A new qualitative trend analysis algorithm based on global polynomial fit

Static gain estimation for nonlinear dynamic systems from steady-state values hidden in historical data

Static gains are often required for control, diagnosis and optimization of nonlinear dynamic systems. This paper proposes a new approach to estimate static gains for nonlinear dynamic systems from steady-state values hidden in historical data. First, steady-state values of system inputs and outputs are extracted by automatically finding data segments in steady-state conditions. Second, static gains of nonlinear dynamic systems in different operating conditions are estimated via linear regression from these steady-state values. The proposed approach has two practical features: (i) estimated static gains can be verified in a convincing way, because the validness of extracted steady-state values is confirmed by visualizing data segments in steady-state conditions, and the accuracy of estimated static gains is verified by comparing the extracted steady-state values and their estimates; (ii) the proposed approach is simple to understand and implement in practice, since it only involves a linear equation between steady-state values and static gains, as well as a basic technique of linear regression. Numerical simulation and industrial application demonstrate the effectiveness of the proposed approach.

Extracting kinetic information in catalysis: an automated tool for the exploration of small data

Kinetically relevant information for heterogeneously catalysed reactions is automatically extracted from small datasets by means of a newly-developed machine learning chemically-enriched tool.

Early Fault Diagnosis Method for Batch Process Based on Local Time Window Standardization and Trend Analysis

The products of a batch process have high economic value. Meanwhile, a batch process involves complex chemicals and equipment. The variability of its operation leads to a high failure rate. Therefore, early fault diagnosis of batch processes is of great significance. Usually, the available information of the sensor data in batch processing is obscured by its noise. The multistage variation of data results in poor diagnostic performance. This paper constructed a standardized method to enlarge fault information as well as a batch fault diagnosis method based on trend analysis. First, an adaptive standardization based on the time window was created; second, utilizing quadratic fitting, we extracted a data trend under the window; third, a new trend recognition method based on the Euclidean distance calculation principle was composed. The method was verified in penicillin fermentation. We constructed two test datasets: one based on an existing batch, and one based on an unknown batch. The average diagnostic rate of each group was 100% and 87.5%; the mean diagnosis time was the same; 0.2083 h. Compared with traditional fault diagnosis methods, this algorithm has better fault diagnosis ability and feature extraction ability.