Auto-commissioning Technology of Engineering Equipment Driven by Machine Learning

The auto-commissioning system of engineering equipment requires real-time identification of the working mode with the whole product. Determine whether there is any abnormality in the commissioning process according to the parameter standards of each working mode, to evaluate the compliance rate of the commissioning. In this article, the working mode of engineering equipment is determined by Toeplitz Inverse Covariance-based Clustering (TICC) and the time series data are segmented and clustered. Each mode in the TICC is defined by a Markov Random Field (MRF), which characterizes the interdependence between different factors in the mode. On this basis, highlight the characteristics of the model and the importance of each factor. By using the TICC method to commissioning the concrete pump truck, the results of automatic identification show that the method has high accuracy in the recognition of the working mode of engineering equipment. The successful application of the online commissioning and monitoring system of the whole machine based on this technology provides a new idea for the development of the industry.