Improving the prediction of petroleum reservoir characterization with a stacked generalization ensemble model of support vector machines

The ensemble learning paradigm has proved to be relevant to solving most challenging industrial problems. Despite its successful application especially in the Bioinformatics, the petroleum industry has not benefited enough from the promises of this machine learning technology. The petroleum industry, with its persistent quest for high-performance predictive models, is in great need of this new learning methodology. A marginal improvement in the prediction indices of petroleum reservoir properties could have huge positive impact on the success of exploration, drilling and the overall reservoir management portfolio. Support vector machines (SVM) is one of the promising machine learning tools that have performed excellently well in most prediction problems. However, its performance is a function of the prudent choice of its tuning parameters most especially the regularization parameter, C. Reports have shown that this parameter has significant impact on the performance of SVM. Understandably, no specific value has been recommended for it. This paper proposes a stacked generalization ensemble model of SVM that incorporates different expert opinions on the optimal values of this parameter in the prediction of porosity and permeability of petroleum reservoirs using datasets from diverse geological formations. The performance of the proposed SVM ensemble was compared to that of conventional SVM technique, another SVM implemented with the bagging method, and Random Forest technique. The results showed that the proposed ensemble model, in most cases, outperformed the others with the highest correlation coefficient, and the lowest mean and absolute errors. The study indicated that there is a great potential for ensemble learning in petroleum reservoir characterization to improve the accuracy of reservoir properties predictions for more successful explorations and increased production of petroleum resources. The results also confirmed that ensemble models perform better than the conventional SVM implementation.     

Improvement of dielectric breakdown strength and energy storage performance in Er2O3–modified 0.95Sr0.7Ba0.3Nb2O6-0.05CaTiO3 lead-free ceramics

In this study, 0.95?Sr_0.7Ba_0.3Nb₂O₆-0.05CaTiO₃-x wt% Er₂O₃ ceramics (SBNCTEx; x?=?0–5) were synthesized using traditional solid-state method, and we investigated the microstructure, energy storage properties as well as the relationship between dielectric breakdown strength and interfacial polarization. As compared with pure 0.95?Sr_0.7Ba_0.3Nb₂O₆-0.05CaTiO₃ ceramics, the Er₂O₃ dopants suppressed the grain growth of SBNCTEx, and the doped ones showed the dense microstructure. The secondary phase was found for x?≥?1 according to the EDS results, and the influence of the secondary phase on relative dielectric breakdown strength has also been studied. The dielectric breakdown strength increased from 18.1?kV/mm to 34.4?kV/mm, which is good for energy storage. The energy storage density of 0.28?J/cm³ and the energy storage efficiency of 91.4% were obtained in the SBNCTE5 ceramics. The results indicate that SBNCTE ceramics can be used as energy storage capacitors.     

A novel Ag–CuAlO2 sealant for reactive air brazing of 3YSZ and AISI 310S

Based on reactive air brazing (RAB), we designed a new type of sealant (Ag–xCuAlO₂) for joining 3 mol.% yttria-stabilized zirconia (YSZ) ceramics and AISI 310S stainless steel. The CuAlO₂ content affected the wettability of the sealant on the YSZ surface, and the joints had a high shear strength when Ag–2 wt.%CuAlO₂, which had a small contact angle on the YSZ substrate, was used as the sealant. In addition, the thickness of the oxide layer was reduced compared to that for the Ag–CuO sealant. The effects of the processing parameters on the microstructure and shear strength of the joints were investigated, and the as-brazed joints reached their highest shear strength (93.7 MPa) when brazed at 1040 °C for 30 min. After high-temperature oxidation at 800 °C for 200 h, the shear strength of the joints remained at 50 MPa, and no apparent change in the microstructure was observed, proving that the joints possessed excellent oxidation resistance.     

Effects of corrosion in liquid fluoride salt on the tensile strength of domestic SiC fibers

The relationship between the tensile strength of corroded domestic second-generation (2ed-gen) SiC fibers at various temperatures for 500 h in 46.5LiF-11.5NaF-42.0KF (mol. %) eutectic salt and the typical microstructure was studied. Weibull theory was used to analyze the critical defects that caused the tensile fracture, and the microstructure of fibers before and after corrosion was characterized. It is concluded that the decrease of tensile strength after corrosion at 800 °C is caused by the surface injury of fibers, which led to the shift of critical defects from the internal defects of virgin fibers to surface defects. Moreover, corrosion at higher temperature accelerates the corrosion process and dissolve the surface O-contained layer thoroughly. This shifts the critical defects back to the internal defects and will be helpful for the recovery of tensile strength of corroded fibers at the higher temperature.     

Effects of structural parameters on water film properties of transpiring wall reactor

Corrosion and salt deposition problems severely restrict the industrialization of supercritical water oxidation. Transpiring wall reactor can effectively weaken these two problems by a protective water film. In this work, methanol was selected as organic matter, and the influences of vital structural parameters on water film properties and organic matter removal were studied via numerical simulation. The results indicate that higher than 99% of methanol conversion could be obtained and hardly affected by transpiration water layer, transpiring wall porosity and inner diameter. Increasing layer and porosity reduced reactor center temperature, but inner diameter's influence was lower relatively. Water film temperature reduced but coverage rate raised as layer, porosity, and inner diameter increased. Notably, the whole reactor was in supercritical state and coverage rate was only approximately 85% in the case of one layer. Increasing reactor length affected slightly the volume of the upper supercritical zone but enlarged the subcritical zone.     

Ergonomically based design of tractor control tools

Musculoskeletal injuries are well-known disorders among the agricultural tractor operators. Overexertion is a critical factor which can agitate these injuries. Physical body characteristics should be measured for an ergonomically best-fit-optimal design for the operators. In this study, a designed setup was employed to derive the applied forces by tractor operators on the control tools. The different muscle strengths including leg/foot strength, hand push/pull strength, and torque strength applied by both hands were measured. A comparison was made for the obtained values for different strengths by considering the effects of hand dominance. The obtained data were used to estimate the maximum allowed forces in these tools. In contrast to the previous studies, the minimum allowed actuating forces of the pedals were calculated using reasonable assumptions. These values could provide more comfort and less exhaustion for the tractor operators. The obtained ranges were benchmarked against corresponding recommended values in some standards (ISO, ISIRI, and ASABE family). The results revealed the unsuitability of evaluated standards for a proper design and the excessive overestimation of those recommended values (in some cases more than 3 times). In all of the design procedure, a suitable attention was paid to accommodate it with more than 90% of target population.Relevance to industryA prosperous industry which considers ergonomic factors in the design of agricultural machine workplace can overcome the disorders and generate more comfort. Evaluating more exact mechanical forces can result in a suitable design of workplace.     

Seismic behavior of geosynthetic-reinforced retaining walls backfilled with cohesive soil

This study investigates the seismic performance of geosynthetic-reinforced modular block retaining walls backfilled with cohesive, fine grained clay-sand soil mixture. Shaking table tests were performed for three ½ scaled (wall height 190 cm) and ¼ scaled model walls to investigate the effects of backfill type, the influence of reinforcement length and reinforcement stiffness effects. The El Centro and Kobe earthquake records of varying amplitudes were used as base acceleration. Displacement of the front wall, accelerations at different locations, strains on the reinforcements, and the visual observations of the facing and the backfill surface were used to evaluate the seismic performance of model walls. The model walls were subjected to rigorous shaking and the walls did not exhibit any stability problems or signs of impending failure. The maximum deformations observed on the models with cohesive backfill was less than half of the deformation of the sand model. The load transfers between the geogrid and cohesive soil was comparable to that of sand and hence the needed reinforcement length was similar as well. As a result; the model walls with cohesive backfills performed within acceptable limits under seismic loading conditions when compared with granular backfilled counterparts.     

Delay compensated control of the Stefan problem and robustness to delay mismatch

This paper presents a control design for the one‐phase Stefan problem under actuator delay via a backstepping method. The Stefan problem represents a liquid‐solid phase change phenomenon which describes the time evolution of a material's temperature profile and the interface position. The actuator delay is modeled by a first‐order hyperbolic partial differential equation (PDE), resulting in a cascaded transport‐diffusion PDE system defined on a time‐varying spatial domain described by an ordinary differential equation (ODE). Two nonlinear backstepping transformations are utilized for the control design. The setpoint restriction is given to guarantee a physical constraint on the proposed controller for the melting process. This constraint ensures the exponential convergence of the moving interface to a setpoint and the exponential stability of the temperature equilibrium profile and the delayed controller in the norm. Furthermore, robustness analysis with respect to the delay mismatch between the plant and the controller is studied, which provides analogous results to the exact compensation by restricting the control gain.     

Strength of pure alumina ceramics above 1 GPa

Up to now, commercially available alumina ceramics were claimed to have strength between 400 and 550 MPa. However, our study shows strength ~ 2 times higher for commercially available alumina than commonly believed. The average and characteristic strength, measured on 31 pure alumina ceramic discs by ball on three balls (B3B) test, were 1205 ± 93 MPa and 1257 MPa, respectively, with a Weibull modulus of m = 11.8. Tested specimens were in form of discs with a diameter of 5 mm and thickness 0.5 mm. The grain size distribution of the alumina is bimodal with an average grain size of ~ 850 nm measured at the surface. The fracture reveals a mixed transgranular / intergranular failure mode. To avoid incorporation of additional flaws, the discs were tested as sintered. The characteristic flexural strength measured in B3B was recalculated according to Weibull theory for standard 4-point bending bars of size 3 × 4 × 45 mm as bend 856 MPa. The measured strength of nearly 900 MPa shows the potential of strength for high purity alumina ceramics.     

Experimental and numerical study on compressive performance of perforated brick masonry after fire exposure

This paper discusses the compressive performance of perforated brick masonry after fire exposure. Compressive strength tests of the mortar, clay perforated brick, and perforated brick masonry specimens were performed in accordance with ISO834 fire tests of different durations. The temperature distribution of the masonry materials and specimens was simulated using the finite element software ABAQUS, with the thermal parameters of masonry materials recommended by European standard Eurocode 6 and related literature. The compressive strength reduction factors of mortar and clay perforated brick exposed to different fire durations were calculated via the layered method suggested by European standard Eurocode 1. In addition, the compressive strength reduction factors after cooldown were obtained from the experimental data of the masonry materials, and by considering further reductions in the compressive strength after cooling from high temperatures. Experimental data of the masonry specimens were compared with the numerical results obtained using the reduction factors proposed in this work. The comparison revealed an overall acceptable approximation. Thus, the method presented in this paper can be used to evaluate the residual capacity of masonry structures after fire.