53 results about "Steel design" patented technology

The invention discloses a BIM technology fused fabricated steel structure assembly optimization method and system, and relates to the technical field of data processing.The method comprises the steps that fabricated steel structure design information of a target assembly project is obtained, and a fabricated steel structure digital twinborn model is constructed; collecting a multi-angle image of a to-be-assembled node, extracting surface defects and connection quality features, and determining a node quality factor; and carrying out assemblability authentication based on the quality factor, if the authentication is passed, carrying out analogue simulation through an assembly type steel structure digital twinborn model, and optimizing an assembly scheme in combination with real-time environmental data. The technical problems that in traditional steel structure assembling in the prior art, node quality evaluation is not accurate, an assembling scheme lacks intelligent optimization and dynamic adjustment, and the assembling precision and the construction efficiency are affected are solved, the node quality is accurately evaluated by fusing the BIM technology, the assembling scheme is optimized in real time, and the construction efficiency is improved. The steel structure assembling precision and the construction efficiency are improved, and the construction risk is reduced.

The invention discloses a digital modeling steel structure multi-dimensional collaborative optimization design method and system, belongs to the technical field of steel structure design, and aims to solve the problems that multi-dimensional comprehensive consideration and automatic optimization tools are lacked, and complex multi-objective optimization requirements are difficult to quickly respond. Comprising the steps of establishing a full-parameterized digital model containing construction process parameters and environmental protection indexes, constructing a multi-objective evaluation system of structural safety, economical efficiency, construction feasibility and environmental influence, performing automatic optimization by adopting an improved multi-objective evolutionary algorithm, selecting 10 groups of candidate schemes, generating a visual interface, supporting human-computer interaction decision, and generating an optimization report. According to the method, multi-dimensional collaborative optimization is realized by constructing a multi-target evaluation system of structural safety, economy, construction feasibility and environmental influence, construction process parameters and environmental protection indexes are integrated through the digital modeling unit, it is ensured that factors of all parties are comprehensively considered in design decision, and the design efficiency is remarkably improved.

The invention discloses a machine learning guidance laser forming ultrahigh strength and toughness steel design method based on fusion of physical and chemical characteristics, which combines the physical and chemical characteristics with Shapley additive interpretation and analysis, and overcomes the limitation that a traditional pure data driving model lacks theoretical support. The quantitative analysis of the influence between the input characteristics and the output performance is realized, the internal association between the physical and chemical characteristics and the material strengthening and toughening theoretical mechanism is disclosed, the contribution degree and the interaction effect of each alloy element and the heat treatment process parameters are determined, the theoretical basis of variable screening is provided for multi-objective optimization, and the optimization efficiency is improved. Therefore, the efficiency of obtaining the non-dominated solution set is remarkably improved. According to the method, the physical and chemical characteristic combination can be conveniently and rapidly determined, the relation between the input characteristic and the output performance can be quantified, and optimal design of the laser forming ultrahigh strength and toughness steel alloy components and the heat treatment process is achieved.

The invention provides a fabricated steel structure beam-column connection performance monitoring method based on ultrasound, and relates to the technical field of performance monitoring, and the method comprises the steps: restoring steel structure design information of a target building through BIM technology modeling, extracting connection node parameters, and classifying nodes by using a node importance evaluation model. And on the basis of a stress conduction fitting result, M beam-column connection monitoring trees are constructed. A mechanical monitoring early warning device and a performance fault recognizer are pre-constructed, the performance of the top connection node is monitored in real time, and a fault node is positioned. According to the process, the monitoring efficiency and the structural safety are improved. According to the method and the device, the technical problems that difference exists between design information and actual construction, the efficiency is reduced and the structural safety is further influenced due to the fact that effective information integration and modeling means are lacked and different nodes cannot be monitored differentially in the prior art can be solved. The accuracy, the real-time performance and the efficiency of performance monitoring of the beam-column connection node in the fabricated steel structure building are improved.

The invention discloses a steel structure system based on intelligent optimization and real-time monitoring, and the system comprises a multi-objective optimization module which carries out multi-objective optimization design based on a practical application scene of a structure, and a BIM model integration module which integrates geometric and mechanical characteristics and state data. And the real-time monitoring module is used for acquiring state parameters such as stress, temperature and humidity of key nodes of the steel structure in real time. The multi-target optimization module generates a global optimal design scheme by using finite element analysis and a multi-target optimization algorithm, the BIM model serves as a core platform of design, construction and operation and maintenance, and the real-time monitoring module realizes dynamic feedback of a structure state through a sensor network. The safety and accuracy of steel structure design are improved, the service life of the structure is prolonged, the maintenance cost is reduced, and the method is suitable for bridges, buildings and other complex steel structure projects.

The invention relates to a medium-high carbon steel reverse component design method and system based on a conditional generative network. The method comprises the following steps: converting a steel design index into a hardenability curve; inputting the hardenability curve and a preset random latent code into a trained and checked generator; the generator reversely generates steel components and grain size based on the hardenability curve; and the generated grain size and components are adjusted based on the component adjusting module so as to meet the smelting requirement. By adopting the method, a hardenability GAN algorithm can be taken as a core, database input and real hardenability curve input are increased, and a CGAN-based hardenability model is constructed. The model can learn a hardenability data probability distribution dependent on the alloy composition and grain size, and samples extracted from the multi-dimensional distribution will represent the alloy composition and grain size with predictable attributes.

The invention relates to the technical field of building information models and intelligent design, and provides a bridge steel structure collaborative design method and system based on the BIM technology, and the method comprises the steps: obtaining a plurality of bridge steel structure BIM models from a BIM database, and design parameter vectors, structure topological graphs and collaborative design data vectors thereof; constructing a structural feature extraction model by training a BIM structure encoder model, calculating the similarity between the models, and retrieving a similar model; establishing a BIM data fusion model, and training by combining the design parameter vector of the target model and the collaborative design data vector of the similar model to obtain a collaborative design prediction model; and searching a similar model for a to-be-collaborative design model, and generating collaborative design data through a prediction model based on design parameters of the to-be-collaborative design model and collaborative data of the similar model. According to the method, intelligent collaborative optimization of bridge steel structure design can be realized, the design efficiency and accuracy are improved, and manual intervention and repeated work are reduced.

The invention belongs to the technical field of bridge steel structure design, and discloses a method and system for determining the arrangement positions of multiple longitudinal stiffening ribs of a steel bridge web, and the method comprises the steps that constraint of a steel top plate, a steel bottom plate and two transverse stiffening ribs on a mother plate is simply supported; dividing the stiffening plate into four-side simply supported sub-grids according to the longitudinal stiffening ribs, calculating bending and shearing buckling coefficients and obtaining critical buckling stress; a bending and buckling coefficient is expressed as a function of a clear distance between longitudinal stiffening ribs based on geometric similarity; and adopting a bending and shearing interaction buckling criterion, recursively solving the position of each longitudinal stiffening rib from a pressed edge, and carrying out constraint screening according to monotonically increasing distance, arrangement not crossing a neutral axis and the like. According to the method, reasonable arrangement can be directly output, and design consistency and efficiency are improved.

An improved multi-target regression algorithm based on target specific features is combined with a non-dominated sorting genetic algorithm to construct a double-layer structure multi-target algorithm, so that the problems of data distortion possibly caused by data enhancement, poor feature engineering generalization ability, negative migration caused by large inter-domain difference and the like are avoided, and the method is suitable for large-scale popularization and application. By capturing the correlation among a plurality of output targets, a high-precision model for a high-dimensional small data set is constructed, and the machine learning assisted hot-rolled ultrahigh-toughness steel component and process design with low data set cost is realized.

The present invention discloses an assembly optimization method and system for prefabricated steel structures integrating BIM technology, which relates to the technical field of data processing. The method includes: obtaining the design information of the prefabricated steel structure of the target assembly project and constructing a digital twin model of the prefabricated steel structure; collecting multi-angle images of the nodes to be assembled, extracting surface defect and connection quality features, and determining the node quality factor; performing an assemblability certification based on the quality factor. If the certification is passed, then a simulation is carried out through the digital twin model of the prefabricated steel structure, and the assembly plan is optimized in combination with real-time environmental data. The present invention solves the technical problems in the prior art that the node quality assessment in traditional steel structure assembly is inaccurate, the assembly plan lacks intelligent optimization and dynamic adjustment, which affects the assembly accuracy and construction efficiency, and achieves the technical effect of accurately assessing the node quality and optimizing the assembly plan in real time by integrating BIM technology, improving the assembly accuracy and construction efficiency of the steel structure, and reducing the construction risk.

The invention discloses a construction method, device and equipment of an assembly type steel structure building and a storage medium, and relates to the technical field of assembly type buildings. The method comprises the steps that in response to a construction instruction of a target building, construction information parameters of the target building are determined, and a reference steel structure design model matched with the target building is determined from a pre-stored structure design model library according to the construction information parameters; determining a target steel structure design model matched with the target building based on the reference steel structure design model; generating a building information model matched with the target building according to the target steel structure design model, generating component manufacturing data based on the building information model and the building information parameters, and converting the component manufacturing data into processing control data; and processing the structural material based on the processing control data to obtain prefabricated parts, and assembling the prefabricated parts on the construction site to obtain a target building. According to the scheme, the design efficiency, the material utilization rate and the construction precision can be improved.

The utility model provides a stainless steel integral ventilation pipeline air shower structure, which relates to the technical field of air showers and comprises an air shower, a top bin, an air supply bin and an air shower channel. Air supply assemblies for blowing air into the air shower channel are arranged in the two air supply bins; each air supply assembly comprises a fan box, a main air supply pipe, a plurality of groups of air outlets and a telescopic air pipe; according to the design, stainless steel design is adopted as a whole, transportation is convenient, deformation is not prone to happening, the service life is long, the heat dissipation effect is good, the heat dissipation effect is good, the heat dissipation effect is good, and the heat dissipation effect is good. The whole air shower is provided with the face recognition access control machine, the electric door and the infrared sensor, the electric door can be opened through face recognition and automatically closed in cooperation with human body sensing, manual operation of workers is omitted, intelligence is high, in addition, a plurality of transverse air blowing and vertical air blowing are formed in the air shower channel, and the air shower is more intelligent. And dust on the body of a worker can be conveniently blown away.

The invention belongs to the technical field of industrial building digital design, and particularly discloses a shipyard steel structure component cross-software model reconstruction method, which comprises the following steps that a shipyard steel structure design stage software project file is collected, and the project file comprises all modeling components of a steel structure specialty; carrying out modeling on the modeling component by adopting a component nesting mode; performing parameter data sorting on the modeled part to obtain attribute data; processing positioning data of the component in the item; forming a shipyard steel structure member data table according to the acquired attribute data and positioning data; importing data in the shipyard steel structural member data table into construction deepening modeling software, and re-analyzing the data into parameter names and parameter values; performing model reconstruction according to the analyzed parameter names and parameter values; the component is disassembled to the basic granularity, and the transmission data is stored in a unified parameter table form, so that the problem of incompatibility of cross-software data formats is effectively solved, and the data standardization and compatibility are improved.

The utility model discloses a reversing valve and a pressure test device thereof, comprising a valve casing assembly, the top of the valve casing assembly is provided with a valve core assembly, the valve casing assembly comprises a valve casing, the outer wall of one side of the top of the valve casing is provided with a mounting hole, the valve core assembly is inserted in the mounting hole, the valve core assembly comprises a limit seat, and the limit seat is arranged outside the valve casing. A handle is slidably inserted into the limiting seat, and a fixing rod is inserted into the outer wall of one side of the top of the handle and mounted in the mounting hole through a bearing. The square steel design is adopted for the valve shell, material consumption can be reduced to the maximum extent on the premise that strength and performance are guaranteed, meanwhile, stability under high temperature and high pressure is guaranteed through the special steel design, the handle can be limited through the limiting lock, equipment damage and maintenance cost caused by misoperation are reduced, and in the long-term using process, the service life of the valve shell is prolonged. The problem that the handle moves due to the fact that the valve element is impacted for a long time can be prevented, unnecessary maintenance and replacement can be effectively avoided, and a large amount of cost is saved for a user.

The invention relates to a steel structure damage intelligent prediction method based on LLM-FEM fusion, and relates to the technical field of civil engineering structure health monitoring and artificial intelligence crossing. The invention aims to improve the intelligence and interpretability level of civil engineering structure health monitoring. A steel frame structure model is established through finite element analysis software (ANSYS), various health and damage states are simulated, and response index data including displacement, stress, modal frequency and the like are obtained; secondly, structuring the data into a natural language input format, and constructing a fine tuning instruction set related to an impairment identification task; performing efficient parameter fine adjustment on the large language model (LLaMA-38B) to enable the large language model to have structural damage identification and interpretation capabilities; and finally, any structural response data can be input, and structural state prediction, damage type judgment and semantic explanation output are realized. According to the method, physical simulation data and language reasoning ability are fused, generalization, interpretation and practicability are achieved, and the method is suitable for the whole process of steel structure design, monitoring and operation and maintenance management.

The present invention relates to a high-preload torsion shear type high-strength single-sided self-tightening bolt and a method for using the bolt. The structure comprises a bolt body, a threaded sleeve is sleeved on the bolt rod of the bolt body, the two ends of the bolt rod are respectively a bolt head and a plum blossom head, a nut is installed on the bolt rod close to the plum blossom head through a thread, a first sleeve, a second sleeve, a third sleeve and a shear washer are sleeved on the bolt rod in sequence from the bolt head to the plum blossom head, an annular circular arc groove is provided on the inner circumferential wall of the first sleeve; the threaded sleeve is located in the third sleeve, when the plum blossom head of the bolt body is subjected to an axial force, the annular circular arc groove is deformed outwardly, the threaded sleeve may be positionally offset relative to the third sleeve, and at the same time, the threaded sleeve and the third sleeve exert pressure on the shear washer, and the third sleeve enters the inner cavity of the shear washer; the present invention can simply and quickly realize single-sided tightening operation, and the preload force and bearing capacity can meet the requirements of connection tightening in the steel structure design standard.

The invention relates to a parametric modeling method for a plane truss of an end expansion support node, and is suitable for the field of steel structure design. The method comprises the following steps: generating a corresponding overall line unit model based on a structure type of a plane truss in combination with overall size parameters; on the basis of component size parameters of the side columns and the chord members and corresponding line segments of the overall line unit model, section feature points are determined, and then a section profile curve is generated; based on the section profile curves of the side columns and the chord members, generating shell unit models of the side columns and the chord members in combination with the corresponding line segments of the integral line unit model; determining contour feature points based on the component size parameters and the node size parameters of the support and the overall line unit model line segments corresponding to the support, and further generating a contour line of the support; based on the contour line of the support, a support web model and a support flange model are generated, and a support model is obtained; and obtaining an integral shell unit model of the plane truss based on the shell unit model of the side columns and the chord members and the supporting model.

This utility model discloses a precision mold with a built-in venting insert, including an upper mold base, a lower mold base, a cavity located at the bottom of the upper mold base, and a core located at the top of the lower mold base. A split venting insert is embedded in the melt end region of the core. The venting insert is composed of at least two layers of permeable steel stacked and fixed along the thickness direction. The pore diameter of the upper layer of permeable steel is smaller than that of the lower layer. The venting insert has an internal venting channel penetrating through the multiple layers of permeable steel, with one end extending to the molding surface of the venting insert and the other end connected to a venting interface on the mold sidewall. The multi-layer permeable steel design, combined with a spiral guide groove, uses small pores in the upper layer to prevent melt overflow and large pores in the lower layer to accelerate venting. Combined with the spiral guide for efficient venting, this significantly reduces defects such as bubbles and depressions in the plastic part, and significantly improves molding quality.

The utility model discloses a reinforcing steel structure at the joint of steel structures, which belongs to the technical field of steel structures and is characterized by comprising an inserting block, a connecting structure is fixedly connected to the outer side of the inserting block, an auxiliary structure is bolted to the outer side of the connecting structure, and a fastening structure is movably connected to the outer side of the connecting structure. The bottom of the mounting block is in bolting connection with the top of the supporting block, the top of the supporting block is in bolting connection with the bottom of the stabilizing block, the inner side of the stabilizing block is in bolting connection with the outer side of the rotating plate, the outer side of the rotating plate is in bolting connection with the inner side of the mounting piece, and the bottom of the mounting piece is in bolting connection with the top of the mounting block. When an existing steel structure is designed, the safety coefficient possibly reserved is insufficient, so that the load exceeds the designed bearing capacity in the actual use process, and after the structure is used for a long time, the following problems that the structure is aged, corroded, reduced in bearing capacity and the like possibly occur.

The utility model discloses a rigidity variable ballastless track plate temporary limiting monitoring device which comprises a base fixed on a roadbed, an inclined strut is arranged in the middle of the base, a stabilizing plate and a transverse baffle are arranged below the inclined strut, and the stabilizing plate and the transverse baffle are respectively fixed with the base. The transverse baffle is inserted into the stabilizing plate and does not make contact with the stabilizing plate, a transverse hydraulic device making transverse contact with the ballastless track plate is arranged at the end of the transverse baffle, a transverse laser range finder is arranged on the transverse baffle, and a force bearing table is arranged at the top of the inclined strut. A vertical hydraulic device in vertical contact with the ballastless track plate is mounted below the bearing table, a vertical laser range finder is arranged on the bearing table, and a transverse pressure sensor and a vertical pressure sensor are arranged at the end of the transverse hydraulic device and the end of the vertical hydraulic device respectively. The temporary limiting device is designed by adopting a steel structure, and compared with a concrete structure, the temporary limiting device does not need to be poured, is convenient to install and arrange, and can be recycled.

The application belongs to the technical field of CrMo high strength and toughness steel design, and discloses a design method of CrMo high strength and toughness steel based on atomic physical feature coupling machine learning and a preparation method thereof. By introducing atomic scale physical and chemical features (especially "weighted variance" features) as key inputs of machine learning, the application accurately designs a CrMo alloy steel which still maintains excellent plasticity under ultrahigh strength (>1400MPa) or maintains high strength under high toughness. The application first introduces atomic physical and chemical feature parameters such as "ionization energy variance" into steel design, reveals the strengthening mechanism at the electron level, avoids blind component trial and error, and significantly reduces the research and development cost.

The utility model relates to the technical field of photovoltaic support assemblies, and discloses a photovoltaic support C-shaped steel, which comprises a fixed steel mechanism, the fixed steel mechanism comprises a first C-shaped steel bar, and a limiting steel bar is fixedly connected below the inner side wall of the first C-shaped steel bar and located at each of the front end and the rear end of a notch. The two ends in the first C-shaped steel bar are each provided with a movable steel mechanism, and each movable steel mechanism comprises a U-shaped steel bar connected into the first C-shaped steel bar in a sliding mode. According to the utility model, a combined photovoltaic support C-shaped steel structure design is adopted as a whole, the whole photovoltaic support C-shaped steel structure comprises a fixed steel structure and two movable steel structures, and the two movable steel structures are slidably installed in the fixed steel structure in an embedded manner. And the two movable steel structures are provided with self-locking structures between the two movable steel structures and the fixed steel structure in a matched manner, so that the length of the whole photovoltaic bracket C-shaped steel can be reliably and conveniently adjusted, and the length can be quickly adjusted and matched according to different mounting length requirements, so that the photovoltaic bracket C-shaped steel is relatively convenient.

The present invention relates to a casting device for an arc-shaped furnace wall, which comprises a bottom ring beam, a plurality of formwork vertical bars, a plurality of lower columns, an arc-shaped formwork, a plurality of connecting ring beams, a plurality of jacking devices, a plurality of legs, a plurality of upper columns and a top ring beam. The formwork vertical bars are of an obtuse angle structure, one end of which is connected to the bottom ring beam, and the middle part of the lower column is connected to the other end of the formwork vertical bar. The arc-shaped formwork is installed on the outer sides of the formwork vertical bars and the lower columns. The connecting ring beams connect the bottoms of adjacent lower columns. The jacking devices jack up the connecting ring beams. The legs are connected to the lower columns through second cross bars. The bottom of the upper column is connected to the top of the lower column. The top ring cross beam is connected to the tops of a plurality of upper columns. The top ring beam is of an angle steel structure. The present invention improves the casting construction efficiency of the furnace wall through the integral arc-shaped formwork, provides reliable support for the furnace top formwork through the angle steel design of the top ring beam, and the arc-shaped furnace wall casting device can move along the furnace bottom frame under the support of the lower columns and the legs, with simple operation.

The invention discloses an anti-progressive-collapse reinforcement design method for a steel support, belongs to the field of buildings, and solves the problem of how to design the steel support for progressive collapse. The method comprises the following steps: calculating a limit load beta max of a structure, and defining a critical load coefficient lambda as a ratio of a design load to the limit load; assuming that the number of the supports is k, the bearing capacity provided by a single support is (1-lambda) * (1.2 DL + 0.5 LL) / k; according to the method, a reinforced column and another adjacent column are dismantled at the same time, and the bearing capacity provided by a single support in different working conditions is calculated; the maximum bearing capacity max [(1-lambda) * (1.2 DL + 0.5 LL) / k] provided by a single support in all working conditions is obtained, and the axial force of the single support can be obtained according to a structural mechanics formula; and checking calculation and model selection are carried out on a single support section according to 'Steel Structure Design Standard' (GB 50017-2017).

This invention discloses a welding method for cryogenic steel designed for extremely cold environments, belonging to the field of welding technology. The process uses cryogenic steel plate as the base material, machining a V-groove with a blunt edge, a groove angle of 55–65°, a blunt edge of 5–6 mm, and an assembly gap of 3–5 mm for flux-cored wire arc welding and 0 mm for submerged arc welding. The groove area is thoroughly cleaned. Welding is performed using flux-cored wire arc welding or submerged arc welding: for flux-cored wire arc welding, DW-A55LSR welding wire and 80% Ar and 20% CO2 shielding gas are used; for submerged arc welding, PREMIERWELDNi1K welding wire and 8500 flux are used. Preheating and interpass temperature are controlled at 125–150℃, matched with specific welding current, voltage, and welding speed. This invention effectively suppresses grain coarsening in the heat-affected zone and improves the low-temperature toughness of the joint through bevel optimization, matching of Ni-containing welding materials, and precise thermal cycling control. The resulting joint has a tensile strength greater than 500 MPa, excellent impact toughness at -40℃, and outstanding resistance to fracture and fatigue, ensuring the long-term safe service of steel structures in harsh freeze-thaw environments.

The present application relates to a kind of moisture-proof high-strength corrugated paperboard and its preparation method, belong to packaging material technical field.The paperboard is by surface layer, first corrugated layer, intermediate flat layer, second corrugated layer and inner layer sequentially composite;First corrugated layer is A type corrugation, and the height of herringbone is 4.5-5.5 mm;Second corrugated layer is B type corrugation, and the height of herringbone is 2.5-3.2 mm;Surface layer and inner layer surface are coated with waste protein-based modified sizing agent layer.Preparation method includes: preparation waste protein-based modified sizing agent and biomass adhesive;Each layer base paper is compounded by biomass adhesive, and paperboard blank is obtained by drying under negative pressure;Again, surface sizing, drying are obtained.The present application is by "A herringbone, flat layer, B herringbone" I-shaped steel structure design, in combination with waste protein resource utilization of environmental protection sizing agent, and low-temperature negative pressure compounding process, so that paperboard has excellent moisture-proof performance and high-strength characteristics, simultaneously realizes clean production.

The invention relates to the technical field of power transmission line engineering foundation construction, in particular to a PHC tubular pile and power transmission tower foot self-locking all-steel connecting device which comprises a self-locking connector serving as a connecting component with a power transmission tower foot and used for transmitting load of a power transmission tower to a pile top end plate; the pile top end plate is pre-buried at the pile top of the PHC pipe pile and serves as a connecting foundation between the pipe pile and the self-locking type connector; the self-locking device is connected between the self-locking connector and the pile top end plate and used for achieving butt joint and locking of the self-locking connector and the pile top end plate. The self-locking type connector is composed of a connector top plate, a connector inner cylinder, a rib plate and a connector bottom plate which are connected into a whole in a welded mode. The self-locking device is composed of a connecting pin, a self-locking block, a pressure spring and a groove shell. Through the design of the self-locking device and the all-steel structure, rapid, reliable and efficient connection between the PHC pipe pile and the tower foot of the power transmission tower is achieved, and the problems that in the prior art, the construction efficiency is low, and the tension bearing capacity is insufficient are effectively solved.

The invention provides a modular super high-rise building steel structure design method, and belongs to the technical field of building design. According to the method, firstly, format normalization processing is carried out on an existing geometric parameter data set, a data set is constructed, and on the basis, the strength of each connection node is calculated; meanwhile, performing parameterization on each geometric configuration by utilizing a trained condition model, and then performing multiple characterization; and constructing a geometric configuration-design parameter corresponding relation by using the multi-representation data and the structural strength data. And training the constructed classification diffusion model according to the corresponding relation, inputting given construction data to obtain primary design data, and correcting by using specified data to obtain a final design scheme. According to the method, a machine learning scheme is introduced, model parameters are adjusted through data to optimize prediction performance, and then a parameterized design scheme is represented and optimized. By applying the method, the design precision and the design efficiency can be remarkably improved, and the correction frequency and the error rate are reduced.

The invention relates to a multi-objective optimization hot work die steel design method, belongs to the technical field of ferrous metallurgy, and solves the technical problem of limitation of single-objective optimization in the prior art. The multi-objective optimization hot work die steel design method comprises the steps that 1, data of hot work die steel are collected, null value filling is carried out, and an original data set is formed; 2, performing feature screening to form an initial data set; step 3, carrying out normalization processing on the characteristic values; 4, selecting a plurality of machine learning algorithms to perform model training; step 5, evaluating each model, and selecting a machine learning algorithm with an optimal training effect from the models so as to obtain a prediction model; step 6, performing multi-objective optimization by using an NSGA-II genetic algorithm to obtain multiple groups of optimal solutions; and step 7, determining components and heat treatment process parameters of the hot work die steel. Various optimization schemes are provided for material design, and different engineering requirements can be met.

The utility model provides a converter steelmaking workshop high-rise frame top dust removal system which comprises a high-rise frame, a smoke gathering cover, a dust removal branch pipe and a dust removal header pipe, the smoke gathering cover is arranged on the top of the high-rise frame, and a closed gathering cavity is defined by a corresponding area of the smoke gathering cover and the top of the high-rise frame through a steel plate. According to the utility model, the roof flue gas collecting cover in a high-rise frame area and a roof steel structure are designed and combined into a whole, flue gas is effectively collected into a dust removal system in time, the investment cost is reduced, and the construction is safe and efficient.