9 results about "Manufacturing intelligence" patented technology

The application relates to the field of spring manufacturing intelligent control, and discloses a spring horizontal processing and single heat treatment coordinated intelligent regulation and control system, which comprises the following steps: a disturbance characteristic online coding module, which is used for online acquisition and coding of physical disturbance generated by each spring in horizontal processing procedures such as coiling and welding, and generates a unique disturbance characteristic spectrum; an online control law dynamic calibration module, which receives the disturbance characteristic spectrum and inversely solves a compensatory individualized heat treatment instruction sequence for the spring; an individualized heat treatment execution module, which executes accurate single heat treatment on a single spring according to the instruction sequence; and a quality feedback and model self-optimization module, which optimizes a control model in a long period according to the final measured performance of the spring. Through construction of a direct mapping and feedback optimization closed loop from horizontal processing disturbance to single heat treatment control, the application realizes deep coordination between the two, effectively compensates for process fluctuation, and significantly improves the consistency of spring product quality.

The invention provides an intelligent scheduling method and device for product manufacturing, and relates to the technical field of intelligent manufacturing, and the method comprises the steps: obtaining an original workpiece set and a new arrival workpiece set, enabling the original workpiece set to comprise original workpieces, enabling the new arrival workpiece set to comprise new arrival workpieces, and enabling the new arrival workpiece set to comprise new arrival workpieces; an initial optimal scheduling scheme is correspondingly provided; setting a selectable processing strategy for each newly arrived workpiece; the absolute value of the difference between the completion time of the original workpiece in the new scheduling scheme and the completion time of the original workpiece in the initial optimal scheduling scheme is limited not to exceed a preset threshold value, and the maximum completion time deviation constraint is obtained; constructing an objective function according to the weighted total completion time, the maximum completion time deviation cost, the compression cost and the rejection cost; and establishing a mixed integer programming model based on the target function and the maximum completion time deviation constraint, and realizing global optimization or approximate optimization of the total cost on the premise of guaranteeing the stability of the original plan while accepting a new order.

The invention discloses a modular plug-in connection structure and method for a transformer winding lead and a sleeve, and relates to the technical field of power transformer manufacturing. Comprising a plug module, a socket module and a winding lead, and the plug module is fixedly connected to the tail end of the winding lead; the plug module comprises a plug base and a male conductive contact arranged on the plug base, and the socket module comprises a socket base and a female conductive contact arranged on the socket base; a first guide part and a first locking part are arranged on the plug base; the socket base is provided with a second guide part matched with the first guide part and a second locking part matched with the first locking part; an inner cavity of the female conductive contact is internally provided with an elastic contact member which is in crimping cooperation with the male conductive contact. According to the invention, the assembly and maintenance time is greatly shortened, the connection consistency and safety are improved, and the manufacturing intelligence and operation and maintenance efficiency of the transformer are supported.

The application provides a product manufacturing intelligent scheduling method and device, and relates to the technical field of intelligent manufacturing. The method comprises the following steps: acquiring an original workpiece set and a newly-arrived workpiece set, wherein the original workpiece set comprises original workpieces, the newly-arrived workpiece set comprises newly-arrived workpieces, and there is an initial optimal scheduling scheme corresponding to the original workpiece set; setting an optional processing strategy for each newly-arrived workpiece; limiting the absolute value of the difference between the completion time of the original workpiece in a new scheduling scheme and the completion time of the original workpiece in the initial optimal scheduling scheme to be not more than a preset threshold value, and obtaining a maximum completion time deviation constraint; constructing a target function according to a weighted total completion time, a maximum completion time deviation cost, a compression cost and a rejection cost; and based on the target function and the maximum completion time deviation constraint, a mixed integer programming model is established, so that the global optimal or approximate optimal total cost is realized while the new order is accepted and the stability of the original plan is ensured.

The application relates to the technical field of intelligent equipment manufacturing, and specifically discloses an AI-based equipment manufacturing process energy consumption optimization and carbon footprint tracking system, which comprises a central collaborative scheduler, and the central collaborative scheduler is communicatively connected with the following modules: a data self-checking reconstruction module, a wavelet neural network optimized by using an improved particle swarm algorithm is used to construct a data self-checking model, and time sequence analysis and correlation comparison are carried out on multi-source heterogeneous sensing data of an equipment manufacturing process; the application can dynamically identify and correct inherent errors of sensing data by deploying a multi-source heterogeneous sensor network, combining a precise time synchronization protocol, constructing a time sequence alignment sequence, using a wavelet neural network optimized by using an improved particle swarm algorithm to construct a data self-checking model, outputting a high-fidelity data stream, and solving the problem of insufficient reliability of carbon footprint accounting data in a traditional manufacturing process from the source, thereby providing a data basis for energy consumption optimization and carbon emission tracking, and ensuring the authenticity and effectiveness of accounting results.

This invention discloses an intelligent control system for electrode foil formation process parameters that integrates diffusion models and ensemble learning. The system comprises five modules: multi-source data preprocessing and feature extraction, anomaly identification, time-series data generation, multi-objective performance prediction, and a front-end interface. Feature extraction employs a multi-scale comparative learning mechanism to extract time-series and batch features. Anomaly identification utilizes principal component analysis and weighted voting for real-time detection. Time-series data generation is based on a conditional diffusion model, learning the process and performance distribution mapping to generate controllable data. Performance prediction integrates multiple models and wavelet transform decomposition to jointly predict indicators such as specific capacitance and bending. The front-end is built on a responsive platform based on Grado, supporting asynchronous high concurrency. The system uses a diffusion model as its core, reconstructing full-cycle time-series data to reveal the control direction, and heatmaps enhance interpretability. Experimental results show that the system combines real-time performance with accuracy, identifying anomalies, predicting performance, and providing process suggestions, thereby improving the level of manufacturing intelligence.

The invention relates to the technical field of transformers, in particular to a transformer design and process adaptive optimization method and system based on deep learning. Through a multi-modal data fusion technology, multi-source heterogeneous data in design, material and manufacturing processes are represented in a unified manner. A physical information neural network is utilized to construct an efficient multi-physical field agent model, and an optimization design scheme is quickly generated in combination with a material knowledge graph. And the physical manufacturing process is mapped in real time and the product performance is predicted through the digital twin. And finally, on the basis of a deep reinforcement learning model, according to the state prediction and target deviation of the digital twin, adaptively adjusting subsequent process parameters or feeding back a fine tuning design scheme, and forming a'design-process-detection-optimization 'closed loop. According to the method, the problems that the design and manufacturing links of the transformer are separated, the transformer depends on experience, and online optimization is difficult are solved, data driving and self-adaptive collaboration of the whole process are achieved, and the product performance consistency, the design efficiency and the manufacturing intelligence level are remarkably improved.

This invention relates to the field of intelligent manufacturing and industrial automation technology, specifically to a manufacturing intelligent scheduling and dispatching method based on AI edge computing terminals. The method includes: generating a theoretical scheduling baseline timeline based on work order BOMs and standard process routes (SOPs) issued by ERP / MES, as well as real-time data collected by the edge computing terminal on equipment OEE time-series slices, workstation cycle times, and edge buffer pool inventory levels; performing parametric disturbance simulation on this data to generate a theoretical residual time-series set; generating a real residual time-series based on actual workstation completion times; determining the disturbance type using dynamic time warping distance calculation and similarity calculation based on process route topology; and generating local work order translation scheduling instructions accordingly, followed by dynamic calibration to optimize the scheduling accuracy of subsequent production plans.