A Deep Residual PLS for Data-Driven Quality Prediction Modeling in Industrial Process

Partial least squares(PLS)model is the most typical data-driven method for quality-related industrial tasks like soft sensor.However,only linear relations are captured between the input and output data in the PLS.It is difficult to obtain the remaining nonlinear information in the residual subspaces,which may deteriorate the prediction performance in complex industrial processes.To fully utilize data information in PLS residual subspaces,a deep residual PLS(DRPLS)framework is proposed for quality prediction in this paper.Inspired by deep learning,DRPLS is designed by stacking a number of PLSs successively,in which the input residuals of the previous PLS are used as the layer connection.To enhance representation,nonlinear function is applied to the input residuals before using them for stacking highlevel PLS.For each PLS,the output parts are just the output residuals from its previous PLS.Finally,the output prediction is obtained by adding the results of each PLS.The effectiveness of the proposed DRPLS is validated on an industrial hydrocracking process.

Modeling and Validation of Thrust Prediction of Underwater Solid Rocket Motor

The solid rocket motor driven system is one of the common ways for submarines to launch underwater missiles. It has significant advantages in improving the missile’s water exit speed, anti-interference capability, and enemy striking power. The prediction of the underwater loading is a preliminary factor for the power system design of the underwater vehicle. This paper presents a rapid prediction method and validated by the experimental study for the underwater thrust of the solid rocket motor. Based on the potential flow assumption of the water field, a model of the bubble and a one-dimensional quasi-steady model of the nozzle are established to directly solve the flow status of the nozzle. The aerodynamic thrust and hydrodynamic thrust have been calculated and analyzed. The calculation results are within 5% error of the experimental results. Moreover, a design platform to predict the underwater thrust of the solid rocket motor has been developed based on Python and the PyQt library, which shows excellent system adaptability and computational efficiency.

Theoretical Modeling and Surface Roughness Prediction of Microtextured Surfaces in Ultrasonic Vibration-Assisted Milling

Textured surfaces with certain micro/nano structures have been proven to possess some advanced functions,such as reducing friction,improving wear and increasing wettability.Accurate prediction of micro/nano surface textures is of great significance for the design,fabrication and application of functional textured surfaces.In this paper,based on the kinematic analysis of cutter teeth,the discretization of ultrasonic machining process,transformation method of coordinate systems and the cubic spline data interpolation,an integrated theoretical model was established to characterize the distribution and geometric features of micro textures on the surfaces machined by different types of ultrasonic vibration-assisted milling(UVAM).Based on the theoretical model,the effect of key process parameters(vibration directions,vibration dimensions,cutting parameters and vibration parameters)on tool trajectories and microtextured surface morphology in UVAM is investigated.Besides,the effect of phase difference on the elliptical shape in 2D/3D ultrasonic elliptical vibration-assisted milling(UEVAM)was analyzed.Compared to conventional numerical models,the method of the cubic spline data interpolation is applied to the simulation of microtextured surface morphology in UVAM,which is more suitable for characterizing the morphological features of microtextured surfaces than traditional methods due to the presence of numerous micro textures.The prediction of surface roughness indicates that the magnitude of ultrasonic amplitude in z-direction should be strictly limited in 1D rotary UVAM,2D and 3D UEVAM due to the unfavorable effect of axial ultrasonic vibration on the surface quality.This study can provide theoretical guidance for the design and fabrication of microtextured surfaces in UVAM.

Tidal modeling based on satellite altimetry observations of TOPEX/ Poseidon, Jason1, Jason2, and Jason3 with high prediction capability: A case study of the Baltic Sea

This research aims to optimize the utilization of long-term sea level data from the TOPEX/Poseidon,Jason1,Jason2,and Jason3 altimetry missions for tidal modeling.We generate a time series of along-track observations and apply a developed method to produce tidal models with specific tidal constituents for each location.Our tidal modeling methodology follows an iterative process:partitioning sea surface height(SSH)observations into analysis/training and prediction/validation parts and ultimately identi-fying the set of tidal constituents that provide the best predictions at each time series location.The study focuses on developing 1256 time series along the altimetry tracks over the Baltic Sea,each with its own set of tidal constituents.Verification of the developed tidal models against the sSH observations within the prediction/validation part reveals mean absolute error(MAE)values ranging from 0.0334 m to 0.1349 m,with an average MAE of 0.089 m.The same validation process is conducted on the FES2014 and EOT20 global tidal models,demonstrating that our tidal model,referred to as BT23(short for Baltic Tide 2023),outperforms both models with an average MAE improvement of 0.0417 m and 0.0346 m,respectively.In addition to providing details on the development of the time series and the tidal modeling procedure,we offer the 1256 along-track time series and their associated tidal models as supplementary materials.We encourage the satellite altimetry community to utilize these resources for further research and applications.

A systematic review of machine learning modeling processes and applications in ROP prediction in the past decade

Fossil fuels are undoubtedly important, and drilling technology plays an important role in realizing fossil fuel exploration;therefore, the prediction and evaluation of drilling efficiency is a key research goal in the industry. Limited by the unknown geological environment and complex operating procedures, the prediction and evaluation of drilling efficiency were very difficult before the introduction of machine learning algorithms. This review statistically analyses rate of penetration(ROP) prediction models established based on machine learning algorithms;establishes an overall framework including data collection, data preprocessing, model establishment, and accuracy evaluation;and compares the effectiveness of different algorithms in each link of the process. This review also compares the prediction accuracy of different machine learning models and traditional models commonly used in this field and demonstrates that machine learning models are the most effective technical means in current ROP prediction modeling.

Machine learning prediction of methane,ethane,and propane solubility in pure water and electrolyte solutions:Implications for stray gas migration modeling

Hydraulic fracturing is an effective technology for hydrocarbon extraction from unconventional shale and tight gas reservoirs.A potential risk of hydraulic fracturing is the upward migration of stray gas from the deep subsurface to shallow aquifers.The stray gas can dissolve in groundwater leading to chemical and biological reactions,which could negatively affect groundwater quality and contribute to atmospheric emissions.The knowledge oflight hydrocarbon solubility in the aqueous environment is essential for the numerical modelling offlow and transport in the subsurface.Herein,we compiled a database containing 2129experimental data of methane,ethane,and propane solubility in pure water and various electrolyte solutions over wide ranges of operating temperature and pressure.Two machine learning algorithms,namely regression tree(RT)and boosted regression tree(BRT)tuned with a Bayesian optimization algorithm(BO)were employed to determine the solubility of gases.The predictions were compared with the experimental data as well as four well-established thermodynamic models.Our analysis shows that the BRT-BO is sufficiently accurate,and the predicted values agree well with those obtained from the thermodynamic models.The coefficient of determination(R2)between experimental and predicted values is 0.99 and the mean squared error(MSE)is 9.97×10^(-8).The leverage statistical approach further confirmed the validity of the model developed.

Gas sand distribution prediction by prestack elastic inversion based on rock physics modeling and analysis

Seismic inversion is one of the most widely used technologies for reservoir prediction. Many good results have been obtained but sometimes it fails to differentiate the lithologies and identify the fluids. However, seismic prestack elastic inversion based on rock physics modeling and analysis introduced in this paper is a significant method that can help seismic inversion and interpretation reach a new quantitative （or semi-quantitative） level from traditional qualitative interpretation. By doing rock physics modeling and forward perturbation analysis, we can quantitatively analyze the essential relationships between rock properties and seismic responses and try to find the sensitive elastic properties to the lithology, porosity, fluid type, and reservoir saturation. Finally, standard rock physics templates （RPT） can be built for specific reservoirs to guide seismic inversion interpretation results for reservoir characterization and fluids identification purpose. The gas sand distribution results of the case study in this paper proves that this method has unparalleled advantages over traditional post-stack methods, by which we can perform reservoir characterization and seismic data interpretation more quantitatively and efficiently.

LVP Modeling and Dynamic Characteristics Prediction of A Hydraulic Power Unit in Deep-Sea

A hydraulic power unit （HPU） is the driving ＂heart＂ of deep-sea working equipment. It is critical to predict its dynamic performances in deep-water before being immerged in the seawater, while the experimental tests by simulating deep-sea environment have many disadvantages, such as expensive cost, long test cycles, and difficult to achieve low-temperature simulation, which is only used as a supplementary means for confirmatory experiment. This paper proposes a novel theoretical approach based on the linear varying parameters （LVP） modeling to foresee the dynamic performances of the driving unit. Firstly, based on the varying environment features, dynamic expressions of the compressibility and viscosity of hydranlic oil are derived to reveal the fluid performances changing. Secondly, models of hydraulic system and electrical system are accomplished respectively through studying the control process and energy transfer, and then LVP models of the pressure and flow rate control is obtained through the electro-hydraulic models integration. Thirdly, dynamic characteristics of HPU are obtained by the model simulating within bounded closed sets of varying parameters. Finally, the developed HPU is tested in a deep-sea imitating hull, and the experimental results are well consistent with the theoretical analysis outcomes, which clearly declare that the LVP modeling is a rational way to foresee dynamic performances of HPU. The research approach and model analysis results can be applied to the predictions of working properties and product designs for other deep-sea hydraulic pump.

Multiple sclerosis：integration of modeling with biology,clinical and imaging measures to provide better monitoring of disease progression and prediction of outcome

Multiple Sclerosis（MS） is a major cause of neurological disability in adults and has an annual cost of approximately $28 billion in the United States. MS is a very complex disorder as demyelination can happen in a variety of locations throughout the brain; therefore, this disease is never the same in two patients making it very hard to predict disease progression. A modeling approach which combines clinical, biological and imaging measures to help treat and fight this disorder is needed. In this paper, I will outline MS as a very heterogeneous disorder, review some potential solutions from the literature, demonstrate the need for a biomarker and will discuss how computational modeling combined with biological, clinical and imaging data can help link disparate observations and decipher complex mechanisms whose solutions are not amenable to simple reductionism.

Statistical prediction of waterflooding performance by K-means clustering and empirical modeling

Statistical prediction is often required in reservoir simulation to quantify production uncertainty or assess potential risks.Most existing uncertainty quantification procedures aim to decompose the input random field to independent random variables,and may suffer from the curse of dimensionality if the correlation scale is small compared to the domain size.In this work,we develop and test a new approach,K-means clustering assisted empirical modeling,for efficiently estimating waterflooding performance for multiple geological realizations.This method performs single-phase flow simulations in a large number of realizations,and uses K-means clustering to select only a few representatives,on which the two-phase flow simulations are implemented.The empirical models are then adopted to describe the relation between the single-phase solutions and the two-phase solutions using these representatives.Finally,the two-phase solutions in all realizations can be predicted using the empirical models readily.The method is applied to both 2D and 3D synthetic models and is shown to perform well in the P10,P50 and P90 of production rates,as well as the probability distributions as illustrated by cumulative density functions.It is able to capture the ensemble statistics of the Monte Carlo simulation results with a large number of realizations,and the computational cost is significantly reduced.

Forward modeling of fracture prediction based on seismic attribute modeling

Fractured reservoirs have always been a big favorable area for oil and gas reservoirs,so prediction of fractures is also a research hotspot in recent years.Due to the diversity of fracture development and the unclear development mechanism,fracture prediction has always been a major problem.Simple numerical simulation In this paper,seismic attribute is combined with numerical simulation,logging data and actual seismic profile are used as constraints,inversion impedance value and coherent attribute are combined,and finally a property model more in line with the actual geological conditions is established.The wave equation calculation and migration processing were used to obtain the numerical simulation profile,and the actual seismic profile,fracture detection profile and numerical simulation profile were combined for analysis:①The numerical simulation section under this modeling method can greatly correspond to the actual seismic section,and the reflected results can better reflect the changes of response characteristics.②The reliability and applicability of the fracture detection technology can be determined by comparing the forward simulation profile with the fracture detection profile.

An integrated modeling method for prediction of sulfur content in agglomerate

Based on the idea of fusing modeling, an integrated prediction model for sintering process was proposed. A framework for sulfur content prediction was established, which integrated multi modeling ways together, including mathematical model combined with neural network(NN), rule model based on empirical knowledge and model-choosing coordinator. Via metallurgic mechanism analysis and material balance computation, a mathematical model calculated the sulfur content in agglomerate by the material balance equation with some parameters predicted by NN method. In the other model, the relationship between sulfur content and key factors was described in the form of expert rules. The model-choosing coordinator based on fuzzy logic was introduced to decide the weight of result of each model according to process conditions. The model was tested by industrial application data and produced a relatively satisfactory prediction error. The model also preferably reflected the varying tendency of sulfur content in agglomerate as the evidence of its prediction performance.

DTHMM based delay modeling and prediction for networked control systems

In the forward channel of a networked control system （NCS）, by defining the network states as a hidden Markov chain and quantizing the network-induced delays to a discrete sequence distributing over a finite time interval, the relation between the network states and the network-induced delays is modelled as a discrete-time hidden Markov model （DTHMM）. The expectation maximization （EM） algorithm is introduced to derive the maximumlikelihood estimation （MLE） of the parameters of the DTHMM. Based on the derived DTHMM, the Viterbi algorithm is introduced to predict the controller-to-actuator （C-A） delay during the current sampling period. The simulation experiments demonstrate the effectiveness of the modelling and predicting methods proposed.

Modeling and scenario prediction of a natural gas demand system based on a system dynamics method

Based on the study of the relationship between structure and feedback of China’s natural gas demand system, this paper establishes a system dynamics model. In order to simulate the total demand and consumption structure of natural gas in China, we set up seven scenarios by changing some of the parameters of the model. The results showed that the total demand of natural gas would increase steadily year by year and reach in the range from 3600 to 4500 billion cubic meters in 2035. Furthermore, in terms of consumption structure, urban gas consumption would still be the largest term, followed by the gas consumption as industrial fuel, gas power generation and natural gas chemical industry. In addition, compared with the population growth, economic development still plays a dominant role in the natural gas demand growth, the impact of urbanization on urban gas consumption is significant, and the promotion of natural gas utilization technology can effectively reduce the total consumption of natural gas.

Modeling and Evaluating of Surface Roughness Prediction in Micro-grinding on Soda-lime Glass Considering Tool Characterization

The current research of micro-grinding mainly focuses on the optimal processing technology for different materials. However, the material removal mechanism in micro-grinding is the base of achieving high quality processing surface. Therefore, a novel method for predicting surface roughness in micro-grinding of hard brittle materials considering micro-grinding tool grains protrusion topography is proposed in this paper. The differences of material removal mechanism between convention grinding process and micro-grinding process are analyzed. Topography characterization has been done on micro-grinding tools which are fabricated by electroplating. Models of grain density generation and grain interval are built, and new predicting model of micro-grinding surface roughness is developed. In order to verify the precision and application effect of the surface roughness prediction model proposed, a micro-grinding orthogonally experiment on soda-lime glass is designed and conducted. A series of micro-machining surfaces which are 78 nm to 0.98 ~tm roughness of brittle material is achieved. It is found that experimental roughness results and the predicting roughness data have an evident coincidence, and the component variable of describing the size effects in predicting model is calculated to be 1.5x 107 by reverse method based on the experimental results. The proposed model builds a set of distribution to consider grains distribution densities in different protrusion heights. Finally, the characterization of micro-grinding tools which are used in the experiment has been done based on the distribution set. It is concluded that there is a significant coincidence between surface prediction data from the proposed model and measurements from experiment results. Therefore, the effectiveness of the model is demonstrated. This paper proposes a novel method for predicting surface roughness in micro-grinding of hard brittle materials considering micro-grinding tool grains protrusion topography, which would provide significant research theory and experimental reference of material removal mechanism in micro-grinding of soda-lime glass.

Online Predictive Monitoring and Prediction Model for a Periodic Process Through Multiway Non-Gaussian Modeling

A new on-line predictive monitoring and prediction model for periodic biological processes is proposed using the multiway non-Gaussian modeling. The basic idea of this approach is to use multiway non-Gaussian modeling to extract some dominant key components from daily normal operation data in a periodic process, and subsequently combining these components with predictive statistical process monitoring techniques. The proposed predictive monitoring method has been applied to fault detection and diagnosis in the biological wastewater-treatment process, which is based on strong diurnal characteristics. The results show the power and advantages of the proposed predictive monitoring of a continuous process using the multiway predictive monitoring concept, which is thus able to give very useful conceptual results for a daily monitoring process and also enables a more rapid detection of the process fault than other traditional monitoring methods.

The application of modeling and prediction with MRA wavelet network

As there are lots of non-linear systems in the real engineering, it is very important to do more researches on the modeling and prediction of non-linear systems. Based on the multi-resolution analysis (MRA) of wavelet theory, this paper combined the wavelet theory with neural network and established a MRA wavelet network with the scaling function and wavelet function as its neurons. From the analysis in the frequency domain, the results indicated that MRA wavelet network was better than other wavelet networks in the ability of approaching to the signals. An essential research was can:led out on modeling and prediction with MRA wavelet network in the non-linear system. Using the lengthwise sway data received from the experiment of ship model, a model of offline prediction was established and was applied to the short-time prediction of ship motion. The simulation results indicated that the forecasting model improved the prediction precision effectively, lengthened the forecasting time and had a better prediction results than that of AR linear model. The research indicates that it is feasible to use the MRA wavelet network in the short-time prediction of ship motion.

Effects of Estrogen Contamination on Human Cells: Modeling and Prediction Based on Michaelis-Menten Kinetics

In this paper, we propose a novel prevention strategy to alert citizens when water is contaminated by estro-gen. Epidemiological studies have shown that chronic exposure to high blood level of estrogen is associated with the development of breast cancer. The preventive strategy proposed in this paper is based on the predic-tion of estrogen effects on human living cells. Based on first principle insights, we develop in this work, a mathematical model for this prediction purpose. Dynamic measurements of cell proliferation response to es-trogen stimulation were continuously monitored by a real-time cell electronic sensor (RT-CES) and used in order to estimate the parameters of the model developed.

Modeling of hot deformation behavior and prediction of flow stress in a magnesium alloy using constitutive equation and artificial neural network(ANN)model

The aim of the present study was to investigate the modeling and prediction of the high temperature flow characteristics of a cast magnesium(Mg-Al-Ca)alloy by both constitutive equation and ANN model.Toward this end,hot compression experiments were performed in 250-450℃and in strain rates of 0.001-1 s^(−1).The true stress of alloy was first and foremost described by the hyperbolic sine function in an Arrhenius-type of constitutive equation taking the effects of strain,strain rate and temperature into account.Predictions indicated that unlike low strain rates and high temperature with dominant DRX activation,in relatively high strain rate and low temperature values,the precision of the models become decreased due to activation of twinning phenomenon.At that moment and for a better evaluation of twinning effect during deformation,a feed-forward back propagation ANN was developed to study the flow behavior of the investigated alloy.Then,the performance of the two suggested models has been assessed using a statistical criterion.The comparative assessment of the gained results specifies that the well-trained ANN is much more precise and accurate than the constitutive equations in predicting the hot flow behavior.

Tidal Prediction in the Sea Scheldt (Belgium) Using a Combination of Harmonic Tidal Prediction and 1D Hydraulic Modeling

The vertical tide in the Sea Scheldt (Belgium) is predicted using a combination of harmonic tidal prediction and 1D hydraulic modeling. At Prosperpolder (a measurement station close to the Dutch-Belgian border), four years of water level data (2009-2012) are analyzed to obtain the harmonic components at that location. The accuracy of the harmonic prediction is checked with a statistical analysis of an astronomical hindcast for 2009-2012 against measurements. An existing 1D hydraulic model of the tidally influenced part of the Scheldt estuary is cut off at Prosperpolder. The time series of tidally predicted water levels at Prosperpolder is used as a downstream boundary condition for the hydraulic model. In this way, a tidal prediction can be obtained for any location in the Sea Scheldt, also for locations where no harmonic components are available, whilst guaranteeing the consistency between the predicted time series.