In a control system the controller parameters haveto be chosen so that the system behaves in thedesired way. There are two approaches to findproper values of the controller parameters. The firstapproach is to assume a mathematical model of theprocess and then find the controller parametersbased on the assumed model. The second approachis to choose some controller parameters, observe thebehavior of the feedback loop and modify thecontroller parameters until the desired behavior isachieved.Model-based controller design is becoming morepopular in engineering research studies. Manyadvanced control strategies incorporate variousaspects of the internal model principle, whichrequires a model of the system. Some proportionalintegral-derivative(PID) controllers also include animplicit process model in their design. For somecontroller design approaches, such as a Smithpredictor scheme, a process model is a requirement.Therefore, being able to obtain an accurate processmodel is an important task.Recently, the relay feedback control (Aström andHagglund, 1984) has been widely used for theidentification of an assumed model. The method wasoriginally proposed for autotuning of a process byusing limit cycle information, Kc and ωc, directly,but later was also suggested for use in for parameterestimation of a plant transfer function (Luyben,1987).There are several reasons behind the success of therelay feedback method. First, the relay feedbackmethod, as normally used, gives importantinformation about the process frequency response atthe critical gain and frequency, which are theessential data required for controller design.Second, the relay feedback method is performedunder closed loop control. If appropriate values ofthe relay parameters are chosen, the process may bekept in the linear region where the frequencyresponse is of interest. Third, the relay feedbackmethod eliminates the need for a careful choice offrequency. Finally, the method is so simple thatoperators understand how it works.In the literature, the use relay feedback method foropen loop stable, unstable and integrating processescan be found. However, in practice it is possible toencounter processes with inverse response as well.There are only a few studies considering the use ofrelay feedback control system for identification ofsuch processes. Also, the numbers of unknowncoefficients in model transfer function of inverseresponse processes are increased; henceidentification approaches existing in literature maybecome ineffective.Therefore, to overcome the difficulty in identifyingmodel parameters of processes with inverseresponse, this paper a genetic based identificationmethod using relay feedback control system forinverse response processes is given. Obtained modeltransfer function and the real process transferfunction frequency response characteristics andlimit cycle oscillations are compared to illustrate theeffectiveness of the proposed identification method.