One of the most important raw materials in the pharmaceutical and food industry is the essential oil of medicinal plants. The originality and purity of the essential oil is an important subject from an economical and practical point of view. Conventional methods for identifying and evaluating the authenticity of essential oils have weaknesses, and the use of electronic nose systems covers these disadvantages. In this study, an electronic nose system consisting of 8 metal oxide semiconductor sensors was designed to determine the purity of peppermint essential oil. The principal component analysis (PCA) method was used to reduce the dimensional of the data and identify the effective sensors in detecting the degree of purity and eliminating useless sensors. Then, classification accuracy was calculated by using the classification techniques of SVM. Based on the results, the PCA method with two main components, PC1, and PC2, explained 82% of the data variance. Also, based on the loading diagram, the sensors that had the most impact on detecting the degree of purity of essential oil, including TGS822, MQ8, MQ3, MQ5, MQ9, and TGS813, were identified. The diagnostic algorithm based on the support vector machine was also able to separate the samples of essential oils with a purity of zero to 100% from each other with an accuracy of 75%. Therefore, the proposed electronic nose system based on the mentioned  algorithm could detect the purity of peppermint essential oil with acceptable accuracy.