127 results about "Intelligent manufacturing system" patented technology

The invention discloses an intelligent manufacturing system and method based on an industrial robot, and relates to the technical field of industrial robot control, and the method comprises the steps: constructing a workpiece posture-space structure topological graph according to a cross-scale visual recognition result, carrying out the space comparison with an original trajectory planning graph, outputting a space deviation mapping relation, and carrying out the calculation of a spatial deviation mapping relation; performing spatial correlation analysis and path reachability evaluation on the workpiece attitude-spatial structure topological graph by using a graph neural network to obtain an end execution path instruction; driving the industrial robot to perform intelligent manufacturing operation through the tail end execution path instruction, and obtaining an actual operation result image; and performing feature alignment and difference comparison processing on the actual operation result image and the process reference image to obtain an operation deviation feature mapping relation, performing operation quality evaluation, and outputting an operation result visual detection label. According to the method, the adaptability and the manufacturing precision of the operation path of the industrial robot are effectively improved.

The invention relates to a flexible intelligent manufacturing system which comprises a rack and a plurality of working modules. A first standard interface group is arranged on the rack; a first module interface group is arranged at the bottom of each working module, and the first standard interface group is matched with the first module interface group to enable the working modules to be detachably mounted on the rack, so that the working modules of the same type or different types can be exchanged. The flexible intelligent manufacturing system comprises a first working mode, a second working mode and a third working mode, and the first working mode is configured to move materials from the feeding module to the discharging module. The second working mode is configured to move the materials from the first discharging assembly to the second discharging assembly. And the third working mode is configured as follows: the materials are moved from the material supply module to the functional module to be processed, and then the processed materials are moved to the discharging module through the feeding module. The system has multiple working modes, and the circulation path and the processing sequence of the materials can be flexibly adjusted according to different production requirements.

The invention discloses a dynamic scheduling method for an intelligent manufacturing system, and particularly relates to the technical field of intelligent scheduling. Through a scheduling performance evaluation mechanism fusing a task switching interference index and a target function offset index, a polynomial regression model is utilized to realize scheduling health score prediction, and scheduling performance abnormity is accurately identified; under the abnormal condition, the system can dynamically adjust and dispatch a target function structure and algorithm disturbance parameters according to different index sources, the capability of jumping out of local optimum is effectively enhanced, and the global optimization effect is improved; through a closed-loop scheduling execution and feedback mechanism, the robustness, the self-adaptability and the execution feasibility of the scheduling system are remarkably improved, it is guaranteed that high-quality tasks are completed in time, and the overall production efficiency is improved.

The invention relates to the technical field of intelligent manufacturing, in particular to a flexible intelligent manufacturing system for multi-variety small-batch production, which comprises a flexibility enhancement module, a cost efficiency improvement module, an information interaction enhancement module, a technology depth fusion module and a decision ability optimization module, rapid switching and optimization of the production process can be achieved, so that production efficiency and product quality are improved, technological parameters are intelligently adjusted according to real-time production requirements, production requirements of diversified products are met, production preparation time is effectively shortened, the production cycle is shortened, meanwhile, by means of the Internet of Things technology, the system can monitor the state of production equipment in real time, and production efficiency is improved. In addition, through data analysis and a prediction model, the system can optimize inventory management, reduce the production cost, significantly improve the production flexibility and efficiency in a multi-variety small-batch production environment, and bring significant technical effects and economic benefits to the manufacturing industry.

The invention relates to a packaging method for modeling and production unit combination of digital twin virtual equipment, which realizes modeling of the virtual equipment through an abstract process from top to bottom, and ensures high cohesion packaging of key attributes, states and behaviors of the virtual equipment in combination with an information hiding and uniform interface mechanism. A production unit-level combination and hierarchical packaging framework is further constructed based on the equipment model, and recursive combination and interoperation of multiple layers of modules are realized through unified station-level, production line-level and workshop-level interfaces and scheduling logic; according to the method, the modeling and packaging process of the digital twin virtual equipment is defined, the high cohesion packaging and interface uniformity of the model are highlighted, and cross-level combination and scheduling logic design are supported, so that the consistency and the implementability of the model in the system integration, evolution extension and module multiplexing processes are remarkably improved, and the modeling efficiency of the digital twin virtual equipment is improved. And universal and normalized technical support is provided for hierarchical construction and efficient deployment of virtual equipment in an intelligent manufacturing system.

The invention relates to a platform-based intelligent manufacturing MES system, and the system comprises a plan management module which is used for generating a production plan; the planning and scheduling module decomposes the production plan into specific operation tasks and generates an operation plan scheduling instruction; the document management module is responsible for managing and maintaining various documents involved in the production process; the operation management module converts an operation plan scheduling instruction of the planning and scheduling module into a specific production operation instruction; the automatic acquisition module acquires data of production equipment in real time and transmits the data to the plan management module in real time; the operation information module sends a control instruction to the automatic acquisition module, automatically acquires equipment working information, and feeds back the equipment working information acquired by the automatic acquisition module to the plan management module; and the material management module performs data interaction with the planning and scheduling module. Intelligent, automatic and fine management of the production process can be realized, and the system has important significance for improving the competitiveness of lithium battery copper foil production enterprises.

The invention provides a fault diagnosis method and system for operation and maintenance of an intelligent manufacturing system, and the method comprises the steps: firstly constructing an equipment association diagram which is composed of equipment component nodes and component association edges, then obtaining the operation monitoring data of each equipment component node, extracting node features, generating working condition time sequence features, and carrying out the operation monitoring of each equipment component node; meanwhile, edge features are extracted from operation monitoring data of nodes at the two ends of a component associated edge to generate cooperative change features, then a pre-trained graph reasoning model is called, fault propagation analysis is carried out on the equipment associated graph, the working condition time sequence features and the cooperative change features, and a fault propagation result containing an abnormal originating node identifier and a propagation path sequence is generated; and finally, based on the result, matching a historical fault case library, positioning a root cause component, generating an operation and maintenance scheme containing a maintenance operation sequence and parameter adjustment guidance, and pushing the operation and maintenance scheme to an equipment control system to trigger a fault repair operation, so that the fault can be accurately diagnosed, the root cause can be positioned, and the operation and maintenance scheme can be quickly generated. And the operation and maintenance efficiency and accuracy of the intelligent manufacturing system are improved.

The invention discloses an intelligent manufacturing system deadlock prediction method based on Petri-Net-GCN. The method comprises the following steps: dividing an intelligent manufacturing system into a production equipment module, a production process module and a production resource module; carrying out formalized modeling on the module on the basis of a Petri network; a Petri-Net-GCN deadlock prediction model is constructed, and the Petri-Net-GCN deadlock prediction model comprises a house-to-house transition message transmission module and a transition-to-house message transmission module; performing bidirectional aggregation updating on features among nodes in the Petri net graph by using a graph neural network structure; collecting initial Tokenn distribution, an incidence matrix and a deadlock label of the intelligent manufacturing system to construct a data set, and inputting the data set into a model for training; predicting a deadlock risk in an unknown system state by using the trained model; according to the method, rapid prediction and judgment are carried out in the current state of the intelligent manufacturing system, and prior early warning information is provided for production scheduling and resource configuration.

The invention provides a production scheduling method, device and equipment. The method comprises the following steps: acquiring real-time production data through an intelligent manufacturing system; determining constraint conditions of a target optimization model according to the real-time production data; obtaining a plurality of dimension production targets; determining a composite objective function according to the multi-dimensional production objective; determining a target optimization model according to the constraint condition and the composite target function; iteratively solving the target optimization model through at least one optimization model to obtain a target solution set; and controlling a production schedule module to output a target production schedule according to the target solution set. According to the invention, the scheduling quality and efficiency of the production line are improved, and the adaptability to the dynamic production environment is enhanced.

The invention discloses an intelligent manufacturing system and process for a corrugated steel cylinder fiber reinforced pipe structure, and relates to the technical field of industrial automatic control, the system comprises a real-time monitoring module used for monitoring the machining quality of a plurality of procedures, a central processing module used for carrying out instantaneous analysis on data of the real-time monitoring module and generating a regulation and control instruction, and a processing module used for processing the regulation and control instruction. On the basis of data collected by the real-time monitoring module and output of the central processing module, closed-loop control over the whole process from data collection and analysis to equipment adjustment is achieved, it is ensured that the quality parameters of all procedures are stabilized within the qualified range, and therefore the precision, high efficiency and intelligentization of the pipe manufacturing process are achieved; the problems that in the production process, manual control is dominant, all manufacturing procedures are relatively independent, and effective integration and collaboration are lacked are effectively solved.

The invention relates to the technical field of intelligent manufacturing and reinforcement learning, and discloses a causal-driven intelligent manufacturing strategy optimization method and system, and a medium. Comprising the following steps: collecting state information of an intelligent agent and a production environment, and constructing an environment data set and a zero action data set; constructing a causal decoupling dynamic model comprising a causal intervention module and an environmental evolution module; mixing the environment data set and the zero action data set, and training a causal decoupling dynamic model by using a first mixed data set; performing intervention simulation on the environment data set by using the trained causal decoupling dynamic model to obtain a model data set; mixing the environment data set and the model data set, and training an unbiased strategy optimizer by using a second mixed data set; and deploying the trained unbiased strategy optimizer into a production system, and driving an intelligent agent to execute production operation according to the state information. Through causal-driven modeling and unbiased strategy optimization, high-precision and high-reliability decision control of the intelligent manufacturing system in a complex dynamic environment is realized.

The invention relates to the technical field of scheduling, in particular to an artificial intelligence-driven intelligent manufacturing system scheduling method, which comprises the following steps of monitoring order state parameters of a manufacturing execution system in real time, identifying equipment failure shutdown signals or order insertion signals, extracting associated equipment codes and current work order numbers, and establishing core disturbance information pairs. According to the method, the order state parameters of the manufacturing execution system are monitored in real time, the equipment fault shutdown signal and the order insertion signal are dynamically identified, and the equipment code and the current work order number are extracted, so that the core disturbance information pair highly associated with the disturbance source can be constructed, and the pertinence and accuracy of the scheduling process response are ensured. And in combination with the original plan completion time of the affected process, evaluating local delay caused by disturbance, gradually deducing to form the delay amount of the whole plan, describing the diffusion trend of the disturbance in the production progress, and defining a scheduling adjustment time window.

Data centric smart manufacturing systems are described. In an embodiment, the data centric smart manufacturing system includes several systems providing raw data, several reusable data model profiles that ingest the raw data and contextualize the raw data, where a data model profile defines contextualized data, configurations, and data connectivity protocols for a particular type of system, and several data transformation models integrated with the data model profiles and instantiated with contextualized data to provide higher level operational insights.

The invention discloses a multi-channel Ethernet and TTP data conversion hardware platform. The multi-channel Ethernet and TTP data conversion hardware platform comprises a core processing module, a network data interface module, a TTP data interface module, a configuration and storage module, a power module, a clock module and a monitoring module. According to the invention, a more reliable and more efficient data conversion and transmission hardware platform can be provided for industrial intelligent manufacturing and system-level power management. The core processing module adopts FPGA + ARM isomerism, so that efficient protocol data conversion, high-speed data analysis and calculation and interface type interaction functions can be realized, and high efficiency of operation is ensured; the network interface module and the TTP data interface module can realize multi-channel data transmission of a network layer and a physical layer, so that the reliability of the data is ensured; and the configuration and storage module can realize storage of configuration information and monitoring acquisition data, so that the effectiveness of the information is protected. Compared with a traditional data conversion platform, the data conversion platform has the advantages of reliable protocol conversion, high function expansibility, large storage space, low data processing delay and the like.

A Comprehensive Energy-Saving and Carbon-Negative system (CESCN) includes a Carbon-negative Emissions Device (CED) based on Carbon Capture, Utilization and Storage (CCUS). CED can obtain a carbon emission reduction target from a current Industry 4.2-Green intelligent Manufacturing (14.2-GiM) system, and then collect the material consumption and equipment operation energy consumption data of the CCUS process of CED through a Cyber Physical Agent (CPA) which is the Internet of Things (IoT) component. An intelligent method is used to identify the execution progress of CCUS and improve the automation and intelligent operation of CCUS. The CESCN can effectively reduce the manpower requirements of implementing CCUS and the overall energy consumption of the production line. In addition, it can calculate the amount of the carbon reduction, the amount of the carbon offset and amount of feasible carbon trading according to the amount of carbon fixation.

The invention discloses a quartz crystal oscillator quality analysis method and system based on big data of an intelligent manufacturing system, and relates to the technical field of quartz crystal resonators. Appearance images and electrical performance parameters of all batches of quartz crystal oscillators are obtained from detection equipment, and appearance quality is judged according to appearance image parameters through an appearance quality judgment model; qualified products enter an electrical performance quality judgment link. By calculating electrical performance quality characteristic values such as a mean value, a standard deviation, a range and a target value, quality stability evaluation indexes such as a target fluctuation value and an overall discreteness value are obtained, and the electrical performance quality is judged by means of an electrical performance quality judgment model. Unqualified batches are substituted into a further analysis model to judge whether abnormity can be detected, screened and removed again or not, if yes, redetection is carried out according to a new detection rule, otherwise, relevant parameters are sent to technicians, and meanwhile recycling treatment is carried out.

The invention relates to the technical field of intelligent manufacturing control, and discloses a dynamic continuous polymerization and online block regulation and control method and system for a polyurethane hot melt adhesive. The invention aims to solve the technical problems of long formula development period, black box in the process and poor batch stability in the traditional polyurethane reaction extrusion process. According to the method, a closed-loop adaptive control system of virtual simulation guidance and physical data correction is constructed, so that intelligent optimization from target performance to an optimal process is realized. The core of the method is that space-time alignment of full-cycle data is realized by utilizing a material retention time distribution function, and internal parameters of an aggregation kinetic model are reversely corrected and a formula knowledge base is updated based on actually measured evolution data and theoretical prediction deviation characteristics. By constructing an intelligent manufacturing system with transparent perception and accurate regulation and control, the formula development efficiency and the product quality consistency are remarkably improved, and the self-adaptive regulation capability in the production process is greatly enhanced.

The invention discloses a multi-algorithm collaborative optimization water turbine key component additive manufacturing method, and relates to the technical field of additive manufacturing. According to the method disclosed by the invention, a complete intelligent manufacturing system is constructed: in a data acquisition stage, a high-precision laser scanning technology (the precision reaches 0.01 mm) is adopted to realize accurate three-dimensional reconstruction of a damaged area; in the modeling analysis link, thermodynamic behaviors in the restoration process are accurately predicted through finite element simulation of multi-physics field coupling; in the aspect of process optimization, an adaptive differential evolution algorithm, an improved NSGA-II multi-objective optimization algorithm and deep reinforcement learning (DRL) are innovatively and organically combined to form a full-process intelligent decision-making system for coverage deviation analysis, path planning and parameter optimization. Particularly, due to introduction of a deep reinforcement learning algorithm, millisecond-level dynamic adjustment of key process parameters such as wire and powder feeding speed and laser power is achieved, and the stability and the material utilization rate of the manufacturing process are greatly improved.

The invention discloses an intelligent manufacturing production line practical training system based on digital twinning and a virtual-real cooperative control method. The system comprises a physical execution layer which comprises a stereoscopic warehouse used for workpiece storage and positioning, an annular conveying line used for workpiece circulation, a visual inspection table used for workpiece identification and a robot used for workpiece transfer; the control layer comprises a PLC main control unit and a man-machine interaction unit and is used for realizing equipment cooperative control and operation monitoring; and the digital twin layer comprises three-dimensional virtual models corresponding to the devices in the physical execution layer, realizes bidirectional data interaction with the physical execution layer through a communication protocol, and supports virtual-real cooperative control and fault simulation. According to the invention, a practical training environment is constructed in a virtuality and reality combination mode, and the cognition, programming and maintenance capabilities of students on the intelligent manufacturing system are cultivated.

The invention relates to a flexible intelligent manufacturing system based on AI intelligent control. The flexible intelligent manufacturing system comprises a rack, a first working module, a second working module, a position detection unit and a control unit. The rack is provided with a standard interface group; the first working module is provided with a module interface group, the standard interface group is matched with the module interface group to enable the first working module to be detachably installed on the rack, and the module interface group and the standard interface group have the same matching size and connection form to achieve interchange of working modules of the same type or different types. The control unit is configured to obtain an offset change vector in a first unit time according to the real-time position data, and predict a predicted offset of a first time node according to the offset change vector; and if the predicted offset exceeds a first preset threshold value, performing prevention operation on each working module. The working module is adjusted in advance according to the predicted offset, and the problems of continuous production interruption and safety caused by position offset of the working module are effectively solved.

The invention relates to the technical field of intelligent manufacturing system design, and discloses an intelligent manufacturing production line automatic design method and system based on a large model, and the method comprises the steps: building a semantic understanding engine through a pre-training large language model, and converting user unstructured text input into a standardized design element set; based on the process knowledge graph and the product manufacturing feature library, performing process path reasoning and task level disassembly by using a graph neural network, and disassembling the standardized design element set into a plurality of sub-tasks; constructing an equipment capability database, realizing automatic matching of a plurality of subtasks and equipment through vectorization similarity retrieval and a multi-objective optimization model, and outputting a recommended equipment combination list; based on the recommended equipment combination list and the spatial constraint condition, a digital workshop sketch is established by adopting a 3D spatial modeling module, the equipment layout and the logistics path are optimized by applying a genetic algorithm, and an optimal layout scheme set is output; according to the invention, intelligent design and optimization support of the whole life cycle are provided.

The invention relates to a flexible intelligent manufacturing system which comprises a rack and a plurality of working modules. And a first standard interface group is arranged on the mounting surface of the rack. A first module interface group is arranged at the bottom of each working module, the first standard interface group is matched with the first module interface group to enable the working module to be detachably mounted on the rack, and the first module interface group and the first standard interface group have the same matching size and connection form; therefore, the working modules of the same type or different types can be exchanged. Wherein the feeding module comprises a feeding module body and a plurality of special pickup assemblies, the feeding module body comprises a second standard interface group, each special pickup assembly is provided with a second module interface group, and the second standard interface group is matched with the second module interface group so that the special pickup assemblies can be detachably installed on the feeding module body. According to the flexible intelligent manufacturing system, the working module is set to be integrally replaced to be matched with local replacement of the special pickup assembly, and the universality of the equipment is further improved.

The utility model discloses an industrial control board based on STM32F103 singlechip, it includes main control chip, RS 485 level conversion circuit, digital I / O circuit and LED pilot lamp, and RS 485 circuit realizes efficient level conversion through three stage anti -interference framework magnetic pearl filtering, photo -coupler isolation, TVS protection, and digital I / O circuit adopts photo -coupler and isolation amplifier to enhance signal stability, and is equipped with LED pilot lamp feedback state, and the application effectively reduces the code rate less than 10 ‑7 , reduces signal dithering, and the temperature drift attenuation is only 2.1%, is suitable for industrial automation and intelligent manufacturing system, has simple structure, low in cost, stable performance and the advantages such as.

1. The name of the design product: programmable controller (VG700). 2. The use of the design product: used for switch logic control, analog control, motion control, process control, data processing and networking communication of intelligent manufacturing system equipment in automated production. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.

The present invention discloses a method and system for quartz crystal oscillator quality analysis based on big data of intelligent manufacturing systems, which relates to the technical field of quartz crystal resonators. The present invention obtains the appearance images and electrical performance parameters of each batch of quartz crystal oscillators from detection equipment, uses an appearance quality judgment model to judge the appearance quality based on the appearance image parameters, and qualified products enter the electrical performance quality judgment link. By calculating electrical performance quality characteristic values such as mean, standard deviation, range, target value, etc., quality stability evaluation indicators such as target volatility value and overall discreteness value are obtained, and an electrical performance quality judgment model is used to judge the electrical performance quality. For unqualified batches, they are brought into a further analysis model to determine whether they can be re-detected and screened to eliminate abnormalities. If so, they are re-inspected according to the new detection rules, otherwise the relevant parameters are sent to technical personnel, and at the same time, recycling treatment is carried out.

The invention relates to the technical field of collision sensing devices, and discloses a collision sensing device for an industrial robot capable of being conveniently installed, the collision sensing device comprises at least one collision sensing module, at least one data processing module, a shell and a quick release type adhesion fixing mechanism, the collision sensing module is used for detecting collision and outputting capacitance information; the data processing module is used for collecting and processing capacitance information output by the collision sensing module; the shell comprises a sensing end shell, a sensing and processing end shell and a processing end shell, collision sensing modules are installed in the sensing end shell and the sensing and processing end shell, and data processing modules are installed in the sensing and processing end shell and the processing end shell; the quick-release adhesion fixing mechanism is used for fixing the sensing end shell, the sensing and processing end shell and the processing end shell to the surface of the industrial robot, real-time and accurate sensing of the collision behavior of the industrial robot is achieved, and the safety and reliability of the intelligent manufacturing system are improved.

This invention discloses a method for processing multimodal data acquisition in intelligent manufacturing systems, relating to the field of industrial data governance technology. The method includes: acquiring multimodal data streams; segmenting raw data blocks and standardizing and encapsulating them to generate metadata records; establishing time indexes, batch indexes, and process indexes; hashing the metadata records to generate content addresses and writing them to object storage; recalculating the hash and comparing the content addresses to complete consistency verification and writing the results to a commit log table; generating operator records for successfully committed data blocks and hashing them to obtain operator addresses; registering lineage edges to form directed acyclic lineage relationships; generating leaf lists according to a preset range and aggregating them to obtain root digests; verifying content addresses object by object based on the leaf lists and root digests; replaying and recalculating to generate replay-derived data blocks; comparing them to generate audit records and storing them. This invention ensures continuous monitoring of data quality during big data acquisition through the replay and recalculation processing of directed acyclic lineage relationships.

Intelligent manufacturing systems for the optimized curing of adhesives for battery assemblies, methods for manufacturing / using such systems, and stored instructions for automating the operation of such systems are presented. One method for assembling a battery module involves aligning a stack of battery cells on a workpiece carrier and compressing the cell stack to a predefined length. Module housing side plates are positioned on opposite lateral sides of the compressed cell stack, and a thermosetting structural adhesive (SAM) is injected between the side plates and the lateral sides of the cell stack. A conductive heating system heats the module housing side plates to cure the SAM. While the side plates are heating, a cell thermal conditioning system cools a selected surface of the compressed cell stack.After determining that a monitored curing time has reached a predefined curing time, the system interrupts the heating of the side plates and the cooling of the battery cells.

The application discloses an industrial full-link through implementation method based on unique identification and double contract anchoring, and belongs to the technical field of intelligent manufacturing informatization. The method takes a plan number as a unique and unchangeable identification throughout the full life cycle from raw material warehousing to finished product warehousing, takes a contract hash value as a cross-table association anchor point, adopts a step-by-step anchoring mechanism of sales contract priority binding and procurement contract subsequent binding, and combines batch processing, transaction safety control and full-chain backtracking synchronization technology to realize bidirectional synchronous updating of procurement and sales contract information in full life cycle data tables such as raw material inventory tables and production process quality inspection record tables. The application breaks the strong coupling of the procurement and production processes, supports cost information post-recording, solves the pain points of data disconnection, untraceability, low efficiency and maintenance difficulty of traditional industrial software, has a simple architecture, high performance and stable operation, and is suitable for various intelligent manufacturing systems such as MES and ERP. The application has been applied in actual industrial scenes and has industrialization popularization capability.

The invention relates to the technical field of additive and subtractive integrated intelligent manufacturing, and discloses an intelligent manufacturing system and method for coaxial feeding, stirring and friction solid-phase additive-subtractive machining integrated equipment. And efficient additive deposition and precise subtractive machining can be achieved on one equipment platform. A metal material is fed into a friction stir head through a coaxial feeding device, surface finishing and surface layer removal are carried out through a material reducing module while additive manufacturing is carried out through solid heating and plastic deformation technologies, surface, interlayer and internal structure performance regulation and control are carried out in combination with needle-free friction stir treatment and synchronous induction heating rolling, and the mechanical property of the metal material is improved. The problems of precision, surface quality and production efficiency which cannot be independently achieved through single additive manufacturing or subtractive machining are solved, efficient utilization of materials can be achieved in manufacturing of high-performance and large complex structural parts through the additive and subtractive composite technology, and meanwhile the forming precision and the mechanical property are guaranteed.