Abstract
In modern industrial processes, various types of soft sensors are used in process monitoring, control, and optimization, and the soft sensors designed to maintain or update these models are highly desirable in the industry. This paper proposes a novel technique for monitoring and control optimization of soft sensors in automation industry for fault detection. The fault detection has been carried out using probabilistic multi-layer Fourier transform perceptron (PMLFTP), and the input data has been pre-processed for removal of samples containing null values for fault detection and diagnosis process through Fourier transform-based detection and multi-layer perceptron-based diagnosis in the manufacturing process. The controlling of data in soft sensors has been optimized using auto-regression-based ant colony optimization (AR_ACO), and the experimental results have been reported in terms of computational rate of 40%, QoS of 78%, RMSE of 45%, fault detection rate of 90%, and control optimization of 93%.