This paper presents the development of a digital model of the production process at a mechanical engineering enterprise, aimed at improving management efficiency using Big Data technologies and multi-criteria optimization methods. The structure of a machine shop was formalized, identifying the main functional elements of the production system, including production areas, buffers, product flow routes, and intra-shop logistics. Parametric models of production units were developed, enabling the assessment of throughput, equipment utilization, work-in-progress volumes, and operating costs. The study analyzed the influence of machining process parameters on surface quality indicators. Predictive dependences of machining quality on cutting speed, feed rate, vibration level, spindle power, and tool wear were constructed. Three-dimensional models of surface roughness variations and heat maps of equipment utilization were developed, enabling the identification of bottlenecks in the production process. An intelligent methodology for optimizing a production system is proposed, based on machine learning, multi-criteria analysis, and digital modeling. The obtained results confirm the possibility of applying the developed approach to creating digital twins of production processes and improving the management efficiency of mechanical engineering enterprises

Optimizing the parameters of the manufacturing process for products in terms of metalworking equipment is one of the key tasks in technological preparation for production. This process is structurally complex, characterized by an ordered set of actions of various types. The basis for improving the efficiency of the technological process is the comprehensive optimization of the parameters of individual elements that form its structure. To solve this problem, an integrated model for comprehensive multi-criteria optimization of a structurally complex process has been developed, establishing a clear hierarchical relationship between its elements. The model is based on the structural decomposition of two processes: the process of forming individual design elements and the technological process of manufacturing a product. Structural hierarchical models have been developed for each process. The structure of the integrated model contains six levels of control. For each level of control, a set of target indicators and control parameters has been formed. The article presents the results of testing the proposed model using the example of optimizing the technological process of mechanical processing for the “Housing” product. As part of the study, structural and parametric optimization of the manufacturing process for this part was carried out. During the study, the structure of the technological processing route was optimized, as well as individual technological operations and technological transitions. Over the course of the work, the technological equipment and processing methods used for shaping a number of surfaces were replaced. As a result of the optimization, the overall labor intensity of the technological process for manufacturing the “Housing” product was reduced by 19.8%, and the manufacturing accuracy of the most critical surfaces was increased by 16.4%. The results confirm the effectiveness of the proposed model for comprehensive optimization of the mechanical processing technological process.

The purpose of this study is to develop an effective hybrid model for automatic document classification by combining statistical and semantic text vectorization techniques with machine learning algorithms. The methodology integrates Term Frequency–Inverse Document Frequency (TF-IDF) and Word2Vec embeddings with classifiers such as Support Vector Machine (SVM) and Random Forest. The proposed approach includes data preprocessing (tokenization, normalization, stop word removal, and lemmatization), feature extraction, model training, and evaluation using classification metrics such as accuracy, F1-score, Matthews Correlation Coefficient (MCC), and Cohen’s Kappa. Experimental results demonstrate that the Word2Vec + SVM model outperforms other configurations, achieving 90.2% accuracy and an F1-score of 82.52%, thus highlighting the advantage of incorporating semantic context into vector representation. The study concludes that hybrid methods combining TF-IDF and Word2Vec with robust classifiers improve both the precision and generalizability of document analysis models. Practical implications include potential applications in sentiment analysis, topic modeling, text classification for legal and healthcare domains, and multilingual contexts. This research provides a foundation for developing high-performance text analysis systems applicable to various real-world natural language processing tasks.

The article presents a comparative study of LDPC decoding algorithms in an additive white Gaussian noise (AWGN) channel. The aim is to identify the most efficient algorithms for reliable data transmission. Simulations were carried out using the AFF3CT tool with BPSK modulation. Several decoders were analyzed, including GALA, GALB, GALE, PPBF, WBF and MWBF. Performance was evaluated by bit error rate (BER) and frame error rate (FER). The results show that the GalE decoder achieves the best error-correction performance for long codewords (length 20480), with BER values reaching 10-5 and 10-10. For shorter code lengths, MWBF and GalE algorithms also demonstrate good results, with MWBF reaching BER ≈ 10-3 at SNR = 7 dB. In resource-limited conditions, simplified bit-flipping algorithms can provide reasonable efficiency