121 results about "Design phase" patented technology

The invention provides a whole-process engineering consultation management design method, which comprises the following steps of: constructing a unified data exchange standard and protocol, converting heterogeneous data output by design tools of different professions and different units into a standardized data format, realizing seamless joint and real-time sharing of data through data middleware, eliminating data barriers, and improving the data exchange efficiency. The collaborative design efficiency is improved; according to the method, digital technologies such as BIM are adopted, a digital twin model of an engineering project is constructed in a design stage, a design scheme is deepened through virtual construction simulation and optimization, factors such as a construction process, construction procedures and resource allocation are fully considered, and the construction feasibility and economic rationality of design are improved; a collaborative mechanism of a design stage and a construction stage is established, experienced construction managers and technicians are invited to participate in design review, improvement suggestions and suggestions are provided from the construction perspective for a design scheme, a designer is helped to comprehensively understand construction requirements, and the design scheme is optimized.

The invention relates to the technical field of project cost management, and discloses a project cost dynamic management method. The method comprises the following steps: marking a timestamp of a data updating node in a historical cost database, extracting a consumption index of each subentry project in a specified interval before and after the timestamp, and constructing a consumption feature set dynamically associated with the cost; inputting the consumption feature set into an optimized neural network, calculating the deviation degree of the same sub-project in the construction stage and the design stage through time sequence comparative analysis, and generating the difference representation of the actual cost and the plan cost; a material price fluctuation coefficient is used as an adjusting variable, a fuzzy comprehensive evaluation model is adopted to carry out multi-dimensional reasoning on the difference representation, and the influence weight value of each cost component on the cost deviation is obtained; key parameters related to the market supply and demand index and the construction progress deviation rate are mined, the key parameters are input into a pre-trained evaluation model, a screening threshold value is dynamically adjusted according to a model output numerical value, and core parameters with influence weight values higher than the adjusted threshold value are screened out.

According to the multi-mode man-machine interaction view and component expression method and system, the design state, the development state and the operation state are integrated, and the problems of scene linkage integration, multi-model association collaborative scheduling and the like of an aerospace equipment MOM system are solved by means of graphical interaction and the like. The method comprises construction of a knowledge graph and demand modeling in a design state, visual design and code generation in a development state, and fault diagnosis in an operation state. Compared with the prior art, knowledge can be deeply mined, codes can be automatically generated, system stability is guaranteed, development efficiency and reliability are improved, and the manufacturing and development requirements of aerospace equipment are met.

The invention discloses a data operation coding platform throughout the full life cycle of rail transit engineering, which is used in the technical field of constructional engineering and comprises a design module used for selecting and managing design-level components in a design stage and inputting coding information related to design; the construction module is used for selecting and managing construction-level components in the construction stage and inputting coding information related to construction; the operation module is used for selecting and managing maintenance-level components in an operation stage and inputting code information related to maintenance; the operation module is used for operating the coding information input in the design module, the construction module and the operation module to generate a coding system; and the transmission module is used for transmitting related data among the design, construction and operation stages. According to the invention, each component is coded and calculated, so that the data can be freely combined and transmitted, and the identification degree, standardization, automation and sharing of the data are greatly improved.

The invention discloses a micro-architecture design space exploration method based on deep learning. The method comprises the following steps: acquiring micro-architecture parameters of a target processor, forming a design space, acquiring performance indexes of different design points in the design space, and dividing key modules based on the design points; creating a directed acyclic sub-graph according to the key module, and constructing a prediction model by using a graph attention network to obtain a parameter optimal solution meeting a design target in the directed acyclic sub-graph; splicing the directed acyclic sub-graphs into a global graph to obtain interconnection parameters of key modules, introducing federal learning to train a global prediction model, and predicting performance data of an optimal solution of the evaluation parameters based on the global graph; and when a performance evaluation result meets a preset performance standard, outputting a target configuration parameter of the target processor under each configuration dimension. According to the method, the micro-architecture design space is explored in the graph embedding space, decision support is provided for chip design, and the design efficiency and flexibility are improved by adopting the thought that different design stages and design modes are coordinated.

Examples provide a system and method for dynamically improving and validating automation plans using generative artificial intelligence (AI). An automation manager analyzes automation plans during the design phase and the testing phase. The automation plan makes suggestions for improving the automation plan in real time using natural language prompts. The automation plan validates the automation plan against guardrails defining restrictions on the actions performed by the system during automation plan execution. The system generates explainability data describing the next planned actions and reasons why each planned action is selected for execution during the automation to increase user confidence in the automation. The system requests user approval prior to performing each action for more accurate and efficient workflow automation while reducing system resource usage consumed during execution of inefficient or ineffective automation plans.

The invention discloses a modeling method for each stage of a bridge based on meta-components. The method comprises the following steps: constructing a bridge full-life-cycle digital representation description rule based on the meta-components; developing a meta-component model in a construction drawing design stage; performing simplification and recombination on the basis of the meta-component model of the construction drawing design stage, and generating models of a preliminary design stage and a planning stage; carrying out refined expansion on the basis of the meta-component model of the construction drawing design stage, and generating models of a construction stage and an operation stage; and establishing a full-cycle model management system. According to the modeling method for each stage of the bridge based on the meta-components, the full-life-cycle digital representation description rule is constructed, the meta-component models in the construction drawing design stage are developed, effective conversion of models in different stages is achieved, and a full-cycle model management system is established; the problems of low efficiency and the like caused by incomplete information transmission and repeated model creation in the prior art are solved.

The invention provides an assembly interference analysis method based on CATIA (computer-graphics aided three-dimensional interactive application). Comprising the steps that simulation resources are prepared, and technical state confirmation and lightweight format conversion are conducted on products, assembly parts and tool models; assembling path planning: planning a collision-free motion path from a starting point to an end point for the to-be-assembled part in the virtual environment; static interference inspection: detecting space overlap among all components of the assembly body in a non-motion state; dynamic interference detection: static interference detection is carried out on a part movement envelope and an external part, and the interference condition in the movement process is judged; and interference analysis output: outputting an analysis result in a visual highlight, data report and image / video form. Through systematized static and dynamic interference check processes, the problem of assembly interference of products in the design stage is effectively solved, and the design quality and the assembly efficiency are greatly improved. The method is suitable for being applied as a CATIA-based assembly interference analysis method.

The invention discloses an intelligent analysis method for an assembly preset value of an oversized truss structure, and belongs to the technical field of intelligent calculation of building structures, and the method comprises the following steps: building a design stage basic model, and extracting key data of the design stage basic model; classifying and calibrating node information and unit information in the key data of the basic model in the design stage; connecting node information and connecting unit information of a hoisting stage, a chord member connecting stage, a hook loosening stage and a support position diagonal web member connecting stage in the construction stage are set, and a basic model of the construction stage is established; key data of the construction stage basic model are extracted from the information data of the construction stage basic model, other data are integrated, and all information data of the construction stage basic model are generated; calculating and analyzing all information data of the basic model in the construction stage to obtain a calculation result; and extracting node deformation data of the construction stage basic model used for calculating the splicing preset value, and calculating to obtain the splicing preset value.

The invention relates to the technical field of fan foundation design, and particularly provides a steel tower drum fan foundation design method based on machine learning, which comprises the following steps: selecting an input variable and an output parameter, and establishing a data set containing the input variable and the output parameter; screening of the machine learning model: delimiting a training set, and performing hyper-parameter optimization of the machine learning model; based on the prediction effect of each group of models in the test set, obtaining the predicted average statistic estimated value and variance of each group of models on the input variable, and establishing a comparison matrix of each group of models; screening out a GBDT algorithm model as an optimal machine learning model based on the weight coefficient and the normalization coefficient obtained by the comparison matrix; and the optimized GBDT algorithm model is improved, and the complete engineering quantity of the high-precision fan foundation is obtained. According to the method, rapid and accurate prediction of the wind turbine foundation engineering quantity is realized, and the method can be applied to rapid estimation of a bidding stage and engineering quantity checking of a design stage, so that a design scheme is optimized, and engineering time and cost are saved.

The invention provides a thermal resistance model construction method of an LDMOS (Laterally Diffused Metal Oxide Semiconductor) device, which is characterized in that a plurality of N-type doped isolation layers are formed on a substrate, an LDMOS structure is formed on each N-type doped isolation layer, all LDMOS structures are divided into different test groups according to different key sizes, and the key sizes at least comprise a total channel width and a cross index; measuring the thermal resistance of the LDMOS structure in each test group so as to respectively extract a thermal resistance value array of each group, and performing data fitting on the thermal resistance value array of each group so as to obtain a thermal resistance model of the relationship between the thermal resistance value of the LDMOS structure and the critical dimension; according to the method, the thermal resistance model of the full-size LDMOS device can be constructed by only utilizing a limited number of LDMOS structures in a primary tape, so that the thermal resistance of the LDMOS devices with different sizes can be predicted, the self-heating effect of the device can be accurately evaluated in the design stage, the device design is optimized, the development cost of the device is reduced, and the research and development period is shortened.

The invention discloses a multi-field fusion digital prototype development system and a digital prototype construction method thereof, and belongs to the technical field of digital prototypes. According to the method, by introducing the FACE architecture, professional models in other fields are subjected to virtual modeling again, and multi-scale and multi-dimensional models are unified, so that the professional models in different subject fields can be integrated comprehensively, and a complete digital prototype model is obtained. Meanwhile, after virtualization modeling, the model can be decoupled from the operation platform, and multiplexing of the model on different operation platforms is realized, so that the model can seamlessly run through a system design stage and a system implementation stage, repeated development and test of the model are avoided, and research and development efficiency of a spacecraft system can be further improved.

The invention discloses a large-space air duct prefabrication modular rapid assembly construction method, and particularly relates to the technical field of building engineering construction, the method comprises the following steps: S1, digital design and modular planning; s2, factory intelligent prefabrication production is carried out; s3, on-site accurate measurement and positioning; s4, standardized installation of the support hanger; and S5, quickly assembling the air duct module. According to the method, static design is upgraded into dynamic adjustable intelligent planning through a closed loop of BIM, 4D construction simulation and self-adaptive adjustment, collision is avoided in the design stage, field change can be actively adapted in the construction stage, the first-pass yield of construction is greatly improved, rework caused by design change and field errors is reduced, and the construction efficiency is improved. The air duct module is accurately, stably and efficiently hoisted, so that the high-altitude manual assembly workload is reduced, the overturning risk in the hoisting process is completely eradicated, and the safety and the hoisting efficiency are both improved.

The application relates to the technical field of ship design, in particular to a ship design method based on ship type flexible customization and a storage medium. A flexible customization design tool set visual push design system platform based on a knowledge graph can automatically match corresponding design modules according to design content in the process of ship digital design by a designer, and can push design tools corresponding to the modules according to design stages, design specialties, operator information and the like. The designer only needs to select corresponding module design objects in the design process, and the module design tool set can be automatically pushed out. After the corresponding design tools are selected, knowledge rules matched with the current design tools and design environment are automatically reasoned and called based on the constructed knowledge graph, and intelligent design based on knowledge driving is realized through the design tools, so that the problem of poor use and configuration flexibility of different professional and different functional design function modules and design tools of a traditional ship three-dimensional design software platform is solved.

The invention relates to the technical field of building construction, in particular to an AI-based BIM (Building Information Modeling) and design budget integration method, which comprises the following steps of: firstly, constructing a high-precision enhanced BIM by fusing laser scanning point cloud, texture data and IoT (Internet of Things) environment data with a BIM original model; then, the trained multi-task deep learning model is utilized to automatically identify defects such as equipment missing, redundancy and geometric distortion in the enhanced BIM model, and a mapping relation between components and cost items is synchronously constructed; and then, calling a predefined strategy or a generative AI to repair the model according to the defect information, and updating a bill of quantity and a budget report in real time in a linkage manner. And finally, through difference degree evaluation and reinforcement learning driven closed-loop optimization, a compliant repair scheme with the lowest cost is automatically selected. According to the method, full-process automation and optimization from defect identification and intelligent repair to cost synchronization are realized, and the model quality and the cost control precision in the design stage are remarkably improved.

The present invention provides a method, system, medium and computer for compiling electric power construction costs based on a three-dimensional model. The method includes: obtaining the three-dimensional model provided in the design stage of cost compilation and mapping the three-dimensional model to a standard bill of materials; creating corresponding quota statistical rules, list statistical rules and project division mounting rules in the three-dimensional model according to the quota statistical conditions, list statistical conditions and project division statistical conditions in different stages of cost compilation; processing the cost documents in different stages according to the quota statistical rules, list statistical rules and project division mounting rules, and outputting the corresponding cost results. According to the three-dimensional model provided in the design stage, the present invention completes the parsing work of the three-dimensional model through component parsing rules and attribute parsing rules, and completes the output of cost results in different stages through the rules for applying quotas and lists in different stages and the statistical rules for engineering quantities, achieving the output of cost results in multiple stages with the same model.

This invention discloses a construction project cost feedback system and method based on quantity analysis; it includes a drawing acquisition module for acquiring multiple versions of drawing data generated at different design stages of a construction project; and a quantity analysis engine connected to the drawing acquisition module for automatically extracting quantity data from any version of drawing data based on preset building component identification rules in response to the import of such data; the quantity data includes at least the amount of building materials used and the corresponding construction quantities; by directly connecting the quantity analysis engine to the drawing acquisition module, this invention achieves automatic quantity calculation upon import of design drawings, and simultaneous pricing by the cost calculation engine, enabling designers to obtain the corresponding project cost amount while completing the design of any version of drawings, transforming the traditional serial process of "design-delivery-quantity calculation-feedback" into a parallel process of "design-quantity calculation-feedback", significantly shortening the design iteration cycle.

This invention provides a method and system for implementing a simulation interaction process between a PLC and an MES in the MES field. The method includes: S1: defining trigger signals and writing a business scenario signal interaction flowchart; S2: writing trigger signal scripts to implement business processing feedback logic; S3: configuring a signal generator; S4: configuring multiple workstations and specifying the line-start workstation as the entry point for the program; S5: importing the trigger script and generator configuration into the main program and starting the program; S6: debugging and verifying the PLC or MES program through process-driven execution, completing the debugging from a single workstation to the entire line of workstations. This invention achieves MES and PLC interaction process simulation through signal-triggered simulation. Whether it's the MES or PLC, process simulation is implemented during the development and design phase, correcting obvious errors in the design phase, advancing the debugging process, shortening the implementation cycle, and reducing economic costs.

The invention discloses a method and system for verifying an RISC-V processor and a computer readable storage medium. The method comprises the following steps: analyzing an RISC-V official manual and a micro-architecture user manual, and generating a static instruction-resource mapping table; and generating a first test instruction sequence for each instruction in the static instruction-resource mapping table, executing the first test instruction sequence by using an RISC-V processor simulation model constructed by a software simulator, and dynamically calibrating the static instruction-resource mapping table in the execution process. And traversing the instruction and resource mapping relationship in the calibrated static instruction-resource mapping table, analyzing RISC-V processor verification logic, and if a conflict is found, outputting a conflict report so as to complete defect repair before RTL code writing. According to the application, hardware behaviors can be accurately associated, the problem of disjunction of semantics and micro-architecture is solved, and conflict prediction in an architecture design stage and end-to-end automatic verification from instruction semantics to micro-architecture behaviors are realized.

The invention belongs to the technical field of spiking neural networks. The invention provides a construction method of a reversible pulse neural network supporting parallel computing. According to the embodiment of the invention, the reversible calculation structure is introduced, the neuron state of an intermediate layer does not need to be explicitly stored in the forward propagation process of the network, and the reconstruction of the activation value can be realized through the reversible mapping relation in the backward propagation stage. In the design stage of the reversible structure, hardware mapping characteristics are fully considered, and forward calculation and reverse reconstruction processes of reversible mapping are simultaneously incorporated into a parallel execution framework of a configurable calculation array. Through collaborative design of a data path and control logic, forward propagation and reverse reversible reconstruction can be efficiently and parallelly operated in the same array, and inter-stage calculation idle time and data waiting time are remarkably shortened. On the premise of ensuring reversibility, streamlined and parallel execution of forward and reverse calculation is realized, and the throughput rate and the training speed of the system are integrally improved.

The invention relates to a method for manufacturing a two- or three-dimensional part having a composite architecture with at least two different micro-lattices connected to each other, comprising the following steps: • performing (100) a computer-implemented design step comprising the following steps: A) defining (100A) a domain representing said part to be manufactured, then defining a first sub-domain for a first micro-lattice and a second sub-domain, complementary to the first sub-domain, to delimit a second micro-lattice different from the first micro-lattice; B) defining (100B), over the entire domain, the coordinates of generating centers for the two micro-lattices, C) defining (100C) the first micro-lattice D) defining (100D) the second micro-lattice E) connecting (100E) the second micro-lattice to the first micro-lattice.the design stage also providing for defining a shape and associated transverse dimensions for each micro-beam, then: • manufacturing (200) the architecture thus designed.

The invention belongs to the technical field of building industrialization and computer aided design, and discloses an assembly type component model generation method and system.The method comprises the steps that basic design data and construction deviation historical data of target assembly type building engineering are obtained, and an initial design data set and a standardized construction deviation historical data set are generated respectively; establishing a construction deviation distribution characteristic parameter set based on the construction deviation distribution characteristic parameter set, wherein the parameters are associated with component types, spatial position ranges and connection forms; determining a target component set and an assembly path relation, and matching corresponding construction deviation distribution characteristic parameters for each component; and taking the basic design data and the matching parameters as generation constraint parameters, inputting the generation constraint parameters into a component generation sub-module based on an encoder-decoder architecture, and generating a fabricated component model. Deviation adaptation logic is integrated in the design stage, the construction rework probability can be reduced, the structural stability and component universality are improved, and the method is suitable for multi-layer or high-rise fabricated concrete structure buildings.

This invention discloses a deep learning-based product structure parameterized design optimization method and system, relating to the field of computer-aided design technology. The key technical solutions include the following steps: collecting multi-source heterogeneous data on product structure design, including parameter design documents, simulation data, process execution records, and failure case reports; generating a parameter full-process influence correlation map based on the multi-source heterogeneous data; performing feature judgment on the parameter full-process influence correlation map to obtain a set of key constraint parameters; and generating an optimization target system based on the priority ranking and interactive constraint relationships of the key constraint parameter set. This optimization target system includes structural parameter targets in the design phase, structural manufacturing targets in the process phase, and structural stability targets in the usage phase. The effect is to avoid the problems of insufficient production adaptability and poor usage stability caused by focusing only on a single stage target, improving the parameter coordination throughout the product lifecycle, and shortening the product development iteration cycle.

This invention discloses a high-precision fatigue analysis method for spring arms, comprising the following steps: S1: Preprocessing the model using mesh preprocessing software and calculating the stress distribution of the part under fatigue conditions using finite element analysis; S2: Analyzing the fatigue life using fatigue analysis software; S3: Comparing the fatigue results obtained through experiments with the analyzed values. The method closely approximates actual experiments in simulating the constraints and loads on the spring arm's motion, resulting in better convergence of the force analysis. It addresses the accuracy issues caused by the complex forces at the spring points of the spring arm, and the analysis results show high consistency with actual experimental verification. This allows for early risk identification in the design phase, improving development efficiency and reducing development costs. It features high versatility and accurate calculation results.

A technology is provided that can predict the environmental load of a manufacturing process based on the influencing factors of the manufacturing process at the design stage. [Solution] The environmental load prediction device of the present invention stores a prediction formula configured to calculate the environmental load using parameters that represent the characteristics of parts processed in the manufacturing process, and predicts (simulates) the environmental load of the manufacturing process by reading the parameters from process data that describes the design values ​​of the parameters and substituting them into the prediction formula.

The invention relates to a noise evaluation method, device and equipment of a compressor, a medium and a program product. The method comprises the steps that a multi-body dynamics simulation model corresponding to the compressor is established based on geometric structure parameters of all parts in the compressor and the motion relation between all the parts; the multi-body dynamics simulation model comprises a plurality of body units and kinematic pairs among the body units; on the basis of the multi-body dynamics simulation model and corresponding preset driving of the compressor under the preset working condition, dynamic response of the compressor is predicted, and a prediction result is obtained; and based on the prediction result, the knocking noise risk of the compressor is evaluated, and an evaluation result is obtained. Thus, the actual running state of the compressor can be effectively simulated, the potential knocking problem can be recognized in advance, the knocking abnormal sound problem of the compressor product can be effectively found or predicted without depending on test and error, and the risk prediction capacity and optimization efficiency in the design stage are improved.

The present invention provides a design verification method for a vehicle's swing value, comprising the following steps: step S1, obtaining vehicle design data; step S2, using the design data to establish a vehicle model in drawing software; step S3, using the vehicle model to measure the vehicle's swing value; step S4, determining whether the swing value meets the requirements, and if so, terminating the verification; if not, redesigning the design data until the swing value meets the requirements. The present invention can establish a vehicle model in drawing software based on the vehicle's design data, simulate the vehicle's actual turning state, and measure the vehicle's swing value, thereby obtaining the vehicle's swing value during the vehicle design phase, thereby improving measurement efficiency and reducing the manpower, material resources, time, and development costs required to redesign the vehicle when the swing value does not meet the requirements.

This application relates to the field of electronic circuit design technology, and in particular to a PCB layout optimization method suitable for signal transmission. This method acquires manufacturer-specific process capability parameters, constructs a manufacturing disturbance model including conductor geometric deviations, dielectric non-uniformity, and interlayer alignment errors, and embeds an electromagnetic simulation engine to form a dynamic signal integrity analysis model. Based on this, an adaptive layout constraint rule set is generated, driving the layout and routing algorithm to perform manufacturing robustness-oriented automatic routing. This solves the problem of signal integrity degradation in high-speed signal links on PCBs due to manufacturing fluctuations, pre-compensating for manufacturing-introduced non-ideals during the design phase, and improving the first-pass success rate and signal performance consistency of high-speed PCBs.

The invention relates to the technical field of computer-aided engineering and material science, and discloses a pavement construction material ratio intelligent calculation and scheme generation system, which comprises the following steps of: firstly, constructing a response manifold model under multi-scale constraint; accurately representing a nonlinear mapping relation among a material ratio parameter, a working condition disturbance parameter and a macroscopic performance index; an active learning and model iteration module is utilized to iteratively optimize the model in a mode of minimizing the number of physical tests; then, a ratio scheme reverse generation module reversely solves a robust reference ratio scheme which meets performance constraints and is insensitive to working condition disturbance based on the model; and finally, in the construction stage and the construction process, a self-adaptive correction module obtains field working condition disturbance data in real time, the model is used for calculating the proportion adjustment amount, and dynamic correction of the production process is achieved. According to the method, the efficiency and the quality of proportioning design are remarkably improved, the robustness of a proportioning scheme is ensured, and closed-loop control of a design stage and a production stage is realized.

This invention provides a fault prediction method, apparatus, electronic device, and storage medium. The method includes: performing fault prediction based on component attribute data of the product under test (BUT) during the design phase; applying a fault hierarchy model to infer the root cause of faults based on the predicted fault probability distribution; and obtaining the fault propagation path corresponding to the fault modes involved in the BUT. The fault hierarchy model is configured with a multi-layer topology from the product component level to the product whole-machine level, and the transmission relationship of faults in the multi-layer topology from the product component level to the product whole-machine level. This not only realizes the leap from qualitative experience analysis to quantitative data prediction, but also transforms isolated component risks into visualized fault propagation paths. This allows designers to clearly see the specific impact chain of underlying design defects on the reliability of the whole machine, thereby enabling targeted optimization before product manufacturing and greatly improving R&D efficiency and the final quality of the product.