Application of Adaptive Neuro-Fuzzy Inference System in Flammability Parameter Prediction

Abstract

The fire behavior of materials is usually modeled on the basis of fire physics and material composition. However, significant strides have been made recently in applying soft computing methods such as artificial intelligence in flammability studies. In this paper, multiple linear regression (MLR) was employed to test the degree of non-linearities in flammability parameter modeling by assessing the linear relationship between sample mass, heating rate, heat release capacity (HRC) and total heat release (THR). Adaptive neuro-fuzzy inference system (ANFIS) was then adopted to predict the HRC and THR of the extruded polystyrene measured from microscale combustion calorimetry experiments. The ANFIS models presented excellent predictions, showing very low mean training and testing errors as well as reasonable agreements between experimental and predicted datasets. Hence, it can be inferred that ANFIS can handle the non-linearities in flammability modeling, making it apt as a modeling technique for accurate and effective flammability assessments.Several chemistry-based models, such as inverse modeling, quantitative structure-property relationship (QSPR), quantitative structure-activity relationship (QSAR) and additive molar group contribution methods, have been developed over the years to estimate these important fire safety parameters (HRC and THR). Although effective, some disadvantages, like large prediction errors, have been identified in the traditional modeling approaches and need to be addressed.Until now, correlation analysis and statistical prediction models have been appropriate analytical tools in material flammability [11]. The significance of the prediction models lies in the employment of robust techniques and strategies for the accurate estimation of flammability parameters, whereas correlation analysis assesses the relationship between the predicted or measured parameters. Statistical analysis is mostly empirical, devoid of the chemical compositions and physical structure of the material under consideration [12]. It is imperative to note that fire experiments are demanding, expensive and time consuming. Similarly, traditional flammability parameter predictions involve sophisticated fire modeling and calibration, requiring a great deal of expertise and computing power. It is, therefore, quite convenient for researchers to opt for these system theoretical models as opposed to conceptual models. Statistical models in recent times largely embrace the artificial neural network (ANN) due to its ability to capture complex nonlinearities in a system when compared to linear regression methods. ANN mimics the operation of the human brain by processing information available to the input layers to achieve a desirable output.Generalized regression and the ANN's feed-forward back propagation methods have been applied in flammability studies to predict peak heat release rate, heat release capacity, total heat released, etc., with a high level of accuracy [13,14]. Deviation of the predicted results from the actual or ex...

Artificial Neural Network to Forecast Enhanced Oil Recovery Using Hydrolyzed Polyacrylamide in Sandstone and Carbonate Reservoirs

“…First, the fuzzy input is made based on transforming input data by defining a membership function (MF) [ 48 ]. The computed membership degree of every input factor is reproduced, resulting in the firing strength, as shown below: where is the calculated firing strength, is the degree of membership of the th MF for the th input, and m employs the input counter.…”

“…First, the fuzzy input is made based on transforming input data by defining a membership function (MF) [48]. The computed membership degree of every input factor is reproduced, resulting in the firing strength, as shown below:…”

Reducing the Burn Marks on Injection-Molded Parts by External Gas-Assisted Injection Molding

“…Regression analysis is a useful method to investigate the relationships between variables [ 22 , 23 , 24 ] and it was introduced to quantify the influence of gas parameters on burn marks in this study. A model was established by stepwise regression analysis in Minitab to describe the relationship between the gas parameters and burn marks.…”

Modeling of the Influence of Input AM Parameters on Dimensional Error and Form Errors in PLA Parts Printed with FFF Technology

“…Further examples of the application of fuzzy logic can be found in the study from Xia et al [ 26 ] where surface roughness obtained in wire arc additive manufacturing is predicted by using an ANFIS, that of Sahu et al [ 27 ] where a Mamdani FIS combined with Taguchi method is employed to improve the dimensional accuracy of FFF ABSP 400 parts, and that of Saleh et al [ 28 ] where building orientation, layer thickness, and slurry impact angle are used as input variables in an ANFIS for modelling the effect of slurry impacts on polylactic acid processed by fused deposition modeling or that of or that of Mensah et al [ 29 ] where an ANFIS in employed for flammability parameter modeling among many others.…”