Nearest fixed boundary negative selection algorithm based method for early-warning of centrifugal compressor unit without fault data

In the modern industrial process, a complete production process is achieved by requiring a variety of equipment to cooperate with each other. The abnormality in any equipment will have a large or small impact on process safety or product quality, resulting in increased risk. In recent years, many data-driven early-warning methods have been developed in academia. However, most of the methods need to be implemented on the support of normal and fault data. In order to overcome the problem, this paper establishes a new early-warning model based on negative selection algorithm (NSA) for centrifugal compressor unit without fault data. Firstly, a nearest neighbor fixed boundary negative selection algorithm (NFB-NSA) is proposed by optimizing detector generation mechanism and matching rules for test samples. Secondly, the performance of NFB-NSA is tested by Iris dataset. The experimental results among NFB-NSA, V-detector, and other anomaly detection methods for Iris dataset shows that NFB-NSA can achieve the highest detection accuracy and the lowest false alarm rate in most cases. Finally, the early-warning of centrifugal compressor unit under normal samples is carried on by NFB-NSA in this paper. Validated by field data, NFB-NSA is demonstrated to be of excellent accuracy and robustness by results of experiments. Moreover, the influence of size of training sample on performance of NFB-NSA is obtained.