8 results about "Process output" patented technology

The application relates to the motor winding technology field and provides a motor winding process automatic control method and system.The method comprises the following steps: obtaining motion state information, stress state information and material characteristic information of a flat wire; inputting the motion state information, the stress state information and the material characteristic information into a preset flat wire mechanical simulation model to obtain a predicted torsion angle of the flat wire in a bending process output by the preset flat wire mechanical simulation model; obtaining an actual torsion angle of the flat wire; adjusting a parameter value of an equivalent shear modulus of the flat wire in the preset flat wire mechanical simulation model according to the predicted torsion angle and the actual torsion angle to obtain an adjusted preset flat wire mechanical simulation model; and performing winding control on the flat wire based on the adjusted preset flat wire mechanical simulation model. The accuracy of motor winding can be controlled.

The application provides a production cycle determination method, device, equipment, medium and program product, and relates to the oil and gas well mining process technical field.The method comprises the following steps: obtaining target production time sequence data of a plunger gas lift process; the target production time sequence data comprises tubing pressure data and casing pressure data corresponding to a plurality of time points respectively; inputting the target production time sequence data into a recognition model, recognizing the target production time sequence data through the recognition model, and obtaining a running cycle recognition result of the plunger gas lift process output by the recognition model; and determining a production cycle corresponding to the plunger gas lift process based on the running cycle recognition result.The production cycle determination method, device, equipment, medium and program product provided by the application improve the recognition efficiency and recognition accuracy of the production cycle of the plunger gas lift process, reduce the labor cost, and improve the automation level and production efficiency of the plunger gas lift process.

To configure the control agent (POL), pre-given training data is read in, specifying the state dataset (S), action dataset (A), and the obtained performance values ​​(R) of the technical system (TS). Based on this training data, a data-driven dynamic model (NN) is trained to reproduce the obtained performance values ​​(R) based on the state dataset (S) and action dataset (A). Furthermore, a action evaluation process (VAE) is trained to reproduce the action dataset (A) based on the state dataset (S) and action dataset (A) after information reduction, where reproduction errors (DR, D0, D1) are determined. To train the control agent (POL), training data is fed to the trained dynamic model (NN), the trained action evaluation process (VAE), and the control agent (POL). Here, the performance values ​​(R1, R2) output by the trained dynamic model (NN) are fed into a pre-given performance function (P). Additionally, the reproduction errors (D0, D1) output by the trained action evaluation process (VAE) are fed into the performance function (P) as parameters affecting performance reduction. In this way, the control agent (POL) is trained to output an action dataset (A) that optimizes the performance function (P) based on the state dataset (S).

Machine learning systems and methods for extreme weather event modeling using generative diffusion models are provided. The system includes a weather modeling processor and a weather modeling engine executed by the processor. The weather modeling engine causes the processor to: receive a dataset including a plurality of vorticity samples; process the dataset using a deterministic mean model having a temporal attention unit to model spatial, cross-channel, and temporal dependencies using dynamical attention units; and process output of the deterministic mean model using a reverse diffusion model to capture stochastic fine scale features and to generate a denoised output. A downscaling pipeline can also be executed by the weather modeling engine to downscale outputs of the system.

Machine learning systems and methods for extreme weather event modeling using generative diffusion models are provided. The system includes a weather modeling processor and a weather modeling engine executed by the processor. The weather modeling engine causes the processor to: receive a dataset including a plurality of vorticity samples; process the dataset using a deterministic mean model having a temporal attention unit to model spatial, cross-channel, and temporal dependencies using dynamical attention units; and process output of the deterministic mean model using a reverse diffusion model to capture stochastic fine scale features and to generate a denoised output. A downscaling pipeline can also be executed by the weather modeling engine to downscale outputs of the system.

This invention discloses a method and system for designing robust operating conditions for industrial production processes. Considering various uncertainties in industrial production, and addressing scenarios where process mechanism models are unknown or simulation costs are high, this method utilizes only the input and output data of the production process. By constructing a robust Bayesian optimization model, it can determine nominal operating condition setpoints with strong disturbance resistance for the production process. The implementation process is as follows: sampling and testing within the operable range of the operational variables to obtain process output data; defining constraints, constructing the robust operating condition design problem as an optimization proposition that minimizes the maximum constraint value; establishing a Gaussian process regression surrogate model based on the sampled data, and constructing a sampling function that integrates the predicted mean, uncertainty, and constraint satisfaction probability; employing a two-stage Bayesian optimization framework, iteratively sampling and updating the model until convergence is achieved to obtain the robust operating condition setpoints.

The application belongs to the technical field of structured process design. The application provides a radar assembly process structured design method based on a process model. The disclosure embodiment realizes multi-specialty collaborative process design of precision assembly, electronic assembly, surface treatment and the like by clearly defining the responsibility boundary of the main process engineer end and the collaborative process engineer end, standardizing the cross-specialty collaborative process, and solves the multi-specialty collaborative integrated process design problem of the radar assembly process. Relying on basic resources such as process library, process model library and typical process resource library, the application reduces repeated design and shortens the process preparation cycle. The standardized process procedure template reduces the dependence on individual experience, improves the quality stability of process design, and ensures the consistency and reliability of process output. The application establishes a perfect process change process, realizes the flexibility and standardization of multi-specialty process collaborative change, ensures the consistency and accuracy of the changed process file, improves the reliability of the radar assembly process, and provides protection for process design optimization and improvement.

Architectures and techniques for initializing a simulation architecture are described. A platform model and an environment model are run on recorded data during a first period of time. The platform model and the environment model provide information to control modules. The platform model is run on a blended combination of recorded data and data from the set of control modules and the environment model is run on processed output data from the platform model during a second period of time. The platform model is run on data from the set of control modules and the environment model is run on output from the platform model from a previous period of time during a third period of time. Output signals from the platform model can be adjusted based on a subset of the recorded data during the first, second and / or third period of time.