Prediction of soil compaction under pneumatic tires a using fuzzy logic approach

Artificial intelligence systems are widely accepted as a technology offering an alternative way to tackle complex and ill-defined problems. They can learn from examples, are fault tolerant in the sense that they are able to handle noisy and incomplete data, are able to deal with non-linear problems, and once trained can perform prediction and generalization at high speed. Compared with traditional approaches, fuzzy logic is more efficient in linking the multiple inputs to a single output in a non-linear domain. The purpose of this study was to investigate the relationship between tire working parameters and soil compaction characteristics, and to illustrate how Fuzzy expert system might play an important role in prediction of soil. All experimental values were collected from soil bin. The trials were conducted in different tire types, vertical loads, inflation pressures and forvard velocities. In this paper, a sophisticated intelligent model, based on Mamdani approach fuzzy modeling principles, was developed to predict the changes in penetration resistance, final pressure and bulk density of soil due to wheel traffic. The verification of the proposed model is achieved via various numerical error criteria. For all parameters, the relative error of predicted values was found to be less than the acceptable limits (10%).     

Prediction of paddy soil normal adhesion to steel surfaces by fuzzy logic

Numerous data concerning paddy soil composition, water content and soil-steel normal adhesion were collected in South China during 1974-1983. The fuzzy logic relation of adhesion with clay content and water content was derived, by which paddy soil adhesion to steel surfaces was predicted if soil composition and water content were known.     

Predicting USCS soil classification from soil property variables using Random Forest

Soil classification systems are widely used for quickly and easily summarizing soil properties and provide a shorthand method of communication between scientists, engineers, and end-users. Two of the most widely used soil classification systems are the United States Department of Agriculture (USDA) textural soil classification system and the Unified Soil Classification System (USCS). Unfortunately, not all soil map units are classified according to the USDA or USCS systems, and previous attempts to provide a crosswalk table have been inconsistent. Random Forest machine learning model was used to create a USCS prediction model using USDA soil property variables. Important variables for predicting USCS code from available soil properties were USDA soil textures, percent organic material, and available water storage. Prediction error rates less than 2% were achieved compared to error rates of approximately 40% using crosswalk methods.     

Complex turbulent compressible flow computation using a two-layer approach

A two-layer approach is proposed to compute complex flows including separations. For high- and low-Reynolds-number regions we use a two-equation k-? model and a one-equation k-L model respectively. A robust algorithm is proposed for the treatment of the convective part of the turbulence equations. Several complex configurations including separations are computed.     

An empirical model to predict soil bulk density profiles in field conditions using penetration resistance, moisture content and soil depth

Cylindrical soil probes measuring 300 mm in diameter by 300 mm in height were prepared in the laboratory using samples extracted from a well drained loamy soil (FAO classification: Vertic Luvisol). These probes were compacted at different moisture contents [3, 6, 9, 12, 15 and 18 (% w/w)] and using different compaction energies (9.81, 49.05, 98.1 and 981 J). The soil penetration resistance was determined by means of the ASAE 129 mm² base area cone and seven other different cones with base sizes of 175, 144, 124, 98, 74, 39 and 26 mm². The variability of the penetration resistance measurements increased as the size of the cone decreased. Nevertheless, the penetration resistance values proved to be independent of the cone used, as long as the size of the latter was equal to or greater than 98 mm². This confirms the possibility of using cones with areas smaller than the ASAE standard when measurements are to be carried out in dry soils with high levels of mechanical resistance. The experimental data were used to develop an empirical model, a linear additive model on a log–log plane, capable of estimating soil bulk density depending on soil penetration resistance, soil moisture content and depth. This model has provided good results under field conditions and has allowed soil bulk density profiles and accumulated water profiles to be accurately estimated.     

Evaluation of factors and current approaches related to computerized design of tillage tools: a review

The objectives of this paper are to evaluate the factors that are involved in the tillage process, and to explore the potential approaches for the computer-aided design of tillage tools. An overview related to the dynamic effect on the performance of tillage operations has been conducted. Compared with the analytical methods, the finite element method (FEM) has some advantages for the computerized design of tillage tools. The artificial neural networks (ANN) may be useful for the integrated evaluation of tillage performance with multi-objectives. ANN can be employed for simulation of a dynamic constitutive model and identification of soil conditions for agricultural soils. The integral approach of ANN analysis with FEM is found to be promising for optimizing design of tillage tools.     

Thermo-mechanical constitutive modeling of shape memory polyurethanes using a phenomenological approach

This study examined the constitutive modeling of shape memory polyurethanes (SMPUs). SMPUs exhibit a thermo-responsive shape memory behavior, i.e., a thermally fixed temporary shape at a low temperature that returns to its original (permanent) shape when heated. This unique property arises from the molecular configuration of their hard and soft segments; the latter can form a variable state ranging from a rubbery (active) to rigid (frozen) phase according to temperature, while the former undergoes little deformation and acts as a fixed net between the soft segments. In this study, a three-phase phenomenological model (one hard segment phase and two (active and frozen) soft segment phases) was developed to describe the deformation behavior of SMPUs according to their microstructure. The stress and strain relationships of each phase are described mathematically using one three-element viscoelastic and two Mooney–Rivlin hyperelastic equations, respectively. The total stress was calculated by combining those equations via some internal variables that can track the volume fractions of the active and frozen phases and a non-mechanical frozen strain. For validation, the cyclic thermo-mechanical behavior of a SMPU was predicted. These predictions were compared with the experimental results with reasonable agreement between them.     

A simplified solution for piled-raft foundation analysis by using the two-phase approach

In common practice, the pile–soil–raft interaction still remains a challenging problem in the analysis of piled-raft foundations. In the present study, a simplified analytical approach is introduced to analyze a vertically-loaded piled-raft foundation by using a developed homogenization technique called the two-phase approach. In spite of classical and simplified methods in the literature, the proposed method considers the pile–soil interaction. The other major advantage is the ability to predict the axial pile load along the pile length. The problem is solved in the domain of elasticity and simple closed-form solutions are presented for the prediction of the settlement and the pile load sharing of a piled raft as well as the pile's axial force distribution along its length. The applicability of the proposed method is validated by considering case studies and field measurements. A comparison of the results indicates that the method can be utilized safely in a proper, quick, and effective manner with the least computational effort in comparison with sophisticated numerical approaches. The raft settlement can be accurately predicted while the pile load sharing might be over/under estimated. A parametric study is also carried out to investigate the response of piled-raft foundations including the influence of the parameters of the soil and the geometric characteristics of the piles.     

Modeling crack growth during Li insertion in storage particles using a fracture phase field approach

Fracture of storage particles is considered to be one of the major reasons for capacity fade and increasing power loss in many commercial lithium ion batteries. The appearance of fracture and cracks in the particles is commonly ascribed to mechanical stress, which evolves from inhomogeneous swelling and shrinkage of the material when lithium is inserted or extracted. Here, a coupled model of lithium diffusion, mechanical stress and crack growth using a phase field method is applied to investigate how the formation of cracks depends on the size of the particle and the presence or absence of an initial crack, as well as the applied flux at the boundary. The model shows great versatility in that it is free of constraints with respect to particle geometry, dimension or crack path and allows simultaneous observation of the evolution of lithium diffusion and crack growth. In this work, we focus on the insertion process. In particular, we demonstrate the presence of intricate fracture phenomena, such as, crack branching or complete breakage of storage particles within just a single half cycle of lithium insertion, a phenomenon that was only speculated about before.