a strategic resource region and is important for future ecological environment and tourism development. Based on the “dual-carbon” targets, the Single index quantification, Multiple index synthesis, and Poly-criteria integration evaluation model were used in this study to measure the coordinated development index of the ecological environment, public service, and tourism economy along the Silk Road Economic Belt and to analyze its spatial and temporal evolution. Further, it explores the dynamic evolution and development trend of the three systems using the Kernel Density and Grey Markov Prediction Model. The results show that the coordinated development index along this region needs to be improved during the study period. Furthermore, the coordinated development index of the Southwest region is relatively higher than that of the Northwest region. From the development trend of the three systems, all of them develop in a stable manner; however, the tourism economy system is easily affected by external disturbances. The coordinated development index of the three systems changes dynamically and tends to be in a good state of coordination. There is a certain spatial and temporal heterogeneity. The gravity center of the coordinated development index has been in the Southwest region. During the forecast period, the coordinated development index along this region will improve significantly, while insufficient and unbalanced development will continue.

Application of near-infrared spectroscopy for predicting the wood density of teakwood stands by increment cores and thin wood surface sampling

Density, as the most critical information for wood materials could be predicted by near-infrared (NIR) spectroscopy. Increment cores and thin wood samples of teakwood ( Tectona grandis) served as research materials for this new approach to sampling for NIR spectroscopy, explained in detail. Density data were combined with their NIR spectra data for analysis using cross-validation partial least squares regression as chemometrics to produce a density prediction model. A new approach of increment cores from teakwood stands for NIR spectroscopy measurements for density predictions resulting in a 0.34 coefficient of determination for cross-validation (R2CV) and 0.40 of R2CV for thin wood samples as the best result from the first derivative with 25 smoothing points of NIR spectra. The improvement from the previous research for density prediction accuracy resulted in an R2CV value of 0.55. The smaller diameter of the increment core sample than the NIR light beam's diameter and illuminated mixed surface (transversal and radial) are supposed to give weaker prediction accuracy by this new approach.

Deep Learning Model for Magnetic Flux Density Prediction in Magnetic Spring on the Vibration Generator

Deep Learning Model for Magnetic Flux Density Prediction in Magnetic Spring on the Vibration Generator