Search

Wall slip can be defined as a phenomenon in the flow of suspensions due to the movement of particles away from the wall boundary, leaving a thin liquid rich layer adjacent to the wall. It should be taken into consideration in material designing, manufacturing and transportation as it may cause inaccurate rheological measurements such as shear rate and viscosity. The apparent (measured) shear rate is higher than the actual shear rate. The traditional method for actual shear rate determination is not efficient from the perspective of time and cost consumption. Therefore, there is a need to develop a mathematical model that is able to detect the complex pattern of the actual shear rate and accurately predict its value based on the available measured input variables. Volumetric concentration, particle size, temperature and shear stress are selected as the input, while the actual shear rate is kept as output while designing the architecture of ANFIS model. Sixteen ANFIS models with different architecture were designed and evaluated using different statistical indices. Model XVI with number of membership function equal to 3, input product of two sigmoid membership function, output linear membership function type integrated with hybrid optimization method appears to be the most suitable model architecture for predicting the actual shear rate. [ABSTRACT FROM AUTHOR]

The presence of wall slip in concentrated suspensions affect the rheological measurements such as shear stress, shear rate, and viscosity. The measured shear rate will have a value lower than the actual shear rate. Therefore, it is important to have a study on such scenario as the concentrated suspensions have a wide industrial application. The current method for actual shear rate prediction is a challenging task and quite time-consuming as several experimental works are required. Therefore, the development of a mathematical model with an acceptable accuracy is required. Multi-layer perceptron neural network (MLP-NN) is employed to develop the prediction model by applying shear stress, volumetric concentration, particle size, and temperature as the input parameters while the actual shear rate is kept as the output variable. MLP-NN model with 9 hidden neurons is the model that has achieved the best performance in term of statistical analyses. Besides, MLP-NN models for five different temperature ranges (i.e., 11–20 °C, 21–30 °C, 31–40 °C, 41–50 °C, and 51–60 °C) are also proposed to investigate the potential of the developed model to achieve a better accuracy and ease the user while dealing with the specified temperature range. It is found that the MLP-NN models with the best performance for each temperature range are the models with 8 hidden neurons, 10 hidden neurons, 8 hidden neurons, 9 hidden neurons, and 9 hidden neurons respectively. The novelty of this research study is the application of artificial intelligence method to mimic rheological actual shear rate under wall slip condition. [ABSTRACT FROM AUTHOR]

Wall slip is a phenomenon in which particles migrate from solid boundaries, leaving a thin liquid rich layer adjacent to a wall, which can affect the measurement of the rheological properties. Currently, analyses of wall slip are normally carried out through experimental study using a rheometer. These traditional methods are generally time consuming, as several experiment sets are usually required. The aim of this research is to develop an alternative, more efficient approach, by formulating a mathematical model able to predict the wall slip velocity with an acceptable level of accuracy. Specifically, this study investigates a Multi-Layer Perceptron Neural Network (MLP-NN) as an advanced method to predict wall slip velocity. It develops and tests several MLP-NN architectures that accommodate a range of fixed input variables including shear stress, concentration, temperature and particle sizes, with estimated wall slip velocity as the output variable. Using this method, users can perform wall slip velocity analyses by simply plugging different patterns of the proposed input variables into the recommended architecture. Our tests show an MLP-NN model with one hidden layer consisting of nine hidden neurons to be the best architecture for such purposes, producing a strong overall performance with an R2 value of 0.9994 and maximum error of 28%. This research study is innovative in its use of artificial intelligence to predict wall slip velocity in rheological applications. [ABSTRACT FROM AUTHOR]