43 results about "Process development" patented technology

The invention relates to the technical field of data processing, in particular to a code-free configurable task process type development system and method, and the system comprises a task data collection module, a process visualization arrangement module, an event binding engine module, a condition rule analysis module, a task state management module and a resource dynamic loading module. The flow visualization arrangement module generates task nodes and dependency relationship data based on a graphical interface; the condition rule analysis module is used for converting natural language conditions into verification logic capable of being dynamically called; the task state management module drives state transition according to the dependency relationship data, and the task state is atomized and updated after verification logic is called; and the resource dynamic loading module responds to the resource loading instruction to schedule external resources. Through a modularized decoupling mechanism, business personnel use a graphical interface to configure task logic, program codes do not need to be written, and the technical problems of high programming dependency and high task logic and code coupling degree are solved.

The invention relates to an intelligent process research and development system and method based on AI model closed-loop iteration, and belongs to the field of intelligent manufacturing and artificial intelligence. In order to solve the problems that in existing process research and development, due to the fact that links of knowledge analysis, model optimization and experimental verification are separated, the efficiency is low, and manual experience is highly relied on, the method comprises the steps that unstructured process knowledge is automatically analyzed into machine executable scripts, and new process parameters are recommended according to experimental data through a process optimization model. The core of the method is that the system automatically feeds back verification results of new parameters, updates the verification results to a data set, and drives a model to carry out next round of iterative training, so that an automatic closed loop from knowledge to the model to an experiment is constructed, and continuous self-evolution and efficient convergence of process research and development are realized.

The invention provides a narrow gap swing laser welding pool wettability prediction method based on CFD simulation. The method comprises the following steps that an interaction platform is constructed through Python + PyQt5, and geometric modeling, UDF compiling and a material library module are integrated; the groove parameters and the swing track are dynamically loaded to a Fluent solver, and a full-coupling transient model of a steam recoil pressure-buoyancy-molten drop mass source item is established; in CFD-POST, the widest section of the molten pool is positioned on the basis of the contour surface with the volume fraction being 0.5, and Z-direction displacement-flow velocity data are extracted along the two side wall surfaces; fusing defects are predicted through double criteria of a bilateral average flow velocity difference threshold value and F test variance homogeneity; according to the method, dynamic quantitative evaluation of wetting behaviors can be achieved, the process development period is shortened, the defect detection rate is increased, and the method is suitable for aerospace thick plate welding quality control.

The invention discloses a micro-channel heat exchanger additive manufacturing process prediction optimization method based on meta-learning, and the method comprises the steps: defining key geometric parameters and an SLM process parameter space through building a micro-channel parameterized model; multi-size sample pieces are prepared through orthogonal experiment design, and morphology data are obtained through high-precision detection equipment and an image recognition method; a meta-learning model based on an improved model-independent meta-learning algorithm MAML + + is constructed, finite element simulation data is fused for training, and process prediction under small sample cross-size experimental data is achieved; establishing an intelligent process optimization model by adopting a depth deterministic strategy gradient (DDPG) algorithm, and realizing autonomous optimization of process parameters by adopting a multi-scale reward function; finally, a closed loop verification system is constructed to achieve intelligent adjustment and optimization of process parameters, through collaborative optimization of meta learning and reinforcement learning, the number of process development experiments of new structure sizes is greatly reduced, and the technical problems that in micro-channel additive manufacturing, the process optimization period is long, and cross-size adaptability is poor are solved.

The utility model discloses a chromatography and tangential flow filtration integrated device capable of switching flow paths, which comprises two pumps, a circulation tank, a circulation pipeline, a valve and a detection element, and a chromatography and tangential flow filtration structure is integrated on the same device. The types and the number of the circulation pipelines, the valves and the detection elements can be changed according to the process development requirements of chromatography or tangential flow filtration, the function can be rapidly switched by directly replacing the whole flow path and switching operation software, and the upper limit value adjustment of the working flow can be achieved. And the process development work originally completed by two devices can be realized by switching the flow path structure. The device can be used for chromatography and tangential flow filtration operation in a process development stage, is not only suitable for small-scale test process groping tests, but also can be used for preparation of a large number of samples and pilot scale amplification production operation, realizes dual purposes, is simple and rapid in the whole operation process, effectively improves the process development efficiency, and saves the use cost.

The invention discloses a process development platform, a process development method, equipment and a storage medium, and relates to the technical field of data processing, and the platform comprises a visual configuration module which is used for obtaining a process construction demand of a target user; the process modeling layer is used for constructing a target process structure through a process structure construction model based on the process construction requirement, receiving a process adjustment operation of the target user, and modeling the target process structure to obtain a target process modeling model; the third-party docking module is used for acquiring process access data corresponding to the target process modeling model by connecting a third-party standard interface; and the process development module is used for performing process development based on the target process modeling model and the process access data to generate a target process. According to the method, real-time data synchronization and standardized docking of the visual process platform and the third-party heterogeneous system can be realized, and interoperability and expansibility of the platform system are remarkably improved.

This application relates to a method and apparatus for determining process parameters in metal compound thin film deposition. The method constructs a two-stage cascaded process prediction model. The first stage, a feature extraction model, performs nonlinear transformations and feature extraction on the process parameters, extracting intermediate feature information that comprehensively characterizes the sputtering process state. The second stage, a probabilistic prediction model, establishes a probabilistic mapping relationship between the intermediate feature information and the thin film response information, decoupling the complex nonlinear coupling relationships between multiple parameters in reactive sputtering. It outputs predicted values ​​and corresponding confidence information. Based on the predicted values ​​and confidence information, process parameters are screened, considering both target performance requirements and prediction reliability requirements. This improves the efficiency and reliability of process parameter screening, reduces the number of invalid experiments, and enables the prediction of key response quantities such as thin film deposition rate and chemical composition even with limited experimental data, shortening the process development cycle.

Disclosed is a method implemented for outputting model(s) for developing or operating a process for a CGT. The method includes receiving, storing, and accessing data items; determining attributes of the data items; selecting one or more machine learning models based on the attributes; accessing one or more mechanistic models; integrating the one or more machine learning models with the one or more mechanistic models to obtain one or more integrated models; selecting one or more predictive models from the one or more machine learning models, the one or more mechanistic models, and the one or more integrated models; applying the one or more predictive models to the data items; adjusting one or more values of one or more parameters of the one or more predictive models to reduce uncertainty in model prediction; and outputting the one or more predictive models with the one or more adjusted values.

The application discloses a kind of high-temperature oxidation rate prediction methods of hot-rolled steel, and the technology belongs to the field of rolling steel.Utilize high-temperature synchronous analyzer TGA, and the oxidation rate of different steel grades at different oxidation temperatures is determined by high-temperature oxidation experiment, and the basic oxidation data set of steel grade is established, which includes the chemical composition of each steel grade, oxidation temperature and oxidation rate.The data set is divided into training set and prediction set by using multiple leave-out method.Using BP neural network, a machine learning model of steel composition-oxidation temperature-oxidation rate is established based on the training data set, and the model accuracy is evaluated using the prediction set.This method greatly shortens the process development time, saves product development cost, and improves new product development efficiency.

The invention provides a wheel product heat treatment process parameter optimization method and system, and the method comprises the steps: taking the production parameters of wheels of different furnaces and corresponding equipment health vectors as features, taking the performances of the corresponding wheels as labels, and constructing sample data, the production parameters including a heating parameter, a cooling parameter and a tempering parameter; constructing a double-layer Bayesian network model, wherein the double-layer Bayesian network model comprises a first-layer Bayesian network model and a second Bayesian network model connected with the first-layer Bayesian network model; and inputting the target performance of the wheel and the current equipment feature vector into a double-layer Bayesian network model, wherein the double-layer Bayesian network model outputs multiple groups of prediction production parameters with high confidence. While multiple performance indexes such as hardness, static balance and residual stress are met, the number of physical tests is reduced, the process development period is shortened, and the production stability is guaranteed through uncertainty quantification and online self-learning.

This invention discloses a dynamic simulation device and a method for optimizing the molding quality of overflow forming of OLED display glass, belonging to the field of glass overflow forming process development technology. The device includes a support frame, an overflow pull-down mechanism, a simulated liquid heating furnace, a cooling mechanism, and a traction roller. The overflow pull-down mechanism is equipped with an overflow trough, which is provided with a near-end and far-end dual lifting mechanism, a far-end height adjustment component, and a material flow rate control valve. It can dynamically adjust the trough depth, far-end height, and inlet flow rate without stopping the machine for disassembly and assembly, completely replicating the entire process of overflow, cooling, and traction forming, and preparing a solid sheet. The method establishes a physical model based on the Reynolds number as a similarity criterion, and adjusts the inlet flow rate, trough depth, and far-end height in a closed loop according to the sheet thickness deviation to quickly correct the thickness uniformity. The parameters can be proportionally converted to the industrial prototype, improving process development efficiency, reducing costs, and compensating for the deviation between numerical simulation and actual production, providing reliable support for the optimization of OLED display glass overflow forming process.

The invention discloses a yield analysis method, which comprises the following steps of: 1, obtaining physical arrangement of each IO (Input / Output) of an SRAM (Static Random Access Memory); and 2, carrying out IO test on the SRAM and outputting an IO test result. A first parameter is introduced into the IO test, and the first parameter corresponds to the IO physical arrangement. And performing classified output of IO test results according to the first parameter. And step 3, according to IO physical distribution, IO test results belonging to different first parameters are combined to obtain required yield data. According to the invention, the required yield data can be obtained according to the process research and development requirements, the test duration is not increased, and the research and development cost can be reduced.

The invention relates to an automobile technological process development human resource investment assessment method. The method comprises the following steps: constructing an automobile process development project model, and dividing a plurality of projects; the method comprises the following steps: constructing an initial human resource input model through historical project data, inputting project information of a current project into the model, and outputting a human input man-hour calibration value; acquiring actual human input working hours of the current project through a working hour system; and comparing the actual human input man-hour of the current project with the human input man-hour calibration value, and correcting the initial human resource input model according to a comparison result to obtain an updated human resource input model. According to the method, through scientific project modeling, real-time man-hour acquisition, model dynamic correction and the like, the accuracy of human resource investment evaluation is improved, the dynamic adaptability of evaluation is enhanced, the model can be continuously optimized according to actual project conditions, and a reliable solution is provided for human resource management in the field of automobile industry process development.

The invention relates to the technical field of robot process automation, and discloses an RPA node automatic recommendation method based on a process development history. The method comprises the following steps: firstly, collecting historical process development data, and extracting node features and process context information from the historical process development data so as to construct a node recommendation basic data set; based on the basic data set, training to obtain a mixed recommendation model comprising a collaborative filtering module and a sequence pattern mining module; applying the trained mixed recommendation model to a current process development scene, performing score prediction on candidate nodes, and generating an initial node recommendation list; and dynamically optimizing the initial node recommendation list according to the recommendation target to obtain a final RPA node recommendation scheme. According to the method, by means of combination of historical development data and the hybrid model, automatic recommendation of the RPA nodes is achieved, and the recommendation result better fits a specific development scene.

Disclosed is a method implemented to output a model for developing or operating a CGT process, the method including receiving, storing, and accessing a data item, determining attributes of the data item, selecting one or more machine learning models based on the attributes, accessing one or more mechanism models, integrating the one or more machine learning models with the one or more mechanism models to obtain one or more integrated models, selecting one or more predictive models from the one or more machine learning models, the one or more mechanism models, and the one or more integrated models, applying the one or more predictive models to the data item, adjusting one or more values ​​of one or more parameters of the one or more predictive models to reduce uncertainty in the model predictions, and outputting the one or more predictive models having the one or more adjusted values.

The invention discloses a software engineering process development method based on big data, and relates to the technical field of software engineering development, the method comprises the following steps: constructing a unified data acquisition layer to capture multi-source heterogeneous development data in real time, and injecting the multi-source heterogeneous development data into a data lake; constructing a software engineering knowledge graph based on the domain ontology, and realizing semantic association of six types of core entities; calculating a process health degree index fusing the four-dimensional index through a sliding window; training a defect high-incidence area prediction model by using an LSTM neural network; and when the health degree is lower than a threshold value or the risk exceeds a limit, triggering an automatic decision engine to generate a regulation and control instruction and reversely injecting a tool chain to realize closed-loop optimization. According to the method, depth observability, quality risk early warning and flow adaptive regulation and control in the development process are realized, and the delivery punctuality rate, the defect prevention capability and the resource utilization efficiency are remarkably improved.

This application provides a method, apparatus, system, and medium for optimizing standard cell layouts. Based on the actual process flow and structural parameters of an initial standard cell layout, electrical simulations are performed. The simulation performance indicators of the initial standard cell layout are calculated based on the simulation results. When the simulation performance indicators match the preset performance indicators, a multinomial model of the layout dependency effect is established based on the fitting factor of the layout dependency effect model of the initial standard cell layout. The structural parameters of the initial standard cell layout are then corrected to obtain the corrected device structural parameters. A compact model is established, and a greedy algorithm is used to optimize the initial standard cell layout. By utilizing semiconductor process and device simulation tools to model based on the layout dependency effect, the cost of test fabrication is reduced. By generating a compact model and combining it with a greedy algorithm, optimized standard cell layouts are quickly generated, improving the efficiency of standard cell layout optimization, guiding the improvement of standard cell layout performance in the early stages of process development, and shortening the R&D cycle.

The application provides a sintering simulation homogenization method and system for a ceramic lattice structure, and belongs to the technical field of ceramic additive manufacturing and numerical simulation; the method comprises the following steps: constructing a lattice structure model and an equivalent homogeneous structure model, and obtaining macroscopic displacement time sequence data; simulating the evolution process of the macroscopic displacement based on the constructed sintering process proxy model; pre-training the sintering process proxy model by using a joint loss function with physical constraint conditions; performing global optimization based on a differential evolution algorithm, and inversely solving equivalent constitutive parameters of the homogeneous structure, so that the displacement time-varying curves of the homogeneous structure and the ceramic lattice structure are consistent under the same sintering process. The application takes ceramic sintering displacement as a core index of homogenization equivalence, can significantly reduce the trial-and-error cost and calculation resource consumption of a large ceramic lattice structure in a process development process, and further provides effective theoretical guidance for ceramic additive manufacturing.

This application provides a data fusion-based process development method, apparatus, device, and medium. It includes: acquiring user requirements and corresponding business data, and dividing the user requirements into business segments to obtain multiple business objectives; determining preset business rules corresponding to the user requirements, and standardizing the business data according to the business objectives and preset business rules to obtain corresponding standard data; determining the business inputs and outputs corresponding to each business objective, and merging the business inputs and outputs according to preset merging rules to obtain an initial business process; and inputting the standard data into the initial business process to generate the target business process. This improves the efficiency and quality of process development.

The application discloses a kind of based on CFD simulation and response surface method's microplate fermentation process rapid development method, comprising: S1, establish microplate CFD model, obtain the quantitative relationship of fluid mechanics parameters and operating condition;S2, with fluid mechanics parameters as constraint, construct response surface model and carry out multi-objective optimization, obtain optimal process parameter;S3, adopt 3D printing to manufacture microplate prototype;S4, carry out high-throughput fermentation verification, correct model;S5, scale-up verification.The application is coupled with CFD simulation and response surface method, realizes accurate prediction and control to fluid mechanics condition while maintaining high-throughput advantage, solves the problem of long cycle, low optimization efficiency, scale-up difficulty in traditional process development.The application can shorten process development cycle by more than 50%, product concentration is higher than traditional method by 10-20%, scale-up success rate is increased to more than 80%, and is suitable for process rapid development of a variety of microbial fermentation system.

The invention discloses a tightening process development method, device and system suitable for a bolt group, and the method comprises the steps: calculating the pre-tightening force range of a bolt based on the material performances of the bolt and a connected part; taking the constraint condition that the final pre-tightening force obtained by each bolt in the bolt group under the action of the tightening torque corresponding to the initial pre-tightening force is within the pre-tightening force range, and continuously iterating the elastic interaction matrix according to the relationship among the target final pre-tightening force matrix, the elastic interaction matrix and the initial pre-tightening force matrix to obtain a final pre-tightening force matrix; and correcting the initial pre-tightening force of each bolt in the initial pre-tightening force matrix to obtain the final initial pre-tightening force of each bolt. According to the invention, the consistency of the connection pretightening force of each bolt in the bolt group can be ensured, and the bolt connection quality is improved.

The invention relates to a metal casting process optimization method, and relates to the technical field of metal casting process optimization, 3D design software is used for constructing a casting three-dimensional model and a mold model, MAGMASOFT software is used for setting process parameters, the process parameters comprise temperature parameters, time parameters and cooling conditions, corresponding thermophysical parameters of a built-in material library of the MAGMASOFT software are called, and the temperature parameters, the time parameters and the cooling conditions of the casting three-dimensional model and the mold model of the casting three-dimensional model are calculated. MAGMASOFT software is operated to carry out multi-physics field coupling simulation, TAG grid adaptive subdivision is adopted, potential defect types and areas are identified, a temperature field cloud picture and solidification animation are generated, the defect types comprise shrinkage cavities, shrinkage porosity, air holes and hot cracks, technological parameters are adjusted, simulation is carried out again, a DOE experimental design method and genetic algorithm iteration are adopted to carry out technological parameter adjustment, and the temperature field cloud picture and solidification animation are obtained. And finally, the required process conditions are met. According to the technical scheme, the casting simulation precision is improved, defects in actual production are reduced, and the production efficiency is improved by optimizing process parameters, reducing the production cost and shortening the process development period.

This invention discloses a method and system for predicting energy density in additive manufacturing based on spatiotemporal decoupling and hardware acceleration. The invention transforms continuous geometric space into a mesh through voxel discretization; constructs a total heat source tensor representing the cumulative energy distribution along the laser scanning path; performs spatiotemporal decoupling on the heat conduction model, transforming the four-dimensional transient problem into a three-dimensional static spatial integration problem; equivalences this integration problem to convolution operations, solving for the energy density field through the convolution of the total heat source tensor and the heat diffusion kernel tensor; utilizes GPU parallel acceleration for the convolution calculation; and finally, performs defect prediction and process optimization based on the energy density field. This invention avoids the time-consuming iterations of traditional transient simulations, achieving efficient and high-fidelity thermal process simulation at the part scale, significantly shortening the process development cycle.

The invention relates to the technical field of air conditioner accessories, and discloses a self-piercing riveting process optimization method and system.The method comprises the steps that firstly, a finite element model simulating the riveting forming process is constructed; secondly, a reference rivet is fixed, and a target riveting die enabling the joint forming quality to be optimal is screened out from the candidate riveting dies through simulation; then, on the basis of the target riveting die, riveting forming simulation and material object preparation are conducted on various candidate rivets, and corresponding simulation connector samples and actual connector samples are obtained; and finally, comprehensively analyzing the section morphology size of the simulation joint and the mechanical property data of the actual joint, screening out a target rivet with the optimal comprehensive performance, and outputting an optimized process parameter combination. According to the method, through the combination of simulation prediction and experimental verification and the step-by-step strategy of firstly optimizing the mold and then optimizing the rivet, accurate and efficient optimization of the process parameters is achieved, and the connection reliability of the base materials to be connected and the process development efficiency are remarkably improved.

The application belongs to the technical field of heat treatment, and provides a GCr15 bearing steel bearing ring heat treatment process parameter optimization method, which comprises the following steps: S1, obtaining the bearing type, geometric parameters, performance constraint conditions and target heat treatment equipment capability boundary of the GCr15 bearing steel bearing ring to be optimized; S2, establishing a collaborative process parameter set composed of independent process parameters and collaborative coupling parameters; S3, establishing a four-field full-coupling dynamic simulation model and verifying; S4, establishing a training data set; S5, establishing a double-level collaborative prediction model; S6, multi-objective collaborative optimization and three-level checking; S7, small-batch trial production and three-level triggering and double-dimension updating closed-loop iteration mechanism; S8, process database updating. Through the mapping relationship between the bearing geometric parameters and the collaborative process parameters, the application realizes the rapid migration and reuse of the heat treatment processes of different types of bearing rings, greatly shortens the process development cycle, and reduces the trial and error cost.

The invention relates to the technical field of workflow management, and discloses a process development system for customizing and constructing an intelligent agent, which comprises a general data component library, a visual editing module, an automatic vector marking module and a business system integration module, and is characterized in that the general data component library is used for storing reusable process node components; comprising a description component, an approval component and an evaluation component, and the approval and evaluation components can be flexibly added according to requirements; the visual editing module provides a dragging type operation interface and supports dynamic adjustment of form components and process nodes through operations such as dragging, clicking, inputting and selecting; the automatic vector marking module carries out vectorization processing on a text input by a user to generate a text feature vector supporting semantic retrieval and correlation analysis; and the business system integration module realizes synchronization of approval process execution records and business system data. The invention aims to solve the problems of repeated flow node configuration, low reusability and insufficient data integration and sharing capability in the existing flow approval system.

This invention discloses a method and system for macroscopic forming control in high-power single-mode laser welding, belonging to the field of laser welding quality monitoring and control technology. The method first establishes a complete quadratic polynomial mapping model between weld penetration depth and laser power, welding speed, and defocusing amount based on process experiments. Through time-scale analysis, a dimensionless number S is defined to characterize the relative magnitude of the evaporation and heat conduction effects at the top and bottom of the keyhole, establishing a keyhole stability criterion. Based on the threshold range of S and the penetration depth model, a process window for good macroscopic forming is defined. In actual welding, the S value is calculated according to process parameters, and combined with the process window, rapid judgment of weld forming quality is achieved. The dimensionless number S criterion provided by this invention quantitatively reflects keyhole stability from a physical mechanism perspective, avoiding the blindness of traditional empirical methods, and can efficiently achieve process parameter control, improving the forming quality and process development efficiency of thick plate laser welding.

Target processing conditions are searched while reducing a process development time and process development costs. A processing condition search device includes a learning database including a processing database storing target processing data for a target process and a reference processing database storing reference processing data for a reference process, a teachered learning execution unit that estimates an I / O model of the target process, which is an I / O model between a target description variable and a target objective variable, a transfer learning execution unit that estimates the I / O model of the target process using a reference I / O mode between a reference description variable and a reference objective variable, and the target processing data, and a transferability determination unit that determines whether the teachered learning execution unit or the transfer learning execution unit is used to estimate the I / O model of the target process.

This application provides a method and related equipment for verifying assembly code, belonging to the field of process development technology. It solves the problems in existing technologies where assembly code is unreadable, the compiler cannot verify it, leading to low efficiency in assembly code development, and difficulties in debugging and locating errors in the assembly code. The method includes: acquiring assembly code data, wherein the assembly code data includes assembly code and control instructions; simulating the execution of the assembly code based on the control instructions to obtain the execution result of the assembly code; converting the execution result into graphical data; and calling a graphical interface to display the graphical data.

This invention relates to the interdisciplinary field of artificial intelligence and welding process optimization, specifically disclosing a rapid optimization method for dissimilar metal welding process parameters based on transfer learning. This method aims to address the core problems of long optimization cycles and high costs in dissimilar metal welding due to scarce experimental data and reliance on trial and error in process development. Its core steps include: constructing a welding process knowledge base integrating multi-source data; generating a dynamic prediction model adapted to the target task using hierarchical transfer learning; establishing a digital twin integrating this model as a virtual optimization environment; applying multi-objective reinforcement learning in the twin for rapid optimization of process parameters; and finally achieving online dynamic control of the process strategy and system generalization across materials. This invention significantly reduces data dependence and achieves rapid and high-quality process optimization under small sample conditions.