2434 results about "Manufacturing systems" patented technology

The invention relates to the technical field of intelligent manufacturing, in particular to an intelligent production scheduling method and system for a manufacturing system, and the method comprises the following steps: collecting an equipment state, a material neat rate and an order emergency degree in real time based on dynamic production data, and calculating an equipment availability coefficient, a material guarantee index and an order priority score through feature analysis; and forming a dynamic production feature set. The system constructs a production scheduling optimization model through work order-equipment matching degree calculation and process priority optimization, and performs multi-objective optimization solution by adopting an NSGA-III algorithm to realize the optimal combination of equipment utilization rate, order delivery rate and inventory balance. Meanwhile, an arbitration mechanism is introduced to coordinate process priority conflicts, and the scheme is verified through time, space and dynamic adaptability, so that feasibility and stability of production scheduling execution are ensured. According to the invention, the production scheduling efficiency of the manufacturing system can be improved, the equipment utilization rate can be improved, the order delivery delay rate can be reduced, and the adaptive ability to the change of the production environment can be enhanced.

The invention discloses an adaptive task division and decision joint optimization-based cloud edge computing resource collaborative scheduling method for a complex manufacturing system. The method comprises the following steps of 1, constructing a hierarchical cloud-edge collaborative computing network model; constructing a multi-objective optimization model, and defining an objective function and constraint conditions; 2, dynamically predicting and calculating a resource state through a resource sensing module based on an LSTM neural network, and generating a node resource prediction matrix; 3, dividing a calculation task generated by the manufacturing system into fine-granularity, medium-granularity and coarse-granularity subtask sets by adopting a multi-granularity subtask division algorithm (MSPA), and mapping the subtasks to corresponding calculation nodes; 4, constructing a task unloading decision model based on the D3QN, and dynamically selecting unloading nodes and an execution sequence of the subtasks in combination with a multi-objective optimization reward function; and 5, iteratively optimizing parameters of the D3QN model through a target network updating mechanism and a self-adaptive exploration strategy to realize real-time dynamic adjustment of a task scheduling decision.

A friction stir additive manufacturing system is provided. In one aspect, the system includes a spindle configured to rotate about a central axis, and a housing configured to receive at least a portion of the spindle, the housing configured to remain stationary relative to the spindle. The housing includes a wire inlet extending between an exterior surface of the housing and an interior surface of the housing, and a track extending from the wire inlet and partially around a circumference of an interior surface of the housing. The system also includes a feeding system configured to receive a wire from a roller and feed the wire through the wire inlet and into the track of the housing.

A friction stir additive welding screw is provided. In one aspect, the friction stir additive welding screw includes a first portion configured to be coupled to a friction stir additive welding device, and a second portion configured to penetrate a work-piece. The second portion includes a plurality of large threads, each large thread extending in a generally longitudinal direction. The second portion also includes a plurality of fine threads positioned along an edge of each large thread, and a plurality of teeth at a tip of second portion.

Disclosed is a wheel cylinder and a drum brake having the same, in which the number of position as well as other elements accompanied with the piston may be reduced, resulting in reduced manufacturing cost.

A friction stir additive welding device configured to join a first work-piece and second work-piece is provided. In one aspect, the device includes a nosecone including a channel extending along a central axis and configured to receive a rotating screw. The device also includes a slot including a first opening in an outer sidewall of the nosecone, a second opening in a wall of the channel of the nosecone, and a passageway through the nosecone between the first opening and the second opening. The slot is configured to receive a portion of a structure positioned between the first work-piece and the second work-piece.

A friction stir additive welding device configured to join a first work-piece and second work-piece is provided. In one aspect, the device includes a nosecone having a sidewall extending from a first end to a second end, a channel extending from the first end to the second end along a longitudinal axis of the nosecone, and a screw positioned within the channel. The first end is configured to couple the nosecone to a robotic arm and the second end has a surface configured to be advanced along a weld line between the first and second work-pieces. A central axis of the screw defines an angle that is less than 90 degrees relative to a plane that is perpendicular to surfaces of the first and second work-pieces as the surface of the nosecone advances along the weld line.

The invention provides a big data bamboo tableware manufacturing system based on production process monitoring, and relates to the field of intelligent detection systems.The big data bamboo tableware manufacturing system comprises an acquisition module, a prediction module, a preliminary distribution module, a disturbance response module, an optimization decision module and an abnormity self-inspection module. A dynamic stability index is calculated in combination with a dynamic image sequence under disturbance response, a rejection target is judged through an optimization decision-making module after scores are fused, a Bayesian method is introduced in the optimization process to dynamically adjust multiple decision-making parameters, a rejection action instruction is generated in real time, and an abnormity self-checking module monitors the rejection rate and score stability. Software and hardware signals are combined to realize multi-level fault diagnosis and system protection control; according to the invention, high-precision identification and dynamic elimination of bamboo tableware defects are realized, and the automation level and the production reliability are improved.

A friction stir additive manufacturing system configured to extrude a material is provided. In one aspect, the system includes a spindle configured to rotate about a central axis, the spindle including a conical portion having a plurality of threads at a deposition end of the spindle. The system also includes a housing configured to remain stationary relative to the spindle, the housing including a wire inlet extending through a side wall of the housing, an interior surface of the side wall defining a truncated cone terminating at a material exit, the truncated cone configured to receive the conical portion of the spindle. The system also includes a feeding system configured to feed a wire through the wire inlet and into a gap between the spindle and the truncated cone of the housing.

The invention discloses a mobile phone silica gel shell appearance detection system based on an optical image sensor, and relates to the technical field of appearance defect detection and intelligent visual identification. An image acquisition module acquires a high-quality multi-channel image through multi-angle synchronous acquisition; the dynamic light field regulation and control module realizes self-adaptive regulation of a regional light source based on reflectivity perception and a gray gradient change rate; the image processing and defect identification module fuses edge features, texture changes and a deep learning model to realize pixel-level defect classification; the material identification and shielding module identifies a non-silica gel area through multi-dimensional spectral features and eliminates interference; a time sequence defect evolution analysis module models a defect evolution track; the trend prediction module is used for predicting the extension trend of potential cracks and fatigue areas; the control feedback module realizes intelligent judgment and response linked with the manufacturing system; the system can realize high-precision and high-robustness automatic defect detection and risk prediction, and is suitable for online quality monitoring of large-batch flexible products.

The invention relates to the field of digital twinning, in particular to an intelligent decision analysis method and system for a digital twinning-based manufacturing system, and aims to improve the generalization ability and adaptability of a digital twinning model in an emerging market small sample scene through deep fusion of meta-learning and adversarial training. According to the method, the problem of prediction distortion caused by data scarcity is relieved, high-quality training samples are expanded in combination with a generative enhancement technology, a multi-target elastic scheduling mechanism is synchronously constructed, dynamic optimization and feasibility verification of a production strategy are realized in a digital twin environment, and finally a closed-loop optimized intelligent decision system is formed. According to the method, through deep fusion of meta-learning and adversarial training, by combining a generative enhancement technology to expand high-quality training samples and a synchronously constructed multi-target elastic scheduling mechanism, dynamic optimization and feasibility verification of a production strategy are realized in a digital twin environment, and finally a closed-loop optimized intelligent decision system is formed.

The invention relates to the technical field of intelligent manufacturing decisions, in particular to a digital twinning-based manufacturing system decision analysis method and system, and the method comprises the steps: deploying a plurality of Internet of Things sensors on a physical manufacturing system, and collecting a physical real-time data stream of equipment in real time; the method comprises the following steps: establishing a virtual data acquisition channel aligned with a physical manufacturing system clock, injecting a physical real-time data stream into a digital twinning creation model, and performing data preprocessing based on distributed edge calculation to delay and compress original data acquisition of the physical real-time data stream to 10ms level, the time sequence database and the NTP / GPS clock are synchronized to ensure the state alignment error lt of the physical-virtual system; compared with the prior art, the deep space-time prediction network is fused with a CNN-LSTM-attention mechanism, the accuracy of multivariable coupled KPI prediction is improved, in addition, model failure is recognized in real time through Page-Hinkley inspection, and a prediction error reaches a relatively stable state through an adaptive retraining mechanism.

A pickleball paddle with novel core characteristics and / or materials, and related systems, methods, and articles of manufacture are provided.

A laser additive manufacturing system and method for a magnesium-based composite material. The system comprises a laser adjuster (1), a laser (2), a forming cover (3), an oxygen content adjuster (4), an inert gas cylinder (5), a powder feeder (6), a substrate (7) and a wire feeder (8), wherein the laser adjuster is used for controlling laser processing parameters of the laser; the laser is connected to a laser processing head (10) by means of an optical fiber (9); the oxygen content adjuster is in communication with the forming cover, so as to control the oxygen content of a processing environment in the forming cover; the inert gas cylinder and the powder feeder both pass through the forming cover to be connected to the laser processing head; the substrate is located inside the forming cover; the wire feeder is connected to a wire feeding head (12) by means of a wire feeding tube (11); the wire feeding head passes through the forming cover to perform laser additive manufacturing for a magnesium-based composite material, together with the laser processing head; and a real-time cooling sleeve (13) is also mounted on the wire feeding tube. Also provided are a method for preparing a magnesium-based composite material using the laser additive manufacturing system for the magnesium-based composite material, and a prepared magnesium-based composite material. By means of the manufacturing system and method, the additive processing of wires and powder is realized, and a magnesium-based composite material with a good mechanical property is prepared.

A method, apparatus, system, and computer program product for manufacturing an unconsolidated composite material. Sensor data is received from a sensor system for a composite material manufacturing system, wherein the sensor data is received during manufacturing of the unconsolidated composite material by the composite material manufacturing system. A set of predicted properties is determined for a number of portions of the unconsolidated composite material as completed from manufacturing by the composite material manufacturing system using the sensor data. A quality level for the number of portions of the unconsolidated composite material is identified based on the set of predicted properties for the number of portions of the unconsolidated composite material.

A method includes generating a causal graph based on a plurality of values, each value corresponding to a causal relationship between two or more sensors of a plurality of sensors in one or more manufacturing systems. The method further includes determining a causal strength index matrix. The method further includes responsive to identifying an anomalous behavior in at least one of the plurality of sensors, determining a root cause of the anomalous behavior using at least one of the causal strength index matrix or the causal graph. The method further includes causing a recommended corrective action to be issued based on the root cause of the anomalous behavior.

To provide a manufacturing system and method for creating multiple tissue constructs from cells.SOLUTION: A system can include a thaw subsystem (if the cells are provided in a frozen state), an expansion subsystem, a concentration subsystem, and a tissue maturation subsystem. Each of these subsystems is modular and can be reconfigured, and a process can be repeated depending on the specific tissue process being implemented. Multiple tissue types can be combined in multiple bioreactors. The activities of multiple bioreactors can be coordinated and controlled in an automated manner by a supervisor controller. The supervisor controller can receive user input at the start of the process, and can manage the process thereafter, alerting the user if user actions are required.SELECTED DRAWING: None

The invention belongs to the field of industrial automation, focuses on industrial robots in the field of semiconductor wafer manufacturing, and provides a system based on multi-mode sensing and intelligent decision making. A plurality of sensors are integrated on a robot and equipment, technologies of multi-sensor fusion, multi-modal data fusion, multi-physical field monitoring and the like are applied, and algorithms of dynamic trajectory planning, deep learning, adaptive control, reinforcement learning, digital twinning and virtual simulation and the like are combined; high-precision wafer carrying, rapid surface defect detection, thin film deposition process optimization, multi-robot collaborative scheduling and manufacturing process overall optimization are achieved, and the problems of precision, efficiency and quality in wafer manufacturing in the prior art are solved.

The invention relates to a complex manufacturing system optimization decision support method, which comprises the following steps of: collecting multiple types of data through distributed sensing nodes, fusing the data into a unified data model through semantic mapping, and constructing a dynamic data graph; key features are mined by using an improved deep learning model, and a multivariable prediction model is constructed to realize advanced prediction of equipment faults and the like; constructing a multi-objective optimization model, and generating and dynamically sorting a Pareto optimal scheme by adopting an adaptive algorithm; and issuing the scheme to an execution system, tracking execution and quantifying an evaluation result, and feeding back the evaluation result to a platform to optimize model parameters and feature weights to form closed-loop iteration. The invention aims to solve the problems of low data integration level, insufficient prediction precision, poor decision scheme adaptability and difficulty in continuous optimization in a complex manufacturing system.

Systems and methods for generating a shape-based graded lattice structure that can be used in additive manufacturing. A slicer computer system generates the lattice structure by simulating the packing of a planar region with variable-sized packing shapes, where packing shape sizes correspond to intensity values of a non-uniform physical field expected to be experienced by the article. An intermediate lattice structure is then generated using a first set of polygonal cells, followed by a second set of polygonal cells that refine the final lattice structure. Tailored sectioning and field-based smoothing can modify polygon packing algorithms to adapt lattice generation. The resultant multi-stage graded lattice structures, which may include multiple lattice patches and transition zones, from shape-based packing, tailored sectioning, field-based smoothing, and slicer-based additive manufacturing processing improve connectivity and manufacturability over traditional lattice structures.

The invention provides a complex manufacturing system production scheduling engine based on large language model spatio-temporal reasoning, and relates to the field of intelligent manufacturing, a scheduling demand is obtained, time-related information and space-related information are extracted, then spatial features and a time constraint graph are jointly coded into LLM analyzable spatio-temporal semantic vectors, and the LLM analyzable spatio-temporal semantic vectors are used for scheduling. And explicitly modeling a multi-dimensional interaction relationship of spatial proximity-time overlapping degree-resource competition intensity through association analysis of scheduling space-time semantics, so that LLM can realize more reliable space-time causal reasoning, and finally a scheduling scheme conforming to complex space-time constraints is generated. Thus, high-dimensional spatial-temporal characteristics in a manufacturing system can be adapted, spatial-temporal information required by user scheduling can be highlighted to adapt to an input format of LLM, then a nonlinear spatial-temporal coupling relationship in the production scheduling of a complex manufacturing system is concerned, and the generalization ability is improved.

A method includes generating a product knowledge causal graph based on causal relationships between multiple sensors in one or more manufacturing systems, parts data of a plurality of parts of the manufacturing system, and equipment constant data of a plurality of equipment constants of the manufacturing system. The method further includes determining a causal strength index matrix. The method further includes, responsive to identifying an anomalous behavior in at least one of the plurality of sensors, determining a root cause of the anomalous behavior using at least one of the causal strength index matrix or the product knowledge causal graph. The method further includes identifying, based on at least a subset of the parts data corresponding to the root cause of the anomalous behavior, or a subset of the equipment constant data corresponding to the root cause of the anomalous behavior, at least one corrective action for the anomalous behavior.

An unwinding device for manufacturing a secondary battery includes an unwinder, a transfer unit, and a correction unit having a rotation shaft. The unwinder is configured for unwinding a coating substrate wound in a roll shape by rotating it around the rotation shaft. The transfer unit includes a first transfer roll disposed closest to the unwinder. The correction unit is configured for correcting (i.e., moving) the position of the rotation shaft with respect to the first transfer roll.

The invention relates to the technical field of peroxide crosslinked polyethylene pipe manufacturing, and discloses a peroxide crosslinked polyethylene pipe manufacturing system and a crosslinking furnace thereof.The crosslinking furnace comprises a first furnace body, a second furnace body and a third furnace body, the first furnace body is provided with a first crosslinking cavity with a front opening and a rear opening, and a pipe can penetrate through the first crosslinking cavity; the first infrared emitter is arranged on the first furnace body, and infrared rays of the first infrared emitter are emitted into the first cross-linking cavity; the second furnace body is provided with a second cross-linking cavity with front and back openings, the second cross-linking cavity can allow the pipe to penetrate through, and the first furnace body and the second furnace body are sequentially arranged in the movement direction of the pipe; the second infrared emitter is arranged on the second furnace body, infrared rays of the second infrared emitter enter the second cross-linking cavity, and the wavelength of the infrared rays emitted by the second infrared emitter is smaller than that of the infrared rays emitted by the first infrared emitter. The inner layer and the outer layer of the pipe can be synchronously heated through infrared rays with different wavelengths, so that the cross-linking reaction of the pipe is more uniform, and the quality of the pipe is improved.

The invention discloses an intelligent welding and grinding integrated manufacturing system and a machining method, and belongs to the technical field of intelligent manufacturing. The system comprises a conveying belt, a portal frame stretching across the conveying belt, and a welding unit and a polishing unit which are arranged on the portal frame. The welding unit comprises a welding cross-shaped moving assembly, a welding-cooling assembly installed on the welding cross-shaped moving assembly and a welding seam tracking system. The grinding unit comprises a grinding cross-shaped moving assembly and a grinding assembly installed on the grinding cross-shaped moving assembly. The core of the system is that a central control system in communication connection with all the components is arranged, and the central control system is configured to receive weld joint track data recognized by the weld joint tracking system, sequentially control the welding device to weld along the track, control the cooling device to forcibly cool the weld joint and control the grinding device to grind along the same track based on the same data flow. Through path unification and procedure integration, continuous automatic operation of welding and grinding is achieved, and the machining precision, the production efficiency and the product quality are effectively improved.

The invention belongs to the field of virtual image display, particularly relates to a spherical reflection cavity virtual calibration method based on a neural radiation field, and aims to solve the problems that micron-level deviation is difficult to accurately capture due to interference of a high-reflection surface, and an executable correction instruction cannot be generated by fusing process constraints. The method comprises the following steps: deploying image acquisition equipment around a cavity to synchronously capture a multi-view optical image sequence; inputting a neural radiation field model, reconstructing a three-dimensional geometric structure and optical properties through a volume rendering technology, and dynamically optimizing and fitting reflection characteristics and curvature changes of a carbon fiber material; extracting spherical radius, local curvature and boundary contour parameters, and comparing the parameters with design specifications point by point to generate a deviation distribution diagram; generating a multi-level calibration instruction set based on the deviation distribution diagram in combination with the laying layer tolerance and the assembly clearance; and outputting an instruction to the manufacturing system to execute physical adjustment, and re-collecting the image to verify the calibration effect until the acceptance index is met. According to the invention, the deviation capturing precision is improved, and a correction instruction can be generated.

The present disclosure relates generally to manufacturing pharmaceutical products using additive manufacturing technology. An exemplary printing system comprises: a material supply module for receiving a set of printing materials; a flow distribution module comprising a flow distribution plate, wherein the material supply module is configured to transport a single flow corresponding to the set of printing materials to the flow distribution plate; wherein the flow distribution plate comprises a plurality of channels for dividing the single flow into a plurality of flows; a plurality of nozzles, wherein the plurality of nozzles comprises a plurality of needle-valve mechanisms; one or more controllers for controlling the plurality of needle-valve mechanisms to dispense the plurality of flows based on a plurality of nozzle-specific parameters; and a printing platform configured to receive the dispensed plurality of flows, wherein the printing platform is configured to move to form a batch of the pharmaceutical product.

The invention provides an implant immediate denture precise manufacturing system based on preoperative planning and three-dimensional registration. An example method includes obtaining first oral data, the first oral data including three-dimensional data of a denture model and three-dimensional data of a marker; acquiring second oral cavity data, wherein the second oral cavity data comprises scanning data of a plurality of bases fixed in the oral cavity and a marker; registering the first scanning data and the second scanning data based on the matching of the three-dimensional data of the marker and the scanning data of the marker; a denture model to be processed is generated based on a result of the registration, the denture model to be processed comprising three-dimensional data of the denture model and positioning information of a plurality of holes, each hole being for accommodating one of the plurality of abutment. According to the embodiment of the invention, the accurate positioning of the false tooth model and the abutment is realized by using a digital technology, the accurate matching of the false tooth and the abutment is ensured, and the comfort and experience of a dental implant patient are improved.

The invention relates to a manufacturing system risk control knowledge matching method based on semantic embedding and clustering analysis, and the method comprises the following steps: collecting and preprocessing risk control text data: collecting unstructured text data of a manufacturing system history record, and obtaining preprocessed risk control text data, constructing a professional corpus for a discrete manufacturing scene; text semantic embedding generation; semantic clustering modeling: performing unsupervised clustering modeling on all semantic vectors, mining semantic association and potential structures between texts, obtaining semantic representations of risk control knowledge through a clustering algorithm, and assisting in generating clustering tags; and a risk knowledge matching mechanism.

The invention discloses a robot cooperative machining method under the constraint of form and position errors. The robot cooperative machining method comprises the steps that 1, a double-machine cooperative machining in-situ manufacturing system for machining through a symmetric ground rail and double mechanical arms is constructed; step 2, establishing a conversion relation of all coordinate systems of the dual-machine collaborative processing in-situ manufacturing system; step 3, establishing a machining process flow integrating scanning measurement, blank assembly, allowance machining and precision detection; and 4, the double-machine cooperative machining in-situ manufacturing system conducts visual guidance double-machine cooperative machining on the large-size component based on the conversion relation and the machining technological process, and double-mechanical-arm cooperative error calculation and cooperative error correction based on visual feedback are conducted according to the shape and position error constraint of the large-size component. According to the invention, repeated measurement, disassembly and machining of parts in large-size assembly parts and error superposition of single-machine precision in a double-machine operation process are avoided.