Estimation of Heating Temperature for Fire-Damaged Concrete Structures Using Adaptive Neuro-Fuzzy Inference System

A Proposal of an Adaptive Neuro-Fuzzy Inference System for Modeling Experimental Data in Manufacturing Engineering

In Manufacturing Engineering there is a need to be able to model the behavior of technological variables versus input parameters in order to predict their behavior in advance, so that it is possible to determine the levels of variation that lead to optimal values of the response variables to be obtained. In recent years, it has been a common practice to rely on regression techniques to carry out the above-mentioned task. However, such models are sometimes not accurate enough to predict the behavior of these response variables, especially when they have significant non-linearities. In this present study a comparative analysis between the precision of different techniques based on conventional regression and soft computing is initially carried out. Specifically, regression techniques, based on the response surface model, as well as the use of artificial neural networks and fuzzy inference systems along with adaptive neuro-fuzzy inference systems will be employed to predict the behavior of the aforementioned technological variables. It will be shown that when there are difficulties in predicting the response parameters by using regression models, soft computing models are highly effective, being much more efficient than conventional regression models. In addition, a new method is proposed in this study that consists of using an iterative process to obtain a fuzzy inference system from a design of experiments and then using an adaptive neuro-fuzzy inference system for tuning the constants of the membership functions. As will be shown, with this method it is possible to obtain improved results in the validation metrics. The means of selecting the membership functions to develop this model from the design of experiments is discussed in this present study in order to obtain an initial solution, which will be then tuned by using an adaptive neuro-fuzzy inference system, to predict the behavior of the response variables. Moreover, the obtained results will also be compared.

Using a Fuzzy Inference System to Obtain Technological Tables for Electrical Discharge Machining Processes

Technological tables are very important in electrical discharge machining to determine optimal operating conditions for process variables, such as material removal rate or electrode wear. Their determination is of great industrial importance and their experimental determination is very important because they allow the most appropriate operating conditions to be selected beforehand. These technological tables are usually employed for electrical discharge machining of steel, but their number is significantly less in the case of other materials. In this present research study, a methodology based on using a fuzzy inference system to obtain these technological tables is shown with the aim of being able to select the most appropriate manufacturing conditions in advance. In addition, a study of the results obtained using a fuzzy inference system for modeling the behavior of electrical discharge machining parameters is shown. These results are compared to those obtained from response surface methodology. Furthermore, it is demonstrated that the fuzzy system can provide a high degree of precision and, therefore, it can be used to determine the influence of these machining parameters on technological variables, such as roughness, electrode wear, or material removal rate, more efficiently than other techniques.

A Method for Instant Estimation of the Temperature Experienced by Fire-Damaged Reinforced Concrete Structures Using Titanium

When a concrete structure is exposed to fire, its structural safety is significantly compromised due to the spalling of members and scaling of concrete. In addition, its durability is substantially reduced due to certain chemical changes such as the dehydration of Ca(OH)₂, the main hydration product of concrete, and the rehydration of CaO. Therefore, when fire damage occurs to a reinforced concrete (RC) building, rapid diagnosis and evaluation techniques are required for immediate repair and reinforcement, requiring a crucial step of quantitatively determining the heating temperature. This study aims to demonstrate a method of estimating the heating temperature experienced by fire damaged RC buildings. The experiments utilized two short RC column specimens with embedded titanium strips. The discoloration characteristics of titanium at high temperatures provided a quick, accurate, and simple mechanism for the estimation of the heating temperature by depth. Empirical equations were derived to estimate the heating temperature as a function of the discoloration characteristics of titanium. Thereafter, a comparison of this estimated temperature with the actual heating temperature measured using thermocouples revealed an average error of less than 20 °C, thereby demonstrating a significantly good correlation and an extremely high reliability of the proposed method.