Scientists Train Neural Network to Generate Process Plans from 3D Models
Researchers at the HSE FCS AI and Digital Science Institute have developed CAD2TechSpec, a framework that converts 3D models of mechanical parts into machining process plans—step-by-step instructions for machine tools. The solution aims to reduce the time required for the design and preparation of technical process documentation in mechanical engineering, aircraft manufacturing, and other high-tech industries. The study findings have been published in PeerJ Computer Science.
Today, many complex mechanical parts, such as turbine blades, are designed using specialised 3D modelling software. However, a 3D model cannot simply be sent directly to a machine tool. Engineers must manually develop a processing algorithm, taking into account the part’s geometry, the equipment's capabilities, the available tools, and applicable production standards. This process is time-consuming and requires extensive domain expertise.
The CAD2TechSpec framework addresses this challenge by taking a three-dimensional model as input and converting it into a structured description of the manufacturing process that can be understood by a CNC (Computer Numerical Control) machine. Such machines can produce parts with extremely complex geometries based on computer-generated instructions. First, the model is rendered from 28 different angles. The most informative views are then selected and combined into a multi-view image collage, which, together with a textual prompt, is fed into a multimodal language model capable of 'seeing' the images and 'understanding' the text.
The model then generates a machining plan for producing the part. To improve accuracy and reduce errors, the system uses RAG (Retrieval-Augmented Generation), which acts as a kind of reference guide for the neural network. Before generating a response, the system retrieves information from two sources: an ISO (International Organization for Standardization) database containing standards for equipment, tools, and manufacturing processes, and a library of validated solutions. If the neural network identifies a part similar to one it has encountered before, it can use an existing machining plan rather than generating one from scratch.
The system’s performance was evaluated according to three criteria: the correctness of the output file structure; the accuracy of the manufacturing process and its conformity with the geometry of the described part; and the relevance of the applied ISO standards. The experiments were conducted on 1,236 models from an open database, with the results evaluated by both automated systems and mechanical engineering experts. The best performance was achieved by the Mistral Large 3 model when used with the ISO knowledge base.
Maxim Minets
'Experiments have shown that the quality of the generated process plans depends not only on the model itself but also on the context provided to it. A knowledge base containing information on ISO standards and reference examples of parts significantly improves the quality of the generated specifications,' notes article co-author Maxim Minets, Research Assistant at the Laboratory of Methods for Big Data Analysis (LAMBDA) at HSE FCS.
The system is designed to serve as an intelligent assistant to manufacturing engineers, handling routine tasks involved in preparing preliminary process plans. Experts rated the generated plans at 86–89 points out of 100, while error analysis showed that the system’s performance could be further improved by providing the neural networks with additional training datasets.
Denis Derkach
'The solution can be applied in precision engineering, aircraft manufacturing, and other industries where preparing technical documentation accounts for a significant share of engineers’ working time. CAD2TechSpec is designed to accelerate routine tasks rather than fully automate decision-making. The final verification and approval of the process plan remain the responsibility of the human operator,' emphasises Denis Derkach, Head of the Laboratory of Methods for Big Data Analysis (LAMBDA) at HSE FCS.
See also:
HSE University to Launch 11 Projects with Research Centres from Five Countries
HSE University has announced the results of its International Academic Cooperation (IAC) competition for joint fundamental research projects. Five projects have received full funding, while six more have been awarded partial funding. The research teams include scholars from Brazil, South Africa, China, India, and Oman. Alexander Balyshev, HSE University Vice President, shared details of the 2026 IAC competition winners.
Leo Tolstoy, Specifications, Counterpoint, and AI Inclusivity: HSE University Discusses Vibe Coding
HSE University hosted the first international conference on vibe coding, VIBE CODING RUSSIA 2026. More than 450 participants and speakers from universities, banks, the telecommunications and cybersecurity sectors, and the vibe-coding community discussed how AI is shortening the path from research findings to products and who is responsible for code written by an algorithm.
Window into the Body: Scientists Develop Neural Network to Detect Risk of 15 Diseases from Retinal Images
Russian universities, with the participation of HSE University, Sber, and Z-union, have developed a neural network that can simultaneously assess the risk of 15 types of pathology from retinal photographs, including not only eye diseases but also cardiovascular conditions. The AI system can help clinicians detect potentially concerning changes at an early stage, identify signs reflecting the condition of retinal blood vessels, and determine whether a patient may need further examination. The paper has been published in Frontiers in Medicine.
HSE Researchers Show How Congenital Motor Disorders Affect Brain Development
Researchers from HSE University’s Institute for Cognitive Neuroscience have synthesised the findings of their previous studies on brain development in children with obstetric brachial plexus palsy and arthrogryposis. Their analysis shows that impaired motor function in early childhood not only limits children’s motor experience but also affects memory, categorical thinking, and information processing. The study has been published in Frontiers in Psychology.
AI Users Earn Up to 41.8% More Than Non-Users
Research conducted by economists at HSE University has revealed a significant correlation between the regular use of GenAI in the workplace and higher pay among Russian employees. The study found that individuals who frequently use GenAI in their professional activities earn notably more than those who reject these new tools or resort to them occasionally. The salary premium for highly qualified specialists reaches 41.8%. The article was published in the Voprosy Ekonomiki journal.
AI Robot for Environmental Recognition Tested at HSE University
Engineers and researchers at the HSE Institute for Robotics Systems have successfully run the first tests of an AI-powered environmental recognition model deployed on a robot dog. The robot navigated around the HSE Pokrovka building and Pokrovsky Bulvar, analysing the surrounding environment to identify its location.
Personal Interest in Doctoral Thesis Topic Most Important for Confidence in Successful Defence
A researcher at HSE University analysed data on 1,539 doctoral students from 161 Russian universities to identify which features of a thesis topic are associated with academic success and engagement. The most important factor was found to be personal interest in the research topic, which was associated with almost all key aspects of doctoral programme experience—from engaging with the academic supervisor to research activity and confidence about successfully defending the thesis. The findings have been published in Higher Education.
Algebra, Geometry, and AI: Russian and Vietnamese Mathematicians Discuss Current Research
A delegation of scientists from Hanoi visited the HSE Faculty of Computer Science and then took part in a Russian-Vietnamese conference in St Petersburg. The events were part of the three-year project ‘Flexibility and Computational Methods.’ Over the course of the project, the researchers have prepared joint publications and obtained new mathematical results.
Researchers Develop Methodology to Assess the Quality of Legal Representation in Criminal Proceedings
Having a good defence attorney in criminal proceedings can largely determine whether a defendant retains their freedom, health and good name. Researchers at HSE University propose a method for predicting an attorney’s performance based on the outcomes of their previous cases. The methodology takes into account the severity of the charges, the complexity of the cases, and the most likely outcome, drawing on judicial statistics.
When Pictures Hinder Understanding: Illustrations May Impede Learning of Abstract Ideas
Illustrations can help remember specific actions but do not always make abstract ideas easier to learn. Researchers from HSE University and Humboldt University compared how people learn from texts with different levels of abstractness. They found that participants remembered illustrations better and performed better on related tasks after reading a multimedia text about yoga asanas than after reading an abstract text about the Nash equilibrium. The findings could help improve the selection of illustrations for educational and informational materials. The study has been published in Learning and Instruction.