Energy inefficiency diagnosis in industrial process through one-class machine learning techniques

In the era of Industry 4.0, the ease of access to precise measurements in real-time and the existence of machine-learning (ML) techniques will play a vital role in building practical tools to isolate inefficiencies in energy-intensive processes. This paper aims at developing an abnormal event diagnosis (AED) tool based on ML techniques for monitoring the operation of industrial processes. This tool makes it easier for operators to accomplish their tasks and to make quick and accurate decisions to ensure highly efficient processes. One of the most popular ML techniques for AED is the multivariate statistical control (MSC) method; it only requires the dataset of the normal operating conditions (NOC) to detect and identify the variables that contribute to abnormal events (AEs). Despite the popularity of MSC, it is challenging to select the appropriate method for detecting and isolating all possible abnormalities a complex industrial process can experience. To address this limitation and improve efficiency, we have developed a generic methodology that integrates different ML techniques into a unified multiagent based approach, the selected ML techniques are supposed to be built using only the normal operating condition. For the sake of demonstration, we chose a combination of two ML methods: principal component analysis and k-nearest neighbors (k-NN). The k-NN was integrated into the proposed multiagent to take into account the nonlinearity and multimodality that frequently occur in industrial processes. In addition, we modified a k-NN method proposed in the literature to reduce computation time during real-time detection and isolation. Finally, the proposed methodology was successfully validated to monitor the energy efficiency of a reboiler located in a thermomechanical pulp mill.