Title Block Research Articles

ПОДХОД К ВЕКТОРИЗАЦИИ ЧЕРТЕЖЕЙ КОНСТРУКТОРСКОЙ ДОКУМЕНТАЦИИ НА БУМАЖНОМ НОСИТЕЛЕ

The work proposes a solution to the problem of vectorization and machine interpretation of drawings of design documentation on paper, which provides the ability to automate the transfer of images of products, parts and assembly units into CAD systems. A number of neural network architectures have been proposed for detecting and recognizing the main elements of a drawing (frame, title block, specification, views, projections and sections), inscriptions, dimension and extension lines, as well as primitives that directly describe the product. For hierarchical and interconnected vectorization, a mechanism for semantic segmentation of drawings based on a graph neural network is proposed. The results of the implementation of the main stages of solving the problem of vectorization of design drawings are presented.

Intelligent Extraction of Multi-style and Multi-template Title Block Information Based on Fuzzy Matching

ABSTRACT Title blocks are crucial primary data on drawings necessary for the operation of modern manufacturing enterprises. However, their uniform export poses a challenge due to the heterogeneity across multiple sources and the variety of export templates. Therefore, this paper proposes an intelligent extraction method for title block information (TBI) based on fuzzy matching. This method evaluates the geometrical composition of the title block, the logical relationship between information cells, and the diversification of the title block. It establishes a weighted intersection point matrix for the title block as the topological structure model. The fuzzy matching, based on the intersection matrix points, disregards the variations in the size and position of the title block and focuses only on the style that impacts the extraction of information. The matched title blocks are categorized, and the base table of each type determines the information distribution of the title block. A hash table is then created between the description cell and the value cell of information to accumulate the TBI. The method is integrated into the AutoCAD software and presented with an interactive program interface. Finally, an example is presented to further demonstrate the stability, reliability, and efficiency of the method and the system.

An Approach to Engineering Drawing Organization: Title Block Detection and Processing

During the last 20 years the world has been meeting digitalization challenges in many areas of life and business. Companies convert their business processes to digital form as much as possible, what allows reducing costs and increasing profits. The paper considers a case of the company aimed at manufacturing and servicing spare parts for mining equipment. The company has collected a large amount of engineering drawings in a paper form that need to be organized in a digital form to simplify and support quick access to these documents. We propose an approach to engineering drawing organization based on modern artificial intelligence technologies for detection of main engineering drawing elements as well as extracting metadata from them. Based on the metadata we propose organizing engineering drawings into a structured digital collection with a possibility of quick access to them. All metadata in drawings are usually located in the title block. We show how we detect the title block as well as process it and recognize needed text-based information. The open-source Google Tesseract framework is used for text recognition in English, Finnish, Spanish, and Portuguese languages. For Cyrillic text recognition our own neural network-based model has been developed and trained on Russian GOST engineering drawings. We developed a drawing organization service and evaluated it based on the company engineering drawings database. The evaluation shows a good accuracy for documents that have a good quality (about 74% for title block detection as well as metadata identification).

Investigation of the applicability of natural language processing methods to problems of searching and matching of machinery drawing images

In this work it is shown that the application of the technique of local feature descriptors in its pure form to the task of searching and matching of drawings is ineffective. It is revealed that this is mainly due to the presence in the drawings of a large number of identical elements (frames, a title block, extension lines, font elements, etc.). It is proposed that this problem should be solved using a tf-idf (term frequency-inverse document frequency) method, which is widely known in natural language processing. In the study, instead of the word vectors used in the original tf-idf technique, descriptors of image feature points calculated using the ORB and BRISK algorithms were used. The study has led to the following conclusions: 1) the proposed approach offers high efficiency in finding a copy of the image-query in the database. Thus, copies of all images presented for search and having their full analogs in the database are revealed. 2) The identification rate of modified image-queries varies, depending on the algorithm used for finding keypoints and descriptors. So, the maximum percentage of identified modified analogs is 60% when using ORB and 80% when using BRISK - out of all image analogs in the database. 3) The proposed approach shows a limited efficiency in finding images that can be attributed to the same class as the image queries (for example, a drawing of an excavator, a bulldozer, or a truck crane). Here, the maximum proportion of false identification has reached 60%.

AUTOMATION OF DATA PROCESSING IN THE UNIFIED SYSTEM OF CADASTRAL REGISTRATION OF REAL ESTATE

On the basis of the analysis of world achievements, the state of the cadastre and real estate, recommendations on the further development of the cadastre system in Ukraine are given. For the first time, a unified real estate cadastre registration System was proposed, which records the establishment and termination of immovable property rights, their restrictions and encumbrances, and contains the data necessary to fulfill the cadastre tasks in accordance with the requirements of the current legislation. The scientific bases of cadastral real estate registration have been worked out, the purpose, principles of creation, composition of information, procedure of keeping, requirements and means of realization of cadastral registration of real estate have been determined. The cadastral classification of real estate was developed, including the classification of lands, structures and other land improvements by quantitative and qualitative characteristics, rights, their encumbrances and restrictions, as well as by value. In order to automate the processing of geospatial information on real estate, an appropriate system of codification of cadastral information was developed. The cadastral classification of real estate contains: identification block, title block and codifier of real estate groups. The identification block includes: the characteristics by which the cadastral classification of the real estate is made, the block of names - the full names of the groups, and the codifier of the real estate groups - the list of cadastral codes.

Unsupervised Speaker Identification in TV Broadcast Based on Written Names

Identifying speakers in TV broadcast in an unsupervised way (i.e., without biometric models) is a solution for avoiding costly annotations. Existing methods usually use pronounced names, as a source of names, for identifying speech clusters provided by a diarization step but this source is too imprecise for having sufficient confidence. To overcome this issue, another source of names can be used: the names written in a title block in the image track. We first compared these two sources of names on their abilities to provide the name of the speakers in TV broadcast. This study shows that it is more interesting to use written names for their high precision for identifying the current speaker. We also propose two approaches for finding speaker identity based only on names written in the image track. With the late naming approach, we propose different propagations of written names onto clusters. Our second proposition, Early naming, modifies the speaker diarization module (agglomerative clustering) by adding constraints preventing two clusters with different associated written names to be merged together. These methods were tested on the REPERE corpus phase 1, containing 3 hours of annotated videos. Our best late naming system reaches an F-measure of 73.1%. early naming improves over this result both in terms of identification error rate and of stability of the clustering stopping criterion. By comparison, a mono-modal, supervised speaker identification system with 535 speaker models trained on matching development data and additional TV and radio data only provided a 57.2% F-measure.

Synthesis and Properties of Partially Fluorinated Poly(arylene ether) Block Copolymers Containing Ammonium Groups as Anion Conductive Membranes

Abstract Synthesis and properties of aromatic block copolymers containing fluorinated phenylene and biphenylene groups and ammonium-substituted fluorene groups are reported. High-molecular-weight poly(arylene ether) block copolymers were prepared from the corresponding telechelic oligomers and were chloromethylated. Quaternization reaction of the chloromethylated precursors with trimethylamine provided the title ammonium-substituted block copolymers (QPE-bl-4). The QPE-bl-4 membrane with the highest ion-exchange capacity (IEC = 1.3 mequiv g−1) showed high hydroxide ion conductivity (45 mS cm−1) at 80 °C due to its phase-separated morphology with interconnected ion-transporting pathway. The accelerated stability test in aqueous KOH solution containing hydrazine revealed that the ammonium groups decomposed to certain extent while the polymer main chains were rather robust to maintain the self-supporting membranes.

Proton conductive aromatic block copolymers from a new bistriazole monomer

We have designed and synthesized a new bistriazole compound, 3,3′-(1,3-phenylene)bis[4-phenyl-5-(4-fluorophenyl)-4H-1,2,4-triazole], as a comonomer for a series of sulfonated block poly(arylene ether) copolymers. The bistriazole was successfully synthesized from isophthalic dihydrazide and 4-fluorobenzoyl chloride via bisoxadiazole. The bistriazole monomer was polymerized with 4,4′-biphenol or 4,4′-dihydroxydiphenyl ether to obtain hydroxyl-terminated hydrophobic oligomers, which were copolymerized with sulfonated oligomers to obtain the title block copolymers. The block copolymers were high-molecular-weight (Mw = 91–500 kDa) and provided tough and bendable membranes by solution casting. Because of the sequenced block copolymer structures, the membranes exhibited hydrophilic/hydrophobic phase-separated morphology as confirmed by scanning transmission electron microscopic (STEM) images. The membranes showed proton conductivity under humidified conditions; the highest proton conductivity was 6 × 10−2 S cm−1 at 95% relative humidity (RH) and 80 °C. The membranes were mechanically stable with high storage moduli (ca. 109 Pa) and loss moduli (ca. 108 Pa). These mechanical properties were independent on the ion exchange capacity (IEC) of the membranes. The triazole groups were effective in improving the mechanical and oxidative stability of the sulfonated poly(arylene ether) block copolymer membranes.

A Study on Extraction Method of Non Geometry Information in Engineering Drawing Title Block

When designer designing a new engineering drawing, they will refer to the previous valid design document that same or nearly match with their new design specification. Previous design have been reviewed, analyzed and proven to be successful. By using the previous design, it likely saves significant resources and manpower. In real situations, engineering drawing is usually in large quantities and not in order. This paper describes a research and development of an extraction technique in the field of engineering drawing. Non-geometry information that will be emphasis in this research is information that available in the title block.

The ‘art which conceals’: a cottage industry and the invention of Cushing's Island

The ‘art which conceals’: a cottage industry and the invention of Cushing's Island

SYNTHESIS AND CHARACTERIZATION OF WELL-DEFINED BLOCK COPOLYMERS CONTAINING PENDANT, SELF-COMPLEMENTARY QUADRUPLE HYDROGEN BONDING SITES

The title block copolymer (defined as PSUEA) containing pendant, self-complementary quadruple hydrogen bonding sites has been prepared successfully by three steps. First, poly(styrene-b-2-hydroxyethyl acrylate) (defined as PSHEA) was prepared by living radical polymerizing 2-hydroxyethyl acrylate (HEA) initiated by polystyrene (PSt) macro- initiator, which was prepared via nitroxide-mediated polymerization (NMP) technique. After treated by excessive 3-isocyanatomethyl-3,5,5-trimethylcyclohexyl isocyanate (IPDI), PSHEA was transferred into an intermediate polymer (defined as PSIEA) with isocyanate groups in the second block. Finally, PSIEA was reacted with excessive 2-amino-4- hydroxy-6-methyl-pyrimidone (MIS) to obtain PSUEA bearing pendant quadruple hydrogen bonding 2-ureido-4(1H)- pyrimidone (Upy) units. Based on 1 H-NMR, FT-IR and GPC analysis, all the polymers with well controlled structures were obtained. Preliminary thermal analysis of the block polymers indicated that the introduction of Upy units significantly increased the glass transition temperature. The possibility to form quadruple hydrogen bonding should make PSUEA suitable as new building component for supramolecular assembling.

Synthesis and self‐assembly of highly incompatible polybutadiene–poly(hexafluoropropylene oxide) diblock copolymers

AbstractA versatile coupling reaction for the preparation of polybutadiene–poly‐(hexafluoropropylene oxide) (BF) diblock copolymers is described. Six diblock copolymers with different block lengths were characterized by nuclear magnetic resonance spectroscopy and size exclusion chromatography; all six had total molecular weights below 15,000. Microphase separation of the block copolymers in the bulk state was established by small‐angle X‐ray scattering (SAXS) and differential scanning calorimetry. SAXS data suggest that the diblocks are characterized by an unusually large Flory‐Huggins interaction parameter, χ, on the order of 10. However, extraction of χ from the order–disorder transition gave large (order 1) but significantly different values, thereby suggesting that these copolymers are too small and too strongly interacting to be described by block copolymer mean‐field theory. Dynamic light scattering was used to analyze dilute solutions of the title block copolymers in four selective organic solvents; the sizes of the micelles formed were solvent dependent. The micellar aggregates were large and nonspherical, and this is also attributed to the high degree of incompatibility between the two immiscible blocks. © 2005 Wiley Periodicals, Inc. J Polym Sci Part B: Polym Phys 43: 3685–3694, 2005

The synthesis of an isobutylene-?-methylstyrene block copolymer with olefinic head-group: (CH3)2C=CHCH2-PIB-b-P?MeSt

The title head-functionalized block copolymer was synthesized by first preparing a polyisobutylene carrying a (CH3)2C=CH2-head-group and -Cl end-group, and subsequently starting the block copolymerization of α-methylstyrene from the -Cl terminus.

Well Symbols and Title Blocks on Geological Maps: GEOLOGICAL NOTES

Geological maps should use symbols which accurately represent the true conditions to which references are made. The proper title block on a map will aid in a rapid analysis.