14 results about "Cloud manufacturing" patented technology

The invention provides an energy-saving cloud manufacturing multi-target scheduling method and system for improving rate-driven heterogeneous aggregation, and the method comprises the steps: A, setting algorithm parameters, job attributes and machine constraints, generating a weight vector and a neighborhood, and randomly binding an initial aggregation method; b, generating an initial population, performing heuristic decoding, and initializing an ideal point and an external archive set; c, calculating a dynamic switching threshold value based on the current iteration progress; d, executing sequential crossover and swap mutation operators to generate offspring individuals, and performing heuristic decoding based on consistency increment evaluation; e, updating an ideal point and maintaining an external archive set; f, executing self-adaptive environment selection according to the dominating relation and the relative improvement rate, and updating a neighborhood solution and a bound aggregation method; and G, if the termination condition is not met, returning to the step D, otherwise, outputting a non-dominated scheduling scheme set. The method has the advantages that the convergence problem under the multi-target conflict is effectively solved through self-adaptive cooperation of heterogeneous strategies. According to the method, heuristic batch decoding and time sequence linkage are adopted, a heuristic decoding algorithm with cluster constraints is designed, through real-time calculation of idle increments and switching losses, deep fusion of cross-process and cross-region resources is achieved, the cooperation efficiency of the whole cloud manufacturing process is guaranteed, and the maximum completion time and the total manufacturing cost can be balanced on the premise that production constraints are guaranteed; and thus, a high-quality collaborative scheduling solution set is stably obtained.

The invention discloses a cloud manufacturing optimization system for a linear cutting workshop. The cloud manufacturing optimization system comprises a user layer, a service center layer, a scheduling entity layer and a user feedback layer, the user layer is provided with a cloud terminal and is used for exchanging data with the service center layer; the business center layer comprises a model center, a data center, a search center, a computing center and a planning center; the scheduling entity layer comprises an enterprise level, a workshop level and a production line level, three levels of automatic scheduling systems exchange data with the service center layer respectively, and distributed automatic scheduling systems are arranged in the three levels of automatic scheduling systems respectively; the user feedback layer feeds back the work summarization condition to the user layer; according to the method, a cloud system of a whole wire cutting product is integrally redesigned by utilizing a new computing mode, a business mode and an application mode of cloud computing according to a design concept of'cloud centralized management of discrete manufacturing resources and on-demand service of overall planning of cloud resources.

The invention relates to the technical field of cloud manufacturing services, in particular to a cloud manufacturing enterprise low-carbon cooperative evolution analysis method and related products. The evolutionary game process of suppliers, demanders and supply and demand parties is analyzed from the three aspects of transverse low-carbon cooperation between supplier clusters, transverse low-carbon cooperation between demander clusters and longitudinal low-carbon cooperation between suppliers and demanders; therefore, suppliers, demanders and supply and demand parties can be guided to make specific low-carbon cooperation decisions. And meanwhile, the cloud platform can be guided to select low-carbon cooperation incentive decisions matched with suppliers, demanders and supply and demand parties, so that the transformation of low-carbon cooperation of supply and demand enterprises is better promoted.

This invention discloses a novel method for adaptive robust service composition and optimal selection in cloud manufacturing, belonging to the field of cloud manufacturing technology. The method includes the following steps: 1) establishing an Adaptive Robust Service Composition and Optimal Selection (ARSCOS) model; 2) solving the model in step 1) using the Enhanced Multi-Objective Artificial Hummingbird Algorithm (EMOAHA). The ARSCOS model of this invention enhances the anti-interference capability of CMS and reduces the negative impact of uncertainty on the task execution process.

The invention discloses a task time sequence tight coupling cloud manufacturing energy consumption and service quality collaborative scheduling optimization method, belongs to the field of cloud computing, intelligent manufacturing and resource scheduling optimization, and aims to solve the problems of preheating energy consumption waste, service occupation conflict, supply and demand benefit imbalance, insufficient optimization performance and the like in the prior art. Comprising the following steps: decomposing a customized task into independent sub-tasks and matching a candidate service set; constructing a bilevel planning model in which the preheating energy consumption of the upper layer focuses on the minimum supplier and the lower layer is based on the QoS weighting preference of the demand side; designing an energy perception scheduling generation scheme containing service occupation scheduling and connection degree scheduling; and solving an optimal Pareto solution through an adaptive NSGA-II algorithm integrated with MEOS, and outputting a service combination and a subtask execution plan. On the premise that QoS constraints are met, preheating energy consumption is averagely reduced by 2%-8%, service occupation conflicts are effectively avoided, benefits of a supply party and a demand party are balanced, the Pareto frontier is better, the method is suitable for cloud manufacturing scenes with preheating processes, and diversified requirements of personalized manufacturing tasks can be met.

The invention discloses a machine tool equipment cloud service dynamic optimization configuration method with an idle time window, and relates to the technical field of cloud manufacturing. According to the invention, by analyzing the focus of a machine tool equipment resource supplier in cloud service cooperation, a multi-target optimization configuration model giving consideration to service benefits and service risks under the constraint of a machine tool idle time window is constructed; according to the machine tool equipment cloud service dynamic optimization configuration method with the idle time window, the problem of comprehensive quantification and collaborative optimization of cloud manufacturing task benefits and risks in minute-level fragmentary time periods is solved, the matching process of cloud manufacturing service resources is divided into a combination stage and an optimization stage, and in the combination stage, the cloud manufacturing task benefits and risks are optimized in a collaborative mode. Generating all feasible candidate subtask combination schemes based on an idle time window of the machine tool; in the optimization stage, an improved GOOSE-ESC algorithm is used for solving the feasible schemes, and a global optimal task scheduling scheme with the maximum service benefit and the minimum service risk is obtained.

The application provides a kind of cloud manufacturing environment under automobile parts die casting resource intelligent scheduling method, and the technical field is artificial intelligence and intelligent manufacturing.It is characterized by: the method combines the production characteristics of automobile parts die casting under cloud manufacturing environment, and carries out the task decomposition of automobile parts die casting order project and under cloud manufacturing environment, and classifies die casting resources;Establish a die casting resource scheduling model, determine the objective function and constraint condition of optimization scheduling;And using deep policy gradient (DDPG) algorithm to solve the die casting resource scheduling problem of automobile parts.The application is widely used in automobile parts die casting enterprises and vehicle manufacturing enterprises, can meet the real-time scheduling needs of automobile parts die casting resources, and can effectively solve the difficulty of automobile parts die casting resource scheduling problem under current cloud manufacturing environment.

The invention discloses a cloud manufacturing scheduling method based on discrete event simulation and multi-agent reinforcement learning, and belongs to the technical field of intelligent manufacturing and cloud manufacturing service scheduling. According to the method, each manufacturing task is modeled as an independent agent, a partially observable Markov decision process model is constructed, information fusion among the agents is realized through a strategy network, and global value estimation is performed by adopting a value hybrid network meeting monotonicity constraint; in a discrete event simulation environment, an event-driven mechanism is used for triggering an agent collaborative decision, factory distribution actions are mapped into manufacturing or logistics events, and a priority experience playback mechanism is used for network training. According to the method, the sequence limitation of a traditional method of sequencing first and then selecting is broken through, synchronous joint optimization of service selection and task scheduling is achieved, the scheduling efficiency and the sample utilization rate are remarkably improved in a complex manufacturing scene, and the method is suitable for a multi-task and multi-factory distributed cloud manufacturing environment.

Provided is a wide-area cloud manufacturing industrial service system and method based on an Internet of Things large model. The system includes a service cloud platform and a user platform. The service cloud platform is configured to: acquire a constraint indicator; determine first service data from historical service data corresponding to a user based on the constraint indicator; in response to the first service data satisfying a user demand, display the first service data to the user; in response to the first service data not satisfying the user demand, determine a candidate service pool based on the constraint indicator and the user demand, and generate a matching degree between each candidate service data and the user demand; and take one or more candidate service data whose matching degree satisfies a preset matching condition as one or more second service data, and present the second service data to the user.

This application provides a collaborative method, apparatus, electronic device, and readable storage medium based on cloud manufacturing. The method includes: decomposing the development task of the product to be developed and determining a collaborative development decomposition process; assigning corresponding R&D personnel to each collaborative development node in the collaborative development decomposition process and granting them corresponding collaborative development permissions; for each R&D personnel, responding to their R&D operations, generating corresponding R&D results, and synchronizing these results with other R&D personnel in the collaborative development decomposition process, so that other personnel can conduct R&D based on the synchronized results to obtain unified model data of the product to be developed; the unified model data includes development data related to the development task of the product to be developed. This method aims to improve the efficiency of product development and manufacturing.

The application discloses an LED light splitting ribbon real-time defect detection compensation method and system based on edge calculation. The method comprises the following steps: obtaining an LED target image collected for pre-processing to obtain an image sequence; using a network model deployed on an edge calculation device to perform real-time inference on the image sequence to obtain an inference result, wherein the inference result comprises an appearance defect and a position offset; generating a rejection control instruction according to the appearance defect, and performing online rejection on the LED chip with defects before entering the ribbon process; generating a real-time motion control compensation instruction according to the position offset, and sending the real-time motion control compensation instruction to a pick-and-place execution mechanism of a ribbon machine to correct the placement position of the LED chip; and uploading the detection result, compensation data and device state information processed by the edge calculation device to a cloud manufacturing execution system asynchronously. The application improves the mounting precision and yield, realizes edge-cloud collaborative real-time defect detection, fuses visual and force sensing double compensation, and improves the detection precision.

The invention discloses a supply chain carbon footprint multi-source information collaborative management method and system based on a cloud manufacturing platform, and the method comprises the steps: defining a product system boundary, and determining all stages needing to be considered in a product life cycle; constructing a product supply chain network based on a product system boundary, and completing unified identity authentication on the cloud manufacturing platform; based on a data interface and a service management interface of the cloud manufacturing platform, a supplier enterprise is cooperated to call a product carbon footprint life cycle evaluation platform, carbon footprint evaluation work is carried out, and data interaction and storage are realized; based on a data interface and a service management interface of a cloud manufacturing platform, a supplier enterprise is cooperated to call a product carbon footprint life cycle evaluation platform, carbon footprint evaluation work is carried out, and data interaction and storage are realized. Through cooperative management of the cloud manufacturing platform and the supply chain, efficient collection, cooperative processing and optimization analysis of the carbon footprint data are realized, the transparency and efficiency of supply chain carbon footprint management are improved, and construction of a green supply chain is promoted.

The application provides a process flow simulation method and system for a cloud manufacturing mode, relates to the technical field of industrial virtual simulation, acquires process flow collection data and determines collection environment parameters, further performs multi-environment parameter evaluation to acquire multi-environment estimated collection data, acquires cooperation process collection data sets by using a cloud manufacturing platform, acquires simulation process product demand parameters and performs standard demand parameter deviation value calculation, sets cooperation process collection data set weight values, assembles local training data to perform federated learning, optimizes model parameters according to cooperation process collection data set weight values, and determines process flow simulation parameter information, so that the technical problem that the acquisition method for missing parts in the collection data has certain limitations in the prior art, the acquisition process is not rigorous enough, the finally determined data is not sufficient in actual fitting degree, and the accuracy of simulation is affected is solved, and the accurate simulation that is consistent with the process flow simulation demand is realized.

The invention provides an intelligent scheduling method for automobile part die-casting resources in a cloud manufacturing environment, and belongs to the technical field of artificial intelligence and intelligent manufacturing. The method is characterized by comprising the following steps of: decomposing automobile part die-casting order items and tasks and classifying die-casting resources in the cloud manufacturing environment by combining the die-casting production characteristics of the automobile parts in the cloud manufacturing environment; establishing a die-casting resource scheduling model, and determining an objective function and constraint conditions of optimal scheduling; and a depth strategy gradient (DDPG) algorithm is adopted to solve an automobile part die-casting resource scheduling problem. The method is widely applied to automobile part die-casting enterprises and finished automobile manufacturing enterprises, the real-time scheduling requirement of the automobile part die-casting resources can be met, and the difficulty of the automobile part die-casting resource scheduling problem in the current cloud manufacturing environment can be effectively solved.