CAD System Research Articles

Optimized Xception Learning Model and XgBoost Classifier for Detection of Multiclass Chest Disease from X-ray Images.

Computed tomography (CT) scans, or radiographic images, were used to aid in the early diagnosis of patients and detect normal and abnormal lung function in the human chest. However, the diagnosis of lungs infected with coronavirus disease 2019 (COVID-19) was made more accurately from CT scan data than from a swab test. This study uses human chest radiography pictures to identify and categorize normal lungs, lung opacities, COVID-19-infected lungs, and viral pneumonia (often called pneumonia). In the past, several CAD systems using image processing, ML/DL, and other forms of machine learning have been developed. However, those CAD systems did not provide a general solution, required huge hyper-parameters, and were computationally inefficient to process huge datasets. Moreover, the DL models required high computational complexity, which requires a huge memory cost, and the complexity of the experimental materials' backgrounds, which makes it difficult to train an efficient model. To address these issues, we developed the Inception module, which was improved to recognize and detect four classes of Chest X-ray in this research by substituting the original convolutions with an architecture based on modified-Xception (m-Xception). In addition, the model incorporates depth-separable convolution layers within the convolution layer, interlinked by linear residuals. The model's training utilized a two-stage transfer learning process to produce an effective model. Finally, we used the XgBoost classifier to recognize multiple classes of chest X-rays. To evaluate the m-Xception model, the 1095 dataset was converted using a data augmentation technique into 48,000 X-ray images, including 12,000 normal, 12,000 pneumonia, 12,000 COVID-19 images, and 12,000 lung opacity images. To balance these classes, we used a data augmentation technique. Using public datasets with three distinct train-test divisions (80-20%, 70-30%, and 60-40%) to evaluate our work, we attained an average of 96.5% accuracy, 96% F1 score, 96% recall, and 96% precision. A comparative analysis demonstrates that the m-Xception method outperforms comparable existing methods. The results of the experiments indicate that the proposed approach is intended to assist radiologists in better diagnosing different lung diseases.

Designing the working surfaces of rotary planetary mechanisms

Purpose. To design a method for smoothing the working surfaces of stator and rotor with the use of computer simulation to eliminate the impact of the rotor on the stator when they interact. Methodology. Special and general methods of research have been used: interpolation of the point series – to determine the contour nodes of the rotor and the stator of the rotary-planetary machine; formation of B-splines – to construct a point series whose coordinates are structurally determined; technology of automated formation of curves in CAD-system SolidWorks – for modelling of functional surfaces of a planetary-rotary compressor. Findings. Algorithms for formation of the contours representing curves defined analytically or constructively with a given accuracy have been developed. The obtained contours are used in the CAD system as linear elements of the surface model. The developed method has been tested in the simulation of functional surfaces of a planetary-rotary compressor. Optimization of the body shape and rotor profiles in order to increase the productivity of the rotary-planetary machine has been carried out. Originality. The developed algorithms make it possible to determine the original point series belonging to any curve and provide a given interpolation accuracy when forming a B-spline contour or second-order curve arcs. Computer models of the body surfaces of the rotor are formed on the basis of the gear ratio of the planetary-rotary mechanism and the rotor dimensions. In order to increase the performance of the compressor, the working surfaces of the rotor have been optimized. The maximum volume of the working chamber was increased by increasing the radius of the moving gear of the planetary-rotary mechanism. In order to prevent the rotor from jamming during compressor operation, the rotor contour was changed. Practical value. The method for modelling the surfaces of complex shape in CAD-system has been developed on the basis of creating contours which with given accuracy represent lines from the surface determinant. This method makes it possible to form computer models of complex surfaces on the basis of a framework consisting of curves absent in CAD libraries.

ETER: Elastic Tessellation for Real-Time Pixel-Accurate Rendering of Large-Scale NURBS Models

We present ETER, an elastic tessellation framework for rendering large-scale NURBS models with pixel-accurate and crack-free quality at real-time frame rates. We propose a highly parallel adaptive tessellation algorithm to achieve pixel accuracy, measured by the screen space error between the exact surface and its triangulation. To resolve a bottleneck in NURBS rendering, we present a novel evaluation method based on uniform sampling grids and accelerated by GPU Tensor Cores. Compared to evaluation based on hardware tessellation, our method has achieved a significant speedup of 2.9 to 16.2 times depending on the degrees of the patches. We develop an efficient crack-filling algorithm based on conservative rasterization and visibility buffer to fill the tessellation-induced cracks while greatly reducing the jagged effect introduced by conservative rasterization. We integrate all our novel algorithms, implemented in CUDA, into a GPU NURBS rendering pipeline based on Mesh Shaders and hybrid software/hardware rasterization. Our performance data on a commodity GPU show that the rendering pipeline based on ETER is capable of rendering up to 3.7 million patches (0.25 billion tessellated triangles) in real-time (30FPS). With its advantages in performance, scalability, and visual quality in rendering large-scale NURBS models, a real-time tessellation solution based on ETER can be a powerful alternative or even a potential replacement for the existing pre-tessellation solution in CAD systems.

Design and Development of Interior Design CAD System Based on Class Definition

Design and Development of Interior Design CAD System Based on Class Definition

Research on the Construction of Music Animation CAD System Based on Music Form and Emotion Recognition

Research on the Construction of Music Animation CAD System Based on Music Form and Emotion Recognition

Survey of Denoising, Segmentation and Classification of Pancreatic Cancer Imaging

Pancreatic cancer is one of the most serious problems that has taken many lives worldwide. The diagnostic procedure using the traditional approaches was manual by visually analyzing the large volumes of the dataset, making it time-consuming and prone to subjective errors. Hence the need for the computer-aided diagnosis system (CADs) emerged that comprises the machine and deep learning approaches for denoising, segmentation and classification of pancreatic cancer. There are different modalities used for the diagnosis of pancreatic cancer, such as Positron Emission Tomography/Computed Tomography (PET/CT), Magnetic Resonance Imaging (MRI), Multiparametric-MRI (Mp-MRI), Radiomics and Radio-genomics. Although these modalities gave remarkable results in diagnosis on the basis of different criteria. CT is the most commonly used modality that produces detailed and fine contrast images of internal organs of the body. However, it may also contain a certain amount of gaussian and rician noise that is necessary to be preprocessed before segmentation of the required region of interest (ROI) from the images and classification of cancer. This paper analyzes different methodologies used for the complete diagnosis of pancreatic cancer, including the denoising, segmentation and classification, along with the challenges and future scope for the diagnosis of pancreatic cancer. Various filters are used for denoising and image smoothening and filters as gaussian scale mixture process, non-local means, median filter, adaptive filter and average filter have been used more for better results. In terms of segmentation, atlas based region-growing method proved to give better results as compared to the state of the art whereas, for the classification, deep learning approaches outperformed other methodologies to classify the images as cancerous and non- cancerous. These methodologies have proved that CAD systems have become a better solution to the ongoing research proposals for the detection of pancreatic cancer worldwide.

C2FTFNet: Coarse-to-fine transformer network for joint optic disc and cup segmentation

Glaucoma is a leading cause of worldwide blindness and visual impairment, making early screening and diagnosis is crucial to prevent vision loss. Cup-to-Disk Ratio (CDR) evaluation serves as a widely applied approach for effective glaucoma screening. At present, deep learning methods have exhibited outstanding performance in optic disk (OD) and optic cup (OC) segmentation and maturely deployed in CAD system. However, owning to the complexity of clinical data, these techniques could be constrained. Therefore, an original Coarse-to-Fine Transformer Network (C2FTFNet) is designed to segment OD and OC jointly , which is composed of two stages. In the coarse stage, to eliminate the effects of irrelevant organization on the segmented OC and OD regions, we employ U-Net and Circular Hough Transform (CHT) to segment the Region of Interest (ROI) of OD. Meanwhile, a TransUnet3+ model is designed in the fine segmentation stage to extract the OC and OD regions more accurately from ROI. In this model, to alleviate the limitation of the receptive field caused by traditional convolutional methods, a Transformer module is introduced into the backbone to capture long-distance dependent features for retaining more global information. Then, a Multi-Scale Dense Skip Connection (MSDC) module is proposed to fuse the low-level and high-level features from different layers for reducing the semantic gap among different level features. Comprehensive experiments conducted on DRIONS-DB, Drishti-GS, and REFUGE datasets validate the superior effectiveness of the proposed C2FTFNet compared to existing state-of-the-art approaches.

Machine-readable documents in building information modeling standards

Introduction. Since 2021, adoption of building information modeling technologies has become mandatory in constructing objects using information modeling technologies. Processes of constructing buildings and structures have remained unchanged over the past two years. The time-saving effect of digitalization in construction has not been achieved, and the need to develop information models of capital construction objects resulted in additional costs for manual identification of data in the array of regulatory documents and in ignoring most of the existing requirements. Standard technical documents, even if they are written for automation purposes, do not provide for possible automated data isolation when working with them.Aim: to develop methods for translating standard technical documents into a machine-readable format based on marking up documents with codes of a building information classifier.Materials and methods. The methodology involved analyzing the schemes of documents posted on the website of the Ministry of Construction, which have been issued after the requirements on mandatory use of the classification systems in the development of building information models were included into the Town Planning Code of the Russian Federation. The analysis provided for possible unambiguous identification of data between various XML schemes of documents and the availability of a building information classifier for interfacing with the graphic part of the design documentation made in the format of the information model of the capital construction object.Results. The author proposes rules for constructing text and tabular documents with the inclusion of codes of the building information classifier for the development of XML-schemes. Allocation and markup of the tabular part serve for separating the structured and unstructured parts of the document. The marked tabular part can be exported to CAD systems and can serve a source of software settings. Tables, information about the structured coded tables, and a section of terms and definitions that are used to form the machine-readable data are subject to coding.Conclusion. Machine-readable documents can be generated both at the level of national standard technical documents and at the level of company standards reflecting the current configuration of the software adopted for capital construction projects. A set of structured tables exported from the company standards and national standard technical documents can be adopted to replace the established approach to the formation of requirements for information exchange and project implementation plans using information modeling technologies.

ECG Arrhythmia Classification Using Recurrence Plot and ResNet-18

Cardiovascular diseases are the leading cause of death worldwide, claiming approximately
 17.9 million lives each year. In this study, a novel CAD system to detect and classify electrocardiogram (ECG) signals is presented. Designed system employs the recurrence plot (RP) approach that transforms a ECG signal into a 2D representative colour image, finally performing their classifications via employment of Deep Learning architecture (ResNet-18). Novel system includes two steps, where the first step is the preprocessing one, which performs segmentation of the data into two-second intervals, finally forming images via the RP approach; following, in the second step, the RP images are classified by the ResNet- 18 network. The proposed method is evaluated on the MIT-BIH arrhythmia database where 5 principal types of arrhythmias that have medical relevance should be classified. Novel system can classify the before-mentioned quantity of diseases according to the AAMI Standard and appears to demonstrate good performance in terms of criteria: overall accuracy of 97.62%, precision of 95.42%, recall of 95.42%, F1-Score of 95.06%, and AUC of 95.7% that are competitive with better state-of-the-art systems. Additionally. the method demonstrated the ability in mitigating the problem of imbalanced samples.

AUTOMATED DEVICE PARTS TRANSPORTATION SYSTEM IN THE CONDITIONS OF MEDIUM-SERIES PRODUCTION

The article analyzes previous research and publications on the development and application of various types of automated transport carts used in serial production, from which a conclusion is drawn about the need to develop an automated transport cart that can be used in instrument manufacturing and which will increase the productivity of the transport system.
 After conducting the analysis, the main element of the automated transportation system was developed, which is an automated transport cart mounted on mecanum wheels, which ensure its all-directional movement, without changing the orientation in space or its change regardless of the direction of movement, with two on-board manipulators that have removable gripping devices, and an individual removable storage device. Changeable elements increase the flexibility of the automated cart, because this feature allows the cart to be adapted to a large number of various technological processes. With the help of the CAD system, a three-dimensional model of the schematic design of the automated transport cart was developed, which takes into account all its important elements, as well as a detailed model of the mecanum wheels, designed specifically for the design of the cart.
 Using the parameters of the developed automated transport cart, the kinematics of the cart were calculated and formulas for solving the forward and inverse kinematics problem were determined, as well as the algorithms of the cart operation were developed, which describe each cycle performed by the cart at each workplace. Based on formulas for solving kinematics problems, formulas and methods for leveling spatial errors that occur during movement from one point to another are defined, as well as functions for optimizing the process of moving an automated transport cart are defined, and how optimization affects performance is determined.

Component development using Topological Methods

The article aims to briefly summarize the design aids which can be used nowadays, such as topology optimization and generative design, which are common in integrated CAD systems. A case study is used to present the results and comparisons provided by the previously mentioned methods.

Логическая модель построения пошаговой контекстной помощи пользователю САПР

Automatic stepwise contextual help for CAD systems users reduces time to solve the application task since it saves time to search the prompt message in system documentation. Petri nets (PN) can be used to bind available actions of the user considering the state of application data (context). Application of the Petri net inversion method, which uses limited enumeration to construct chains of recommended actions is preferable than using the standard reachability analysis procedure based on exhaustive enumeration. However, the absence in the known implementations of an explicit separation of the axioms of inversion (knowledge) from the mechanism of their processing (inference) deprives the stepwise contextual help system of the necessary flexibility when changing the axioms to consider the assumptions associated with a particular model. Thus, the aim of this research is to provide the necessary flexibility of the contextual help system by separating the knowledge representation model from the inference engine. A colored PN is used as a model of user action scenarios. The inversion axioms are implemented in the PROLOG language. The standard inference engine of the PROLOG language is used as a tool to construct chains of recommended actions. The authors have proposed an axiomatic model of PN inversion and a method to construct a stepwise contextual help by the standard inference engine of the PROLOG language. The method differs by explicit separation of knowledge (inversion axioms) from the inference engine (stepwise recommendations). It reduces the computational costs of adapting the contextual help system when changing the inversion axioms. The proposed method allows to reduce the time spent on adapting the contextual help system, since the field of the changes is limited by the declarations of the inversion axioms. The reliability of the results is confirmed since the proposed method of contextual help is used for the CAD “Model and Archive” user of CSoft company. The results obtained allow creating contextual help services for existing applications with minimal changes to their code base.

Интеллектуализация строительно-технической экспертизы кровель как инструмент управления ее жизненным циклом

The program "Digital Economy of the Russian Federation", approved by the Government of the Russian Federation, is being actively implemented in the building construction industry, mainly at the stages of engineering surveys and architectural and construction design. Building information modeling (BIM) technologies are used by most foreign and domestic CAD system vendors. At the other stages of the building's life cycle, digitalization has not been widely distributed, despite the fact that the operation stage is the longest and the trouble-free existence of building structures at this stage is the key to the economic and social efficiency of building ownership. Flat rolled roofs in our country are the most common type of roofs and at the same time the most susceptible to defect formation structural element of a building. The standard operation period of such roofs is 10 years, despite the fact that the actual period of trouble-free operation of flat rolled roofs rarely exceeds 7 years. The assessment of the technical condition of the roofs is carried out by a construction and technical expertise, performed, as a rule, after the occurrence of leaks. Assessment of the degree of damage, as well as the prevalence of defects, is carried out by an expert visually, often without the use of measuring equipment. Due to the fact that the assessment of damage by an expert is purely subjective, it is impossible to correctly assess the development of the defect over time. The proposed technology of automation of construction and technical expertise of flat rolled roofs of a building allows timely detection of defects, assess the degree of their danger and make forecasts of their development over time. This approach allows you to make a timely decision on the need to carry out current repairs or to plan their implementation in the future. This will increase the service life of a flat rolled roof without increasing the cost of the life cycle.

Feature-based modeling for variable fractal geometry design integrated into CAD system

Fractal geometry has been widely applied in computer graphics to visually represent natural objects, which cannot be easily represented by Euclidean geometry. Other than visual representation, parametric fractal-like CAD models have been used in industry for the design and manufacture of products with self-similarity geometric features. However, contemporary CAD systems cannot construct CAD fractal models efficiently, as most CAD fractal models are still built manually by designers. The construction and modifications for such CAD fractal models are tedious and time-consuming.This paper aims to build and modify CAD fractal models more efficiently in CAD systems. A method for automatically modeling parametric fractal-like geometry objects in CAD systems is proposed. Feature-based modeling methods have been applied for realizing algorithm-based CAD fractal model generation. A new type of feature, called CAD fractal feature is proposed and implemented to bridge the gap between CAD and fractal geometry. The fractal-like CAD model is constructed iteratively with a dynamic generator for each iteration cycle. Design parameters are extracted as inputs for dynamic fractal generators, which allows users to define, parameterize, generate and edit a fractal design with variable parameters. The parameters of the fractal generator can also take different values for different model construction iterations, which makes the generated models not necessarily to be strictly fractal but can also be fractal-like. The iterative generation method (IGM) is proposed as a built-in method in a CAD fractal feature for modeling complex but self-similar geometric models in an objected-oriented approach with high efficiency and sufficient design flexibility. As a result, designers do not need advanced knowledge of fractal geometry to build and modify CAD models with self-similar features. An extruded Koch Snowflake CAD model with parametric geometric variants has been built as a case study for demonstration of the proposed modeling method.

A METHOD FOR REDUCING FUZZINESS AND ACCELERATING NEW PRODUCT MODELLING IN CAD: THE CASE OF DESIGN FOR MANUFACTURING

AbstractImprovements in product development can increase the competitiveness of firms. However, new product development in CAD systems involves difficulties and uncertainties that increase along with the pressure to develop the products. A distinct characteristic of CAD modeling for new product development is its uncertainty. This is because the information is usually approximate and incomplete during CAD modeling. Thus, the main objective of this paper is to propose a robust and flexible CAD approach to reduce uncertainty and accelerate new product modeling in the context of design for manufacturing. This methodology permits the convergence towards different product forms depending on the selected manufacturing process. Application of this approach has shown that when uncertainty is high, approving a complete CAD modeling results in a delay in product development. In contrast, CAD modeling using fuzzy models results in a gain of valuable development time because the model is completed when knowledge about manufacturing technologies, company fit and capabilities, and markets is available.

CERTIFICATE PROGRAMS OF THE AVIATION FIELD FROM THE PROGRESSTECH-UKRAINE COMPANY

The paper considers the implementation of certificate programs at the bachelor's level of higher education for students of five technical faculties of The National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute» as an element of dual education. Certificate programs include such courses as: passenger aircraft design, passenger aircraft systems, «heavy» CAD system CATIA, aircraft construction technologies, the general structure of aircraft and their units, features of the science-intensive products construction of machine-building production and conducting pre-diploma practice. The development of these courses and the conduct of classes are carried out exclusively by Progresstech-Ukraine engineers. Training takes place on the basis of the Learning Management System (LMS). Currently, 103 students are studying according certificate programs.

Оценка технологического потенциала деталей

The article describes a methodology for assessing the technological potential of parts, based on the sociophysical theory of potentials and dimensional analysis of the technological process. The technological potential of a part acts as a system characteristic of a complex technical system. The program A'PROPOS was chosen as a tool for calculating the technological potential. A hypothesis has been put forward that the technological potential of the part is associated with the complexity of the technological process of manufacturing this part. It is possible to evaluate it using dimensional analysis using CAD tools. Methods and materials. The emergence and creation of fundamentally new technologies is considered a historical process of development of the designed technical system, in this case, the DSE. The technological potential of the part is formed as the technological process is implemented. The value and structure of the potential are determined and consistent with the properties of the designed part. Based on the results of the analysis of the technological process of manufacturing a part, the construction of a sketch of a part in A'PROPOS., the technological potential is calculated using a mathematical model. The potential is calculated on the basis of the initial data of the enterprise for the object of study. Result. Based on the constructed model, the technological process is optimized. The result is a new machining plan containing the compositions and accuracy of the surfaces machined in the stages and the minimum allowance. Based on the model with variations of dimensional relationships, the dimensional structure is improved to expand the tolerance fields with guaranteed maintenance of technological parameters. Based on this, the deviation in the recommended labor intensity is calculated compared to the real one. Next, the accumulated technological potential of the part was calculated. Conclusions. The system makes it possible to iteratively perform technological calculations, as well as integration with CAD systems in the enterprise. When calculating the technological potential, instead of using the initial data of the enterprise, it is interpreted by the adequacy of the model.

Novel computer aided diagnostic system using hybrid neural network for early detection of pancreatic cancer

One of the most dangerous tumours in the world, pancreatic cancer (PC), has an unimpressive five-year survival rate of about 5%. An early PC identification is crucial for raising patient survival rates. Diagnosis of PC requires computed tomography (CT), magnetic resonance imaging (MRI) with magnetic resonance cholangiopancreatography (MRCP), or biopsy. The proposed CAD design approach includes image preprocessing, segmentation, feature extraction, and classification phases. Preprocessing is done by using Colour conversion and an isotropic diffusion filter approaches. After that, proposed Fuzzy K-NN Equality algorithm used in segmentation procedures. Deep Learning with feature extraction is used as a classification tool. Tumour cells are classified using the features collected from the pancreatic sample. Train values and testing datasets are part of the image classification criterion. For the purpose of detecting pancreatic cancer, a hybrid Deep Convolutional Neural Network with Deep Belief Network (DCNN_DBN) algorithm is used. According to the experimental findings, the current CAD system offers massive prospects as well as safety in the automated diagnosis of both benign as well as malignant cancers and produces the accuracy of 99.6%. Using this classifier, computing complexity is massively diminished. The suggested technique could be enhanced to detect more pancreatic cancer cell abnormalities.

Stress-based evolutionary topology optimization via XIGA with explicit geometric boundaries

This paper presents a novel approach to stress-based topology optimization that employs NURBS representations of explicit geometric boundaries to address stress minimization and stress-constrained problems. The proposed methodology is compatible with CAD systems and utilizes Extended IsoGeometric Analysis (XIGA) to ensure an accurate representation of stress field in the evolving structure. A p-norm aggregation scheme is used to measure global stress levels, and the aggregated stress constraint is augmented to the objective (compliance) via a Lagrange multiplier in stress-constrained problems. The proposed approach introduces a novel and efficient Lagrange multiplier trail strategy aimed at reducing computational costs. Additionally, a normalization scheme and a partial differential equation filter are presented to stabilize the highly nonlinear stress-based optimization. Validation studies demonstrate the effectiveness and characteristics of the proposed approach. Moreover, control points of the structural design can be directly edited to further improve strength performance. Comparative studies show clear advantages of the proposed methodology in terms of computational efficiency compared to other Finite element analysis (FEA)-based optimization methods. Overall, this paper presents a practical and novel approach that addresses the limitations of existing FEA-based optimization methods in terms of accuracy, flexibility, and degree of freedom (DOF) cost, and makes a significant contribution to the field of stress-based topology optimization.

Making Design Tools Like a Weaver: Four Rules

What would happen if we designed CAD systems like a weaver designs cloth? Drawing from our ongoing collaborations with weavers, we suggest four rules to bring these qualities to your own practice: follow the materials, privilege the present and personal, form kinships with the past, and design systems of notations.