153 results about "Production model" patented technology

The present invention discloses a digital production operation management method for data quality assessment and analysis, including: step 1: constructing a multi-level distributed data acquisition system; step 2: designing a multimodal data fusion framework, combining graph neural network and time series data processing technology to realize data fusion and multidimensional analysis; step 3: constructing an intelligent scheduling engine to realize dynamic adaptive scheduling strategy to cope with real-time changes in the production environment; step 4: designing a decentralized self-organizing production network to realize flexible adjustment and optimization of the production process; step 5: realizing the coordinated optimization of product design and equipment maintenance through topology optimization, multi-objective optimization and machine learning algorithms; step 6: constructing a virtual production network to realize real-time monitoring, dynamic prediction and optimization decision support of the production system. Through the present invention, enterprises can break the limitations of traditional production models, improve production efficiency, flexibly respond to changes in market demand, and optimize resource allocation.

The invention provides a method and a system for regulating and controlling a raw material ratio and parameter combination in production of a nitrogen-phosphorus-potassium ternary fertilizer, and belongs to the technical field of automatic control of fertilizers. The production data is collected in real time through the sensor, the production model is established by using the convolutional neural network and the long-short-term memory network, the optimal parameter combination is calculated by using the particle swarm optimization algorithm, and real-time optimization and self-learning of the production process are realized. By adopting the method and the system for regulating and controlling the raw material ratio and the parameter combination in the production of the nitrogen-phosphorus-potassium ternary fertilizer, the real-time optimization of the production process can be realized, the product quality and the production efficiency can be improved, and the production cost can be reduced.

The invention particularly relates to a hydrogeological analysis system and method based on big data, and relates to the technical field of hydrogeological analysis, and the method comprises the steps: placing a new model and an old model in an A / B test stage, and carrying out the parallel processing of real-time data; performing automatic judgment according to a preset performance index, and deciding whether to upgrade the candidate model to a new production model; and applying the model selected after decision making to hydrogeological analysis to solve the problem of long-term prediction precision under dynamic change of the hydrogeological system. According to the method, dynamic threshold monitoring, K-S outlier sample examination, sub-model optimization and A / B test smooth iteration processes are constructed, and a mechanism and machine learning coupling model and parallel calculation are combined, so that the model drift identification delay is reduced, the prediction precision is improved, scenes such as underground water over-mining prevention and control and pollution emergency are effectively supported, and the prediction accuracy is improved. And an accurate and efficient scientific decision basis is provided for water resource management.

The invention discloses a time sequence production model deduction method and apparatus, a terminal device and a storage medium. The method comprises the steps of obtaining a first time sequence production model of a power system; four different thinking chains are constructed; wherein the thinking chain is solved by using time decomposition, space decomposition or parallel calculation; the first time sequence production model is solved according to the four thinking chains, and a fourth solving result is obtained; the result with the minimum Euclidean distance sum with all the solving results is calculated and serves as a target result; and planning and scheduling the power system according to the numerical value of the decision variable in the target result. According to the method, the simulation precision is remarkably improved through time decomposition and space decomposition. Through parallel calculation, the solving speed is improved, important details are reserved, and errors caused by simplification are reduced. In addition, the thinking chain integration effectively integrates the results of a plurality of reasoning paths, and the representativeness and accuracy of the simulation result are improved.

The invention discloses an oil reservoir water content prediction method based on a graph neural network and Transform, and belongs to the technical field of oil and gas field development, and the method comprises the following steps: S1, converting an oil reservoir injection-production model at each time point into a graph structure, and constructing a connection network from a water injection well to a production well; and S2, constructing a GNT proxy model in combination with the graph neural network and Transform, training the GNT proxy model, and predicting the water content of each production well. According to the constructed GNT proxy model, an oil reservoir injection-production structure is converted into graph data through a GCN module, the information transmission strength between nodes is dynamically adjusted through an edge feature enhanced message transmission mechanism, and inter-well communication features are accurately captured; and the multi-head self-attention mechanism of the Transform encoder module is combined to process the time sequence dependence, so that the long-distance time dynamic relationship is effectively modeled, and an efficient and reliable agent model is provided for the dynamic analysis of the oil reservoir.

The utility model relates to a vibration exciter assembly line. Comprising a rack platform, a moving platform is installed on the rack platform, a rotating platform is arranged on the moving platform, an overturning platform is arranged on the rotating platform, a box body is arranged on the overturning platform, and a four-column three-cross-beam hydraulic work station is arranged on the front portion of the moving platform. A bearing clamping and feeding mechanism, a main shaft clamping and feeding mechanism and a gear clamping and feeding mechanism are respectively mounted on two sides of a rack platform below the four-column three-cross-beam hydraulic workstation machine; an oil retainer assembly unit, a shaft sleeve assembly unit, an automatic gluing unit, a through hole cover assembly unit, an automatic bolt assembly unit, a labyrinth cover assembly unit, a spacer bush assembly unit, an eccentric block assembly unit and an unloading point are sequentially arranged on the front portion of the gear clamping and feeding mechanism. The device has the advantages of saving a large amount of space, conforming to an intensive production mode, liberating manpower, occupying a small space and improving the working efficiency.

Example methods and systems relate to the modeling of production processes to include intermediate products. An enterprise resource planning (ERP) system receives user input to define an intermediate product, and generates a master data record for the intermediate product. The ERP system further receives user input to include the intermediate product in a production model within the ERP system. The production model is associated with a real-world production process. The production model is updated based on the master data record to integrate the intermediate product into a sequence of activities. The sequence of activities comprises a first activity that produces the intermediate product and a second activity that consumes the intermediate product. The ERP system executes a production order based on the production model. Execution of the production order includes tracking state information of the intermediate product within the ERP system.

An intent-based automation engineering method for automation of a production process includes: receiving an intent model, correlating to process intent, including production process functions, constraints on measurable properties on the production process functions, and / or production process function sequences required for the production process, as a received intent model; receiving a process model, correlating to process knowledge including a production process behavior, as a received process model; determining a machine-readable production model linking the received intent model to the received process model as a provided production model; and determining a control strategy for controlling the production process dependent on the provided production model as a determined control strategy.

The invention discloses a multi-target flexible job shop scheduling method based on a graph network and reinforcement learning, which can effectively characterize key features of a production model by using features of a double-graph attention network deep mining process and a machine. The depth characterization capability can not only improve the performance of the model, but also enhance the adaptability of the model to different production models, so that the model can flexibly cope with various unseen production scenes, and shows excellent generalization performance. Besides, in the field of multi-objective optimization, how to balance the relationship between different objectives is an important and challenging problem, so that the model can find an optimal balance point among the multiple objectives by distributing different weights for different optimization objectives, and the method not only can improve the solving efficiency, but also can improve the optimal balance point among the multiple objectives. And moreover, a high-quality Pareto frontier solution set can be generated, and an effective solution is provided for a multi-target flexible job shop scheduling problem.

The invention discloses a data production and training method and a related device. A knowledge document, training parameters, a data production model and a pre-training model are obtained. And according to the knowledge document and the first cue word, processing through a data production model to obtain a seed data set. And according to the seed data set and the second cue word, performing expansion through a data production model to obtain an expanded data set including the seed data set. And according to a training mode indicated by the training parameters and the extended training set, performing fine tuning on the pre-training model to obtain a target model. And deploying the target model so that a user can use the target model. The data production model is rapidly manufactured and expanded to obtain the expanded data set, the efficiency of manufacturing the data set is improved, the prompt words can make the pre-training model clear own tasks during fine adjustment, and the accuracy of the target model is improved. Meanwhile, full-process automatic processing of data set making, pre-training model fine tuning and target model deployment is achieved, and the efficiency of the whole fine tuning process is improved.

The invention relates to a multi-cycle collaborative production scheduling method of an oil refining production and utility system under an uncertain condition. The method comprises the following steps: S1, obtaining operation data and price data of outsourcing power coal and electricity; s2, predicting the boundary of the uncertainty set according to the price data, and constructing a dynamic uncertainty set; s3, establishing a multi-cycle collaborative production scheduling model of a refinery plant production system and a public system under the dynamic uncertainty set; s4, introducing the model by adopting a distribution robust optimization method based on a dynamic uncertainty set; and S5, solving the multi-cycle collaborative production scheduling model of the oil refining production and utility system under the uncertain condition by adopting a robust dual reconstruction mode, and outputting a production plan. Compared with the prior art, the method has the advantages that the robustness and the conservative property of the production plan output by the model are improved, and the like.

The invention belongs to the technical field of production management, and provides an intelligent order delivery method and delivery system. The method comprises the following steps: selecting actual production data of a plurality of historical orders from a production database to construct a training sample; performing iterative training on the machine learning model based on the training sample until a preset number of iterations is reached so as to obtain an order delivery model; obtaining the specified delivery duration of the order to be delivered, the actual equipment state and the inventory of each production node, inputting the order delivery model, and outputting the predicted delivery duration and the predicted production model; generating a prediction production scheme based on the prediction production model, and performing simulation operation in the digital production line model to obtain a simulation delivery duration; when it is judged that the simulated delivery duration is smaller than the predicted delivery duration and the second duration difference value is smaller than a second preset difference value, an actual production scheme is generated based on the predicted production model to be put into a production line for production. According to the invention, the actual product delivery cycle is adaptive to the specified product delivery cycle.

The invention discloses a digital twinborn simulation optimization system and method for mining dilution rate and loss rate, relates to the technical field of digital mines, and solves the problem of isolated operation of geology, production and automation subsystems in a traditional system by fusing a geologic model and a production model in a unified platform. And an integrated intelligent system with data intercommunication and business collaboration is formed. And the management of the dilution rate and the loss rate is changed from the traditional post statistics to the instantaneous perception and the abnormal diagnosis based on the real-time data, so that the online monitoring and the active intervention of the production process are realized, and the resource waste is reduced. Parallel deduction and multi-objective optimization are carried out on multiple schemes through a simulation engine, and a global optimal scientific decision scheme under multiple objectives can be provided. Through real-time feedback of an execution result, the twin mining area model is continuously calibrated and optimized, the defect that the precision of a traditional static model is attenuated along with time is overcome, and a reliable basis is provided for long-term optimization.

The invention discloses a fault prediction method, system and device for credible features of power transmission and transformation equipment and a medium, and the method comprises the steps: collecting multi-source data of the power transmission and transformation equipment, carrying out the preprocessing of the multi-source data, obtaining noise reduction data, and extracting time dimension feature data and space dimension feature data from the noise reduction data; extracting vibration signal data from the noise reduction data, calculating probability distribution of the vibration signal data, and extracting entropy feature data from the vibration signal data through the probability distribution; performing dimension reduction visualization processing on the entropy feature data, the time dimension feature data and the space dimension feature data to obtain a sensor feature set; and inputting the operation state data into the equipment fault probability production model, outputting a production prediction result, and tracking and obtaining fault equipment through the production prediction result. According to the method, a complete technical closed loop is formed from data noise reduction, multi-dimensional feature fusion to fault source tracing, and the accuracy and reliability of power transmission and transformation equipment fault prediction are improved.

The invention discloses a parallel hyper-heuristic injection-production optimization method based on an agent model, which belongs to the technical field of oil reservoir injection-production optimization, and comprises the following steps: step 1, constructing a three-dimensional geologic model and an oil reservoir injection-production model; step 2, constructing a water-drive reservoir injection-production optimization model and an initial database; step 3, constructing an agent model; 4, generating a filial generation population through parallel evolution by using four algorithms, and evaluating filial generation individuals by using an agent model to obtain respective candidate solutions of each evolution algorithm; 5, constructing a hyper-heuristic guide search strategy and an online parameter return method, and adjusting the search behavior of the evolver based on the candidate solution; step 6, repeating the step 3 to the step 5 until a preset maximum optimization iteration number is reached; and step 7, outputting an optimal Pareto frontier scheme and a corresponding economic net present value. According to the method disclosed by the invention, the search direction is dynamically adjusted by utilizing a hyper-heuristic guide search strategy and an online parameter return method while the injection-production optimization efficiency of the water-drive reservoir is improved.

The invention discloses a traceability supervision method and system for a smart park, and relates to the technical field of traceability supervision. The method comprises the following steps: acquiring a plurality of production lines for target products in a smart park; constructing a product production graph model according to the plurality of production lines; setting a process data structure on each process point, configuring a process data collector, setting a circulation data structure on each process connection edge and production conversion edge, and configuring a circulation data collector; obtaining first process execution data based on the process data collector, and obtaining first circulation execution data based on the circulation data collector; performing structure storage to obtain a first product production drawing, and adding the first product production drawing to a production drawing database of the target product; and performing traceability supervision on the target product based on the production drawing database. The technical problem that products produced in a smart park are difficult to trace precisely in the prior art is solved, and the technical effect of improving the product traceability accuracy is achieved by constructing the product production model diagram.

Task assignment for multi-robot systems (MRSs) in a smart factory (Industry 4.0) is described. Aspects are directed to a hypergraph based MRS and production model facilitating the cooperation among robots and serving frequent reconfiguration desired in Industry 4.0. Aspects are directed to a time complexity friendly search algorithm for real-time application using a hypergraph model to get task assignment(s). Parameters are provided for a tradeoff between solution optimality and time complexity. In an implementation, an example system can include a MRS including robots, wherein the MRS is configured to perform a manufacturing task, and a computing device configure to perform a multi-robot task allocation (MRTA) for the MRS. In an implementation, an example method can include generating task assignments, using MRTA, for robots of a MRS including the robots, wherein the MRS is configured to perform a manufacturing task, and providing the task assignments to the MRS.

The invention provides an industrial defect sample generation method based on a generative model, and the method comprises the steps: enabling the generative model to learn the distribution characteristics of image data, then reconstructing new image data which is the same as an original image in distribution and is different from the original image in sampling, and generating new defect sample images of the same type and different forms. The defect sample generation method based on the generative model can efficiently generate a large number of defect sample images in various forms, can be used for solving the problems of difficulty in defect sample collection and insufficient diversity in a product appearance quality inspection link, and enables training data to cover defect samples in all forms as much as possible, thereby improving the detection capability of the model and improving the detection efficiency. The number of times of iterative optimization of the model is reduced; the invention belongs to the technical field of visual detection.

The invention relates to an intelligent mold production monitoring method based on artificial intelligence, and aims to improve the production efficiency and the product quality and reduce the rate of defective products at the same time. According to the method, mold production model information is matched through a product information base, and key production basic data is obtained; historical and real-time parameter data of production equipment are recorded by using a public time axis, and a detailed data set is constructed; judging whether the product is qualified or not by comparing the actual parameters of the product with the basic parameters and combining a defective product error threshold value; and further analyzing the equipment parameters in the abnormal production time period, predicting the working trend of the equipment, and comparing the predicted trend with the abnormal working trend to identify potential production risks. And finally, equipment parameters are automatically adjusted according to the risk early warning regulation and control strategy, and defective products are prevented from being generated. Intelligent monitoring and regulation in the production process are achieved, and the product quality and production efficiency of mold production are improved.

The invention relates to the technical field of industrial Internet of Things, edge calculation, silk-screen and the like, and provides a substrate silk-screen method and equipment based on an intelligent silk-screen unit, and the method comprises the steps: configuring a feeding mechanism, a dust removal mechanism, a pre-printing alignment mechanism and a printing mechanism which are connected in sequence, and establishing an industrial Internet of Things information sensing layer and an edge gateway which are in two-way communication with the feeding mechanism, the dust removal mechanism, the pre-printing alignment mechanism and the printing mechanism. Order and formula data are received through a gateway, multi-source sensing point location real-time data are fused, a production model with a unified time reference and batch identification is constructed, and process parameters are dynamically issued. And during feeding, the model and the warping degree of the substrate are automatically recognized, and dust removal parameters are synchronously adjusted. In the printing process, screen tension, scraper stress, motor current and printing ink rheological property are monitored in real time and fused to obtain a printing ink comprehensive rheological characteristic value, scraper parameters and an ink return time sequence are cooperatively regulated according to the printing ink comprehensive rheological characteristic value, and a printing quality estimated value is output. According to the method, collaborative optimization and quality estimation of the whole printing process are achieved, and the production adaptability and consistency of product printing are improved.

The present disclosure provides a method for processing a substrate that can maintain a production amount even when a production model is changed. The method for processing a substrate comprises: disposing the substrate on a levitation stage; measuring a distance between the substrate and an inkjet head module; and changing a discharging speed of ink to be discharged from the inkjet head module based on the measured distance.

The invention provides an intelligent aluminum oxide ceramic production system and sintering equipment, the intelligent aluminum oxide ceramic production system comprises manufacturing equipment, a sensor module and an intelligent terminal, the manufacturing equipment produces materials and is provided with the sensor module, and the sensor module and the intelligent terminal are networked and realize data transmission; and the intelligent terminal analyzes and optimizes the data obtained by the sensor module and feeds back the optimized structure to the manufacturing equipment. Through combination of the sensor module and the intelligent terminal, the system can monitor key parameters in real time. A production model is established based on time sequence analysis, equipment parameters are dynamically adjusted, and particularly, the temperature of sintering equipment is controlled through a GARCH model; the temperature can be accurately controlled, and the influence of temperature fluctuation is reduced, so that the product quality and stability are improved, and meanwhile, the energy consumption and the maintenance cost are reduced.

The invention relates to the technical field of industrial control, in particular to a synthetic ammonia production control method, system and equipment, a medium and a product. The method comprises the following steps: acquiring production modeling data of a synthetic ammonia field section, performing unsupervised analysis on the production modeling data through a preset big data model, determining key features and an analysis result of the key features in a synthetic ammonia production process, performing visualization processing on the key features, generating a visual chart, and displaying the visual chart on a database. Therefore, semantic analysis and causal reasoning are carried out on the visual chart and the analysis result through a preset large language model, a target optimization strategy is generated, optimization control is carried out on a synthetic ammonia production site, and the production efficiency of synthetic ammonia is improved.

The present invention relates to a method for constructing digital ship intelligent manufacturing. The construction method comprises the following steps: digital dock construction; digital weight and center of gravity control; hull response monitoring system construction; operation and management integrated digital management platform construction: building a digital overall framework, mainly including a basic layer, an equipment resource layer, an execution basic layer, a coordination business layer, an operation management layer and a decision management layer; digital inspection management platform construction. The advantages of the present invention are: with the help of digital transformation, the components are based on engineering decomposition, with planning management as the command, and an integrated solution for overall design, materials, production, quality and cost management is constructed. Through the construction of the industrial Internet and the integrated application of the information system, a digital shipyard based on digital twins is constructed, facilities, equipment, resources, etc. are interconnected, early warning and analysis are carried out from multiple angles, a big data operation system is explored, a digital operation model is constructed, and finally a new digital production model is formed.

The invention discloses an acquisition and analysis method and system based on intelligent data of a smart factory, and relates to the technical field of intelligent data acquisition and analysis, and the method comprises the steps: S10, analyzing the dynamic production data and basic production data of each production line of the smart factory; s20, analyzing the real-time risk coefficient of the production plan executed by the smart factory; s30, analyzing the dynamic production data regulation and control value of each production line of the smart factory in the remaining working time period; and S40, carrying out intelligent management and control on the real-time work plan of each production line of the smart factory. According to the method, the dynamic production model of the intelligent factory is constructed according to the analyzed production data, the real-time completion degree of the intelligent factory on the production plan can be rapidly analyzed, the influence of the number of unqualified products and the equipment aging condition on the analysis result does not need to be considered in the process, the analysis time is shortened, and meanwhile the production efficiency is improved. And the analysis precision is improved.

The present disclosure relates to techniques for privacy-preserving computing to protect a subject's privacy while using the subject's data for secondary purposes such as training and deploying artificial intelligence tools. Particularly, aspects are directed to receiving, at a local server, subject data regarding a first subject, performing, by the local server, a de-identifying operation, an anonymizing operation, or both on the subject data, sending the subject data to a remote server, receiving a production model from the remote server, the production model including parameters derived in part from the processed subject data, receiving, at the local server, subsequent data regarding a second subject, inputting, by the local server, the subsequent data into the production model to analyze the subsequent data and generate an inference or prediction from the analysis of the subsequent data; and sending, by the local server, the inference or the prediction to a computing device.

An example system may include an energy storage unit and various processors configured to communicate with components of the energy storage unit. An example system may determine a consumption model that predicts future consumption of a node based on local power consumption of the node. The system may receive weather forecast data for the node and determine a power production model for the node that predicts future power production using the weather forecast data. The system may calculate a predicted power difference using the consumption model, the production model, and the current environment of the node. The system may perform automated operations using the predicted power difference, such as charging or discharging an energy storage unit or controlling one or more electrical loads.

This invention provides a low-abnormality horizontal electroplating control system for diamond wire magnetic materials, belonging to the field of diamond wire electroplating technology. This invention uses a real-time pre-control compensation mechanism to capture and suppress early-stage anomalies, while dynamic optimization at the meso-level continuously adjusts process parameters to their optimal state. These two mechanisms work collaboratively within a macro-steady-state baseline framework, fundamentally changing the passive nature of traditional production models and enabling proactive management of production anomalies, significantly reducing the probability of defects such as agglomerates and incomplete plating. By establishing a learning loop that feeds micro-level intervention experience back to the meso-level optimization model, and by incorporating slow-time-varying factors such as plating solutions into the macro-baseline modeling, the system can continuously absorb knowledge from production practice, automatically adapting to long-term changes such as plating solution aging and raw material batch differences, reducing reliance on manual experience.

The application provides a design method of a light truck tire, relates to the technical field of tire design, and comprises the following steps: collecting the use environment data of the light truck tire, and generating the working parameter requirement of the light truck tire; then generating the contour data of the light truck tire; further generating the size data and preliminary material selection of each part structure of the light truck tire; finally generating a preliminary model; adjusting the preliminary model after simulation analysis to obtain a production model; selecting the tire pattern and the use air pressure range of the light truck tire based on the working parameter requirement of the light truck tire; adding the tire pattern and the use air pressure range of the light truck tire to the production model; producing a sample tire based on the production model, and detecting and verifying the design effect on site. Through the investigation on the use environment of the light truck tire, the accuracy of the working parameter requirement of the light truck tire is improved, through the comprehensive consideration of multiple factors such as the material, structure and pattern of the tire, and the mutual influence relationship among each part structure, the comprehensive improvement of the performance of the tire is realized.

The present invention relates to the field of edge data acquisition, and specifically to an edge data acquisition method, system and medium for a smart factory based on the Internet of Things, comprising: an edge acquisition module, a local modeling module, an abnormality recognition module, an edge communication module and a local adjustment module. The edge acquisition module is used to collect working parameters and environmental parameters of production equipment, the local modeling module is used to calculate end point coordinates and an environmental impact matrix, the abnormality recognition module is used to correct the acquired environmental data and identify abnormal sensors, the edge communication module is used to build a communication link, and the local adjustment module is used to adjust the variable parameters of the production equipment and automatically adjust them. The present invention can achieve the integration and consistency of different data sources, ensure the quality and availability of data, and at the same time help to improve data quality, timely discover sensor failures or inaccurate data, and achieve a more efficient and safer production mode.