Model For Prediction Of Thickness Research Articles

Numerical and experimental investigation of calcium sulfate crystallization fouling under upward subcooled flow boiling

In this paper, a quasi-unsteady mathematical model was presented to examine the crystallization fouling of the calcium sulfate aqueous solutions under upward subcooled flow boiling (SFB). An experimental set-up is also fabricated to collect experimental data for validating the model results. The developed model can axially and radially determine the temperature variation. An asymptotic predictive model was also used to calculate the heat transfer coefficients. Theoretical results of the bulk and surface temperatures at any desired location of the test section were coupled with the fouling formation equations to provide an integrated model for prediction of variable fouling resistance and deposit thickness along the heat transfer surface. Besides, variation of local heated surface and deposit surface temperatures as well as the pressure drop were theoretically evaluated over time while the deposit grows on the heated surface. The simulation results showed that reaction is the controlling mechanism when SFB is predominant.

Minimum cutting thickness prediction model for micro-milling machining and experimental Study of FeCoNiCrMn high-entropy alloy machining

FeCoNiCrMn high entropy alloy has excellent properties such as high hardness, high strength and high wear resistance, which has a broad application prospect in aerospace, military and other fields. As an emerging difficult-to-machine material, the minimum cutting thickness determines the highest machining accuracy of micro-milling. In order to improve the micro-milling quality of FeCoNiCrMn high-entropy alloy, a minimum cutting thickness prediction model based on the effective front angle of the tool is established according to the analysis of micro-milling force model. Through the FeCoNiCrMn high-entropy alloy micro-milling processing experiments, the milling force parameters are calculated by substituting them into the prediction model, and the minimum cutting thickness value of FeCoNiCrMn high-entropy alloy is 1.367 μm when the flank radius of the milling cutter is 5 μm.When the feed rate of each tooth is in the range of 1 μm–1.5 μm, the severe size effect and the ploughing effect lead to the specific cutting energy nonlinearly increase, and the cutting force and surface roughness increase sharply with large fluctuations. From this, the range of the minimum cutting thickness of the high-entropy alloy was judged to be between 1 μm and 1.5 μm, and the accuracy of this prediction model was verified.

Joint prediction method for strip thickness and flatness in hot strip rolling process: A combined multi-indicator Transformer with embedded sliding window

Thickness and flatness are important quality indicators for strip. It is important that the rapid and accurate prediction of the exit thickness and flatness for the optimal control of the hot strip rolling process. Due to the fast and long rolling process, there are time delays, non-linearity and strong coupling among the variables, which cause difficulties in the establishment of prediction models. In this paper, the variables related to thickness and flatness are selected by analyzing the rolling process mechanism and data. Based on the data related to the rolling quality, a rolling exit thickness and flatness joint prediction model combined multi-indicator Transformer with embedded sliding window (SW-MTrans) is proposed. First, a sliding window is embedded into the input layer of the model in order to address the effect of the time delay among variables. Then a Transformer network is improved to achieve accurate prediction of thickness and flatness simultaneously. It is verified that the proposed method can predict the thickness and flatness at the same time with higher prediction accuracy and generalization ability compared with other methods through actual production data. The mean absolute error (MAE) for thickness prediction was reduced by 19.37% and MAE for flatness prediction was reduced by 14.03% compared to the existing prediction model.

Tolerated outlier prediction method of excavation damaged zone thickness of drift based on interpretable SOA-QRF ensemble learning

ABSTRACT Drift excavation induces excavation damaged zones (EDZ) due to stress redistribution, impacting drift stability and rock deformation support. Predicting EDZ thickness is crucial, but traditional machine learning models are susceptible to potential outliers in dataset. Directly eliminating outliers, however, impacts training effectiveness. This study introduces an EDZ thickness prediction model utilising quantile loss and random forest (RF) optimised by the seagull optimisation algorithm (SOA), enabling median regression with tolerated outlier performance. 209 sets of data sets containing 34 mine borehole data were used to establish the prediction model. Evaluation using R 2, explained variance score (EVS), mean absolute error (MAE), and mean square error (MSE) demonstrates the superior accuracy of the proposed SOA-QRF model compared to traditional models. Based on the discussion on the treatment of outliers, the outcomes indicate that the SOA-QRF model is more suitable for the dataset with outliers as well as being able to effectuate tolerated outlier prediction. Additionally, three interpretation methods were utilised to explain the SOA-QRF model and enhance the transparency of the model’s prediction process and facilitating the analysis of dispatcher regulation.

Transmission Line Icing Prediction Based on Dynamic Time Warping and Conductor Operating Parameters

Aiming to improve on the low accuracy of current transmission line icing prediction models and ignoring the objective law of icing of transmission lines, a transmission line icing prediction model considering the effect of transmission line tension on the bundle of icing thickness is proposed, based on a convolutional neural network (CNN) and bidirectional gated recurrent unit (BiGRU). Firstly, the finite element calculation model of the conductor and insulator system was established, and the change rule between transmission line tension and icing thickness was studied. Then, the convolutional neural network and bidirectional gated recurrent unit were used to construct a transmission line icing thickness prediction model The model incorporated a weighted fusion of soft−dynamic time warping (Soft−DTW) and the icing change rule as the loss function. Optimal weights were determined through the utilization of the grid search algorithm and cross−validation, contributing to an enhancement of the model’s generalization capabilities and a reduction in prediction errors. The results indicate that the proposed prediction model can consider the impact of line operating parameters, avoiding the shortcomings of prediction results conflicting with actual physical laws. Compared with traditional non−mechanical models, the proposed model showed reductions in root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) by 0.26–0.51%, 0.24–0.44%, and 5.77–13.33%, respectively, while the coefficient of determination (R2) increased by 0.07–0.13.

Top burr thickness prediction model in milling of thin-walled workpiece considering tool and workpiece deformation

Top burr thickness prediction model in milling of thin-walled workpiece considering tool and workpiece deformation

Spreading process and characteristics of silicone oil with multi-viscosities on calm liquid surface with low temperature: Spreading length, stable thickness and morphology

Oil spreading on the sea has been a great focus, especially along with the intensification of oil development activities in arctic regions, leading to an increase in the frequency of oil spills in extremely cold regions. Currently, the effect of extreme low temperature on oil spreading behavior has not been fully studied, and the applicability of existing models of oil spreading characteristics in low temperature scenarios is not clear. An experimental platform was customized to set up low temperature liquid substrate environments (−20∼20 °C). A series of oil spreading experiments of silicone oil with viscosities of 50, 100, 350 and 1000 cs and five released volumes (1–5 ml) on low temperature substrates were carried out. The effects of experimental variables including temperature, viscosity and volume on oil spreading characteristics of spreading length, stable thickness, morphology, and cone angle were investigated. The entire spreading process of oil was displayed from the top and side views, and gave the variation curves of oil thickness and cone angle with time. Summarized the spreading law for multi-viscosity silicone oils, the values of the pre-exponential coefficient and the power-law exponent were determined, and detailed formulas for calculating the spreading length was proposed. An stable thickness prediction model that integrates all the forces on the oil spreading process was constructed, including surface tension, viscous force, inertia force and gravity. These forces all weakening with time, especially the inertial and viscous forces, which contain time terms, and weaken the most. The heat transfer between the oil and the liquid substrate was also monitored and discussed in the experiments, proposed that low temperatures may hinder the spreading behavior of the oil by decreasing the spreading coefficient of the oil. The findings of this study can provide a theoretical support for the oil spill cleanup.

A two‐stage scheduling model for urban distribution network resilience enhancement in ice storms

AbstractThis paper proposes a two‐stage stochastic scheduling model for urban distribution network resilience enhancement against ice storms, which coordinates mobile deicing equipment routing and distributed energy resources dispatching. An improved line ice thickness prediction model and a photovoltaic power generation prediction method in accordance with conditional generative adversarial networks are proposed to provide data boundaries for scheduling strategy. Facing the uncertainty of line failure, a two‐stage scenario‐based distribution network optimization model is established. At first stage, the mobile deicing equipment routing strategy is decided to mitigate the impact caused by ice storms. The Monte‐Carlo simulation method is introduced to describe the uncertainty of line failure due to ice acceleration. For the second stage, based on the results of photovoltaic forecasting and possible distribution line failure scenario generated by Monte‐Carlo simulation method, the optimal distributed energy resources dispatching strategy can be obtained through the mixed integer programming. The proposed model is simplified to a mixed integer linear programming model that can be solved by a commercial solver. The test results on the modified IEEE 33‐node system and modified 69‐node system demonstrate that the proposed method can effectively improve the resilience performance of urban distribution network under ice storms.

Transmission line icing thickness prediction model based on ISSA-CNN-LSTM

The prediction of transmission line ice cover thickness can effectively guide the scientific operation and maintenance of the power sector. An improved sparrow search algorithm, convolutional neural network and long short-term memory fusion ice cover prediction model is proposed in this paper. Environmental temperature, humidity, wind speed and other data are firstly normalised, CNN is used to both learn the data signature as well as input the results into LSTM, and then ISSA is used to optimise the parameters of LSTM such as the numeration of the neuron, the initial learning rate, and the regularisation coefficient, etc., and then the final output is the predicted value of the icing thickness of the transmission line cover. The simulation results show that the MSE and MAE of the ISSA-CNN-LSTM model are 0.23 and 0.37, respectively, which are much better than the prediction results of the SSA and CNN models.

Asphalt pavement water film thickness detection and prediction model: A review

Asphalt pavement water film thickness detection and prediction model: A review

Modeling and investigation of minimum chip thickness for silicon carbide during quasi-intermittent vibration–assisted swing cutting

In micromachining, the quasi-intermittent vibration—assisted swing cutting technology alleviates the residual height problem of elliptical vibration–assisted cutting (EVC) and inherits its intermittent machining characteristics. The minimum chip thickness has a significant impact on cutting forces, tool wear, and process stability when working with difficult-to-machine materials. This study thoroughly examines the impact of cutting parameters and tool parameters on the quality of the workpiece during machining in order to better understand the time-varying characteristics of the quasi-intermittent vibration–assisted swing cutting (QVASC) machining process and the size effect on micro-cutting of silicon carbide crystal. This paper created the minimum chip thickness prediction model suited to QVASC machining process. The effects of variables such as cutting velocity and tool inclination on the minimum chip thickness were discussed as well as the scribing tests that were conducted on such challenging materials as silicon carbide. The research findings shown that during the machining process, the critical undeformed chip thickness of silicon carbide decreased continuously as the cutting velocity sequentially increased (1.51 mm/min, 1.88 mm/min, 2.26 mm/min); under the down inclination angle (0–10°), the critical undeformed chip thickness also continuously decreased. These results confirm that cutting too fast reduces the instantaneous undeformed chip thickness, which is not conducive to ductile removal.

Effect of structural parameters of corrugated plate on the evolution of solitary waves and liquid film thickness distribution

The effect of wall distortion of the scrubbing-cooling tube on turbulent falling film is significant. The wall distortion was simplified by using corrugated plates; the effect of structural parameters (amplitude and wavelength) of corrugated plates on the action mechanism of solitary waves and the axial distribution of liquid film thickness were investigated. The results show that the Coanda effect decelerates and accelerates the flowing liquid film attached to the wall, which leads to the generation and extinction of solitary waves on the liquid film. The intensification of the local perturbation easily promotes the solitary waves to form slender water columns. Under the effect of Plateau-Rayleigh instability, the tails of the slender water columns break up to form tiny droplets. The mean liquid film thickness prediction model can accurately predict the mean liquid film thickness on corrugated plates (amplitude/wavelength = 0.02 ∼ 0.08) and the relative errors within ± 15%.

Study of Formation and Growth Behavior of CO<sub>2</sub> Hydrate Films

The objective of this study is to elucidate the formation and growth behavior of CO2 hydrate. Based on hydrate film thickness measurements, the process of hydrate film development was classified into "formation" and "growth". A macro-scale thickness prediction model based on mass transport was constructed for these processes. Molecular dynamics calculations were also introduced and combined with the macro-scale prediction model to construct a model capable of predicting film thickness.

A Coal Seam Thickness Prediction Model Based on CPSAC and WOA–LS-SVM: A Case Study on the ZJ Mine in the Huainan Coalfield

The precise prediction of coal seam thickness in operating mines is crucial for the construction of transparent mines. Geological borehole data or a small amount of seismic information is frequently used in traditional coal seam thickness prediction methods; however, these methods have poor precision. In this study, we introduced a model for predicting coal seam thickness based on the comprehensive preference for seismic attribute combination (CPSAC) and the least squares support vector machine (LS-SVM) optimized by the whale optimization algorithm (WOA). We used the CPSAC to modify the mass disturbed data in the seismic attribute data to predict the coal seam thickness. To achieve this the sample size was reduced by optimizing the seismic attribute combinations, and the modified attribute data was entered into the LS-SVM., Furthermore, to create an accurate prediction model for coal thickness, we employed the WOA to determine the optimal penalty coefficient and kernel coefficient of the LS-SVM. An empirical case study was conducted in the northeast mining area of the ZJ mine in the Huainan coalfield. The coal thickness of two mining faces in this research area were estimated and compared, demonstrating the proposed method’s high prediction accuracy. The proposed method has guiding implications for developing an accurate mining geological model and facilitating the accurate use of coal resources.

Prediction and Simulation of cold rolled strip thickness based on PSO-SVM-AdaBoost

In order to improve the quality of cold-rolled strip production products, this paper focuses on the problem of thickness prediction accuracy in the production process of cold-rolled strip steel. The rolling data is obtained from the simulation model of the MATLAB. Firstly, this paper comprehensively considers the main influencing factors affecting the cold rolling thickness, secondly, analyses the thickness related parameter variables and combines with the actual production environment, finally a cold rolling thickness prediction model based on PSO-SVM-AdaBoost is proposed. The model is based on the SVM model. The particle swarm algorithm(PSO) optimizes the penalty parameters and kernel parameters of the SVM model. The AdaBoost algorithm integrates weak predictors into strong predictors to improve the prediction performance of the algorithm. In order to illustrate the prediction effect of the model, compared with the prediction results of BP neural network, SVM, PSO-SVM and other models, the experimental results show that the PSO-SVM-AdaBoost model has better prediction performance.

Research on Dynamic Assessment System of Composite Fault Risk of Transmission Line Based on Blockchain Energy

In order to study the dynamic assessment system of composite fault risk of transmission line based on blockchain energy and in order to study the transmission line compound fault risk dynamic assessment system based on blockchain, firstly, according to the coupling relationship between power grid and natural disasters, the information resources such as data collected by power grid intelligent devices and natural meteorology are excavated, and the overall architecture of power grid disaster early warning and decision-making system supported by blockchain is built. Then, from the perspective of risk, combined with analytic hierarchy process, an index system for reasonable evaluation of distribution network fault benchmark risk is established. Quantitative assessment and risk classification shall be carried out for the failure probability, failure impact consequence, and comprehensive failure risk, so as to facilitate the adoption of risk response measures. Finally, taking several 220 kV lines in the northwest and central part of a city as examples, the icing prediction analysis verifies the feasibility and effectiveness of the proposed power grid disaster early warning decision system based on blockchain to predict the icing thickness. The experimental results show that taking the icing disaster as an example, the MPC method is used to modify the icing thickness prediction model, improve the accuracy of the icing prediction model, and verify the feasibility and effectiveness of the prediction and early warning system based on blockchain.

Migration and Reaction of Sulfate Ions in Concrete under Stray Current

Abstract The article presents a study on the influence of stray current on the migration and reaction of sulfate ions in concrete. The amount of sulfate ions in concrete is determined using the barium sulfate weighing method. The thickness of the deterioration damage layer of concrete is studied using an ultrasonic flat measurement method, and the thickness prediction model of the concrete deterioration damage layer is established to consider the influence of the intensity of the stray current. The results indicate the following: (1) the greater the stray current is, the more obvious the effect; (2) the influence of the current intensity on the migration of sulfate ions in concrete is 1.55–2.57 times that of the control group without stray current; (3) under stray current, the ratio of the reaction amount of sulfate ions in the concrete to the total amount of sulfate ions is suppressed, whereas the ratio of the reacted sulfate ions to the total amount of sulfate ions increases from 58.8 to 74.5 % with an increase in the current intensity; finally, (4) under stray current and sulfate, the thickness of the concrete damage layer increases with an increase in the deterioration age and the current intensity. The influence coefficients of stray current on the sulfate ion migration and on the sulfate ion reaction are proposed, and the evolution equation of the amount of sulfate ions in the concrete under the action of stray current with the deterioration age is obtained.

Modeling Atmospheric Corrosion under Dynamic Thin Film Electrolyte

A model for prediction of electrolyte film thickness under dynamic environmental conditions is presented. The film thickness is influenced by environmental factors such as relative humidity and temperature. The effects of relative humidity and air temperature, their time rates, salt load density, substrate material, and heat transfer coefficient on the film thickness are studied. A model for prediction of corrosion of AA7075-T6 under dynamic film thickness is also presented. The model can capture the trend of corrosion rate for a given relative humidity and temperature history. The model predictions are compared with experimental data in the literature. Good agreements are observed.

A parametric simulation model for HVOF coating thickness control

High-velocity oxygen-fuel (HVOF) thermal spraying is a coating process involving multidisciplinary aspects, e.g., fuel–oxidant combustion, flame–particle jet, particle deposition, mass and heat transfer, and even robotic kinematics. Like most coating processes, in HVOF processes, coating thickness is a significant property determining the coating performance; hence, this property should be accurately controlled during the process. In view of green, smart, and digital manufacturing, the coating thickness prediction model is demanded to produce high-quality coatings efficiently. This paper presents an approach to parametrically simulate the coating thickness in HVOF processes via an integrated numerical model. Firstly, an axisymmetric computational fluid dynamics (CFD) model is constructed to compute the behaviors of the fuel–oxidant combustion, flame–particle jet, and particle deposition distribution. Secondly, based on the particle distribution in a 2D axisymmetric model, a 3D single coating thickness profile model is developed by constructing a circular pattern using the axis of the nozzle. Further, this profile is smoothened by a Gaussian model, and its mathematical expression is obtained. Finally, a numerical model couples spray paths with the mathematical expression to model the coating thickness distribution on a substrate surface under industrial scenarios. At the end of this paper, to verify the proposed model’s effectiveness, four sets of operating parameters with a single straight path were experimentally implemented. The width and height of the bead-like shape coating were in good agreement with the simulated results. The normalized root-mean-square errors of the cross-sectional profile heights were around 10%.

Dynamic simulation of nutrient distribution in lakes during ice cover growth and ablation

Nutrient transport in seasonally ice-covered lakes is an important factor affecting spring algal blooms in eutrophic waters; because phase changes during the ice growth process redistribute the nutrients. In this study, nutrient transport under static conditions was simulated by using two ice thickness models in combination with an indoor freezing experiment under different segregation coefficient conditions for nutrients. A real-time prediction model for nutrient and pollutant concentrations in ice-covered lakes was established to explore the impact of the ice-on period in eutrophic shallow lakes. The results demonstrated that the empirical degree-day model and the high-resolution thermodynamic snow and sea-ice model (HIGHTSI) could both be used to simulate lake ice thickness. The empirical degree-day model performed better at predicting the maximum ice thickness (measured thickness 0.22–0.55 m; simulated thickness 0.48 m), whereas the HIGHTSI model was more accurate when estimating the mean thickness (5–6% error). When simulating ice growth, the HIGHTSI model considered more meteorological factors impacting ice cover ablation; hence, it performed better during the ablation stage relative to the empirical degree-day model. Two non-dynamic nutrient transport models were developed by combining the segregation coefficient model and the ice thickness prediction model. The HIGHTSI nutrient transport model can be used to predict real-time changes in nutrient concentrations under ice cover, and the degree-day model can be used to predict changes in the lake water ecosystem.