The article proposes an approach to automate the detection of polishing defects in blades using luminescent testing (LUM). Instead of manual visual inspection, a system was developed that utilizes a deep learning neural network for defect segmentation on images and a robotic setup for precise positioning of the camera and the blank. This ensures the repeatability of the inspection. The relevance is driven by the industry's need for high-precision and reliable real-time quality control methods. The mathematical model of the process, software architecture, hardware components, and the data collection process for neural network training are described. The results of applying the system for defect detection are presented. The development optimizes polishing processes.

Keywords: industrial blade polishing, intelligent video analytics, robotic optical scheme, mathematical model of technological process, Lum control

The article focuses on the developement of a stemmer for Pymystem morphological analyser. Theoretical justification for morphological analysis selection as a high-priority task of linguistic text analysis is given. The state-of-art analysers are described, their strengths and shortcomings are highlighted. The authors propose a core algorithm for nested structures splitting into structured class hierarchy. A method for selected parts of speech key features retrieval using regular expression and Python is defined. The main steps of the hierarchy creation algorithm are examined and documented. The researchers analyse core results of the study and describe their findings alongside with propositions for further developement of the presented software.

Keywords: stemmer, morphological analyzer, class tree, regular expression, text analysis, computational linguistics, lemma, token, word-formation, class hierarchy