ABSTRACT
In this work, cost-sensitive decision support was developed. Using Batch Data Analytics (BDA) methods of the batch data structure and feature accommodation, the batch process property and sensor data can be accommodated. The batch data structure organises the batch processes' data, and the feature accommodation approach derives statistics from the time series, consequently aligning the time series with the other features. Three machine learning classifiers were implemented for comparison: Logistic Regression (LR), Random Forest Classifier (RFC), and Support Vector Machine (SVM). It is possible to filter out the low-probability predictions by leveraging the classifiers' probability estimations. Consequently, the decision support has a trade-off between accuracy and coverage. Cost-sensitive learning was used to implement a cost matrix, which further aggregates the accuracy-coverage trade into cost metrics. Also, two scenarios were implemented for accommodating out-of-coverage batches. The batch is discarded in one scenario, and the other is processed. The Random Forest classifier was shown to outperform the other classifiers and, compared to the baseline scenario, had a relative cost of 26%. This synergy of methods provides cost-aware decision support for analysing the intricate workings of a multiprocess batch data system.
ABSTRACT
In this paper, the possibility of applying different welding strategies to overlay an FeCrAl layer against corrosion from heavy liquid metal on a plain plate made of 316L austenitic stainless steel was investigated. This technology could be used in manufacturing the main vessel of CiADS, which may be considered as a more economic and feasible solution than production with the corrosion-resistant FeCrAl alloy directly. The main operational parameters of the laser welding process, including laser power, weld wire feeding speed, diameter of the welding wire, etc., were adjusted correspondingly to the optimized mechanical properties of the welded plate. After performing the standard nuclear-grade bending tests, it can be preliminarily confirmed that the low-power pulse laser with specific operational parameters and an enhanced cooling strategy will be suitable to surface an Fe-10Cr-4Al-RE layer with a thickness of approximately 1 mm on a 40 mm-thick 316L stainless steel plate, thanks to the upgraded mechanical properties incurred by refined grains with a maximum size of around 300 µm in the welded layer.
