146 results about "Smart factory" patented technology

The invention particularly relates to an intelligent factory integrated operation management method based on multi-system integration, and relates to the technical field of intelligent factory operation management. Performing intelligent planning and robustness decision making; performing production execution and monitoring; and carrying out equipment full-life-cycle management. According to the method, the limitation of a traditional static plan is thoroughly broken through through a collaborative mechanism of multi-dimensional risk index linkage, dynamic time buffering and a plan chain; on one hand, the DTB performs real-time calculation based on a supply chain risk index, an equipment health index and a process stability index, approaches reference buffer to avoid resource waste when the risk is low, automatically expands to absorb disturbance when the risk is high, and ensures dynamic balance of plan efficiency and disturbance resistance; and on the other hand, the pre-generated plan chain is rapidly triggered when the disturbance exceeds the limit, global rearrangement is not needed, and continuous production can be guaranteed only through local adjustment.

The invention provides a digital smart factory equipment operation management system based on deep learning, and the system comprises a data collection module, a data preprocessing module, a feature engineering module, a model training and fusion module, a dynamic optimization module, a fault judgment and early warning module and a data storage module which are in communication connection in sequence. According to the method, by providing a multi-algorithm fusion deep learning model architecture and integrating the advantages of time sequence prediction and a nonlinear classification model, the problem that complex data association cannot be mined by a single algorithm is solved, a precise data processing scheme adaptive to industrial data characteristics is designed, and the data quality and the characteristic discrimination degree are improved; and by constructing a model dynamic optimization mechanism, the problem of poor model generalization ability is solved, early-stage accurate early warning of faults is realized, the early warning advance time is prolonged, the non-planned shutdown probability is reduced, the real-time performance and robustness of the system are improved, and the method is adaptive to high-noise industrial scenes.

The utility model belongs to the technical field of furnace slag treatment, particularly relates to an AI identification automatic dust removal robot for a furnace slag treatment smart factory, and aims to solve the problems that furnace slag in a furnace is difficult to completely move out in the process of moving the furnace slag out of the furnace at present, and the furnace slag in the furnace is accumulated during long-time use, so that the furnace slag in the furnace cannot be completely removed. In order to solve the problems that in the prior art, ventilation in a stove is not smooth enough, and normal combustion of coal briquettes is affected, according to the scheme, the stove comprises an electric crawler-type base, a mounting box is welded to the top of the electric crawler-type base, a door plate is hinged to an opening in one side of the mounting box, and a vacuum pump is fixedly mounted on one side of the top of the electric crawler-type base through bolts; according to the furnace slag collecting device, the suction pipe can be transferred into the furnace, furnace slag stored in the furnace can be sucked out and collected into the net cage in a centralized mode, and therefore the furnace slag contained in the furnace can be conveniently and rapidly collected in the centralized mode in the actual use process, and the furnace can work stably and continuously.

The invention discloses a multi-module collaborative integration method based on an intelligent factory management and control system, particularly relates to the technical field of intelligent manufacturing, and is used for solving the problem of cross-module control inconsistency caused by the fact that an interface receipt is not equivalent to an actual state to take effect in the prior art. The method comprises the following steps: receiving a control intention, generating a cooperative control transaction risk index, packaging the cooperative control transaction risk index into a control transaction recording unit, and allocating a unique identifier and an idempotent key; after cross-module consistency check is executed, a control instruction is issued, a preparation receipt and an acceptance receipt are collected, and a to-be-validated verification state is entered; in the allowable effective time window, constructing an execution effective evidence chain based on the equipment and service state evidence, calculating a control effective confidence coefficient index and judging an effective result; and performing compensation rollback and consistency recovery on the effective abnormal transaction, and updating the execution reliability portrait. According to the invention, the observable evidence is used for replacing the receipt as a closed-loop basis, so that the verifiability, rollback performance and traceability of cross-module linkage control are improved.

The invention provides a business processing method of a smart factory platform based on a Beidou grid code, and the method comprises the steps: carrying out the multi-stage grid subdivision of a factory physical space through the Beidou grid code, and generating a unique grid code; the grid coding adopts an integer format to represent position information; equipment sensor data, personnel positioning data and business logic data are bound with the grid codes, and a space-time joint index table is constructed; performing real-time deviation correction on the positioning data through a grid neighborhood topological relation and personnel moving speed constraint to generate a high-precision positioning track; and mapping the service logic to the grid codes through a rule engine, and triggering automatic operation according to grid attributes. Traditional floating point latitude and longitude coordinates are replaced by integer coding, data calculation efficiency is optimized through bit operation, cross-level business association and fast path planning are supported, and business response efficiency is improved.

The invention discloses an intelligent factory data monitoring method and system based on distributed collaborative sampling, belongs to the field of intelligent factory data monitoring, and aims to solve the problems of real-time monitoring, quality control, equipment maintenance and production optimization in the production process. The system is composed of a data acquisition module, a production control module, a local processing module, a data center module and a user interaction module. And efficient data processing and storage are realized through the distributed collaborative sampling network, and the expandability and flexibility of the system are optimized. The production management and control module is responsible for distribution and sampling detection of production tasks, ensures product quality and realizes production continuity when equipment is abnormal. The local processing module analyzes equipment data, establishes a prediction model, and timely finds and early warns deviation in equipment and production. The data center module analyzes early warning production data in real time, transmits an early warning signal through a central node, and drives a production line to operate. And the user interaction module provides dynamic information updating, so that a user can obtain and feed back data in real time.

The invention relates to the technical field of industrial Internet of Things and edge computing, and discloses an edge-end cooperative computing task unloading method and system for an intelligent factory, and the method comprises the steps: building a task unloading decision mechanism of a multi-device multi-edge server, distributing a computing node for each task, determining task delay, and constructing a node speciality matrix; establishing an optimization model; formalizing an optimization problem of the optimization model into a Markov decision process; solving a Markov decision process by using a deep reinforcement learning algorithm, and realizing intelligent workshop environment interaction so as to store generated empirical data into an empirical cache region; synchronously updating network parameters of the deep reinforcement learning algorithm and a node speciality matrix corresponding to the edge server by using the data pairs of the experience cache region; and outputting a strategy network and a node speciality matrix until the deep reinforcement learning algorithm converges. And an optimal task allocation decision is dynamically generated, so that the task completion deviation is effectively reduced.

The invention discloses a smart factory production scheduling and energy supply collaborative optimization method and system integrated with clean energy, particularly relates to the technical field of industrial process control, and is used for solving the problems of insufficient consumption of clean energy and reduction of production efficiency caused by neglecting of production flow sequential logic in the prior art. The method comprises the following steps: calculating a carbon-energy collaborative efficiency index by acquiring energy consumption data, production tasks and clean energy supply information in an industrial production process, judging whether clean energy supply meets a production scheduling requirement, and if not, constructing a directed graph network model of the production tasks and calculating propagation betweenness centrality; key paths are identified, key time sequence conflict points are positioned, system core output performance attenuation caused by all the key time sequence conflict points is simulated, function toughness loss is quantified in the recovery process, the priority is determined, and finally the execution sequence and time sequence of corresponding production tasks are sequentially adjusted according to the priority. The invention aims to minimize time sequence conflicts and maximize clean energy consumption.

This utility model relates to an integrated support and storage structure for lightweight testing equipment in smart factories, belonging to the technical field of support and storage devices. It includes an upper housing and a lower housing, with one end of the upper and lower housing rotatably connected and the other end connected by a latch. The lower housing has a storage slot inside, and the upper housing has a placement slot inside. A baffle plate is slidably engaged inside the upper housing. Telescopic legs are rotatably installed on one side of the upper and lower housings. A handle is engaged at the middle of the ends of the upper and lower housings. The upper and lower housings facilitate the storage and transport of testing equipment and accessories. In use, by unfolding the four telescopic legs, the upper and lower housings form a tabletop support. The baffle plate and extension plate further increase the placement area during support, making it convenient for using testing equipment in a smart factory.

The application provides an industrial internet platform and a manufacturing execution method and system for a smart factory, comprising: obtaining a charge release rate of a residual electrostatic field according to a dust removal voltage amplitude through an adjusted static time range, calculating a matching value of the charge release rate and a static time length by using a linear interpolation algorithm, and obtaining an optimized charge release time sequence; adopting an equalization adjustment scheme of paint mist attraction distribution, combining the uniformity of paint mist aggregation on convex and concave parts of a workpiece curved surface, obtaining a real-time coating thickness of a spraying area, and obtaining a distribution map of coating thickness uniformity; and according to a final synchronous optimization result, obtaining feedback of an electric field strength monitoring module deployed in the industrial internet platform, analyzing the completion degree of charge release of a low-conductivity workpiece, and obtaining a stable control value of the dust removal voltage amplitude.

This invention provides a fault early warning method for low-voltage power distribution systems in smart factories, belonging to the field of low-voltage power distribution fault early warning technology. Based on the low-voltage power distribution system topology, it deploys synchronous current and voltage acquisition terminals and ambient temperature sensors to acquire real-time current waveforms, voltage sag events, neutral current values, and ambient temperature for each circuit. The real-time current waveforms are decomposed into harmonic sequences using Fourier transform, generating a harmonic spectrum distribution matrix. A joint probability table of voltage sag and neutral overcurrent events is constructed by correlating timestamps. Combining the harmonic amplitude growth trend with the characteristics of coupled events whose joint occurrence probability exceeds a set threshold, a candidate circuit set for insulation degradation risk is screened, and temperature field inversion calculation is performed to generate a conductor surface temperature rise distribution map. This method can quantify the temporal coupling relationship between the two types of events, narrowing the fault investigation scope, reducing false alarms and missed detections, accurately reflecting the insulation degradation state of the circuits, and achieving accurate fault early warning for low-voltage power distribution systems.

The invention discloses a distributed data processing method and system for an intelligent factory, and relates to the technical field of communication data processing. Determining target equipment according to the original data; based on the centrality index of the target equipment in the factory equipment topological graph, calculating the centrality index to obtain a topological criticality score; analyzing the original data based on a preset rule base to obtain an event severity score; multiplying the topology criticality score by the event severity score to obtain a final priority; inserting the original data into a priority scheduling queue according to the final priority; the storage nodes with the resource loads lower than a preset health threshold value are summarized into a current available node pool; and taking out the target data with the highest final priority from the head of the priority scheduling queue, selecting a storage node with the lowest resource load from the current available node pool as a target storage node, and preferentially distributing the target data to the target storage node for processing. By implementing the technical scheme, priority processing of high-value data is ensured.

The application relates to the technical field of knowledge engineering, and discloses a production and manufacturing digital twin modeling method based on a knowledge graph, which comprises the following steps: performing data fusion and model construction on original multi-source data, obtaining multi-source fusion data, and generating a digital twin architecture; performing ontological design and semantic modeling on the multi-source fusion data, and generating a manufacturing knowledge graph; wherein the manufacturing knowledge graph is represented by triplets, and the triplets comprise entities-relation-entities / attributes; performing entity modeling on the manufacturing knowledge graph, and obtaining a knowledge-driven geometric model; and performing reasoning based on the manufacturing knowledge graph and historical data, and obtaining a knowledge-driven decision model. The method can construct a digital twin model with knowledge-driven prediction and decision-making capabilities, and provides a high-robustness and sustainable-evolution digital twin modeling method for intelligent manufacturing, smart factories and other fields. The application also discloses a production and manufacturing digital twin modeling device based on the knowledge graph and an electronic device.

The application discloses a kind of intelligent factory blockchain anomaly detection methods, including steps: S10, according to the federation learning under the scene of intelligent factory blockchain, use the local model of each participating node itself, let each local model participate in the update of cloud global model, and the pre-training model is aggregated;S20, again based on pre-training model, training obtains global anomaly detection model;In the training process, the sensitive information of participating node in the training process is protected using privacy protection method;S30, after obtaining global anomaly detection model, the model is used to screen the abnormal state on the intelligent factory blockchain.The application proposes a new blockchain anomaly detection method based on federation learning, which can secretly aggregate the trained user model without revealing the user model.It also has effective fault tolerance capability for user disconnection.The protocol can be executed normally when a large number of users are disconnected during operation.

1. The name of the design product: graphical user interface of smart factory production monitoring board for electronic equipment. 2. The use of the design product: an electronic device. 3. The design points of the design product: the content of the graphical user interface. 4. The picture or photo that best indicates the design points: front view. 5. The use of the graphical user interface: for the production monitoring board of the smart factory. 6. The human-computer interaction mode of the graphical user interface: the front view is the initial interface of the operating system, the left side of the front view displays the options of different production lines, the right side of the front view displays the current displayed production line operator and the related information of the charging pile being produced, and the above data is updated in real time.

A debugging system for software and hardware integration and a debugging method thereof belong to the technical field of Internet of Things, are used for solving the problems of long integration construction period and repeated debugging caused by software and hardware integration linear development, are arranged in parallel between hardware debugging and software online, and comprise an SCADA module and a PLC module, data interaction can be carried out between the two modules; the SCADA module receives the production data from the PLC module and transmits the received production data to a production management and control system to be debugged; the PLC module simulates the operation process of a production operation node through automatic programming and outputs corresponding production data for the SCADA module to collect, and simulation debugging of hardware and software needing to be integrated is achieved through data interaction of the two modules. The method is used for debugging and verifying the matching and coordination operation between the integrated software and hardware, the synchronous development of hardware debugging and hardware and software integrated debugging is realized, and the debugging period of intelligent factory construction is greatly shortened.

1. The name of the design product: factory quality test area data dashboard graphical user interface for electronic equipment. 2. The use of the design product: an electronic device. 3. The design points of the design product: the graphical user interface content in the screen. 4. The picture or photo that best indicates the design points: front view. 5. The use of the graphical user interface: to display the dashboard of the digital smart factory quality test area data, and to view the quality test status in real time. 6. The human-computer interaction mode of the graphical user interface: the front view is the initial interface of the operating system, the left side of the front view displays the options of different shelves, the right side of the front view displays the charging pile related information on the currently selected shelf, and the above data is updated in real time; clicking on any charging pile option in the right front view will enter the interface change state diagram.

The application discloses an intelligent Internet of Things gateway system supporting edge computing deployment functions, and relates to the technical field of Internet of Things application.The gateway has wide adaptability, can be applied to various application scenarios such as intelligent factories, smart homes and smart agriculture, realizes end-to-end capability from a sensing device to an application, guarantees data independence and security, can flexibly deploy functions in gateways of different levels according to requirements, provides edge computing capability, supports unified access of heterogeneous devices, provides various deployment modes, and is high in flexibility, dynamically establishes a route between data and an application, realizes flexible integration of data transmission and processing, and realizes loose coupling between Internet of Things applications and between Internet of Things applications and the gateway.

A smart factory energy efficiency optimization system and method based on digital twin technology. The system comprises a smart factory visualization module, an energy consumption preprocessing module, an energy consumption prediction module, and energy efficiency control module. A predicted operating time of a device for the day is obtained on the basis of a production speed of the device and a production quantity for the day in a real-time production schedule plan; recovered energy of the device for the day is predicted on the basis of the predicted operating time; the recovered energy for the day is then added to original stored energy in an energy recovery system to obtain actual available energy that the energy recovery system can provide for the day; the actual available energy is compared with tiered energy consumption of tiered devices for the day; and corresponding control signals are obtained on the basis of a comparison result. Therefore, recovered energy can be supplied to the tiered devices, maximizing energy utilization efficiency while minimizing the number of times of switching an energy supply mode, thus ensuring the stability of energy supply during operation of a production device.

The invention discloses an indoor base station communication and sensing integrated antenna layout structure and system, and belongs to the technical field of wireless communication and sensing fusion. The structure comprises an annular substrate (1), M communication antenna units (2) and N sensing antenna units (3), and the M communication antenna units and the N sensing antenna units are alternately and sparsely arranged along the circle of the annular substrate. The communication unit adopts horizontal polarization, and the working frequency band is below 6GHz; the sensing unit adopts vertical polarization, and the working frequency band is 24-30 GHz; a signal processing module (4) is arranged in the center. Through triple mechanisms of spatial isolation, polarization orthogonality and frequency band dislocation, the coupling isolation degree of the inductive signals is larger than or equal to 28 dB, 180-degree blind-area-free coverage is achieved, the personnel positioning error is smaller than 0.3 m, and communication and sensing concurrency are supported. The system is compact in structure, can be directly integrated in an existing indoor pico base station, and is suitable for smart factories, shopping malls, hospitals and other scenes. Actual measurement data shows that the sensing refresh rate is increased to 120 Hz, and the communication error rate is reduced to 1e-6 magnitude.

The invention relates to the technical field of machine vision, and particularly discloses a workpiece visual identification system for an intelligent factory. The system comprises a multi-modal data acquisition module, a feature extraction and fusion module, a three-dimensional space reconstruction module, a dynamic identification decision-making module and a system control and output module. And high-precision and high-reliability identification and positioning of the identity and the pose of the workpiece are realized.

This invention discloses a machine learning-based method for visualizing smart factory production data, comprising the following steps: acquiring and preprocessing production data to form window samples, condition vectors, and target sequences; encoding to generate a shared representation sequence; generating a set of working condition color band segments from a color band segment generation structure; outputting a candidate set of beat rates and yield rates from a six-expert trend syntax tree generation structure; applying cross-KPI linked visual syntax and adjudicating fusion to obtain a trend syntax tree and interval band prototypes; performing syntax consistency calibration to output calibration interval bands and correction instructions; and generating intelligent visualization results. This invention utilizes shared representation encoding, working condition color band segment generation, and six-expert trend syntax tree linked calibration to achieve structured intelligent visualization of beat rates / yield rates, possessing advantages such as stable readability, cross-KPI consistency, and traceable correction.

A man-machine collaborative quality detection and early warning system for intelligent factories, comprising an edge visual acquisition terminal, a cognitive anchor generation module and a hybrid intelligent inference engine, the hybrid intelligent inference engine extracts a high-dimensional feature vector of a workpiece image using a residual network and calculates a Mahalanobis distance. When the distance is in a fuzzy decision interval, a man-machine collaboration request is triggered, and a feature heat map is displayed on the terminal. The cognitive anchor generation module receives defect key pixel points labeled by an operator, maps them to a high-dimensional feature space to construct a feature repulsion sphere, and adds the feature repulsion sphere as a regularization term to the loss function of the residual network for online fine-tuning. The scheme corrects the feature boundary in a targeted manner without changing the weight distribution of the model main body, overcomes long-tail defect missed defects, and improves the feature boundary stability of the detection model under continuous production conditions.

The application discloses a plant intelligent factory multidimensional data monitoring and collaborative control method and system, and belongs to the technical field of collaborative control. The method specifically comprises the following steps: collecting multidimensional data of a plant intelligent factory in real time, wherein the multidimensional data comprises plant physiological parameters, environmental factor parameters, nutrient solution parameters, and device and operation state parameters; based on the multidimensional data, a dynamic multi-level causal correlation model between devices, plant physiology, environment and operation is constructed; potential collaborative influence paths in an abnormal state are identified; when an abnormality is detected or a growth process deviates from a trend is predicted, cross-level control is automatically performed; cross-level control instructions are distributed to the device level, the cultivation unit level and the workshop level according to the levels; and the plant intelligent factory is subjected to multi-link joint regulation and control. Through the establishment of the collaborative mechanism of the causal correlation and the path, the regulation and control are more accurate, flexible and adaptive, and the stability, resource utilization rate and intelligent level of plant production are effectively improved.

The present invention relates to a mixed system for a culture process and a purification process for preparing an antibody pharmaceutical, in which at least one device selected from a bioreactor, a chromatography device, and a filtration device is made of at least one material selected from a single-use (SU) bag and stainless steel (SS), at least one device selected from a preparation tank and a storage tank for a culture medium and a buffer is made of an SS material, thereby simultaneously obtaining the advantages of an SS process system and an SU process system, cross contamination can be prevented by independent operation of a culture unit and a purification unit, and a process system is designed to be arranged so that outflow from the separate culture unit is caused to flow into at least one purification unit by using a control part to prevent a bottleneck phenomenon in the purification process, whereby, when the mixed system is used in the preparation of an antibody pharmaceutical, the economic efficiency and efficiency of the process can be improved, and a more efficient smart factory can be realized.

The invention discloses an intelligent factory control system and method based on a distributed architecture. The control system comprises a production control unit and a data processing and storage unit, the production control unit controls production equipment of the intelligent factory; the data processing and storage unit comprises a data acquisition assembly, a data pre-aggregation assembly and a database, and the data pre-aggregation assembly is used for performing pre-aggregation processing on the original production data acquired by the data acquisition assembly to form structured production data and writing the structured production data into the database for storage. The control method is implemented by adopting the control system. According to the method, the data writing performance is remarkably improved, the real-time writing bottleneck is avoided, the efficient operation of the system is ensured, the reliability and stability of the production system are improved, the single-point fault risk is reduced, the safety of data assets and the stability and performance of a production core database are enhanced, and the intelligent level and the operation efficiency of a factory are improved.

The invention relates to the technical field of factory operation and maintenance, in particular to an intelligent factory operation and maintenance scheduling method and system based on multi-source data. The method comprises the following steps: acquiring optimized data streams of all operation equipment based on a factory sensor network; performing equipment state operation analysis on the optimized data stream to generate an equipment real-time operation curve; performing fault prediction and shutdown maintenance planning according to the real-time operation curve of the equipment, and outputting a shutdown time point; calculating a shutdown period productivity gap index based on the shutdown time point to generate a productivity gap index; and carrying out capacity compensation analysis and production line scheduling planning according to the capacity gap index, and generating a multi-device scheduling instruction. According to the method, predictive maintenance and dynamic productivity optimization from equipment level to system level of the intelligent factory are carried out, and the operation and maintenance efficiency and the overall production stability of the factory are improved.

The invention discloses an intelligent material transportation control system of a smart factory, and relates to the technical field of factory material transportation, the intelligent material transportation control system comprises an acquisition assembly, a processing assembly, an analysis assembly and a control assembly, the analysis assembly comprises a priority unit, a path adjustment unit and a comprehensive adjustment unit, and the control component performs task scheduling execution, path tracking and dynamic adjustment and speed real-time adjustment based on the data input by the analysis component. The priority unit evaluates the task priority in combination with dominant indexes and implicit quality influences, the path adjustment unit introduces a path space-time multiplexing coefficient to optimize multi-task path resource multiplexing, the speed adjustment unit is associated with a component fatigue accumulation dynamic adjustment speed, the three units cooperate to form a closed loop, intelligent decision making of the material transportation system is achieved, and the efficiency of the system is improved. Efficiency, production quality and equipment health are guaranteed, and requirements of smart factories are met.

The application relates to the technical field of information management, and provides a smart factory production line management and control method, device, equipment and medium, the method comprises the following steps: acquiring working data streams and category information corresponding to a plurality of production devices on a production line in a smart factory; obtaining a target state judgment rule according to the working data streams and the category information corresponding to the plurality of production devices; performing state judgment on the working data streams corresponding to each production device according to the target state judgment rule to obtain a state judgment result corresponding to each production device; performing fault trend prediction on the production line according to the state judgment result corresponding to each production device to obtain a target fault trend; and generating a production line maintenance plan according to the target fault trend, so that the plurality of production devices on the production line can be maintained according to the production line maintenance plan. The scheme in the application improves the stability and efficiency of the production of the production line in the smart factory.

The application provides a sampling marking method, device, equipment and storage medium, and belongs to the technical field of smart factory. The method comprises the following steps: receiving sampling information sent by a management unit, wherein the sampling information comprises a sampling production line; acquiring a real-time position and a target position corresponding to the sampling production line in each sampling information; arranging and outputting at least N pieces of sampling information according to the real-time position and the target positions, wherein N is a positive integer; in response to receiving a marking instruction for any sampling information, reading product information data corresponding to any sampling information; generating a corresponding bar code according to the product information data, and sending the product information data and the bar code to a mobile printing device, so that the mobile printing device prints the product information data and the bar code into a label. The method of the application outputs the sampling information and automatically prints the product information data and the bar code, thereby reducing the possibility of manual error, and solving the problem of inaccurate sampling inspection results.