Interpretable machine learning optimization(InterOpt)for operational parameters:A case study of highly-efficient shale gas development

An algorithm named InterOpt for optimizing operational parameters is proposed based on interpretable machine learning,and is demonstrated via optimization of shale gas development.InterOpt consists of three parts:a neural network is used to construct an emulator of the actual drilling and hydraulic fracturing process in the vector space(i.e.,virtual environment);:the Sharpley value method in inter-pretable machine learning is applied to analyzing the impact of geological and operational parameters in each well(i.e.,single well feature impact analysis):and ensemble randomized maximum likelihood(EnRML)is conducted to optimize the operational parameters to comprehensively improve the efficiency of shale gas development and reduce the average cost.In the experiment,InterOpt provides different drilling and fracturing plans for each well according to its specific geological conditions,and finally achieves an average cost reduction of 9.7%for a case study with 104 wells.

Prediction of operational parameters effect on coal flotation using artificial neural network

Artificial neural network procedures were used to predict the combustible value （i.e. 100-Ash） and combustible recovery of coal flotation concentrate in different operational conditions. The pulp density,pH,rotation rate,coal particle size,dosage of collector,frother and conditioner were used as inputs to the network. Feed-forward artificial neural networks with 5-30-2-1 and 7-10-3-1 arrangements were capable to estimate the combustible value and combustible recovery of coal flotation concentrate respectively as the outputs. Quite satisfactory correlations of 1 and 0.91 in training and testing stages for combustible value and of 1 and 0.95 in training and testing stages for combustible recovery prediction were achieved. The proposed neural network models can be used to determine the most advantageous operational conditions for the expected concentrate assay and recovery in the coal flotation process.

Analysis of operational parameters affecting denitrification rate of sintering flue gas in cross-flow activated coke purification facility

The denitrification rate of the cross-flow activated coke flue gas purification facility varies with operational parameters. According to the simulated experiments, the denitrification rate with the height drop of the denitrification unit experiences 100%, rapid decreasing, and gradual rising to the equilibrium. According to the correlation analysis results based on production data, several operational parameters affecting the denitrification rate have been obtained. The denitrification rate has negative relationships with the activated coke bed temperature, the flue gas flow, the H2O content, the SO2 content and the NH3 slip, and has positive relationships with the O2 content, the NOx content, the NH3–NOx molar ratio, the flue gas pressure and the regeneration temperature. Properly increasing the sintering air leakage or the cooling air added into flue gas is beneficial to increase the denitrification rate. Priority should be given to O2, NH3–NOx molar ratio and flue gas flow to improve the denitrification rate. Additionally, a linear model, which had been validated, was developed and can be used to predict and control the denitrification rate.

Intelligent decision-making method of TBM operating parameters based on multiple constraints and objective optimization

The decision-making method of tunnel boring machine(TBM)operating parameters has a significant guiding significance for TBM safe and efficient construction,and it has been one of the TBM tunneling research hotspots.For this purpose,this paper introduces an intelligent decision-making method of TBM operating parameters based on multiple constraints and objective optimization.First,linear cutting tests and numerical simulations are used to investigate the physical rules between different cutting parameters(penetration,cutter spacing,etc.)and rock compressive strength.Second,a dual-driven mapping of rock parameters and TBM operating parameters based on data mining and physical rules of rock breaking is established with high accuracy by combining rock-breaking rules and deep neural networks(DNNs).The decision-making method is established by dual-driven mapping,using the effective rock-breaking capacity and the rated value of mechanical parameters as constraints and the total excavation cost as the optimization objective.The best operational parameters can be obtained by searching for the revolutions per minute and penetration that correspond to the extremum of the constrained objective function.The practicability and effectiveness of the developed decision-making model is verified in the SecondWater Source Channel of Hangzhou,China,resulting in the average penetration rate increasing by 11.3%and the total cost decreasing by 10%.

Optimization of Control Loops and Operating Parameters for Three-Phase Separators Used in Oilfield Central Processing Facilities

In this study,the Stokes formula is used to analyze the separation effect of three-phase separators used in a Oilfield Central Processing Facility.The considered main influencing factors include(but are not limited to)the typical size of oil and water droplets,the residence time and temperature of fluid and the dosage of demulsifier.Using the“Specification for Oil and Gas Separators”as a basis,the control loops and operating parameters of each separator are optimized Considering the Halfaya Oilfield as a testbed,it is shown that the proposed approach can lead to good results in the production stage.

Discussion of reasonable drilling parameters in impregnated diamond bit drilling

The impregnated diamond(ID)bit drilling is one of the main rotary drilling methods in hard rock drilling and it is widely used in mineral exploration,oil and gas exploration,mining,and construction industries.In this study,the quadratic polynomial model in ID bit drilling process was proposed as a function of controllable mechanical operating parameters,such as weight on bit(WOB)and revolutions per minute(RPM).Also,artificial neural networks(ANN)model for predicting the rate of penetration(ROP)was developed using datasets acquired during the drilling operation.The relationships among mechanical operating parameters(WOB and RPM)and ROP in ID bit drilling were analyzed using estimated quadratic polynomial model and trained ANN model.The results show that ROP has an exponential relationship with WOB,whereas ROP has linear relationship with RPM.Finally,the optimal regime of mechanical drilling parameters to achieve high ROP was confirmed using proposed model in combination with rock breaking principal.

Study on the operating parameters of the 10 kW SOFC-CHP system with syngas

Solid oxide fuel cell combined with heat and power(SOFC-CHP)system is a distributed power generation system with low pollution and high efficiency.In this paper,a 10 kW SOFC-CHP system model using syngas was built in Aspen plus.Key operating parameters,such as steam to fuel ratio,stack temperature,reformer temperature,air flow rate,and air preheating temperature,were analyzed.Optimization was conducted based on the simulation results.Results suggest that higher steam to fuel ratio is beneficial to the electrical efficiency,but it might decrease the gross system efficiency.Higher stack and reformer temperatures contribute to the electrical efficiency,and the optimal operating temperatures of stack and reformer when considering the stack degradation are 750℃and 700℃,respectively.The air preheating temperature barely affects the electrical efficiency but affects the thermal efficiency and the gross system efficiency,the recommended value is around 600℃under the reference condition.

Effects of operating parameters on the flow field in slab continuous casting molds with narrow widths

Computational simulations and high-temperature measurements of velocities near the surface of a mold were carried out by using the rod deflection method to study the effects of various operating parameters on the flow field in slab continuous casting(CC)molds with narrow widths for the production of automobile exposed panels.Reasonable agreement between the calculated results and measured subsurface velocities of liquid steel was obtained under different operating parameters of the CC process.The simulation results reveal that the flow field in the horizontal plane located 50 mm from the meniscus can be used as the characteristic flow field to optimize the flow field of molten steel in the mold.Increases in casting speed can increase the subsurface velocity of molten steel and shift the position of the vortex core downward in the downward circulation zone.The flow field of liquid steel in a 1040 mm-wide slab CC mold can be improved by an Ar gas flow rate of 7 L·min^−1 and casting speed of 1.7 m·min^−1.Under the present experimental conditions,the double-roll flow pattern is generally stable at a submerged entry nozzle immersion depth of 170 mm.

Parameterized Littlewood-Paley Operators and Their Commutators on Lebesgue Spaces with Variable Exponent

In this paper, by applying the technique of the sharp maximal function and the equivalent representation of the norm in the Lebesgue spaces with variable exponent, the boundedness of the parameterized Litflewood-Paley operators, including the parameterized Lusin area integrals and the parameterized Littlewood-Paley gλ^＊- functions, is established on the Lebesgue spaces with variable exponent. Furthermore, the boundedness of their commutators generated respectively by BMO functions and Lipschitz functions are also obtained.

Effects of structural and operating parameters of ECP fan on dust particles removed in the transition flow regime

An enclosed cyclone passageway(ECP)dust-collecting fan is discussed.The ECP fan separates dust by centrifugal force originating from a driven spiral airflow,and its design takes the constraints of Chinese underground coal mines into consideration.Using the force equilibrium law,a general equation for dust removal in the centrifugal dust removal section(CDRS)of the ECP fan is deduced.This general equation is simplified using the CDRS structure and the fan operating parameters and is analysed numerically.The attractive results show that increases in the airflow rate of the fan,the structural ratio of the ECPs and the radius of the extended axis can improve the dust removal performance of the CDRS.Furthermore,the effects of the structural ratio and the radius on dust removal dominate over that of the flow rate,and the effect of the structural ratio is more significant than that of the radius.

Development of a Novel Feedforward Neural Network Model Based on Controllable Parameters for Predicting Effluent Total Nitrogen

The problem of effluent total nitrogen(TN)at most of the wastewater treatment plants(WWTPs)in China is important for meeting the related water quality standards,even under the condition of high energy consumption.To achieve better prediction and control of effluent TN concentration,an efficient prediction model,based on controllable operation parameters,was constructed in a sequencing batch reactor process.Compared with previous models,this model has two main characteristics:①Superficial gas velocity and anoxic time are controllable operation parameters and are selected as the main input parameters instead of dissolved oxygen to improve the model controllability,and②the model prediction accuracy is improved on the basis of a feedforward neural network(FFNN)with algorithm optimization.The results demonstrated that the FFNN model was efficiently optimized by scaled conjugate gradient,and the performance was excellent compared with other models in terms of the correlation coefficient(R).The optimized FFNN model could provide an accurate prediction of effluent TN based on influent water parameters and key control parameters.This study revealed the possible application of the optimized FFNN model for the efficient removal of pollutants and lower energy consumption at most of the WWTPs.

Effects of operating parameters on oxidative coupling of methane over Na-W-Mn/SiO_2 catalyst at elevated pressures

The effects of operating parameters on oxidative coupling of methane （OCM） over Na-W-Mn/SiO2 catalyst have been studied at elevated pressures of 0.2, 0.3 and 0.4 MPa under low gaseous hourly space velocity （GHSV） and low temperature conditions. Experimental results show that when the operating pressure is increased, C2＋ yield slightly decreases, while the maximum ratio of ethylene to ethane remains unchanged. Moreover, it has been found empirically that increase of pressure does not affect the catalyst behavior permanently, the catalyst recovers its original low pressure performance without hysteresis behavior by reducing the pressure. Under the investigated conditions, when oxygen is completely consumed, the increase of GHSV leads to improvement in C2 selectivity, while C3＋ and COx selectivities decrease slightly. The C2＋ selectivity increases by increase of nitrogen diluent in the feed, but the C3＋ hydrocarbons selectivities decrease with increase of nitrogen since it is possible that further dilution at high pressure may reduce the probability of collision between CH3 and C2＋ hydrocarbons. During the stability test at high pressure, the catalyst performance remains unchanged throughout the 20 h running. The fresh and used catalysts were characterized using XRD, SEM and N2 adsorption-desorption methods. It was found that the phase transformation of the support from α-cristobalite to tridymite and quartz does not have obvious effect on catalyst performance at high pressure.

Dual-radiation-chamber coordinated overall energy efficiency scheduling solution for ethylene cracking process regarding multi-parameter setting and multi-flow allocation

Ethylene cracking process is the core production process in ethylene industry,and is paid more attention to reduce high energy consumption.Because of the interdependent relationships between multi-flow allocation and multi-parameter setting in cracking process,it is difficult to find the overall energy efficiency scheduling for the purpose of saving energy.The traditional scheduling solutions with optimal economic benefit are not applicable for energy efficiency scheduling issue due to the neglecting of recycle and lost energy,as well as critical operation parameters as coil outlet pressure(COP)and dilution ratio.In addition,the scheduling solutions mostly regard each cracking furnace as an elementary unit,regardless of the coordinated operation of internal dual radiation chambers(DRC).Therefore,to improve energy utilization and production operation,a novel energy efficiency scheduling solution for ethylene cracking process is proposed in this paper.Specifically,steam heat recycle and exhaust heat loss are considered in cracking process based on 6 types of extreme learning machine(ELM)based cracking models incorporating DRC operation and three operation parameters as coil outlet temperature(COT),COP,and dilution ratio according to semi-mechanism analysis.Then to provide long-term decision-making basis for energy efficiency scheduling,overall energy efficiency indexes,including overall output per unit net energy input(OONE),output-input ratio per unit net energy input(ORNE),exhaust gas heat loss ratio(EGHL),are designed based on input-output analysis in terms of material and energy flows.Finally,a multiobjective evolutionary algorithm based on decomposition(MOEA/D)is employed to solve the formulated multi-objective mixed-integer nonlinear programming(MOMINLP)model.The validities of the proposed scheduling solution are illustrated through a case study.The scheduling results demonstrate that an optimal balance between multi-flow allocation,multi-parameter setting,and DRC coordinated operation is reached,which achieves 3.37%and 2.63%decreases in net energy input for same product output and conversion ratio,as well as the 1.56%decrease in energy loss ratio.

Parameterized Littlewood-Paley Operators on Weighted Herz Spaces

The strong type and weak type estimates of parameterized Littlewood-Paley operators on the weighted Herz spaces Kq α,p（ω1,ω2） are considered. The boundednessof the commutators generated by BMO functions and parameterized Littlewood-Paley operators are also obtained.

Universal Index Formula of Parameterized Combination Operator for Eco-environmental Quality Evaluation

[Objective] The aim was to evaluate the regional eco-environmental quality by using the universal index formula of parameterization combination operator based normalized index values.[Method] Through setting reference values and normalized transformation formulae for typical ecological environmental indexes appropriately,the difference among the standard normalized values would become very small after normalized transformation,and the ecological environmental indices expressed by normalized values can be equivalent to normalized indices.Under certain optimization conditions,shuffled frog leaping based on immune evolutionary particle swarm optimization algorithm was applied to optimize the parameters in parameterization combination operator formula,and the universal index formula suited to eco-environmental quality assessment was established finally.[Result] The universal index formula of parameterization combination operator,appropriate for any m(1≤m≤23) ecological environmental indices,was used to assess the eco-environmental quality of towns surrounding Headland Reservoir,and the results were in full accordance with those of unascertained measure method,that is,the eco-environmental quality of five towns around Headland Reservoir was the fourth grade.[Conclusion]The universal index formula of parameterization combination operator,suited to eco-environmental quality evaluation,is simple and intuitive in form,easy in computation and universal in application.

Soft ground tunnel lithology classification using clustering-guided light gradient boosting machine

During tunnel boring machine(TBM)excavation,lithology identification is an important issue to understand tunnelling performance and avoid time-consuming excavation.However,site investigation generally lacks ground samples and the information is subjective,heterogeneous,and imbalanced due to mixed ground conditions.In this study,an unsupervised(K-means)and synthetic minority oversampling technique(SMOTE)-guided light-gradient boosting machine(LightGBM)classifier is proposed to identify the soft ground tunnel classification and determine the imbalanced issue of tunnelling data.During the tunnel excavation,an earth pressure balance(EPB)TBM recorded 18 different operational parameters along with the three main tunnel lithologies.The proposed model is applied using Python low-code PyCaret library.Next,four decision tree-based classifiers were obtained in a short time period with automatic hyperparameter tuning to determine the best model for clustering-guided SMOTE application.In addition,the Shapley additive explanation(SHAP)was implemented to avoid the model black box problem.The proposed model was evaluated using different metrics such as accuracy,F1 score,precision,recall,and receiver operating characteristics(ROC)curve to obtain a reasonable outcome for the minority class.It shows that the proposed model can provide significant tunnel lithology identification based on the operational parameters of EPB-TBM.The proposed method can be applied to heterogeneous tunnel formations with several TBM operational parameters to describe the tunnel lithologies for efficient tunnelling.

Prediction of Disc Cutter Life During Shield Tunneling with AI via the Incorporation of a Genetic Algorithm into a GMDH-Type Neural Network

Disc cutter consumption is a critical problem that influences work performance during shield tunneling processes and directly affects the cutter change decision.This study proposes a new model to estimate the disc cutter life(Hf)by integrating a group method of data handling(GMDH)-type neural network(NN)with a genetic algorithm(GA).The efficiency and effectiveness of the GMDH network structure are optimized by the GA,which enables each neuron to search for its optimum connections set from the previous layer.With the proposed model,monitoring data including the shield performance database,disc cutter consumption,geological conditions,and operational parameters can be analyzed.To verify the performance of the proposed model,a case study in China is presented and a database is adopted to illustrate the excellence of the hybrid model.The results indicate that the hybrid model predicts disc cutter life with high accuracy.The sensitivity analysis reveals that the penetration rate(PR)has a significant influence on disc cutter life.The results of this study can be beneficial in both the planning and construction stages of shield tunneling.

Investigation of feature contribution to shield tunneling-induced settlement using Shapley additive explanations method

Accurate prediction of shield tunneling-induced settlement is a complex problem that requires consideration of many influential parameters.Recent studies reveal that machine learning(ML)algorithms can predict the settlement caused by tunneling.However,well-performing ML models are usually less interpretable.Irrelevant input features decrease the performance and interpretability of an ML model.Nonetheless,feature selection,a critical step in the ML pipeline,is usually ignored in most studies that focused on predicting tunneling-induced settlement.This study applies four techniques,i.e.Pearson correlation method,sequential forward selection(SFS),sequential backward selection(SBS)and Boruta algorithm,to investigate the effect of feature selection on the model’s performance when predicting the tunneling-induced maximum surface settlement(S_(max)).The data set used in this study was compiled from two metro tunnel projects excavated in Hangzhou,China using earth pressure balance(EPB)shields and consists of 14 input features and a single output(i.e.S_(max)).The ML model that is trained on features selected from the Boruta algorithm demonstrates the best performance in both the training and testing phases.The relevant features chosen from the Boruta algorithm further indicate that tunneling-induced settlement is affected by parameters related to tunnel geometry,geological conditions and shield operation.The recently proposed Shapley additive explanations(SHAP)method explores how the input features contribute to the output of a complex ML model.It is observed that the larger settlements are induced during shield tunneling in silty clay.Moreover,the SHAP analysis reveals that the low magnitudes of face pressure at the top of the shield increase the model’s output。

VOLUMETRIC MASS TRANSFER COEFFICIENT BETWEEN SLAG AND METAL IN COMBINED BLOWING CONVERTER

The effects of operation parameters of combined blowing converter on the volumetric mass transfer coefficient between slag and steel are studied with a cold model with water simulating steel, oil simulating slag and benzoic acid as the transferred substance between water and oil. The results show that, with lance level of 2.1m and the top blowing rate of 25000Nm3/h, the volumetric mass transfer coefficient changes most significantly when the bottom blowing rate ranges from 384 to 540Nm3/h. The volumetric mass transfer coefficient reaches its maximum when the lance level is 2.1m, the top blowing rates is 30000Nm3/h, and the bottom blowing rate is 384Nm3/h with tuyeres located symmetrically at 0.66D of the converter bottom.

Multi-objective Optimization of Geothermal Extraction from the Enhanced Geothermal System in Qiabuqia Geothermal Field, Gonghe Basin

A geothermal demonstration exploitation area will be established in the Enhanced Geothermal System of the Qiabuqia field, Gonghe Basin, Qinghai–Xizang Plateau in China. Selection of operational parameters for geothermal field extraction is thus of great significance to realize the best production performance. A novel integrated method of finite element and multi-objective optimization has been employed to obtain the optimal scheme for thermal extraction from the Gonghe Basin. A thermal-hydraulic-mechanical coupling model(THM) is established to analyze the thermal performance. From this it has been found that there exists a contraction among different heat extraction indexes. Parametric study indicates that injection mass rate(Q_(in)) is the most sensitive parameter to the heat extraction, followed by well spacing(WS) and injection temperature(T_(in)). The least sensitive parameter is production pressure(p_(out)). The optimal combination of operational parameters acquired is such that(T_(in), p_(out), Q_(in), WS) equals(72.72°C, 30.56 MPa, 18.32 kg/s, 327.82 m). Results indicate that the maximum electrical power is 1.41 MW for the optimal case over 20 years. The thermal break has been relieved and the pressure difference reduced by 8 MPa compared with the base case. The optimal case would extract 50% more energy than that of a previous case and the outcome will provide a remarkable reference for the construction of Gonghe project.