Temperature Control of a Chemical Reactor Based on Neuro-Fuzzy Tuned with a Metaheuristic Technique to Improve Biodiesel Production

Abstract

This work deals with the problem of choosing a controller for the production of biodiesel from the transesterification process through temperature control of the chemical reactor, from the point of view of automatic control, by considering such aspects as the performance metrics based on the error and the energy used by the controller, as well as the evaluation of the control system before disturbances. In addition, an improvement method is proposed via a neuro-fuzzy controller tuned with a metaheuristic algorithm to increase the efficiency of the chemical reaction in the reactor. A clear improvement is shown in the minimization of the integral of time multiplied squared error criterion (ITAE) performance index with respect to the proposed method (8.1657 ×104) in relation to the PID controller (7.8770 ×107). Moreover, the integral of the total control variation (TVU) performance index is also shown to evaluate the power used by the neuro-fuzzy controller (25.7697), while the PID controller obtains an index of (32.0287); this metric is especially relevant because it is related to the functional requirements of the system since it quantifies the variations of the control signal.

BA-Optimized Variable Domain Fuzzy PID Control Algorithm for Water and Fertilizer Ratio Control System in Cotton Field

“…The inputs to the corrected values of the three parameters of the PID and the system deviation into the PID controller, and obtains the corrected values o the three parameters 𝐾 𝑝 , 𝐾 𝑖 , and 𝐾 𝑑 . In the iterative process, the fitness function is needed to calculate the fitness value o each individual, and then evaluate the advantages and disadvantages of the individual The Integral of the Time-weighted Absolute Error (ITAE) metric, which has the ad vantages of fast, smooth, and low overshooting, has been adopted by most of the litera tures [27][28][29], therefore, this paper introduces it into the performance evaluation of the precision fertilizer control system, which serves as an important reference index of the controller and as the fitness function of the BA optimization algorithm. The ITAE criterion In the iterative process, the fitness function is needed to calculate the fitness value of each individual, and then evaluate the advantages and disadvantages of the individual.…”

“…The ITAE criterion In the iterative process, the fitness function is needed to calculate the fitness value of each individual, and then evaluate the advantages and disadvantages of the individual. The Integral of the Time-weighted Absolute Error (ITAE) metric, which has the advantages of fast, smooth, and low overshooting, has been adopted by most of the literatures [27][28][29], therefore, this paper introduces it into the performance evaluation of the precision fertilizer control system, which serves as an important reference index of the controller and as the fitness function of the BA optimization algorithm. The ITAE criterion, i.e., the Time-Multiplied Absolute Error Integral Minimization criterion, can be expressed as follows:…”

A Bilevel Optimization Approach for Tuning a Neuro-Fuzzy Controller

“…The neuro-fuzzy controller, considered as a case study in this work, is an improved version of the definition presented in [22]. It represents an important alternative to onoff systems and PID controllers that are used in industrial processes such as biodiesel production but often perform poorly due to their inadequate handling of disturbances over time [13].…”

“…In [13], a specific case of tuning an NFC applied to a biodiesel production process was presented. Its architecture requires a series of initial values (weights) to operate, where the number of weights is exponential to the number of membership functions.…”

“…Additionally, it is proposed to implement the repulsion strategy described in [18] to obtain the integer type variable, to avoid problems such as the loss of diversification in scenarios with mixed variables, which has been reported in various developments [19][20][21]. Using the proposed process, it is possible to determine the complete tuning of the NFC without depending on the experience or intuition of the designers to determine its architecture (number of membership functions and weights), with results that surpassed those in [13], where the exploration was biased.…”