In the past few years, research into types of electrical defect diagnostics has increased dramatically. Software monitoring capabilities are strongly encouraged by users and producers of these diverse efforts to increase trustworthiness and extensibility. The Internet of Things (IoT) has expanded significantly and is helping to improve current technical developments in industry, medicine, and many environmental services. By incorporating IoT and industrial wireless sensor networks, it introduces a number of new prospects for process control and support offerings processing capability via the cloud. Continuous monitoring allows for early identification of machine failures, which is advantageous for factory automation by delivering effective process control. The identification of pertinent characteristics using an oriented sport vector machine is presented in the study (FO-SVM). The suggested method has the ability to extract the most pertinent feature set, resulting in the correct classification of defects as a result. Higher classification accuracy is achieved by extracting the most pertinent characteristics prior to the classification procedure. The empirical work utilizing the use of the suggested technique offers a solution again for effective tracking of machine status and failure prediction using a cloud-based platforms employing IoT network.