A Novel Hybrid Voter Using Genetic Algorithm and Performance History

Triple Modular Redundancy (TMR) is generally used to increase the reliability of real timesystems where three similar modules are used in parallel and the final output is arrived at usingvoting methods. Numerous majority voting techniques have been proposed in literature howevertheir performances are compromised for some typical set of module output value. Here wepropose a new voting scheme for analog systems retaining the advantages of previous reportedschemes and reduce the disadvantages associated with them. The scheme utilizes a geneticalgorithm and previous performances history of the modules to calculate the final output. Thescheme has been simulated using MATLAB and the performance of the voter has beencompared with that of fuzzy voter proposed by Shabgahi et al [4]. The performance of the voterproposed here is better than the existing voters.